Journal articles on the topic 'DSN normalization'
To see the other types of publications on this topic, follow the link: DSN normalization.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'DSN normalization.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
So, Chi Chiu, Tsz On Li, Chufang Wu, and Siu Pang Yung. "Differential Spectral Normalization (DSN) for PDE Discovery." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 11 (May 18, 2021): 9675–84. http://dx.doi.org/10.1609/aaai.v35i11.17164.
Full textAbstract:
Partial differential equations (PDEs) play a prominent role in many disciplines for describing the governing systems of interest. Traditionally, PDEs are derived based on first principles. In the era of big data, the needs of uncovering PDEs from massive data-set are emerging and become essential. One of the latest advance in PDE discovery models is PDE-Net, which has shown promising predictive power with its moment-constrained convolutional filters, but may suffer from noisy data and numerical instability intrinsic in numerical differentiation. We propose a novel and robust regularization method tailored for moment-constrained convolutional filters, namely, Differential Spectral Normalization (DSN), to allow accurate estimation of coefficient functions and stable prediction of dynamics in a long time horizon. We investigated the effectiveness of DSN against batch normalization, dropout, spectral normalization, weight decay, weight normalization, jacobian regularization and orthonormal regularization and supported with empirical evidence that DSN owns the highest effectiveness by learning the convolutional filters in a robust manner. Numerical experiments further reveal that with DSN there is a substantial potential to uncover the hidden PDEs in a scarce data setting and predict the dynamical behavior for a long time horizon, even in a noisy environment where all data samples are contaminated with noise.
2
Greene, Clint, Matt Cieslak, and Scott T. Grafton. "Effect of different spatial normalization approaches on tractography and structural brain networks." Network Neuroscience 2, no. 3 (September 2018): 362–80. http://dx.doi.org/10.1162/netn_a_00035.
Full textAbstract:
To facilitate the comparison of white matter morphologic connectivity across target populations, it is invaluable to map the data to a standardized neuroanatomical space. Here, we evaluated direct streamline normalization (DSN), where the warping was applied directly to the streamlines, with two publically available approaches that spatially normalize the diffusion data and then reconstruct the streamlines. Prior work has shown that streamlines generated after normalization from reoriented diffusion data do not reliably match the streamlines generated in native space. To test the impact of these different normalization methods on quantitative tractography measures, we compared the reproducibility of the resulting normalized connectivity matrices and network metrics with those originally obtained in native space. The two methods that reconstruct streamlines after normalization led to significant differences in network metrics with large to huge standardized effect sizes, reflecting a dramatic alteration of the same subject’s native connectivity. In contrast, after normalizing with DSN we found no significant difference in network metrics compared with native space with only very small-to-small standardized effect sizes. DSN readily outperformed the other methods at preserving native space connectivity and introduced novel opportunities to define connectome networks without relying on gray matter parcellations.
3
Blayney, Douglas W., Yuankai Shi, Igor Bondarenko, Stephan Ogenstad, Qingyuan Zhang, Lihua Du, Lan Huang, and Ramon Mohanlal. "Head-to-head comparison of single agent (SA) plinabulin (Plin) versus pegfilgrastim (Peg) for the prevention of chemotherapy-induced neutropenia (CIN) in the phase 3 trial PROTECTIVE-1." Journal of Clinical Oncology 39, no. 15_suppl (May 20, 2021): 547. http://dx.doi.org/10.1200/jco.2021.39.15_suppl.547.
Full textAbstract:
547 Background: Peg is the current standard of care (SoC) for the prevention of CIN, with a low absolute neutrophil (N) count (ANC) week 1 after chemotherapy (chemo) with normalization in week 2. Breakthrough designation agent from FDA, Plin, a novel, non-G-CSF agent for the prevention of CIN, produces a normal ANC in week 1 of cycle (C) 1 by potentially protecting progenitor cells in bone marrow from chemo assault, and also has anticancer activity (Blayney, St Gallen 2019; ASCO 2019). Here we report data from a pre-specified interim analysis from PROTECTIVE-1 (Study 105; NCT03102606). Methods: Breast cancer (BC), lung (NSCLC) and prostate cancer (HRPC) pts with at least 1 risk factor as per NCCN, received docetaxel (Doc) 75 mg/m2 with either Peg 6mg (n=53) or Plin 40 mg (n=52) over 4 cycles, and had ANC blood draws on Day (D) 1, 2,6,7,8,9,10,15 in C1 (Covance Central Laboratory). Plin was given on D1, as a 30 min IV infusion, 30 min after Doc, and Peg, 24 hrs after Doc. Primary objective was to demonstrate non-inferiority (NI) of SA Plin vs SA Peg for duration of severe neutropenia (DSN) in C1. NI of Plin vs Peg would be declared if the upper limit of 95% confidence interval for the mean DSN difference between Plin and Peg would be <0.65 day. Other endpoints included C1 platelet count, C1 bone pain scores (validated questionnaire), C1-4 clinical sequelae of CIN through [febrile neutropenia (FN), infection, antibiotic and hospitalization rate, and Doc discontinuation (Discont) and delays], and safety (AEs, hematology and chemistry, vital signs) Results: Predefined DSN NI criterion between SA Plin and SA Peg was met. C1 Grade 4 toxicity was not different between Plin and Peg (p=NS). Clinical sequelae of CIN were comparable or slightly better for Plin vs Peg (see Table). Plin caused less bone pain (p=0.01) and less thrombocytopenia (p<0.0001 on D15) vs Peg. AE frequency and overall safety was comparable for SA Plin and SA Peg. Conclusions: SA Plin has efficacy for Doc CIN prevention non-inferior compared to SoC Peg, and accordingly has comparable (or numerically better) profile for clinical sequelae of CIN. Plin has an advantage for bone pain, platelet counts, convenience of use (same day vs next day dosing) over SoC Peg and has anticancer activity. Clinical trial information: NCT03102606. [Table: see text]
4
Winaktu, George, Lalu Mulyadi, and Edi Hargono DP. "THE SCALE OF PRIORITY FOR THE CONSTRUCTION OF IRRIGATION CHANNELS FOR STAKEHOLDERS PERCEPTIONS OF THE IRRIGATION SERVICE IN SIDOARJO REGENCY." Journal Innovation of Civil Engineering (JICE) 1, no. 1 (November 2, 2020): 18. http://dx.doi.org/10.33474/jice.v1i1.9059.
Full textAbstract:
Sidoarjo Regency is one of the megapolitan Gerbang Kertosusilo. The planted area during the rainy season and dry season reaches 30,000 ha. The area of paddy fields continues to decline, namely 26,334 ha (2002), 22,460 ha (2010), and an estimated 13,544 ha (2009–2029). Sidoarjo Regency Irrigation Service as executor of irrigation management is of course inseparable from construction project activities. In the implementation of the construction of new irrigation networks as well as in rehabilitation and maintenance, it is necessary to implement project management. Before the project is implemented, it must first be submitted through proposals from the village level. In following up the proposal the writer used the Analytic Hierarchy Process (AHP) analysis method. With four aspects that affect the determination of the proposal: The results of the analysis obtained the weight of each criterion as follows: Service Area (ha) 0.3179, Cost 0.3159, Benefits 0.3217, and Network Conditions 0.0445. The results of the above analysis obtained priority ranking from the first to the last sequence as follows: Plengsengan Gedangrowo Channel, Normalization of Reform Channels, Installation of floodgates, Plengsengan ChannelsDs. Suwaluh, Rehabilitation of Ketawang Canal Kec. Sukodono, Rehabilitation of Candi Subdistrict Channel, Plengsengan Channel Ds. Suwaluh, Plengsengan Channels Purboyo II Ds. Popoh, Plengsengan Irrigation Channels Dsn. Kesimbuk, Plengsengan Channel Mangetan Kanal.
5
Mittempergher, Lorenza, Iris de Rink, Marja Nieuwland, Ron M. Kerkhoven, Annuska Glas, Rene' Bernards, and Laura van't Veer. "High concordance for MammaPrint 70 genes by RNA next generation sequencing." Journal of Clinical Oncology 30, no. 15_suppl (May 20, 2012): 3065. http://dx.doi.org/10.1200/jco.2012.30.15_suppl.3065.
Full textAbstract:
3065 Background: The development of new biomarkers often requires fresh frozen (FF) samples. Recently we showed that microarray gene expression data generated from FFPE material are comparable to data extracted from the FF counterpart, including known signatures such as the 70-gene prognosis signature (Mittempergher L et al., 2011). As described by Luo et al (2010) RNA profiling using next generation sequencing (RNA-Seq) is now applicable to archival FFPE specimens. Methods: Technical performance and the comparison between the RNA-Seq 70-gene read-out and the MammaPrint test (Glas et al., 2006) is evaluated in a series of 15 patients (11/15 with matched FFPE/FF material). RNA-Seq was carried out using minor adjustments of the Illumina TruSeq RNA preparation method. RNA sequencing libraries were prepared starting from 100ng of total RNA. Next, the DSN (Duplex-Specific Nuclease) normalization process was used to remove ribosomal RNA and other abundant transcripts (Luo et al, 2010). The libraries were paired-end sequenced on the Illumina HiSeq 2000 instrument with multiplexing of 4 libraries per lane. The resulting sequences were mapped to the human reference genome (build 37) using TopHat 1.3.1(Trapnell et al., 2009). The HTSeq-count tool was used to generate the total number of uniquely mapped reads for each gene. Results: Between 14% and 45% of the total number of reads were assigned to protein-coding genes. The minimum coverage per 1000bp of CDS was 38 reads. The 70 MammaPrint genes were successfully mapped to the RNA-Seq transcripts. We calculated the Pearson correlation coefficient between the centroids of the original good prognosis template (van’t Veer et al., 2002) and the 70-gene read count determined by RNA-Seq of each sample. Predictions based on the 70-gene RNA-Seq data showed a high agreement with the actual MammaPrint test predictions (>90%), irrespective of whether the RNA-seq was performed on FF or FFPE tissue. Conclusions: New generation RNA-sequencing is a feasible technology to assess diagnostic signatures.
6
Jing, Yongcheng, Xiao Liu, Yukang Ding, Xinchao Wang, Errui Ding, Mingli Song, and Shilei Wen. "Dynamic Instance Normalization for Arbitrary Style Transfer." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 4369–76. http://dx.doi.org/10.1609/aaai.v34i04.5862.
Full textAbstract:
Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way. Such manually-defined nature eventually results in the high-cost and shared encoders for both style and content encoding, making style transfer systems cumbersome to be deployed in resource-constrained environments like on the mobile-terminal side. In this paper, we propose a new and generalized normalization module, termed as Dynamic Instance Normalization (DIN), that allows for flexible and more efficient arbitrary style transfers. Comprising an instance normalization and a dynamic convolution, DIN encodes a style image into learnable convolution parameters, upon which the content image is stylized. Unlike conventional methods that use shared complex encoders to encode content and style, the proposed DIN introduces a sophisticated style encoder, yet comes with a compact and lightweight content encoder for fast inference. Experimental results demonstrate that the proposed approach yields very encouraging results on challenging style patterns and, to our best knowledge, for the first time enables an arbitrary style transfer using MobileNet-based lightweight architecture, leading to a reduction factor of more than twenty in computational cost as compared to existing approaches. Furthermore, the proposed DIN provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.
7
Saputri, Riska Nurul, Ichwana Ichwana, and Agus Arip Munawar. "Prediksi Kadar Salinitas, pH dan C-Organik Tanah Menggunakan Near Infrared Kecamatan Baitussalam Kabupaten Aceh Besar." Jurnal Ilmiah Mahasiswa Pertanian 4, no. 4 (March 31, 2020): 542–51. http://dx.doi.org/10.17969/jimfp.v4i4.12940.
