To see the other types of publications on this topic, follow the link: MDLNN.
Journal articles on the topic 'MDLNN'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 30 journal articles for your research on the topic 'MDLNN.'
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
AL-Ghamdi, Abdullah S. AL-Malaise, and Mahmoud Ragab. "Tunicate swarm algorithm with deep convolutional neural network-driven colorectal cancer classification from histopathological imaging data." Electronic Research Archive 31, no. 5 (2023): 2793–812. http://dx.doi.org/10.3934/era.2023141.
Full textAbstract:
<abstract> <p>Colorectal cancer (CRC) is one of the most popular cancers among both men and women, with increasing incidence. The enhanced analytical load data from the pathology laboratory, integrated with described intra- and inter-variabilities through the calculation of biomarkers, has prompted the quest for robust machine-based approaches in combination with routine practice. In histopathology, deep learning (DL) techniques have been applied at large due to their potential for supporting the analysis and forecasting of medically appropriate molecular phenotypes and microsatellite instability. Considering this background, the current research work presents a metaheuristics technique with deep convolutional neural network-based colorectal cancer classification based on histopathological imaging data (MDCNN-C3HI). The presented MDCNN-C3HI technique majorly examines the histopathological images for the classification of colorectal cancer (CRC). At the initial stage, the MDCNN-C3HI technique applies a bilateral filtering approach to get rid of the noise. Then, the proposed MDCNN-C3HI technique uses an enhanced capsule network with the Adam optimizer for the extraction of feature vectors. For CRC classification, the MDCNN-C3HI technique uses a DL modified neural network classifier, whereas the tunicate swarm algorithm is used to fine-tune its hyperparameters. To demonstrate the enhanced performance of the proposed MDCNN-C3HI technique on CRC classification, a wide range of experiments was conducted. The outcomes from the extensive experimentation procedure confirmed the superior performance of the proposed MDCNN-C3HI technique over other existing techniques, achieving a maximum accuracy of 99.45%, a sensitivity of 99.45% and a specificity of 99.45%.</p> </abstract>
2
Ly, Ngoc Q., Tuong K. Do, and Binh X. Nguyen. "Large-Scale Coarse-to-Fine Object Retrieval Ontology and Deep Local Multitask Learning." Computational Intelligence and Neuroscience 2019 (July 18, 2019): 1–40. http://dx.doi.org/10.1155/2019/1483294.
Full textAbstract:
Object retrieval plays an increasingly important role in video surveillance, digital marketing, e-commerce, etc. It is facing challenges such as large-scale datasets, imbalanced data, viewpoint, cluster background, and fine-grained details (attributes). This paper has proposed a model to integrate object ontology, a local multitask deep neural network (local MDNN), and an imbalanced data solver to take advantages and overcome the shortcomings of deep learning network models to improve the performance of the large-scale object retrieval system from the coarse-grained level (categories) to the fine-grained level (attributes). Our proposed coarse-to-fine object retrieval (CFOR) system can be robust and resistant to the challenges listed above. To the best of our knowledge, the new main point of our CFOR system is the power of mutual support of object ontology, a local MDNN, and an imbalanced data solver in a unified system. Object ontology supports the exploitation of the inner-group correlations to improve the system performance in category classification, attribute classification, and conducting training flow and retrieval flow to save computational costs in the training stage and retrieval stage on large-scale datasets, respectively. A local MDNN supports linking object ontology to the raw data, and an imbalanced data solver based on Matthews’ correlation coefficient (MCC) addresses that the imbalance of data has contributed effectively to increasing the quality of object ontology realization without adjusting network architecture and data augmentation. In order to evaluate the performance of the CFOR system, we experimented on the DeepFashion dataset. This paper has shown that our local MDNN framework based on the pretrained NASNet architecture has achieved better performance (14.2% higher in recall rate) compared to single-task learning (STL) in the attribute learning task; it has also shown that our model with an imbalanced data solver has achieved better performance (5.14% higher in recall rate for fewer data attributes) compared to models that do not take this into account. Moreover, MAP@30 hovers 0.815 in retrieval on an average of 35 imbalanced fashion attributes.
3
Khan, Mohammad Ayoub. "An IoT Framework for Heart Disease Prediction Based on MDCNN Classifier." IEEE Access 8 (2020): 34717–27. http://dx.doi.org/10.1109/access.2020.2974687.
Full text
4
Praveena, Anto, and B. Bharathi. "An approach to remove duplication records in healthcare dataset based on Mimic Deep Neural Network (MDNN) and Chaotic Whale Optimization (CWO)." Concurrent Engineering 29, no. 1 (March 2021): 58–67. http://dx.doi.org/10.1177/1063293x21992014.
Full textAbstract:
Duplication of data in an application will become an expensive factor. These replication of data need to be checked and if it is needed it has to be removed from the dataset as it occupies huge volume of data in the storage space. The cloud is the main source of data storage and all organizations are already started to move their dataset into the cloud since it is cost effective, storage space, data security and data Privacy. In the healthcare sector, storing the duplicated records leads to wrong prediction. Also uploading same files by many users, data storage demand will be occurred. To address those issues, this paper proposes an Optimal Removal of Deduplication (ORD) in heart disease data using hybrid trust based neural network algorithm. In ORD scheme, the Chaotic Whale Optimization (CWO) algorithm is used for trust computation of data using multiple decision metrics. The computed trust values and the nature of the data’s are sequentially applied to the training process by the Mimic Deep Neural Network (MDNN). It classify the data is a duplicate or not. Hence the duplicates files are identified and they were removed from the data storage. Finally, the simulation evaluates to examine the proposed MDNN based model and simulation results show the effectiveness of ORD scheme in terms of data duplication removal. From the simulation result it is found that the model’s accuracy, sensitivity and specificity was good.