Full textAbstract:
Abstrak. Akuisisi spektrum Near Infrared Reflectance Spectroscopy (NIRS) terkait kualitas dan kondisi tanah telah banyak dilakukan dalam berbagai penelitian. Pada penelitian ini menggunakan model prediksi Partileal Least Squares (PLS) dengan metode koreksi spektrum Mean Normalization (MN), Savitzky-Golay Smoothing, dan kombinasi Mean Normalization (MN) dan Savitzky-Golay Smoothing. Sampel tanah yang digunakan berasal dari Kecamatan Baitussalam Kabupaten Aceh Besar karena dianggap sesuai untuk prediksi kadar salinitas, pH dan C-Organik tanah. Hasil dari penelitian menunjukkan adanya korelasi antara prediksi Near Infrared Reflectance Spectroscopy (NIRS) dengan hasil aktual laboratorium setelah dilakukan pembangunan model prediksi Partileal Least Square (PLS) dan dievaluasi dengan parameter statistika; penggunaan pretreatment Mean Normalization (MN) merupakan metode terbaik atau pilihan, dimana dapat meningkatkan keakuratan hasil prediksi kadar salinitas, pH dan C-Organik tanah.Prediction of Salinity, pH and C-Organic Soils Level Using Near in Baitussalam Regency, Aceh Besar RegencyAbstract. Near Infrared Reflectance Spectroscopy (NIRS) spectrum acquisition related to soil quality and condition has been carried out in various studies. This study used prediction model Partileal Least Squares (PLS) with the spectrum correction methods used are Mean Normalization (MN), Savitzky-Golay Smoothing, and Combination of Mean Normalization (MN) and Savitzky-Golay Smoothing. The soil samples used were from Baitussalam regency, Aceh Besar regency because they were considered suitable for the prediction of salinity, pH and C-Organic soils. The results of this study showed a correlation between the prediction of Near Infrared Reflectance Spectroscopy (NIRS) with the actual results of the laboratory after the construction of the prediction model Partileal Least Square (PLS) and and evaluated with statistical parameters; the use of pretreatment Mean Normalization (MN) is the best or preferred spectrum correction method, which can improve the accuracy of the predicted results of salinity, pH and C-Organic soil.
8
Pires, Ivan Miguel, Faisal Hussain, Nuno M. M. Garcia, Petre Lameski, and Eftim Zdravevski. "Homogeneous Data Normalization and Deep Learning: A Case Study in Human Activity Classification." Future Internet 12, no. 11 (November 10, 2020): 194. http://dx.doi.org/10.3390/fi12110194.
Full textAbstract:
One class of applications for human activity recognition methods is found in mobile devices for monitoring older adults and people with special needs. Recently, many studies were performed to create intelligent methods for the recognition of human activities. However, the different mobile devices in the market acquire the data from sensors at different frequencies. This paper focuses on implementing four data normalization techniques, i.e., MaxAbsScaler, MinMaxScaler, RobustScaler, and Z-Score. Subsequently, we evaluate the impact of the normalization algorithms with deep neural networks (DNN) for the classification of the human activities. The impact of the data normalization was counterintuitive, resulting in a degradation of performance. Namely, when using the accelerometer data, the accuracy dropped from about 79% to only 53% for the best normalization approach. Similarly, for the gyroscope data, the accuracy without normalization was about 81.5%, whereas with the best normalization, it was only 60%. It can be concluded that data normalization techniques are not helpful in classification problems with homogeneous data.
9
Imjidee, Nuchanad, and Soh Bee Kwee. "Normalization Techniques For Translating Cultural - Specific Expressions." LSP International Journal 7, no. 2 (November 30, 2020): 1–18. http://dx.doi.org/10.11113/lspi.v7.15264.
Full textAbstract:
For readability of audience in target culture (TC), cultural-specific expressions (CSEs) which have been embedded with specific characteristics, need specific techniques to transfer them into target language (TL). This study aims to identify normalization techniques (NTs) from domestication strategies to show that they are particularly necessary for CSE translation. Based on the previous studies of different scholars, the overlap between domestication and normalization is clarified, following by the clarification of the relation between normalization and the use of translator’s subjectivity, as well as the distinction between CSEs and universals for simple explanation on what normalization and CSE are. Last but not least, the overlapping NTs, classified from domestication strategies will be unified. Finally, illustration of normalization of CSEs, selected from Thai target text (TT) and its English source text (ST), The Da Vinci Code (DVC), a novel by Dan Brown, will give an overt explanation of how each NT is used to deal with CSEs in order to show relation between characteristics of CSEs and each NT. This will answer why NTs are necessary.
10
Naumenko, S. V. "Questions of Orthography Normalization in «Tolkovyi slovar’ russkogo yazyka» after edition of D.N. Ushakov." Russian language at school 79, no. 9 (November 15, 2018): 67–74. http://dx.doi.org/10.30515/0131-6141-2018-79-9-67-74.
Full textAbstract:
The article is dedicated to otrthographical content of the first soviet standard «Tolkovyi slovar’ russkogo yazyka» after edition of D.N. Ushakov. The specific aspects of spelling are analyzed in the context of orthographic situation in postreformed period and D.N. Ushakov’s views. It is set the approaches to normalization of such controversial groups of writing as compound adjectives with the meaning of colour shade, stressed vowels о/е after hushings in nouns’ suffixes, н/нн in suffixes of adjectives and participles. The basic groups of orthographic variants in the dictionary are defended, their normative status is determined. It is defended the influence of the dictionary on the normalization postreform spelling.
11
Baqi, Ahmad Mudhofarul. "From Foes to Friends: The Normalization of the United Emirates Arab and Israel Relations." Insignia: Journal of International Relations 9, no. 1 (May 1, 2022): 80. http://dx.doi.org/10.20884/1.ins.2022.9.1.4995.
Full textAbstract:
Abstract
This article aims to explain the reason the United Arab Emirates (UAE) normalized ties within Israel through Abraham Accord. The normalization of the UAE-Israel ties contra with the position of UAE as a part of the members of Gulf Cooperation Council (GCC) and Arab League that have long been conflicting within Israel, due to Israel's annexation over Palestinians. Utilize explanative type and constructivism paradigm based on identity as a tool of analysis, and supported with the secondary data. This article found the difference in religious identity, not automatic interfere step of UAE and Israel normalization process. The normalization of the UAE and Israel drive by the threat of Iran in the region. The threat shape collective identity between UAE and Israel as friends and Iran as a common enemy. The collective identity was also constructed via systemic processes in the form of interdependency and proximity with the United States of America. The collective identity was also constructed through strategic practice by both leaders. Furthermore, amongst UAE and Israel gathered through a type of identity Abraham's religion.
Keyword: Normalization, UAE, Israel, Identity, Iran, and Constructivism
Abstrak
Artikel ini bertujuan untuk menjelaskan alasan Uni Emirat Arab (UAE) menjalin normalisasi hubungan dengan Israel melalui perjanjian Abraham Accord. Normalisasi hubungan UAE dengan Israel kontras dengan posisi UAE sebagai negara teluk (GCC) dan Liga Arab yang telah lama berkonflik dengan Israel atas aksi aneksasi Israel di wilayah Palestina. Menggunakan jenis penelitian eksplanatif dengan paradigma konstruktivisme berbasis identitas sebagai pisau analisis, serta didukung oleh data sekunder. Artikel ini menemukan bahwa perbedaan identitas agama tidak lantas menyurutkan langkah UAE dan Israel melakukan normalisasi hubungan. Israel-UAE normalization didorong oleh konteks ancaman regional berupa agresivitas Iran di kawasan. Konteks ancaman Iran membentuk collective identity antara UAE dan Israel sebagai sahabat dan Iran sebagai musuh bersama. Collective identity juga tercipta melalui proses sistemik berupa interdependensi UAE dan Israel dan kedekatan keduanya dengan Amerika Serikat. Collective identity juga terbentuk lewat praktik strategis kedekatan pemimpin kedua negara. Selain itu, antara UAE dan Israel juga disatukan lewat identitas tipe agama Abraham.
Kata kunci: Normalisasi, UAE, Israel, Identitas, Iran, dan Konstruktivisme
12
Rahmatia, Firsty, Marlenny Sirait, and Yasser Ahmed. "The Effect of Normalization on The Zooplankton Structure in Ciliwung River." Biofaal Journal 1, no. 1 (June 5, 2020): 27–36. http://dx.doi.org/10.30598/biofaal.v1i1pp27-36.
Full textAbstract:
Program normalisasi Sungai Ciliwung menjadi program prioritas pemerintah pusat bersama dengan Pemerintah Provinsi DKI Jakarta yang dimulai sejak tahun 2013. Pemerintah Provinsi (Pemprov) DKI Jakarta menargetkan normalisasi Kali Ciliwung rampung pada tahun 2018 mendatang. Normalisasi bertujuan untuk mengembalikan fungsi sungai dalam menampung, menyimpan dan mengalirkan air yang berasal dari curah hujan ke danau atau ke laut secara alami. Salah satu upaya yang bisa dilakukan untuk mengevaluasi normalisasi adalah dengan memantau kualitas perairan dengan melakukan penelitianmenggunakan indikator biologis seperti plankton dan ikan. Sebelumnya, pada tahun 2016 peneliti telah melakukan penelitian terhadap kelimpahan fitoplankton di Sungai Ciliwung, sehingga perlu dilakukan penelitian lanjutan untuk mengetahui trophic level diatas fitoplankton, yaitu zooplankton. Stasiun pengambilan sampel adalah Sungai Ciliwung bagian hulu sampai dengan hilir. Adapun 10 (sepuluh) stasiun pengamatan yang terbagi atas 3 (tiga) segmen; yaitu Segmen I (Jembatan Gadog, Katulampa, Sentul); segmen II (Kelapa Dua, Kalibata, Kampung Melayu, Manggarai), dan segmen III (Pejompongan, K.H. Mas Mansyur dan Teluk Gong). Pengambilan airdilakukan secara komposit pada tiga titik sampel yangmewakili bagian tengah, tepi kiri, dan tepi kanan sungai.Hasil penelitian menunjukkan bahwa secara keseluruhan, kelas zooplankton yang dapat ditemukan pada semua stasiun adalah Rotifera dan diikuti dengan protozoa. Sementara itu, kelas zooplankton yang paling jarang ditemui di Sungai Ciliwung adalah kelas Gastropoda yang hanya ditemui di stasiun Katulampa. Rotifera yang paling banyak ditemui adalah Asplachna sp. diikuti oleh Brachionus sp.. Sementara itu untuk protozoa, jenis yang paling banyak ditemui adalah Arcella sp. Parameter kualitas air yang berpengaruh terhadap kelimpahan zooplankton pada penelitian ini adalah suhu, Total Suspended Solid (TSS), dan nitrat.
13
Nasution, Darnisa Azzahra, Hidayah Husnul Khotimah, and Nurul Chamidah. "Perbandingan Normalisasi Data untuk Klasifikasi Wine Menggunakan Algoritma K-NN." Computer Engineering, Science and System Journal 4, no. 1 (January 31, 2019): 78. http://dx.doi.org/10.24114/cess.v4i1.11458.
Full textAbstract:
Abstrak— Rentang nilai yang tidak seimbang pada setiap atribut dapat mempengaruhi kualitas hasil data mining. Untuk itu diperlukan adanya praproses data. Praproses ini diharapkan dapat meningkatkatkan keakuratan hasil dari pengklasifikasian dataset wine. Metode praproses yang digunakan adalah transformasi data dengan normalisasi. Ada tiga cara yang dilakukan dalam transformasi data dengan normalisasi, yaitu min-max normalization, z-score normalization, dan decimal scaling. Data yang telah diproses dari setiap metode normalisasi akan dibandingan untuk melihat hasil akurasi terbaik klasifikasi dengan menggunakan algoritama K-NN. K yang digunakan dalam perbandingan adalah 1, 3, 5, 7, 9, 11. Sebelum dilakukan pengklasifikasian dataset wine yang telah dinormalisasi dibagi menjadi data uji dan data latih dengan k-fold cross validation. Pembagian data menggunakan k sama dengan 10. Hasil pengujian klasifikasi dengan algoritma K-NN menunjukkan, bahwa akurasi terbaik terletak pada dataset wine yang telah dinormalisasi menggunakan metode min-max normalization dengan K = 1 sebesar 65,92%. Rata-rata yang diperoleh, yaitu 59,68%. Keywords— Normalisasi, K-fold cross validation, K-NN
14
Singh, Richa, Ashwani Kumar Dubey, and Rajiv Kapoor. "Deep Neural Network Regularization (DNNR) on Denoised Image." International Journal of Intelligent Information Technologies 18, no. 1 (January 1, 2022): 1–16. http://dx.doi.org/10.4018/ijiit.309584.
Full textAbstract:
Image dehazing in supervised learning models suffers from overfitting and underfitting problems. To avoid overfitting, the authors use regularization techniques like dropout and L2 norm. Dropout helps in reducing overfitting and batch normalization reduces the training time. In this paper, they have conducted experiments to analyze combination of various hyperparameters to have better network performance using deep neural network (DNN) on cifar10 dataset. The qualitative and quantitative study is performed by estimating the accuracy of the model on training and test images using with and without batch normalization. The proposed model performs better and is more stable. The results shows that dropout regularization technique is better than L2 technique containing hidden layers with large neurons. The paper assesses performance of DNN for any denoised model with the techniques like batch normalization and dropout, feature map, and adding more layers to the network. The authors quantitatively identify the value model loss and accuracy with the absence and presence of these parameters.
15
Harsanto, Puji, Surya Budi Lesmana, and Sherly Devianty. "Analisis Drainasi di Saluran Cakung Lama Akibat Hujan Maksimum Tahun 2013 dan 2014." Semesta Teknika 17, no. 2 (November 26, 2015): 91–97. http://dx.doi.org/10.18196/st.v17i2.416.
Full textAbstract:
Flooding is an annual disaster for Indonesia. Jakarta is a city that each year nearly always experienced by flooding. The rapid development made the impervious area dropped drastically. Micro drainage is not capable of passing the volume of direct runoff. It makes many regions in Jakarta experienced by floodwaters. The aim of this research is to analyze the micro drainage capacity in Cakung Lama River. Simulations are performed with HEC-RAS 1D. The flood data is maximum rainfall on 2013 and 2014. Two scenarios normalization is done for reducing the inundated area around the river. Based on the simulation results, the existing conditions are not able to accommodate the discharge due to maximum rainfall 2013 dan 2014. Normalization of the river will give good results if the width of the river 5 m and the depth of the river is 3 m.
16
Fikrie, Hafiz, Hafid Adim Pradana, and Dedik Fitra Suhermanto. "Sentiments via #Abrahamaccords on the UAE and Israel Normalization." Jurnal Komunikasi Global 11, no. 2 (December 27, 2022): 227–47. http://dx.doi.org/10.24815/jkg.v11i2.26697.
Full textAbstract:
On 15 September 2020, the UAE normalized relations with Israel, which sparked controversy on Twitter with the #AbrahamAccords. By using Digital Movement Opinion (DMO) and the concept of sentiment analysis, this study aims to determine the sentiment of public opinion that develops on Twitter media related to the normalization of this relationship. This study used a qualitative approach through the use of text mining methods using Natural language Toolkit (NLTK) as a platform in Python to analyze 4900 tweets with #AbrahamAccords. The results of the study showed that the sentiment of public opinion that developed on social media Twitter was a positive sentiment with 75% of the 490 tweets. It also showed that views on the relationship between the UAE and Israel on social media Twitter via #AbrahamAccords tend to support this normalization. Some factors that influenced the positive sentiment were the role of the mass media and political actors. Pada 15 September 2020, UEA melakukan normalisasi hubungan dengan Israel yang yang mengundang kontroversi di Twitter dengan #AbrahamAccords. Dengan menggunakan Digital Movement Opinion (DMO) dan konsep sentiment analisis, penelitian ini bertujuan untuk mengetahui sentimen dari opini publik yang berkembang pada media Twitter terkait dengan normalisasi hubungan tersebut. Penelitian ini menggunakan metode kualitatif melalui pemakaian metode teks mining dengan menggunakan Natural language Toolkit (NLTK) sebagai platform di Python guna menganalisis 4900 tweets dengan #AbrahamAccords. Hasil penelitian menunjukkan bahwa sentimen dari opini publik yang berkembang di media sosial Twitter adalah sentimen positif dengan 75% dari 490 tweet yang di peroleh. Hal ini menunjukkan bahwa pandangan terhadap hubungan UEA dengan Israel pada media sosial Twitter melalui #AbrahamAccords cenderung mendukung adanya normalisasi tersebut. Beberapa faktor yang mempengaruhi sentiment positif yang terjadi ialah peran media massa dan aktor politik.
17
Rath, Shakti P. "Factored front-end CMLLR for joint speaker and environment normalization under DNN-HMM." International Journal of Speech Technology 20, no. 4 (September 4, 2017): 859–67. http://dx.doi.org/10.1007/s10772-017-9453-x.
Full text
18
Nurhaida, Ida, Vina Ayumi, Devi Fitrianah, Remmy A. M. Zen, Handrie Noprisson, and Hong Wei. "Implementation of deep neural networks (DNN) with batch normalization for batik pattern recognition." International Journal of Electrical and Computer Engineering (IJECE) 10, no. 2 (April 1, 2020): 2045. http://dx.doi.org/10.11591/ijece.v10i2.pp2045-2053.
Full textAbstract:
One of the most famous cultural heritages in Indonesia is batik. Batik is a specially made drawing cloth by writing Malam (wax) on the cloth, then processed in a certain way. The diversity of motifs both in Indonesia and the allied countries raises new research topics in the field of information technology, both for conservation, storage, publication and the creation of new batik motifs. In computer science research area, studies about Batik pattern have been done by researchers and some algorithms have been successfully applied in Batik pattern recognition. This study was focused on Batik motif recognition using texture fusion feature which is Gabor, Log-Gabor, and GLCM; and using PCA feature reduction to improve the classification accuracy and reduce the computational time. To improve the accuracy, we proposed a Deep Neural Network model to recognise batik pattern and used batch normalisation as a regularises to generalise the model and to reduce time complexity. From the experiments, the feature extraction, selection, and reduction gave better accuracy than the raw dataset. The feature selection and reduction also reduce time complexity. The DNN+BN significantly improve the accuracy of the classification model from 65.36% to 83.15%. BN as a regularization has successfully made the model more general, hence improve the accuracy of the model. The parameters tuning also improved accuracy from 83.15% to 85.57%.
19
Heriyanto, Heriyanto Heriyanto. "DETEKSI UCAPAN ANGKA SATU SAMPAI SEPULUH BAHASA PALEMBANG MENGGUNAKAN MFCC DAN BOBOT DOMINAN." Telematika 16, no. 1 (April 10, 2019): 52. http://dx.doi.org/10.31315/telematika.v16i1.3024.
Full textAbstract:
Abstract Detecting speech with regional language, one of which is Palembang language, has uniqueness and distinctiveness in accent. Differences in dialects to check how precise and influential the accuracy of using MFCC and dominant weights. This study consists of three stages. The first stage, feature extraction of numerical numbers from one to ten using Mel Frequency Cepstral Coefficient (MFCC). The second stage is the selection of features that will be used as feature tables using the proposed model Normalized Dominant Weight (NBD) with threshold similarity, range, filtering, normalization of weights and dominant weights. The third stage is testing by checking by finding similarities in range, filtering, sequential multiplication and calculation of Suitability of Uniformity Patterns (CTF). The test results of checking MFCC and feature selection with normalization of dominant weights were 70% while without feature selection only 42%. Keywords : extraction, weighting, dominant, normalization, range Abstrak Deteksi ucapan dengan berbahasa daerah salah satunya bahasa Palembang mempunyai keunikan dan kekhasan dalam logat berbahasa. Perbedaan logat bahasa untuk mengecekan seberapa tepat dan berpengaruh terhadap akurasi menggunakan MFCC dan Bobot dominan. Penelitian ini terdiri atas tiga tahap. Tahap pertama, ekstraksi ciri angka bahasa angka satu sampai sepuluh menggunakan Mel Frequency Cepstral Coefficient (MFCC). Tahap kedua adalah pemilihan fitur yang akan dijadikan tabel fitur menggunakan model yang diusulkan Normalisasi Bobot Dominan (NBD) dengan kesamaan threshold, jangkauan, filtering, normalisasi bobot dan bobot dominan. Tahap ketiga adalah pengujian dengan pengecekan dengan cara mencari kesamaan jangkauan, filtering, perkalian sekuensial dan perhitungan Kesesuaian Keseragaman Pola (KKP). Hasil pengujian pengecekan terhadap MFCC dan pemilihan fitur dengan normalisasi bobot dominan sebesar 70% sedangkan tanpa pemilihan fitur hanya sebesar 42%. Kata kunci : ekstraksi, bobot, dominan, normalisasi, jangkauan
20
Alfia, Muaida, Zulfahrizal Zulfahrizal, and Agus Arip Munawar. "Penentuan Kadar Lemak Secara Non-Destruktif Pada Bubuk Biji Kakao (Berbasis Nirs-Partial Least Square) Dengan Menerapkan Metode Mean Normalization Dan De-Trending." Jurnal Ilmiah Mahasiswa Pertanian 1, no. 1 (November 1, 2016): 1027–36. http://dx.doi.org/10.17969/jimfp.v1i1.1164.
Full textAbstract:
Abstrak. Saat ini untuk menentukan kadar lemak pada biji kakao dilakukan dengan mengekstrak biji kakao menggunakan pelarut tertentu yang memakan waktu cukup lama, sehingga metode penentuan mutu secara cepat dan tepat diperlukan untuk menghasilkan komoditas kakao standar mutu tinggi yang dapat diwujudkan dengan metode near infrared reflectance spectroscopy (NIRS). Tujuan yang ingin dicapai dari penelitian ini membandingkan data spektrum antar pretreatment mean normalization (MN) dan de-trending dan (DT) dalam mengkoreksi spektrum NIRS yang dihasilkan serta mengembangkan metode non-destruktif NIRS dalam menduga kandungan lemak pada bubuk biji kakao. Penelitian ini dilakukan di Laboratorium Instrumentasi dan Energi Program Studi Teknik Pertanian pada bulan Maret sampai Mei 2016. Hasil penelitian yang diperoleh bahwa metode NIRS menggunakan preatreatment de-trending dan mean normalization pada panjang gelombang 2300-2400 nm merupakan panjang gelombang yang paling relevan untuk menduga kadar lemak pada bubuk biji kakao. Pendugaan PLS yang didukung pretreatment telah menghasilkan pendugaan yang tergolong good model performance. Pada pendugaan kadar lemak PLS yang sangat baik dalam meningkatkan kinerja PLS pada cross validation adalah de-trending. Abstract. determining fat content in cocoa beans is generally performed by extracting cocoa beans using certain solvent extraction which takes a long time. Determining quality method quickly and exactly required to produce the commodity of high quality standard cocoa that is realized by of near infrared reflectance spectroscopy (NIRS) method. The aim of this research is to compare the spectral data pretreatment mean normalization (MN) and de- trending and (DT) in correcting the NIRS spectrum which is namely and to develop of non-destructive NIRS method in predicting the fat content in cocoa powder. This research was conducted in Instrumentation Laboratory and Energy of Agriculture department from March to May 2016. the results of the research obtained that the NIRS method used de-trending and mean normalization spectra correction methods at a wave-length range of 2300-2400 nm, found to be the most relevant to estimate the fat content in cocoa powder. The estimation of PLS been produced a of good model performance.