5
Lee, Jandee, Chan Hee Kim, In Kyung Min, Seonhyang Jeong, Hyunji Kim, Moon Jung Choi, Hyeong Ju Kwon, Sang Geun Jung, and Young Suk Jo. "Detailed characterization of metastatic lymph nodes improves the prediction accuracy of currently used risk stratification systems in N1 stage papillary thyroid cancer." European Journal of Endocrinology 183, no. 1 (July 2020): 83–93. http://dx.doi.org/10.1530/eje-20-0131.
Full textAbstract:
Objective The characteristics of metastatic lymph nodes (MLNs) have been investigated as important predictors of recurrence and progression in papillary thyroid cancer (PTC). However, clinically applicable risk stratification systems are limited to the assessment of size and number of MLNs. This study investigated the predictive value of detailed characteristics of MLNs in combination with currently used risk stratification systems. Design and methods We retrospectively characterized 2811 MLNs from 9014 harvested LNs of 286 patients with N1 PTC according to the maximum diameter of MLN (MDLN), maximum diameter of metastatic focus (MDMF), ratio of both diameters (MDMFR), lymph node ratio (LNR, number of MLNs/number of total harvested LNs), presence of extranodal extension (ENE), desmoplastic reaction (DR), cystic component, and psammoma body. Results Factors related to the size and number of MLNs were associated with increased risk of recurrence and progression. Extensive presence of ENE (>40%) and DR (≥50%) increased the risk of recurrence/progression. The combination of MDLN, LNR, ENE, and DR had the highest predictive value among MLN characteristics. Combination of these parameters with ATA risk stratification or 1-year response to therapy improved the predictive power for recurrence/progression from a Harrell’s C-index of 0.781 to 0.936 and 0.867 to 0.960, respectively. Conclusions The combination of currently used risk stratification systems with detailed characterization of MLNs may improve the predictive accuracy for recurrence/progression in N1 PTC patients.
6
Sukardi, Hadi Ahmad. "ANALISIS INVESTASI SAHAM DENGAN MENGGUNAKAN CAPITAL ASSET PRICING MODEL." Jurnal SIKAP (Sistem Informasi, Keuangan, Auditing Dan Perpajakan) 5, no. 1 (February 8, 2021): 18. http://dx.doi.org/10.32897/jsikap.v5i1.251.
Full textAbstract:
Analisis menunjukkan bahwa dari 23 saham perusahaan yang terpilih sebagai sampel penelitian, terdapat 5 saham efisien dan 18 saham tidak efisien berdasarkan metode CAPM. Saham-saham efisien adalah saham undervalued dengan nilai R_i > nilai E(R_i ). Saham-saham efisien yaitu PPRO, EMDE, JSPT, DMAS dan PWON. Sedangkan saham tidak efisien adalah saham yang memiliki nilai R_i < nilai E(R_i ) dan dikatakan sebagai saham overvalued. Saham-saham tidak efisien tersebut yaitu APLN, DILD, ELTY, KIJA, SMDM, LPKR, BSDE, SMRA, CTRA, MDLN, COWL, ASRI, MTLA, GPRA, RODA, GWSA, LPCK dan BEST.
7
Chen, Yi, Jin Zhou, Qianting Gao, Jing Gao, and Wei Zhang. "MDNN: Predicting Student Engagement via Gaze Direction and Facial Expression in Collaborative Learning." Computer Modeling in Engineering & Sciences 136, no. 1 (2023): 381–401. http://dx.doi.org/10.32604/cmes.2023.023234.
Full text
8
Lackner, Thomas E. "Advances in Managing Overactive Bladder." Journal of Pharmacy Practice 13, no. 4 (August 1, 2000): 277–89. http://dx.doi.org/10.1106/8843-q9gl-g9xc-mdln.
Full text
9
Wang, Xingmei, Anhua Liu, Yu Zhang, and Fuzhao Xue. "Underwater Acoustic Target Recognition: A Combination of Multi-Dimensional Fusion Features and Modified Deep Neural Network." Remote Sensing 11, no. 16 (August 13, 2019): 1888. http://dx.doi.org/10.3390/rs11161888.
Full textAbstract:
A method with a combination of multi-dimensional fusion features and a modified deep neural network (MFF-MDNN) is proposed to recognize underwater acoustic targets in this paper. Specifically, due to the complex and changeable underwater environment, it is difficult to describe underwater acoustic signals with a single feature. The Gammatone frequency cepstral coefficient (GFCC) and modified empirical mode decomposition (MEMD) are developed to extract multi-dimensional features in this paper. Moreover, to ensure the same time dimension, a dimension reduction method is proposed to obtain multi-dimensional fusion features in the original underwater acoustic signals. Then, to reduce redundant features and further improve recognition accuracy, the Gaussian mixture model (GMM) is used to modify the structure of a deep neural network (DNN). Finally, the proposed underwater acoustic target recognition method can obtain an accuracy of 94.3% under a maximum of 800 iterations when the dataset has underwater background noise with weak targets. Compared with other methods, the recognition results demonstrate that the proposed method has higher accuracy and strong adaptability.