21
Nurcahyo, Ardhyan Dwi, and Elizabeth Titiek Winanti. "Pengaruh model Problem Based Learning terintegrasi pendekatan induktif terhadap kemampuan berpikir spasial dan pengetahuan siswa pada materi mitigasi bencana." Jurnal Pendidikan Geografi 26, no. 1 (January 30, 2021): 41–47. http://dx.doi.org/10.17977/um017v26i12021p041.
Full textAbstract:
The ability to think spatially and mitigation knowledge is very important in everyday life. Problems involving the field of education in Indonesia are less than maximum classroom learning. Geography teachers learn to accept effective models in learning. Research Objectives Obtain appropriate and more effective learning methods that are useful in improving the ability to use spatial thinking and knowledge of disaster mitigation materials. Research Type: quasi-experimental. The research subjects were students of class XI IPS SMA N 2 Ponorogo. Measurement Increased spatial thinking skills and knowledge gained from normalization calculations. The results obtained normalization of the spatial thinking ability of the experimental class 52% and 37% control class. The results of the experimental class knowledge 58% and 43% control class. Independent T-test shows that Probleam-based learning has improved for the better.
22
Kim, Mijung, and K. Selçuk Candan. "Decomposition-by-normalization (DBN): leveraging approximate functional dependencies for efficient CP and tucker decompositions." Data Mining and Knowledge Discovery 30, no. 1 (January 28, 2015): 1–46. http://dx.doi.org/10.1007/s10618-015-0401-6.
Full text
23
Xie, Longhao, Qing Zhao, Chunguang Ma, Binbin Liao, and Jianjian Huo. "Ü-Net: Deep-Learning Schemes for Ground Penetrating Radar Data Inversion." Journal of Environmental and Engineering Geophysics 25, no. 2 (June 2020): 287–92. http://dx.doi.org/10.2113/jeeg19-074.
Full textAbstract:
Electromagnetic (EM) inversion is a quantitative imaging technique that can describe the dielectric constant distribution of a target based on the EM signals scattered from it. In this paper, a novel deep neural network (DNN) based methodology for ground penetrating radar (GPR) data inversion, known as the Ü-net is introduced. The proposed Ü-net consists of three parts: a data compression unit, U-net, and an output unit. The novel inversion approach, based on supervised learning, uses a neural network to generate the dielectric constant distribution from GPR data. The GPR data can be compressed and reshaped the size using data compression unit. The U-net maps the object features to the dielectric constant distribution. The output unit meshes the dielectric constant distribution more finely. A novel feature of the proposed methodology is the application of instance normalization (IN) to the DNN EM inversion method and a comparison of its performance to batch normalization (BN). The validity of this technique is confirmed by numerical simulations. The Mean-Square Error of the test data sets is 0.087. These simulations prove that the instance normalization is suitable for GPR data inversion. The proposed approach is promising for achieving quality dielectric constant images in real-time.
24
Hendra Suputra, I. Putu Gede, Kiki Dwi Prebiana, and Frisca Olivia Gorianto. "Perbandingan Jenis TF terhadap Hasil Evaluasi Information Retrieval." JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) 8, no. 2 (January 16, 2021): 207. http://dx.doi.org/10.24843/jlk.2019.v08.i02.p13.
Full textAbstract:
Pada sebuah sistem temu kembali,salah satu cara untuk mencari kesamaan antara query dengan dokumen adalah dengan menggunakan Term Frequency – Inverse Document Frequency atau TF-IDF. TF yang umum digunakan adalah langsung menggunakan jumlah term frequency padahal banyak jenis TF lainnya yang dapat dikombinasikan dengan IDF. Penelitian ini akan mengkombinasikan 4 jenis TF, yaitu Natural TF, Normalization/max TF, Logaritma TF, dan Boolean TF dengan tujuan untuk mencari jenis TF mana yang lebih baik setelah dikombinasikan dengan IDF. Hasil penelitian menunjukkan bahwa.Logaritma TF adalah yang terbaik dengan nilai F-measure sebesar 0,00662.
Keywords: TF-IDF, Natural TF, Normalization TF, Logaritma TF, Boolean TF
25
Sofiyanurriyanti. "Implementasi Proses Bisnis Dalam Upaya Penerapan Green Hospital." Jurnal Teknik Industri 18, no. 2 (September 14, 2017): 149. http://dx.doi.org/10.22219/jtiumm.vol18.no2.149-158.
Full textAbstract:
Rumah sakit merupakan institusi pelayanan kesehatan yang memberikan jasa pelayanan kesehatan untuk pelayanan umum, tempat berkumpulnya orang sakit maupun sehat. Lingkungan rumah sakit merupakan salah satu aspek yang juga perlu diperhatikan dan juga perlu dikelola dengan baik. Alur aktivitas proses bisnis merupakan kegiatan layanan utama terhadap penanganan rawat inap pasien IDEF0 level 1, proses bisnis tahap verifikasi dan registrasi level 2, menerima pasein dan memberikan tindakan medis level 3, rekomendasi rujuk rawat inap atau rujuk ke instalasi level 4, kegiatan operasional level 5 dan sampai pasien keluar rumah sakit level 6. Salah satu upaya pendekatan untuk mendukung pengelolaan lingkungan yang sehat, bersih dan ramah lingkungan adalah green hospital. Penerapan green hospital ini mencakup lingkungan yang berwawasan lingkungan hijau, efisiensi penggunaan air, energi listrik, penggunaan bahan material yang baik serta pengurangan limbah. Evaluasi dampak lingkungan dirumah sakit terdapat ada lima jenis kategori yaitu limbah medis, limbah non medis, limbah medis tajam, penggunaan air dan penggunaan listrik sedangkan untuk pengolahan data menggunakan software simapro. Penilaiaan dampak lingkungan ada beberapa langkah meliputi characteristization, damage assessment, normalization, weighting dan single score. Metode yang digunakan berdasarkan pada Eco Indikator 99 beberapa dampak lingkungan meliputi carcinogens, respiratory organics, climate change, radiation, ozone layaer, ecotoxity, acidification/ euthrophication, land use, minerals, dan fossil fuel. Sedangkan untuk menilai dampak lingkungan pada limbah dapat dilihat dari hasil life cycle assessment berdasarkan characterization, normalization weighting dan single score.dampak lingkungan yang dihasilkan dirumah sakit yang mempengaruhi human health sebesar 0.153209 Pt, eco system quality sebesar 0.178514 Pt, dan resources 0.359308 Pt.
26
Jaya, Ansar, Irwan Lakawa, Sitti Hawa, and Muh Samtun Bona. "Analisis Kinerja Alat Berat Pada Proyek Normalisasi dan Perkuatan Tebing Sungai." Sultra Civil Engineering Journal 3, no. 1 (June 27, 2022): 1–8. http://dx.doi.org/10.54297/sciej.v3i1.239.
Full textAbstract:
The purpose of this study was to analyze the performance of heavy equipment and the duration of time required to complete the Windo River Cliff Normalization and Reinforcement Project, Pamandati Village, Laeya District, South Konawe Regency. The results showed that the excavator's performance in excavation work (mechanical) was 38.68 m3/hour, dump truck 2.99 m3/hour. As for the embankment work imported from outside, the performance of the excavator is 98.53 m3/hour and the dump truck is 3.05 m3/hour. Where the duration of time required to complete the excavation work (mechanical) with an excavator is 12 days and for embankment work imported from outside is 2 days..
27
Ratnasari, Dewi, Sukarmin Sukarmin, and Y. Radiyono. "Implementasi Pendekatan Konstruktivisme melalui Model Pembelajaran CLIS (Children Learning In Science) dan Pengaruhnya terhadap Aktivitas Belajar dan Kemampuan Kognitif Siswa." Jurnal Penelitian & Pengembangan Pendidikan Fisika 3, no. 1 (June 30, 2017): 111. http://dx.doi.org/10.21009/1.03115.
Full textAbstract:
Abstract
The aim of this research is to implementation constructivism approach through CLIS (Children Learning In Science) learning model and its immpact toward students’ learning activities and cognitive ability. This action resesarch was analyzed by descriptive quantitative. Research subjects is students in 11th grade in the academic year 2013/2014 in the static fluid material. The data of this research from observation technique when learning process and cognitive test in the end of learning. Students’ learning activities in this research consist of visual activities, oral activities dan writing activities that described into many indicators, whereas cognitive test uses multiple choice instrument that has been properness analyzed. Based on research result and data analysis get result as follows: 1) The value of normalization in visual activities is 0,78 (high), oral activities is 0,31 (adequate), writing activities is 0,49 (adequate); 2) The increase of average achievement of students’ cognitive ability based on gain normalization is 0,32 (adequate) after learning with constructivism approach through CLIS (Children Learning In Science) model.
Keywords: learning activities, Children Learning In Science, cognitive ability.
Abstrak
Penelitian ini bertujuan untuk mengimplemantasikan pendekatan konstruktivisme melalui model pembelajaran CLIS (Children Learning In Science) dan pengaruhnya terhadap aktivitas belajar dan kemampuan kognitif siswa. Penelitian tindakan ini dianalisis menggunakan deskriptif kuantitatif dengan subjek penelitian adalah siswa kelas XI pada tahun ajaran 2013/2014 pada materi fluida statis. Data penelitian diperoleh dari hasil observasi selama proses pembelajaran dan hasil tes kognitif pada akhir pembelajaran. Aktivitas belajar siswa pada penelitian ini terdiri dari visual activities, oral activities dan writing activities yang dijabarkan menjadi beberapa indikator, sedangkan tes kognitif siswa menggunakan instrumen pilihan ganda yang telah dianalisis kelayakannya. Berdasarkan hasil penelitian dan analisis data diperoleh hasil sebagai berikut: 1) Nilai gain ternormalisasi pada visual activities sebesar 0,78 (tinggi); oral activities sebesar 0,31 (sedang); writing activities sebesar 0,49 (sedang); 2) Peningkatan rata-rata nilai ketuntasan kemampuan kognitif siswa berdasarkan nilai gain ternormalisasi sebesar 0,32 (sedang) setelah pembelajaran dengan mengimplementasi pendekatan konstruktivisme melalui model CLIS (Children Learning In Science).
Kata-kata Kunci: Aktivitas belajar, Children Learning In Science, kemampuan kognitif.
28
Muslimin, JM, and Mahmoud Mohamed Hosny. "On the Normalization of Diplomatic Relationship Between Israel and Muslim Countries: A Study of Classic Fiqh and Contemporary Fatwas." Al-Jami'ah: Journal of Islamic Studies 59, no. 2 (December 24, 2021): 375–422. http://dx.doi.org/10.14421/ajis.2021.592.375-422.
Full textAbstract:
This article discusses the different legal opinions of Muslim scholars of various trends in the past and modern time, on the normalization of diplomatic relationship between Muslim countries and Israel. The article aims to compare among these different opinions and also to clearly define the common and specific argument on which they agreed, as well as to accurately define the points of disagreement. The focus of study will be the theoretical reasons as well as practical effects, through the analysis of fatwas and their context. The exploration will give the reader a clear understanding of the nature of these differences yet the conflicting arguments among them. This article follows the methodology of the jurisprudential and contextual analytical comparison. The research questions will follow this logical sequence: what are the general opinions of Muslim religious scholars regarding the issue of diplomatic normalization with Israel? what are the areas of agreements and differences between them? and what are the current fatwas and their reasons for their opinions in the perspective of Islamic law? However, in some points, due to its actual and comprehensive argument as well as the worldwide circulation, Yusuf al-Qaradhawi’s legal opinion and fatwa will be cited and referred longer than others as examining stone and completing legal validity and representing contemporary logics of prominent Muslim jurist. The article concludes some points of theoretical differences, similarities and practical implications as well as recommendations of notifications for future study. [Artikel ini membahas perbedaan pendapat antar sarjana muslim mengenai trend di masa lalu dan kini tentang normalisasi hubungan diplomatik antara negara muslim dan Israel. Artikel ini membandingkan perbedaan opini dan dan juga menjernihkan titik kesepahaman dan ketidaksepahaman yang disepakati bersama. Fokus pembahasan mulai dari aspek teoritis hingga efek praktis melalui analisis fatwa dan konteksnya. Pembahasan juga memberikan pemahaman bagi pembaca keadaan yang berbeda termasuk argumen konflik diantara mereka. Artikel ini menggunakan metode analisis perbandingan hukum dan kontekstual. Setidaknya ada dua pertanyaan yang akan dijawab yaitu apa pendangan umum sarjana muslim mengenai wacana normalisasi hubungan diplomatik dengan Israel dan apa fatwa terbaru serta penjelasannya dalam perspektif hukum Islam? Dalam beberapa hal, argumen aktual dan komprehensif mengikuti sirkulasi yang lebih luas. Fatwa dan pendapat Yusuf Qaradawi akan dikutip dan dirujuk lebih banyak sebagai pijakan serta validasi dan representasi komplit logika kontemporer bagi pemikir muslim ternama. Artikel ini menyimpulkan beberapa hal penting terkait perbedaan dan persamaan teoritis serta implikasi praktis, termasuk juga rekomendasi untuk kajian ini ke depan]
29
Golovacheva, V. A., and A. A. Golovacheva. "Principles of Treatment of Patients with Diabetic Polyneuropathy in the COVID-19 Pandemic." Meditsinskiy sovet = Medical Council, no. 19 (December 1, 2021): 126–33. http://dx.doi.org/10.21518/2079-701x-2021-19-126-133.
Full textAbstract:
Patients with COVID-19 may develop various neurological disorders of the central and peripheral nervous systems. It is known that diabetes mellitus (DM) type 1 or 2, cardiovascular diseases, obesity, old age and old age, male gender are risk factors for a severe course and complications of COVID-19. Currently, the COVID-19 pandemic is ongoing, and patients with the listed risk factors are recommended to follow a regime of social restriction or self-isolation. Outpatient treatment is most appropriate for this category of patients. Patients with diabetes who have undergone COVID-19 are at risk of developing or progressing diabetic polyneuropathy (DPN). It seems relevant to develop the principles of effective treatment of patients with DM and DPN in outpatient settings. Glycemic level correction, diet, weight normalization, therapy of combined cardiovascular diseases, an increase of physical activity, sleep normalization, maintenance of normal psychological state are the main principles of treatment of patients with DM and DPN in COVID-19 pandemic conditions. Pathogenetic therapy of DPN continues to be discussed, in our country the preparations of B vitamins, alpha-lipoic acid are widely used. B-group vitamin preparations can be used in the form of tablets or solutions for intramuscular injections. The effectiveness of B vitamins (B1, B6, B12) in the treatment of a severe course of COVID- 19, prevention of complications of COVID-19, especially in elderly patients and with diabetes is discussed.
30
Ruslana, Khairul Abdi, Ichwana Ichwana, and Agus Arip Munawar. "Deteksi Kualitas Air Sumur Masyarakat Akibat Penumpukan Limbah di Sekitar Tempat Pembuangan Akhir Menggunakan Laser Photo-Acoustics Spectroscopy di Gampong Jawa Kecamatan Kuta Raja Banda Aceh." Jurnal Ilmiah Mahasiswa Pertanian 3, no. 4 (November 1, 2018): 869–78. http://dx.doi.org/10.17969/jimfp.v3i4.9396.
Full textAbstract:
Abstrak. Dalam menguji kualitas air di Laboratorium biasanya memerlukan biaya yang mahal dan waktu yang lama. Laser Photo-Acoustics Spectroscopy adalah salah satu metode terbaru untuk uji cepat kualitas air. Tujuan dari penelitian ini adalah untuk menguji keakuratan laser fotoakustik sebagai metode baru yang cepat, efektif, dan efisien dalam mendeteksi kualitas air sumur masyarakat akibat penumpukan limbah di sekitar Tempat Pembuangan Akhir di Gampong Jawa Kecamatan Kuta Raja Banda Aceh dengan menggunakan Laser Fotoakustik. Hasil penelitian ini menunjukkan panjang gelombang relevan untuk prediksi kualitas air sumur menggunakan rentang panjang gelombang 4000 – 10000 cm-1 dimana parameter suhu, kekeruhan, TSS, pH, DO, BOD-5 dan nitrat (NO3-) berada pada rentang panjang gelombang tersebut. Metode koreksi spektrum yang paling baik digunakan untuk prediksi suhu, kekeruhan, TSS dan DO ialah metode koreksi cutting edge filtering, prediksi pH dan NO3- paling baik menggunakan data raw spektrum sementara prediksi BOD-5 paling baik mengggunakan metode koreksi peak normalization. Pada data raw spektrum nilai r berkisar pada 0.8349537 - 0.9926958, nilai RMSEC berkisar pada 0.0387916 - 3.7519751, nilai R2 0.6971 - 0.9854453, nilai RPD 1.942375418 - 6.949700451. Pada metode koreksi peak normalization nilai r berkisar pada 0.8151091 - 0.9910417, nilai RMSEC 0.0447571 - 5.7055745, nilai R2 0.65995 - 0.98216, nilai RPD 1.833200928 - 6.668034607. Pada metode koreksi cutting edge filtering nilai r berkisar 0.882751 - 0.9980677, nilai RMSEC 0.0410234 - 1.9323903, nilai R2 0.76829 - 0.9961392, nilai RPD 2.22078388 - 17.20520953.Detection of Water Quality of Wells of Communities Due to Waste Accumulation Around Final Disposal Site Using Photoacoustics Laser in Gampong Jawa Kecamatan Kuta Raja Banda AcehAbstract. In testing the quality of water in the Laboratory usually requires a high cost and a long time. The Photo-Acoustics Spectroscopy Laser is one of the newest methods for rapid water quality testing. The purpose of this research is to test the accuracy of photoacoustic laser as a new method that quickly, effectively and efficiently in detecting the quality of well water of society due to the accumulation of waste around the Final Disposal Site in Gampong Jawa, Kuta Raja Raja sub-district by using Laser Fotoakustik. The results of this study show the relevant Wavelength for well water quality prediction using the 4000 - 10000 cm - 1 wavelength range where the temperature, turbidity, TSS, pH, DO, BOD - 5 and nitrate (NO3 -) parameters are in the wavelength range. The best spectral correction methods used for prediction of temperature, turbidity, TSS and DO are cutting edge filtering correction methods, pH and NO3 predictions-best using raw spectrum data while BOD-5 predictions best use peak normalization correction methods. In raw data spectrum r value ranges from 0.8349537 - 0.9926958, RMSEC value ranges from 0.0387916 - 3.7519751, value R2 0.6971 - 0.9854453, RPD value 1.942375418 - 6.949700451. In peak correction method normalization r value ranges from 0.8151091 - 0.9910417, RMSEC value 0.0447571 - 5.7055745, value R2 0.65995 - 0.98216, RPD value 1.833200928 - 6.668034607. In correction method of cutting edge filtering r value ranges from 0.882751 - 0.9980677, RMSEC value 0.0410234 - 1.9323903, value R2 0.76829 - 0.9961392, RPD value 2.22078388 - 17.20520953.
31
Adi, Henny Pratiwi, and Slamet Imam Wahyudi. "Edukasi Partisipasi Masyarakat Kelurahan Pandean Lamper dalam Pemeliharaan Bantaran Sungai Banjir Kanal Timur Semarang." Indonesian Journal of Community Services 4, no. 1 (May 31, 2022): 41. http://dx.doi.org/10.30659/ijocs.4.1.41-48.
Full textAbstract:
Kelurahan Pandean Lamper merupakan salah satu daerah rawan banjir di Kota Semarang, karena terletak di DAS Sungai Banjir Kanal Timur. Penanganan terhadap banjir di wilayah tersebut telah dilakukan oleh pemerintah berupa normalisasi sungai dan saluran drainase. Banjir Kanal Timur (BKT) adalah satu sistem pengendali banjir Kota Semarang yang terletak di bagian timur Kota Semarang. Sungai ini memiliki panjang ± 14,50 km. Proyek normalisasi Sungai Banjir Kanal Timur membentang dari hulu di Bendungan Pucanggading hingga berakhir Muara Sungai di Laut Jawa. Dalam tahap I, normalisasi dilakukan sepanjang 6,7 kilometer, dari muara hingga Jembatan Majapahit. Untuk menjamin keberlanjutan pengelolaan normalisasi sungai dan saluran drainase, diperlukan keterlibatan banyak pihak, termasuk partisipasi masyarakat yang bertempat tinggal di dalamnya. Oleh sebab itu warga di kawasan tersebut perlu mendapatkan edukasi bagaimana menjaga keberlanjutan normalisasi sungai dan saluran drainase. Warga Kelurahan Pandean Lamper memerlukan edukasi agar dapat ikut berpartisipasi dalam pemeliharaan sungai dan saluran drainase. Edukasi yang diberikan meliputi pemahaman tentang penyebab dan dampak banjir, penanganan banjir serta pemeliharaan bangunan infrastruktur pengendali banjir. Warga Kelurahan Pandean Lamper masih banyak yang tidak memahami bangunan pengendali banjir yang ada di sekitar lingkungan mereka. Melalui edukasi yang diberikan dalam penyuluhan, diharapkan warga Pandean Lamper bisa memahami peran yang harus dilakukan dalam menjaga keberlangsungan bangunan pengendali banjir. Pandean Lamper Village is one of the flood-prone areas in Semarang City, because it is located in the East Flood Canal River Basin. The government has taken steps to deal with flooding in the area by normalizing rivers and drainage channels. The East Flood Canal (BKT) is a flood control system for the City of Semarang which is located in the eastern part of the City of Semarang. This river has a length of ± 14.50 km. The East Flood Canal River normalization project stretches from the upper reaches of the Pucanggading Dam to the end of the River Estuary in the Java Sea. In phase I, normalization is carried out along 6.7 kilometers, from the estuary to the Majapahit Bridge. To ensure the sustainability of the normalization of river and drainage channel management, it requires the involvement of many parties, including the participation of the people who live in them. Therefore, residents in the area need to receive education on how to maintain the sustainability of normalization of rivers and drainage channels. The residents of Pandean Lamper Village need education so that they can participate in the maintenance of rivers and drainage channels. The education provided includes an understanding of the causes and impacts of floods, flood management and maintenance of flood control infrastructure buildings. There are still many residents of Pandean Lamper Village who do not understand the flood control buildings in their surroundings. Through the education provided in the counseling, it is hoped that the residents of Pandean Lamper can understand the role that must be carried out in maintaining the sustainability of flood control buildings.