10
Huang, Xixian, Xiongjun Zeng, Qingxiang Wu, Yu Lu, Xi Huang, and Hua Zheng. "Face Verification Based on Deep Learning for Person Tracking in Hazardous Goods Factories." Processes 10, no. 2 (February 17, 2022): 380. http://dx.doi.org/10.3390/pr10020380.
Full textAbstract:
Person tracking in hazardous goods factories can provide a significant improvement in security and safety. This article proposes a face verification model which can be used to record travel paths for staff or related persons in the factory. As face images are captured from the dynamic crowd at entrance–exit gates of workshops, face verification is challenged by polymorphic faces, poor illumination and changing of a person’s pose. To adapt to this situation, a new face verification model is proposed, which is composed of two advanced deep learning neural network models. Firstly, MTCNN (Multi-Task Cascaded Convolutional Neural Network) is used to construct a face detector. Based on the SphereFace-20 network model, we have reconstructed a convolutional network architecture with the embedded Batch Normalization elements and the optimized network parameters. The new model, which is called the MDCNN, is used to extract efficient face features. A set of specific processing algorithms is used in the model to process polymorphic face images. The multi-view faces and various types of face images are used to train the models. The experimental results have demonstrated that the proposed model outperforms most existing methods on benchmark datasets such as the Labeled Faces in the Wild (LFW) and YouTube Face (YTF) datasets without multi-view (accuracy is 99.38% and 94.30%, respectively) and the CNBC/FERET datasets with multi-view (accuracy is 94.69%).
11
Chen, Zhong, Jun Zhao, and He Deng. "Global Multi-Attention UResNeXt for Semantic Segmentation of High-Resolution Remote Sensing Images." Remote Sensing 15, no. 7 (March 30, 2023): 1836. http://dx.doi.org/10.3390/rs15071836.
Full textAbstract:
Semantic segmentation has played an essential role in remote sensing image interpretation for decades. Although there has been tremendous success in such segmentation with the development of deep learning in the field, several limitations still exist in the current encoder–decoder models. First, the potential interdependencies of the context contained in each layer of the encoder–decoder architecture are not well utilized. Second, multi-scale features are insufficiently used, because the upper-layer and lower-layer features are not directly connected in the decoder part. In order to solve those limitations, a global attention gate (GAG) module is proposed to fully utilize the interdependencies of the context and multi-scale features, and then a global multi-attention UResNeXt (GMAUResNeXt) module is presented for the semantic segmentation of remote sensing images. GMAUResNeXt uses GAG in each layer of the decoder part to generate the global attention gate (for utilizing the context features) and connects each global attention gate with the uppermost layer in the decoder part by using the Hadamard product (for utilizing the multi-scale features). Both qualitative and quantitative experimental results demonstrate that use of GAG in each layer lets the model focus on a certain pattern, which can help improve the effectiveness of semantic segmentation of remote sensing images. Compared with state-of-the-art methods, GMAUResNeXt not only outperforms MDCNN by 0.68% on the Potsdam dataset with respect to the overall accuracy but is also the MANet by 3.19% on the GaoFen image dataset. GMAUResNeXt achieves better performance and more accurate segmentation results than the state-of-the-art models.
12
Zhang, Mengqi, Xi Wang, V. E. Sathishkumar, and V. Sivakumar. "Machine learning techniques based on security management in smart cities using robots." Work 68, no. 3 (March 26, 2021): 891–902. http://dx.doi.org/10.3233/wor-203423.
Full textAbstract:
BACKGROUND: Nowadays, the growth of smart cities is enhanced gradually, which collects a lot of information and communication technologies that are used to maximize the quality of services. Even though the intelligent city concept provides a lot of valuable services, security management is still one of the major issues due to shared threats and activities. For overcoming the above problems, smart cities’ security factors should be analyzed continuously to eliminate the unwanted activities that used to enhance the quality of the services. OBJECTIVES: To address the discussed problem, active machine learning techniques are used to predict the quality of services in the smart city manages security-related issues. In this work, a deep reinforcement learning concept is used to learn the features of smart cities; the learning concept understands the entire activities of the smart city. During this energetic city, information is gathered with the help of security robots called cobalt robots. The smart cities related to new incoming features are examined through the use of a modular neural network. RESULTS: The system successfully predicts the unwanted activity in intelligent cities by dividing the collected data into a smaller subset, which reduces the complexity and improves the overall security management process. The efficiency of the system is evaluated using experimental analysis. CONCLUSION: This exploratory study is conducted on the 200 obstacles are placed in the smart city, and the introduced DRL with MDNN approach attains maximum results on security maintains.
13
Sukardi, Hadi Ahmad. "ANALISIS INVESTASI SAHAM PADA PERUSAHAAN PERAIH PENGHARGAAN PROPERTY AWARD 2018 YANG LISTED DI BEI DENGAN MENGGUNAKAN CAPITAL ASSET PRICING MODEL." Ekono Insentif 14, no. 1 (April 6, 2020): 54–64. http://dx.doi.org/10.36787/jei.v14i1.211.