32
Wiguna, Ratu Aghnia raffaidy, and Andri Irfan Rifai. "Analisis Text Clustering Masyarakat Di Twitter Mengenai Omnibus Law Menggunakan Orange Data Mining." Journal of Information Systems and Informatics 3, no. 1 (February 28, 2021): 1–12. http://dx.doi.org/10.33557/journalisi.v3i1.78.
Full textAbstract:
Sosial media dengan platform twitter menjadi hal menarik untuk diteliti. Trending topik tersebut menghasilkan komentar masyarakat Indonesia yang mengandung opini berupa emosi. Penelitian ini mencoba menganalisis opini di twitter dengan metode analisis vader yang menghasilkan tweet profiler kemudian visualisasi distribution. Penelitian ini menggunakan tools orange data mining dengan mengaplikasikan Prepocess text yang meliputi transformation, tokenization, normalization, dan filtering yang bertujuan agar text bisa dianalisis. Kesimpulan dari penelitian ini yaitu respon masyarakat terhadap UU Cipta Kerja Omnibus Law mendapat 6 respon dan yang paling tertinggi responnya adalah masyarakat merasa surprise.
33
Ardiansyah, Faisal, Pahru Rozi, and Lili Lailatul Al Fitri. "INTEGRASI KONSEP RELIGIUSITAS ISLAM DENGAN TEKNIK RESTRUKTURISASI KOGNITIF UNTUK MENGATASI KECEMASAN." Khazanah: Jurnal Mahasiswa 2, no. 3 (May 4, 2022): 38–44. http://dx.doi.org/10.20885/khazanah.vol2.iss3.art6.
Full textAbstract:
Latar Belakang: Gangguan kecemasan merupakan gangguan mental yang paling umum ditemukan di dunia dan memiliki dampak besar terhadap penyakit global. Gangguan ini semakin banyak dialami seiring dengan modernitas kehidupan. Maka dari itu, penelitian ini bertujuan untuk mengintegrasikan teknik restrukturisasi kognitif dan aspek religiusitas Islam dalam mengatasi kecemasan. Metode: Metode penelitian ini menggunakan studi pustaka (literature review) dengan teknik analisis deskriptif. Hasil: Teknik-teknik restrukturisasi kognitif dapat diintegrasikan dengan konsep religiusitas Islam berdasarkan hadits Jibril, yaitu Iman, Islam, dan Ihsan. Teknik terdiri dari tahapan identification, normalization, distancing, dan decatastrophizing. Kesimpulan: Berdasarkan hasil penelitian dapat disimpulkan bahwa dalam mengatasi anxiety, teknik restrukturisasi kognitif dapat diintegrasikan dengan konsep religiusitas Islam. Kata kunci: Restrukturisasi Kognitif, Religiusitas Islam, Kecemasan
34
Berzina, Zane, Romans Pavlenko, Martins Jansons, Elena Bartkiene, Romans Neilands, Iveta Pugajeva, and Vadims Bartkevics. "Application of Wastewater-Based Epidemiology for Tracking Human Exposure to Deoxynivalenol and Enniatins." Toxins 14, no. 2 (January 25, 2022): 91. http://dx.doi.org/10.3390/toxins14020091.
Full textAbstract:
Wastewater-based epidemiology (WBE) is a promising biomonitoring approach with the potential to provide direct information on human intake and exposure to food contaminants and environmental chemicals. The aim of this study was to apply WBE while employing the normalization method for exploring human exposure to selected mycotoxins according to population biomarker 5-hydroxyindoleacetic acid (5-HIAA). This type of normalization technique has been previously used to detect various other compounds. However, to the best of our knowledge, this is the first study tracking human exposure to mycotoxins. A sensitive analytical methodology was developed to achieve reliable quantification of deoxynivalenol, enniatins, and beauvericin in wastewater (WW) samples. The applicability of the method was evaluated by testing 29 WW samples collected at WW treatment plants in Latvia. With frequency of detection greater than 86%, enniatins B, B1, A, and A1 were revealed in WW samples. The estimated total daily intake for enniatins was in the range of 1.8–27.6 µg/day per person. Free deoxynivalenol (DON) was determined in all analysed WW samples. Based on the average 5-HIAA excretion level and the determined 5-HIAA content in the samples, the intake of DON by the human population of Riga was estimated at 325 ng/kg b.w. day.
35
Alfiyaturrohmaniyyah, Siti, and Subiyantoro Subiyantoro. "<p style="text-align: justify;">Pembingkaian Wacana Normalisasi Hubungan Israel-Uni Emirat Arab pada Media Massa di Indonesia dan Prancis <em>(</em><em>Discourse </em><em>Framing of Israel-United Arab Emirat Relations Normalization in Indonesia and France </em><em>Mass </em><em>Media)</em></p>." Jalabahasa 18, no. 1 (June 10, 2022): 61–79. http://dx.doi.org/10.36567/jalabahasa.v18i1.833.
Full textAbstract:
Artikel ini bertujuan untuk mengkaji pembingkaian berita dari dua surat kabar daring yang berasal dari dua negara yang berbeda, yakni Prancis dan Indonesia. Data yang digunakan pada penelitian ini merupakan teks berita tentang normalisasi hubungan antara Israel dan Uni Emirat Arab (UEA) yang dimuat oleh media Prancis, Le Monde dan media Indonesia, Jawa Pos. Upaya normalisasi tersebut sangat erat kaitannya dengan isu aneksasi wilayah Palestina yang dilakukan oleh Israel. Penelitian ini menelaah struktur pembingkaian berita yang dilakukan oleh dua media tersebut berdasarkan teori Pan Kosicki.Temuan penelitian kualitatif ini memperlihatkan kecenderungan bahwa salah satu media asal Prancis tersebut memperlihatkan dukungannya terhadap upaya normalisasi hubungan antara UEA dan Israel. Di sisi lain, media Jawa Pos memperlihatkan sikap yang merepresentasikan bahwa media tersebut tidak mendukung upaya normalisasi hubungan antardua negara tersebut karena menganggap upaya tersebut akan sangat merugikan Palestina. This article aims to examine the news framing published by two different online newspapers, Le Monde (France) and Jawa Pos (Indonesia). The data used in this study are news texts about relationship normalization effort between Israel and (UAE) published by two media. That normalization effort is closely related to the issue of the Palestinian territories annexation carried out by Israel. The data analyzed using the theory Pan Kosicki. The findings of the study show a tendency that Le Monde, shows that the media support an effort to normalize relationship between the UAE and Israel. In contrast, the Jawa Pos media did not support that effort to normalize relationship between UEA and Israel because they thought that such efforts would provide very detrimental impacts to Palestine.
36
Chopra, Pooja, N. Junath, Sitesh Kumar Singh, Shakir Khan, R. Sugumar, and Mithun Bhowmick. "Cyclic GAN Model to Classify Breast Cancer Data for Pathological Healthcare Task." BioMed Research International 2022 (July 21, 2022): 1–12. http://dx.doi.org/10.1155/2022/6336700.
Full textAbstract:
An algorithm framework based on CycleGAN and an upgraded dual-path network (DPN) is suggested to address the difficulties of uneven staining in pathological pictures and difficulty of discriminating benign from malignant cells. CycleGAN is used for color normalization in pathological pictures to tackle the problem of uneven staining. However, the resultant detection model is ineffective. By overlapping the images, the DPN uses the addition of small convolution, deconvolution, and attention mechanisms to enhance the model’s ability to classify the texture features of pathological images on the BreaKHis dataset. The parameters that are taken into consideration for measuring the accuracy of the proposed model are false-positive rate, false-negative rate, recall, precision, and F 1 score. Several experiments are carried out over the selected parameters, such as making comparisons between benign and malignant classification accuracy under different normalization methods, comparison of accuracy of image level and patient level using different CNN models, correlating the correctness of DPN68-A network with different deep learning models and other classification algorithms at all magnifications. The results thus obtained have proved that the proposed model DPN68-A network can effectively classify the benign and malignant breast cancer pathological images at various magnifications. The proposed model also is able to better assist the pathologists in diagnosing the patients by synthesizing the images of different magnifications in the clinical stage.
37
Erina, Ahdania Asti, and Lisda Liyanti. "Normalisasi Hubungan Jerman dan Yahudi Melalui Penyembuhan Trauma Sejarah dalam Film The Zookeeper’s Wife." SOSIOHUMANIORA: Jurnal Ilmiah Ilmu Sosial Dan Humaniora 6, no. 2 (August 1, 2020): 1. http://dx.doi.org/10.30738/sosio.v6i2.6711.
Full textAbstract:
This study discusses trauma healing through the film "The Zookeeper's Wife" which was adapted from a novel by Dianne Ackerman and directed by Niki Caro as a way to normalize the relations between Germans and Jews. The purpose of this study was to identify the signs in the film which can be used as a healing from historical trauma due to the holocaust. This study uses qualitative method with data in the form of data extraction that has been taken from the film "The Zookeeper's Wife." Using Charles Sanders Pierce’s semiotic theory and Trauma theory by some experts, the outcome of this research shows that there are two elements for healing historical trauma, namely the trauma healing of Urszula, a Jewish girl and the trauma healing of German that leads to German-Jewish normalization.
38
Radhitya, Made Leo, and Gede Iwan Sudipa. "PENDEKATAN Z-SCORE DAN FUZZY DALAM PENGUJIAN AKURASI PERAMALAN CURAH HUJAN." SINTECH (Science and Information Technology) Journal 3, no. 2 (October 28, 2020): 149–56. http://dx.doi.org/10.31598/sintechjournal.v3i2.567.
Full textAbstract:
Determination of rainfall is important to determine the intensity of rain that occurs in an area. Rain intensity that is too high will certainly have a bad impact. Forecasting or prediction techniques are used to determine the likelihood of intensity occurring in the following year. However, rainfall data are continuous numerical data. Measurement of accuracy becomes more difficult if the data type is like that. So, this study tests the accuracy of rainfall forecasting in the city of Denpasar from a different perspective. This test combines the Z-score method and the Fuzzy set theory to normalize and classify rainfall data. This combination determines the degree of rainfall membership divided into Upper, Middle, and Lower levels. Based on the results of rainfall accuracy testing starting in 2012-2016 obtained an average value of accuracy of 85% with training data that is data in 2007-2015. The normalization process greatly affects the value of the training data.
39
Harsanto, Puji, Muhammad Arif Banjaran Sari, and Surya Budi Lesmana. "Evaluasi Muka Air Cakung Drain Hilir terhadap Hujan Maksimum 2013 dan 2014." Semesta Teknika 17, no. 1 (November 25, 2015): 32–37. http://dx.doi.org/10.18196/st.v17i1.406.
Full textAbstract:
Cakung floodway is a drainage channel that plays an importance rule for the overall of drainage system in Jakarta. Rainfall in 2013 and 2014 produced a big flood in Jakarta. Based on flood map Jakarta 2013 and 2014, there are inundated areas due to 2013’s and 2014’s rainfall. So, it is necessary to analyze the flood water level in channel floodway. Using HEC-RAS, this study aimed to evaluate the water level due to the maximum rainfall in 2013 and 2014. HEC-RAS is a tool for 1D hydraulic modeling and has reliability in routing of canal water level or river flooding. The results show that the maximum rainfall in 2013 provides a significant increasing of water level in Cakung floodway compared with the maximum rainfall in 2014. Soon, the need for canal normalization to reduce flood water level in Cakung floodway should be considered.
40
Khairudin, Nur Arif, and Wahyu Saputro. "KLASIFIKASI KUALITAS MUTU BUAH DELIMA DENGAN MENGGUNAKAN EKSTRAKSI GRAY LEVEL CO-OCCURRENCE MATRIX (GLCM) DAN K-NEAREST NEIGHBOR (KNN)." Jurnal Informatika Teknologi dan Sains 4, no. 3 (August 31, 2022): 273–78. http://dx.doi.org/10.51401/jinteks.v4i3.1990.
Full textAbstract:
Buah Delima merupakan komoditas buah yang memiliki nilai komersial dan prospek yang baik. Kualitas mutu buahDelima memiliki tingkat kondisi berdasarkan tekstur, bentuk dan warnanya. Namun saat ini Penentuan kualitas mutu buahDelima masih dilakukan secara manual dalam pemilahan sehingga dapat memberikan hasil yang kurang tepat dan tidakkonsisten. Untuk mengatasi permasalahan ini dengan memanfaatkan teknik pengolahan citra digital untuk mengklasifikasikankualitas mutu buah Delima. Citra Delima melalui tahap preprocessing cropping, normalization 100x100, konversi grayscale.Untuk analisis proses ekstraksi fitur metode Gray Level Cooccurrence Matrix (GLCM) dengan arah sudut kombinasi 0°, 45°,90°, 135°. Kemudian algoritma K-Nearst Neighbor (KNN) sebagai tahap klasifikasi dengan nilai K. Data yang digunakan sebanyak 1.230 dataset yang terdiriatas 3 jenis buah Delima Grade A dan Grade B. Sebanyak 984 gambar sebagai data training dan 246 gambar lainnya untuk datauji. Hasil penenlitian mendapatkan tingkat akurasi tertinggi pada K=3 yang didapatkan sebesar 89%
41
Fu, Chao, Qing Lv, and Hsiung-Cheng Lin. "Development of Deep Convolutional Neural Network with Adaptive Batch Normalization Algorithm for Bearing Fault Diagnosis." Shock and Vibration 2020 (September 18, 2020): 1–10. http://dx.doi.org/10.1155/2020/8837958.
Full textAbstract:
It is crucial to carry out the fault diagnosis of rotating machinery by extracting the features that contain fault information. Many previous works using a deep convolutional neural network (CNN) have achieved excellent performance in finding fault information from feature extraction of detected signals. They, however, may suffer from time-consuming and low versatility. In this paper, a CNN integrated with the adaptive batch normalization (ABN) algorithm (ABN-CNN) is developed to avoid high computing resource requirements of such complex networks. It uses a large-scale convolution kernel at the grassroots level and a multidimensional 3 × 1 small convolution nuclear. Therefore, a fast convergence and high recognition accuracy under noise and load variation environment can be achieved for bearing fault diagnosis. The performance results verify that the proposed model is superior to Support Vector Machine with Fast Fourier Transform (FFT-SVM) and Multilayer Perceptron with Fast Fourier Transform (FFT-MLP) models and Deep Neural Network with Fast Fourier Transform (FFT-DNN).
42
Permatasari, Monica, and Santika Sari. "Pengukuran Kinerja Supply Chain Susu Kental Manis Menggunakan Metode SCOR dan AHP." Jurnal Optimalisasi 7, no. 1 (April 4, 2021): 109. http://dx.doi.org/10.35308/jopt.v7i1.2702.
Full textAbstract:
PT Frisian Flag Indonesia is a manufacturing company in Jakarta which is engaged in the milk processing industry. PT Frisian Flag Indonesia has not implemented a detailed performance measurement system and only applies a measure of the effectiveness of company performance. The need for Supply chain performance measurement to be able to find out the results of the Supply chain performance of sweetened condensed milk and make improvements to activities that are not optimal. The method used in this research is the AHP-SCOR method and to determine the Supply chain performance score, the Key Performance Indicator (KPI) measurement is used. The results showed 27 valid KPIs using the Snorm De Boer normalization process and the values obtained were: plan was 88,83, make was 93,79, source was 84,545, delivery was 88,149, Return was 38,53. The results of the SCOR model are 81.45. The need for improvements that prioritize performance with the smallest value, namely return.
43
Amalia, Junita, Natasya Yosevin Nababan, Kharisma Grace Tambunan, and Indah Sonia Sinaga. "DECISION TREE DENGAN BINARY BAT ALGORUTHM OPTIMIZATION PADA HEART CATHETERIZATION PREDICTION." Hexagon Jurnal Teknik dan Sains 3, no. 2 (July 10, 2022): 46–51. http://dx.doi.org/10.36761/hexagon.v3i2.1640.
Full textAbstract:
Risiko kateterisasi jantung kanan sangat besar, untuk menentukan seorang pasien akan melakukan kateterisasi jantung kanan secara optimal maka dibutuhkan prediksi apakah seorang pasien membutuhkan atau tidak. Pada penelitian ini, pengklasifikasian apakah pasien membutuhkan kateterisasi jantung kanan dengan algoritma K-Nearest Neighbor, Decision Tree C4.5, dan Decision Tree C4.5 yang dioptimasi dengan Bat Binary Algorithm. Sebelum dilakukan klasifikasi terlebih dahulu dilakukan preprocessing data yang memiliki tujuan untuk menghasilkan data yang baik untuk diproses dan didapatkan hasil klasifikasi yang akurat. Data preprocessing yang dilakukan adalah data cleaning, data selection dan data normalization. Kombinasi nilai parameter terbaik Binary Bat Algorithm sebagai pembangkit feature yang dipilih adalah q = 2, a = 0,2, r = 0,4, n = 30, Mi = 10 dan perbandingan data traning dan testing 90% dan 10%. Dari hasil eksperimen, nilai akurasi klasifikasi Decision Tree C4.5 dengan Bat Binary Algoritma paling tinggi ,yaitu 0,725. Sementara itu, nilai akurasi menggunakan K-Nearest Neighbor sebesar 0,600 dan nilai akurasi menggunakan Decision Tree C4.5 saja sebesar 0,588.
44
Murniningsih, Siti, and Alfisalam Ghifari Mustafa. "ANALISIS DAMPAK NORMALISASI SUNGAI TERHADAP EROSI DAN SEDIMENTASI DI DAERAH PERKOTAAN STUDI KASUS: SUNGAI PESANGGRAHAN, JAKARTA." INDONESIAN JOURNAL OF CONSTRUCTION ENGINEERING AND SUSTAINABLE DEVELOPMENT (CESD) 2, no. 2 (October 15, 2020): 54. http://dx.doi.org/10.25105/cesd.v2i2.6486.
Full textAbstract:
<span><em>Flooding is one of the problems that often occurs in the DKI Jakarta area, which one of the causes is the </em><span><em>change of land use in watersheds that were originally into development areas. Whereas, its often the cross </em><span><em>section of the river will be disrupted due to the loss of the riverbanks and the narrower cross section of the </em><span><em>river. In order to overcome this, the Jakarta Provincial Government in 2013 normalized several rivers that </em><span><em>crossed the DKI Province and one of them was the Pesanggrahan River which will be further investigated. </em><span><em>The purpose of this study is to analyze the effect of river normalization on erosion and sedimentation which </em><span><em>will result in changes in the longitudinal and cross section of the river. To get an accurate map of the</em><br /><span><em>Watershed Area, Arc-GIS software is used while identification of river flow before and after normalization </em><span><em>was carried out based on data from Central Office of River Region Ciliwung-Cisadane, Ministry of Public </em><span><em>Works. Sediment samples were taken at 3 points on the river, upstream, middle and downstream, that were </em><span><em>reviewed to determine the gradation of the sediment grains. The HEC-RAS application is used to simulate </em><span><em>sediment transport on the river section before and after normalization. The simulation results are used to </em><span><em>determine the cross section changes due to erosion and sedimentation and to determine the water level in the </em><span><em>river. From the water level, the hydraulic radius can be calculated and then carried out sediment transport </em><span><em>calculation using Ackers-White equation since the equation using grain distribution from range 0.02 – 4.94 </em><span><em>mm. The results it was found that the sediment transport in the upstream point increased 155.11 tons / year,</em><br /><span><em>at the midpoint increased 89.64 tons / year and the downstream point decreased 0.28 tons / year.</em></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span><br /><br class="Apple-interchange-newline" /></span>
45
Hung, Jeih-weih, Jung-Shan Lin, and Po-Jen Wu. "Employing Robust Principal Component Analysis for Noise-Robust Speech Feature Extraction in Automatic Speech Recognition with the Structure of a Deep Neural Network." Applied System Innovation 1, no. 3 (August 15, 2018): 28. http://dx.doi.org/10.3390/asi1030028.
Full textAbstract:
In recent decades, researchers have been focused on developing noise-robust methods in order to compensate for noise effects in automatic speech recognition (ASR) systems and enhance their performance. In this paper, we propose a feature-based noise-robust method that employs a novel data analysis technique—robust principal component analysis (RPCA). In the proposed scenario, RPCA is employed to process a noise-corrupted speech feature matrix, and the obtained sparse partition is shown to reveal speech-dominant characteristics. One apparent advantage of using RPCA for enhancing noise robustness is that no prior knowledge about the noise is required. The proposed RPCA-based method is evaluated with the Aurora-4 database and a task using a state-of-the-art deep neural network (DNN) architecture as the acoustic models. The evaluation results indicate that the newly proposed method can provide the original speech feature with significant recognition accuracy improvement, and can be cascaded with mean normalization (MN), mean and variance normalization (MVN), and relative spectral (RASTA)—three well-known and widely used feature robustness algorithms—to achieve better performance compared with the individual component method.
46
Anggraini, Novita, and Heri Suroyo. "Comparison of Sentiment Analysis against Digital Payment “T-cash and Go-pay” in Social Media Using Orange Data Mining." Journal of Information Systems and Informatics 1, no. 2 (September 2, 2019): 152–63. http://dx.doi.org/10.33557/journalisi.v1i2.21.
Full textAbstract:
Saat ini pembicaraan publik di sosial media menjadi salah satu hal menarik untuk diteliti. Dari topik pembicaraan itu menghasilkan komentar yang sebagian besar mengandung opini sentimen. Penelitian ini mencoba menganalisis komentar dengan metode analisis vader, yaitu metode analisis lexicon-based berbasis rule-based sentiment analysis. Vader akan menganalisis text berdasarkan lexicon (a library) yang menghasilkan class sentimen berupa positif, negatif, dan neutral dengan tambahan skor total atau compound (combined score). Penelitian ini memanfaatkan Prepocess text yang meliputi transformation, tokenization, normalization, dan filtering yang bertujuan agar text bisa dianalisis oleh Orange Data Mining guna mendapat perbandingan analisis sentimen terhadap T-cash dan Go-pay di sosial media. Dari penelitian yang dilakukan mendapat kesimpulan bahwa T-cash memiliki nilai sentimen positif lebih tinggi dari pada Go-pay dan memiliki sentimen negatif yang lebih rendah dari pada Go-pay. Namun persamaanya T-cash dan Go-pay memiliki kesamaan pola grafik dimana sentimen terbesar adalah neutral, diikuti oleh positif, dan terakhir adalah negative.