Full textAbstract:
Abstrak - Pertumbuhan sektor properti di Indonesia semakin berkembang pesat, dimana hal ini bisa dilihat dengan banyaknya perusahaan yang berdiri dan menjalankan operasionalnya dalam bentuk proyek-proyek. Hal ini peneliti lakukan untuk membantu menganalisa perusahaan-perusahaan induk yang anak-anak perusahaannya mendapatkan penghargaan dari warta ekonomi berupa beberapa kategori dalam memperoleh property award pada tahun 2018 dan bertujuan membandingkan perusahaan-perusahaan tersebut dan dikatakan layak berinvestasi di perusahaan-perusahaan tersebut. Dalam penelitian ini, peneliti hanya memperoleh sebanyak 23 saham perusahaan yang terpilih sebagai sampel penelitian dengan menggunakan purposive sampling. Hasil yang didapat oleh peneliti dalam analisis ini terdapat 5 saham efisien dan 18 saham tidak efisien berdasarkan perhitungan CAPM. Saham efisien adalah saham undervalued dengan nilai > nilai . Saham-saham efisien tersebut yakni : PPRO, EMDE, JSPT, DMAS dan PWON. Sedangkan saham yang tidak efisien adalah saham yang memiliki nilai < nilai dan dikatakan sebagai saham overvalued. Saham-saham tidak efisien tersebut yakni : APLN, DILD, ELTY, KIJA, SMDM, LPKR, BSDE, SMRA, CTRA, MDLN, COWL, ASRI, MTLA, GPRA, RODA, GWSA, LPCK dan BEST. Dilain sisi peneliti memperoleh penjelasan bahwa tingkat risiko tidak selalu berhubungan linier dengan tingkat pengembalian, dimana hal ini terlihat ketika peneliti menganalisa hasil risiko sistematis β (beta) yang hubungannya terbalik dengan ekspektasi pengembalian , dengan adanya perubahan posisi perusahaan yang memiliki risiko paling tinggi ternyata ekspektasi pengembaliannya rendah dan perusahaan yang memiliki risiko paling rendah justru ternyata ekspektasi pengembaliannya menjadi tinggi, hal ini terjadi pada perusahaan BEST dan ELTY. Hasil pengambilan hipotesis yaitu tidak semuanya perusahaan yang dapat peraih property award yang bisa dibeli sahamnya tetapi hanya sebagian saja.
Abstract - The growth of the property sector in Indonesia is growing rapidly, where this can be seen with the number of companies that stand up and run operations in the form of projects. This is done by researchers to help analyze the parent companies whose subsidiaries received awards from the journalists in the form of several categories in obtaining property awards in 2018 and aimed at comparing these companies and said to be worth investing in those companies. In this study, researchers only obtained as many as 23 company shares that were selected as research samples by using purposive sampling. The results obtained by researchers in this analysis there are 5 efficient shares and 18 inefficient stocks based on the CAPM calculation. An efficient stock is an undervalued stock with a value of R_i> value E (R_i). These efficient stocks are: PPRO, EMDE, JSPT, DMAS and PWON. While inefficient stocks are stocks that have a value of R_i <value of E (R_i) and are said to be overvalued shares. The inefficient stocks are: APLN, DILD, ELTY, KIJA, SMDM, LPKR, BSDE, SMRA, CTRA, MDLN, COWL, ASRI, MTLA, GPRA, WHEEL, GWSA, LPCK and BEST. On the other hand the researcher gets the explanation that the level of risk is not always linearly related to the rate of return, where this is seen when the researcher analyzes the results of systematic risk β (beta) whose relationship is inversely related to the expected return of E (R_i), with a change in the position of the company that has the most risk high turns out to have low return expectations and the company with the lowest risk actually turns out to have high return expectations, this happens to BEST and ELTY companies. The results of making a hypothesis that not all companies that can win property awards can be bought but only partial shares.
14
Christal, Suma, G. Uma Maheswari, Prabhjot Kaur, and Anupama Kaushik. "Heart Diseases Diagnosis Using Chaotic Harris Hawk Optimization with E-CNN for IoMT Framework." Information Technology and Control 52, no. 2 (July 15, 2023): 500–514. http://dx.doi.org/10.5755/j01.itc.52.2.32778.
Full textAbstract:
In the current state of medical research, the diagnosis of heart disease has become a challenging medical objective. This diagnosis is dependent on a thorough and accurate review of the detailed medical test results and medical background of the patient. With the aid of the internet of things (IoT) and the huge advancements in the field of deep learning, researchers aim to produce intelligent monitoring systems that assist physicians in both predicting and diagnosing disorders. In this context, this work proposes a novel prediction model based on deep learning and Internet-of-Medical-Things for the efficient and real-time diagnosis of heart disease. In this work, data from the Cleveland dataset is used for training the proposed model and further the data that is gathered from the sensors in the IoMT environment is used for testing the prediction capability of the model. Chaotic Harris Hawk optimization algorithm is employed for the feature extraction from the data and these extracted features are further passed on to the classification stage where Enhanced Convolutional Neural Networks are utilized to classify whether the patient is affected by heart disease or not. In order to evaluate the performance of the proposed model, it is compared with the Machine learning models such as Support Vector Machine with Ant Colony Optimization(SVM-ACO), Random Forest with Particle Swarm Optimization(RF-PSO), Naive Bayes with Harris Hawk Optimization(NB-HHO), K Nearest Neighbor with Spiral Optimization(KNN-SPO). Also, the proposed model is compared against deep learning architectures such as VGG-16, ResNet, AlexNet,ZFNet. Further, the proposed model also outperforms two existing works taken from the literature, Faster R-CNN-ALO, and MDCNN-AEHO, with a higher accuracy of 99.2%.