47
PARDEDE, JASMAN, and MUHAMMAD FAUZAN RASPATI. "Gated Recurrent Units dalam Mendeteksi Obstructive Sleep Apnea." MIND Journal 6, no. 2 (December 12, 2021): 221–35. http://dx.doi.org/10.26760/mindjournal.v6i2.221-235.
Full textAbstract:
AbstrakDalam melakukan penelitian obstructive sleep apnea (OSA), polysomnography (PSG) digunakan untuk diagnosis. Namun subjek diharuskan menginap dilaboratorium selama beberapa malam untuk melakukan tes dengan PSG dan karena banyaknya alat yang harus dikenakan pada tubuh dapat membuat tidak nyaman saat pengambilan data. Belakangan ini, beberapa peneliti mengunakan single-lead ECG untuk melakukan deteksi OSA. Untuk menghasilkan model terbaik, akan dilakukan eksperimen training, dengan batch normalization dan dropout yang berbeda. Pada penelitian ini apnea-ecg dataset digunakan, RR-Interval dan amplitudo QRS complex dari released set berjumlah 35 data akan disegmentasi permenit untuk digunakan sebagai input dari arsitektur yang diajukan adalah gated recurrent unit (GRU). Lalu withheld set berjumlah 35 data akan digunakan untuk pengujian per-segment dan per-recording. Kinerja sistem diukur berdasarkan accuracy, sensitifity, dan specificity dengan pengujian per-segment mendapat hasil accuracy 83.92%, sensitifity 81.28%, dan specificity 85.55%, dan pengujian per-recording mendapat hasil accuracy 97.14%, sensitifity 95.65% dan specificity 100%.Kata kunci: Obstructive sleep apnea, GRU, ECG, RR-Interval, QRS complex.AbstractIn conducting obstructive sleep apnea (OSA) studies, polysomnography (PSG) was used for the diagnosis. However, the subject was required to stay in the laboratory for several nights to carry out tests with the PSG and because of the many devices that had to be worn on the body, it could be uncomfortable to collect data. Recently, several researchers have used single-lead ECG to detect OSA. To produce the best model, training experiments will be conducted, with different batch normalization and dropout. In this study, the apnea-ecg dataset is used, the RR-Interval and the QRS complex amplitude from the released set totaling 35 data will be segmented per minute to be used as input for the proposed architecture is the gated recurrent unit (GRU). Then the withheld set of 35 data will be used for per-segment and per-recording testing. System performance was measured based on accuracy, sensitivity, and specificity with per-segment testing getting 83.92% accuracy, 81.28% sensitivity, and 85.55% specificity, and per-recording testing got 97.14% accuracy, 95.65% sensitivity and 100% specificity.Keywords: Obstructive sleep apnea, GRU, ECG, RR-Interval, QRS complex.
48
Putra, Mohd Nazar Isza, Dewi Sri Jayanti, and Agus Arip Munawar. "Penerapan metode non linier dan linier : support vector machine regression dan multiple linier regression untuk prediksi kualitas internal buah mangga (Mangifera indica LINN)." Jurnal Ilmiah Mahasiswa Pertanian 4, no. 4 (March 31, 2020): 452–61. http://dx.doi.org/10.17969/jimfp.v4i4.12698.
Full textAbstract:
Abstrak, Penelitian ini bertujuan untuk menguji dan mengevaluasi teknologi NIRS sebagai metode non destruktif untuk memprediksi kadar gula dan vitamin C pada mangga menggunakan Support Vector Machine Regression (SVMR) dan Multiple Linear Regression (MLR) sebagai metode kalibrasi serta menentukan pretreatment terbaik menggunakan Standar Normal Variate (SNV) dan Peak Normalalization (PN). Penelitian ini menggunakan 30 sampel mangga Arumanis dan FT-IR Science and Technology T-1516. Pengolahan data menggunakan Unscramble software® X versi 10.5. Prediksi TPT dengan metode SVMR menghasilkan nilai RPD 1,8 dengan interpretasi yang cukup baik, sedangkan metode MLR non-pretreatment menghasilkan nilai RPD sebesar 1,04 dengan interpretasinya adalah prediksi masih kasar. Pretreatment terbaik untuk memperkirakan TPT dengan metode MLR adalah Peak Normalization dengan nilai RPD adalah 0,98, r sebesar 0,421, R2sebesar 0,053 dan RMSEC sebesar 4,537. Hasil prediksi Vitamin C pada mangga dengan metode SVMR menghasilkan model kinerja yang baik dengan nilai RPD 2,4. Pretreatment terbaik untuk memperkirakan Vitamin C dengan metode Multiple Linear Regression (MLR) adalah Standard Normal Variate (SNV) dengan nilai RPD sebesar 0,92, r sebesar 0,339, R2sebesar 0,114 dan RMSEC sebesar 11,268. Berdasarkan penelitian ini dapat dinyatakan bahwa NIRS salah satu teknologi yang dapat digunakan untuk memprediksi kadar gula dan Vitamin C mangga dengan baik.Application of Non-Linier and Linier Method : Support Vector Machine Regression and Multiple Linier Regression to Prediction Internal Quality of Mango (Mangifera indica LINN)Abstract, This research aims to test and evaluate NIRS technology as a non-destructive method to predict SSC and Vitamin C in mangoes using Support Vector Machine Regression (SVMR) and Multiple Linear Regression (MLR) as a calibration method and determine the best pretreatment using Standard Normal Variate (SNV) and Peak Normalalization (PN). This study used 30 samples of Arumanis mangoes and FT-IR Science and Technology T-1516. Processing data using the Unscramble software® X version 10.5. The prediction results of SSC in mangoes by the SVMR method produces an RPD value of 1.8 with a fairly good interpretation, while the MLR method non pretreatment produces an RPD value of 1.04 with its interpretation is still a rough prediction. The best pretreatment for estimating SSC using the MLR method is Peak Normalization with the value of RPD is 0.98, r is 0.421, R2 is 0.053 and RMSEC is 4.537. The prediction results of Vitamin C in mangoes by the SVMR method produced a good performance model with a value of RPD is 2.4. The best pretreatment for estimating Vitamin C by the MLR method is Standard Normal Variate with an RPD value of 0.92, r is 0.339, R2 is 0.114 and RMSEC of 11.268. Based on this research, it can be stated that NIRS is one of the technologies that can be used to predict SSC and Vitamin C well enough.
49
Saputro, Erlangga Zohal. "NORMALISASI KAWASAN KUMUH EKS LOKALISASI PUTAT JAYA, KECAMATAN SAWAHAN, KOTA SURABAYA." Jurnal Kajian Ruang 2, no. 1 (March 31, 2022): 19. http://dx.doi.org/10.30659/jkr.v2i1.20602.
Full textAbstract:
ABSTRAK Normalisasi adalah suatu tindakan mengembalikan fungsi menjadi normal kembali. Gang Dolly adalah salah satu kawasan lokalisasi yang sudah terkenal lama sejak dan termasuk lokalisasi terbesar di Asia Tenggara. Pemerintah kota Surabaya sudah resmi menutup kawasan lokalisasi Gang Dolly pada tahun 2014. Pelaksanaan Normalisasi menjadi aspek penting bagi banyak individu karena yang dahulunya kawasan bersifat negatif kini menjadi normal kembali karena kota merupakan pusat aktivitas penduduk yang dilengkapi dengan berbagai sarana dan prasarana sebagai penunjang kebutuhan hidup penduduknya. Semakin hari kota surabaya semakin berkembang seiring dengan pertumbuhan penduduk yang semakin meningkat. Tak hanya pertumbuhan penduduknya saja, Perkembangan ekonomi semakin berkembang. Mulai banyak bermunculan kawasan kawasan wisata yang positif sehingga menuntut pemerintah kota surabaya untuk terus mengembangkan kotanya menjadi kawasan wisata yang positif. Kelurahan Putat Raya yang dulu terkenal dengan Gang Dolly nya kini sudah berubah 180◦ berbeda dengan dahulu, Kini sudah tidak ada praktek lokalisasi lagi dan ditambah pembangunan sarana dan prasarana nya yang sudah semakin baik dan dikelola baik oleh masyarakat sekitar. Kini sudah tidak terlihat kumuh namun sudah tertata dengan baik dan rapi.Penelitian ini merupakan hasil akhir terhadap kondisi kekumuhan kelurahan Putat Raya. Sehingga metode yang digunakan adalah metode kualitatif dengan melakukan analisa lapangan(primer). Adapun kondisi lapangan yang di analisa menyangkut 7 indikator permukiman kumuh. (Kondisi Jalan,Drainase,Persampahan,sanitasi,air bersih,rumah layak huni,kebencanaan).Kata Kunci : Normalisasi; Lokalisasi ; Surabaya ABSTRACT Normalization is an act of returning the function to normal again. Gang Dolly is one of the localization areas that has been known for a long time and is one of the largest localizations in Southeast Asia. The Surabaya city government has officially closed the Dolly Gang localization area in 2014. The implementation of normalization is an important aspect for many individuals because what was once a negative area has now become normal again because the city is the center of population activity which is equipped with various facilities and infrastructure to support the living needs of its residents. . The city of Surabaya is growing day by day along with the increasing population growth. Not only population growth, economic development is growing. Many positive tourist areas have started to appear, thus demanding the Surabaya city government to continue to develop its city into a positive tourist area.Putat Raya Village, which used to be famous for its Dolly Gang, has now changed 180◦ different from before, Now there is no more localization practice and the construction of facilities and infrastructure is getting better and well managed by the surrounding community. Now it doesn't look shabby, but it's well-organized and neat.This research is the final result of the slum conditions in Putat Raya village. So the method used is a qualitative method by conducting field analysis (primary). The field conditions that are analyzed involve 7 indicators of slum settlements. (road conditions, drainage, solid waste, sanitation, clean water, livable houses, disasters).Keyword: Normalization; localization; Surabaya
50
Putra, Fajar Andhika, Eva Yulia Puspaningrum, and Wahyu SJ Saputra. "Otomatisasi Pewarnaan Citra Monokrom dengan Metode Generative Adversarial Network." Prosiding Seminar Nasional Informatika Bela Negara 1 (November 1, 2020): 137–41. http://dx.doi.org/10.33005/santika.v1i0.37.
Full textAbstract:
Sistem pewarnaan otomatis pada citra greyscale diperlukan agar perbaikan pada citra monokrom dapat dilakukan secara cepat dan tanpa keahlian khusus. Dalam pengimplementasian sistem ini terdapat beberapa kendala seperti domain warna pada satu objek bisa sangat beragam, dimana setiap benda bisa memiliki lebih dari 1 kemungkinan warna. Pada penelitian ini penulis menggunakan SAGAN untuk melakukan pewarnaan otomatis pada dataset Hackaton Blossom (Flower Classification) yang bisa diakses pada situs resmi Kaggle, data ini berisikan citra 102 spesies bunga dengan jumlah data sebanyak 6500 data tes, 1000 data test dan 100 data validasi. SAGAN dipilih sebagai metode yang digunakan karena diklaim dapat menyelesaikan masalah image-to-image translation seperti style transfer, dan image colorization. Pada penelitian ini penulis berhasil mengimplementasikan dan melatih model SAGAN yang konvergen dengan memanfaatkan spectral normalization, selain itu penulis menambahkan SSIM loss untuk mengurangi munculnya artifact pada citra yang dihasilkan, model dilatih hingga 50 epoch dan berhasil memperoleh nilai PSNR diantara 51 dB hingga 73 dB dengan rata-rata nilai PNSR sebesar 61 dB.