15
Turner, Daniel, Pedro J. S. Cardoso, and João M. F. Rodrigues. "Modular Dynamic Neural Network: A Continual Learning Architecture." Applied Sciences 11, no. 24 (December 18, 2021): 12078. http://dx.doi.org/10.3390/app112412078.
Full textAbstract:
Learning to recognize a new object after having learned to recognize other objects may be a simple task for a human, but not for machines. The present go-to approaches for teaching a machine to recognize a set of objects are based on the use of deep neural networks (DNN). So, intuitively, the solution for teaching new objects on the fly to a machine should be DNN. The problem is that the trained DNN weights used to classify the initial set of objects are extremely fragile, meaning that any change to those weights can severely damage the capacity to perform the initial recognitions; this phenomenon is known as catastrophic forgetting (CF). This paper presents a new (DNN) continual learning (CL) architecture that can deal with CF, the modular dynamic neural network (MDNN). The presented architecture consists of two main components: (a) the ResNet50-based feature extraction component as the backbone; and (b) the modular dynamic classification component, which consists of multiple sub-networks and progressively builds itself up in a tree-like structure that rearranges itself as it learns over time in such a way that each sub-network can function independently. The main contribution of the paper is a new architecture that is strongly based on its modular dynamic training feature. This modular structure allows for new classes to be added while only altering specific sub-networks in such a way that previously known classes are not forgotten. Tests on the CORe50 dataset showed results above the state of the art for CL architectures.
16
Huang, Jinchao. "Auto-attentional mechanism in multi-domain convolutional neural networks for improving object tracking." International Journal of Intelligent Computing and Cybernetics ahead-of-print, ahead-of-print (August 30, 2021). http://dx.doi.org/10.1108/ijicc-04-2021-0067.
Full textAbstract:
PurposeMulti-domain convolutional neural network (MDCNN) model has been widely used in object recognition and tracking in the field of computer vision. However, if the objects to be tracked move rapid or the appearances of moving objects vary dramatically, the conventional MDCNN model will suffer from the model drift problem. To solve such problem in tracking rapid objects under limiting environment for MDCNN model, this paper proposed an auto-attentional mechanism-based MDCNN (AA-MDCNN) model for the rapid moving and changing objects tracking under limiting environment.Design/methodology/approachFirst, to distinguish the foreground object between background and other similar objects, the auto-attentional mechanism is used to selectively aggregate the weighted summation of all feature maps to make the similar features related to each other. Then, the bidirectional gated recurrent unit (Bi-GRU) architecture is used to integrate all the feature maps to selectively emphasize the importance of the correlated feature maps. Finally, the final feature map is obtained by fusion the above two feature maps for object tracking. In addition, a composite loss function is constructed to solve the similar but different attribute sequences tracking using conventional MDCNN model.FindingsIn order to validate the effectiveness and feasibility of the proposed AA-MDCNN model, this paper used ImageNet-Vid dataset to train the object tracking model, and the OTB-50 dataset is used to validate the AA-MDCNN tracking model. Experimental results have shown that the augmentation of auto-attentional mechanism will improve the accuracy rate 2.75% and success rate 2.41%, respectively. In addition, the authors also selected six complex tracking scenarios in OTB-50 dataset; over eleven attributes have been validated that the proposed AA-MDCNN model outperformed than the comparative models over nine attributes. In addition, except for the scenario of multi-objects moving with each other, the proposed AA-MDCNN model solved the majority rapid moving objects tracking scenarios and outperformed than the comparative models on such complex scenarios.Originality/valueThis paper introduced the auto-attentional mechanism into MDCNN model and adopted Bi-GRU architecture to extract key features. By using the proposed AA-MDCNN model, rapid object tracking under complex background, motion blur and occlusion objects has better effect, and such model is expected to be further applied to the rapid object tracking in the real world.
17
Pi, Jiangsheng, Peishun Jiao, Yang Zhang, and Junyi Li. "MDGNN: Microbial Drug Prediction Based on Heterogeneous Multi-Attention Graph Neural Network." Frontiers in Microbiology 13 (April 7, 2022). http://dx.doi.org/10.3389/fmicb.2022.819046.
Full textAbstract:
Human beings are now facing one of the largest public health crises in history with the outbreak of COVID-19. Traditional drug discovery could not keep peace with newly discovered infectious diseases. The prediction of drug-virus associations not only provides insights into the mechanism of drug–virus interactions, but also guides the screening of potential antiviral drugs. We develop a deep learning algorithm based on the graph convolutional networks (MDGNN) to predict potential antiviral drugs. MDGNN is consisted of new node-level attention and feature-level attention mechanism and shows its effectiveness compared with other comparative algorithms. MDGNN integrates the global information of the graph in the process of information aggregation by introducing the attention at node and feature level to graph convolution. Comparative experiments show that MDGNN achieves state-of-the-art performance with an area under the curve (AUC) of 0.9726 and an area under the PR curve (AUPR) of 0.9112. In this case study, two drugs related to SARS-CoV-2 were successfully predicted and verified by the relevant literature. The data and code are open source and can be accessed from https://github.com/Pijiangsheng/MDGNN.
18
Lei, Chunli, Linlin Xue, Mengxuan Jiao, Huqiang Zhang, and Jiashuo Shi. "Rolling bearing fault diagnosis by markov transition field and multi-dimension convolutional neural network." Measurement Science and Technology, August 8, 2022. http://dx.doi.org/10.1088/1361-6501/ac87c4.
Full textAbstract:
Abstract Safe and reliable operation of mechanical equipment depends on timely and accurate fault diagnosis. When the actual working conditions are complex and variable and the available sample data set is small, recognition accuracy of the rolling bearing fault diagnosis model is low. To solve this problem, a novel method based on Markov transition field (MTF) and multi-dimension convolutional neural network (MDCNN) is proposed in this paper. Firstly, the original vibration signals are converted into two-dimensional images containing temporal correlation by MTF. Then, a neural network model is constructed by using multi-dimension attention (MDA) and E-Relu activation function to fully extract fault feature information. Finally, the MTF images are input into the model and the data is normalized using the group normalization method. The MDCNN model is validated on two different data sets, and the results show that compared with other intelligent fault diagnosis methods, the MDCNN has higher fault diagnosis accuracy and stronger robustness under both variable working conditions and small sample data sets conditions.
19
CHANG, JIHUI, XUZHONG QIU, HAIJUN HUANG, YUN ZHANG, HAO SHEN, KAI LI, SHUANG ZHANG, JIANGMING KUANG, and JINING YANG. "A COMPARATIVE STUDY OF MIPPO AND MDLIN APPLIED TO THE TREATMENT OF DISTAL TIBIAL FRACTURES." Journal of Mechanics in Medicine and Biology, March 17, 2022. http://dx.doi.org/10.1142/s0219519422400115.
Full textAbstract:
Objective: This study aims to analyze the clinical treatment effects of the minimally invasive percutaneous plate osteosynthesis (MIPPO) and multi-directional locking intramedullary nail (MDLIN) techniques in patients with distal tibial fractures. Methods: A total of 124 patients with distal tibial fractures, admitted to the People’s Hospital of Zhongjiang County from February 2019 to January 2020, were selected as the research subjects. They were randomly divided into groups ([Formula: see text]). The control group received MIPPO treatment, the observation group received MDLIN treatment, and the postoperative therapeutic effects and complications in the two groups were compared. Results: The patients in the observation group had shorter operative time and lower intraoperative blood loss than those in the control group ([Formula: see text]). The two groups had no significant differences in fracture healing time, complete weight bearing time, or functional recovery. The postoperative complication rate in the cases of the observation group was significantly lower than that of the control group ([Formula: see text]). Conclusion: Both techniques can achieve sufficient therapeutic effects; however, the MDLIN technique has certain advantages, including significantly fewer complications, lower intraoperative blood loss, and shorter operative durations compared to the MIPPO technique.
20
Afshar, Shiva, Patricia R. Braun, Shizhong Han, and Ying Lin. "A multimodal deep learning model to infer cell-type-specific functional gene networks." BMC Bioinformatics 24, no. 1 (February 14, 2023). http://dx.doi.org/10.1186/s12859-023-05146-x.
Full textAbstract:
Abstract Background Functional gene networks (FGNs) capture functional relationships among genes that vary across tissues and cell types. Construction of cell-type-specific FGNs enables the understanding of cell-type-specific functional gene relationships and insights into genetic mechanisms of human diseases in disease-relevant cell types. However, most existing FGNs were developed without consideration of specific cell types within tissues. Results In this study, we created a multimodal deep learning model (MDLCN) to predict cell-type-specific FGNs in the human brain by integrating single-nuclei gene expression data with global protein interaction networks. We systematically evaluated the prediction performance of the MDLCN and showed its superior performance compared to two baseline models (boosting tree and convolutional neural network). Based on the predicted cell-type-specific FGNs, we observed that cell-type marker genes had a higher level of hubness than non-marker genes in their corresponding cell type. Furthermore, we showed that risk genes underlying autism and Alzheimer’s disease were more strongly connected in disease-relevant cell types, supporting the cellular context of predicted cell-type-specific FGNs. Conclusions Our study proposes a powerful deep learning approach (MDLCN) to predict FGNs underlying a diverse set of cell types in human brain. The MDLCN model enhances prediction accuracy of cell-type-specific FGNs compared to single modality convolutional neural network (CNN) and boosting tree models, as shown by higher areas under both receiver operating characteristic (ROC) and precision-recall curves for different levels of independent test datasets. The predicted FGNs also show evidence for the cellular context and distinct topological features (i.e. higher hubness and topological score) of cell-type marker genes. Moreover, we observed stronger modularity among disease-associated risk genes in FGNs of disease-relevant cell types. For example, the strength of connectivity among autism risk genes was stronger in neurons, but risk genes underlying Alzheimer’s disease were more connected in microglia.
21
Sparacio, Alessandro, Ivan Ropovik, Gabriela Jiga-Boy, Adar Cem Lağap, and Hans IJzerman. "Stress Regulation via Being in Nature and Social Support in Adults, a Meta-analysis." Collabra: Psychology 9, no. 1 (2023). http://dx.doi.org/10.1525/collabra.77343.
Full textAbstract:
In this meta-analysis, the authors investigated whether being in nature and emotional social support are reliable strategies to downregulate stress. We retrieved all the relevant articles that investigated a connection between one of these two strategies and stress. For being in nature we found 54 effects reported in 16 papers (total N = 1,697, MdnN = 52.5), while for emotional social support we found 18 effects reported in 13 papers (total N = 3,787, MdnN = 186). Although we initially found an effect for being in nature and emotional social support on stress (Hedges’ g = -.42; Hedges’ g = -.14, respectively), the effect only held for being in nature after applying our main publication bias correction technique (Hedges’ g = -.60). The emotional social support literature also had a high risk of bias. Although the being-in-nature literature was moderately powered (.72) to detect effects of Cohen’s d = .50 or larger, the risk of bias was considerable, and the reporting contained numerous statistical reporting errors.
22
Dong, Meilin, Weisheng Li, Xuesong Liang, and Xiayan Zhang. "MDCNN: multispectral pansharpening based on a multiscale dilated convolutional neural network." Journal of Applied Remote Sensing 15, no. 03 (September 8, 2021). http://dx.doi.org/10.1117/1.jrs.15.036516.
Full text
23
Wang, Zheng, Chuanbo Wen, and Yifan Dong. "A Method for Rolling Bearing Fault Diagnosis Based on GSC-MDRNN with Multi-Dimensional Input." Measurement Science and Technology, January 4, 2023. http://dx.doi.org/10.1088/1361-6501/acb000.
Full textAbstract:
Abstract The traditional fault diagnosis methods of rolling bearing through neural networks mostly use data sources collected by a single sensor and use single-dimensional data input, causing fault features in bearings cannot be completely extracted. Moreover, traditional convolution often uses single-size convolution kernels, which is insufficient for fault feature extraction. In response to these problems, the Global Shortcut Connection - Multichannel Deep ResNet Network (GSC-MDRNN) model is proposed. First, a new residual structure, the Global Shortcut Connection, is proposed to fuse two-dimensional and one-dimensional signal features. Second, involution is introduced into the field of fault diagnosis to address the problem of insufficient network feature extraction caused by using single-size convolution kernels. In addition, the CBAM module can adaptively assign the weight of each channel feature to achieve adaptive channel fusion. The verification was performed on the four-category and eight-category data sets collected in the laboratory, and the results show that this method has a high fault recognition rate.
24
Morar, Ulyana, Harold Martin, Robin P. M., Walter Izquierdo, Elaheh Zarafshan, Parisa Forouzannezhad, Elona Unger, et al. "Prediction of Cognitive Test Scores from Variable Length Multimodal Data in Alzheimer’s Disease." Cognitive Computation, July 19, 2023. http://dx.doi.org/10.1007/s12559-023-10169-w.
Full textAbstract:
AbstractAlzheimer’s disease (AD) is a neurogenerative condition characterized by sharp cognitive decline with no confirmed effective treatment or cure. This makes it critically important to identify the symptoms of Alzheimer’s disease in its early stages before significant cognitive deterioration has taken hold and even before any brain morphology and neuropathology are noticeable. In this study, five different multimodal deep neural networks (MDNN), with different architectures, in search of an optimal model for predicting the cognitive test scores for the Mini-Mental State Examination (MMSE) and the modified Alzheimer’s Disease Assessment Scale (ADAS-CoG13) over a span of 60 months (5 years). The multimodal data utilized to train and test the proposed models were obtained from the Alzheimer’s Disease Neuroimaging Initiative study and includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from the neuropsychological tests (Cog). The models developed herein delve into two main issues: (1) application merits of single-task vs. multitask for predicting future cognitive scores and (2) whether time-varying input data are better suited than specific timepoints for optimizing prediction results. This model yields a high of 90.27% (SD = 1.36) prediction accuracy (correlation) at 6 months after the initial visit to a lower 79.91% (SD = 8.84) prediction accuracy at 60 months. The analysis provided is comprehensive as it determines the predictions at all other timepoints and all MDNN models include converters in the CN and MCI groups (CNc, MCIc) and all the unstable groups in the CN and MCI groups (CNun and MCIun) that reverted to CN from MCI and to MCI from AD, so as not to bias the results. The results show that the best performance is achieved by a multimodal combined single-task long short-term memory (LSTM) regressor with an input sequence length of 2 data points (2 visits, 6 months apart) augmented with a pretrained Neural Network Estimator to fill in for the missing values.
25
"Heart Transplantation in Children. Jeffrey MDunn, Richard MDonner. Futura Publishing Company, Mount Kisco, New York, 1990. 273 pp. $49.00." International Journal of Clinical Practice 44, no. 10 (October 1990): 392. http://dx.doi.org/10.1111/j.1742-1241.1990.tb10866.x.
Full text
26
Machina, Venkata Siva Prasad, Sriranga Suprabhath Koduru, Sreedhar Madichetty, and Sukumar Mishra. "A Novel Standalone Implementation of MDNN Controller for DC-DC Converter Resilient to Sensor Attacks- A Design Approach." IEEE Journal of Emerging and Selected Topics in Power Electronics, 2023, 1. http://dx.doi.org/10.1109/jestpe.2023.3242299.
Full text
27
Wang, Hong, Liqun Wang, Shufang Zhao, and Xiuming Yue. "Multi-dimensional Prediction Model for Cell Traffic in City Scale." International Journal of Pattern Recognition and Artificial Intelligence, October 9, 2020, 2150010. http://dx.doi.org/10.1142/s0218001421500105.
Full textAbstract:
Traffic prediction is a classical time series prediction which has been investigated in different domains, but most existing models are proposed based on limited time or spatial scale. Mobile cellular network traffic prediction is of paramount importance for quality-of-service (QoS) and power management of the cellular base stations, especially in the 5G era. Through the statistical analysis of the real historical traffic data obtained in a city scale spanning across multiple months, this paper makes an in-depth study of the temporal characteristics and behavior rules of the model data traffic. Considering that the time series data show different changing rules under the different time dimensions, spatial dimensions and independent dimensions, a multi-dimensional recurrent neural network (MDRNN) prediction model is established to predict the future cell traffic volume over various temporal and spatial dimensions. The data of this paper are trained and tested over real data of a city, and the granularity of the proposed prediction model can be drilled down to the cell level. Compared with the traditional trend fitting method, the proposed model achieves mean absolute percentage error (MAPE) reduction of 6.56%, and provides guidance for energy efficiency optimization and power consumption reduction of base stations in various temporal and spatial dimensions.
28
Wang, Lei, Jian Guo, Zhuang Tian, Samuel Seery, Ye Jin, and Shuyang Zhang. "Developing a Hybrid Risk Assessment Tool for Familial Hypercholesterolemia: A Machine Learning Study of Chinese Arteriosclerotic Cardiovascular Disease Patients." Frontiers in Cardiovascular Medicine 9 (August 3, 2022). http://dx.doi.org/10.3389/fcvm.2022.893986.
Full textAbstract:
BackgroundFamilial hypercholesterolemia (FH) is an autosomal-dominant genetic disorder with a high risk of premature arteriosclerotic cardiovascular disease (ASCVD). There are many alternative risk assessment tools, for example, DLCN, although their sensitivity and specificity vary among specific populations. We aimed to assess the risk discovery performance of a hybrid model consisting of existing FH risk assessment tools and machine learning (ML) methods, based on the Chinese patients with ASCVD.Materials and MethodsIn total, 5,597 primary patients with ASCVD were assessed for FH risk using 11 tools. The three best performing tools were hybridized through a voting strategy. ML models were set according to hybrid results to create a hybrid FH risk assessment tool (HFHRAT). PDP and ICE were adopted to interpret black box features.ResultsAfter hybridizing the mDLCN, Taiwan criteria, and DLCN, the HFHRAT was taken as a stacking ensemble method (AUC_class[94.85 ± 0.47], AUC_prob[98.66 ± 0.27]). The interpretation of HFHRAT suggests that patients aged <75 years with LDL-c >4 mmol/L were more likely to be at risk of developing FH.ConclusionThe HFHRAT has provided a median of the three tools, which could reduce the false-negative rate associated with existing tools and prevent the development of atherosclerosis. The hybrid tool could satisfy the need for a risk assessment tool for specific populations.
29
Wu, Peiyan, Yan Jiang, Hanshuo Xing, Wenbo Song, Xin-wu Cui, Xing Long Wu, and Guoping Xu. "Multimodality deep learning radiomics nomogram for preoperative prediction of malignancy of breast cancer: a multicenter study." Physics in Medicine & Biology, July 31, 2023. http://dx.doi.org/10.1088/1361-6560/acec2d.
Full textAbstract:
Abstract Background: Breast cancer is the most prevalent cancer diagnosed in women worldwide. Accurately and efficiently stratifying the risk is an essential step in achieving precision medicine prior to treatment. This study aimed to construct and validate a nomogram based on radiomics and deep learning for preoperative prediction of the malignancy of breast cancer (MBC). 
Methods: The clinical and ultrasound (US) imaging data, including brightness mode (B-mode) and color Doppler flow imaging (CDFI), of 611 breast cancer patients from multiple hospitals in China were retrospectively analyzed. Patients were divided into one primary cohort (PC), one validation cohort (VC) and two test cohorts (TC1 and TC2). A multimodality deep learning radiomics nomogram (DLRN) was constructed for predicting the MBC. The performance of the proposed DLRN was comprehensively assessed and compared with three unimodal models via the calibration curve, the area under the curve (AUC) of receiver operating characteristics (ROC) and the decision curve analysis (DCA).
Results: The DLRN discriminated well between the MBC in all cohorts [overall AUC (95% confidence interval): 0.983 (0.973-0.993), 0.972 (0.952-0.993), 0.897 (0.823-0.971), and 0.993 (0.977-1.000) on the primary cohort (PC), validation cohort (VC), test cohorts1 (TC1) and test cohorts2 TC2 respectively]. In addition, the DLRN performed significantly better than three unimodal models and had good clinical utility.
Conclusion: The DLRN demonstrates good discriminatory ability in the preoperative prediction of MBC, can better reveal the potential associations between clinical characteristics, US imaging features and disease pathology, and can facilitate the development of computer-aided diagnosis systems for breast cancer patients.Our code is available publicly in the repository at https://github.com/wupeiyan/MDLRN.
30
Senthil, P., and S. Selvakumar. "A hybrid deep learning technique based integrated multi-model data fusion for forensic investigation." Journal of Intelligent & Fuzzy Systems, June 25, 2022, 1–14. http://dx.doi.org/10.3233/jifs-221307.
Full textAbstract:
Digital evidence is an integral part of any trial. Data is critical facts, encrypted information that requires explanation in order to gain meaning and knowledge. The current process of digital forensic research cannot effectively address the various aspects of a complex infrastructure. Therefore, digital forensics requires the optimal processing of a complex infrastructure that differs from the current process and structure. For a long time, digital forensic research has been utilized to discuss these issues. In this research, we offer a forensic investigation hybrid deep learning approach based on integrated multi-model data fusion (HDL-DFI). First, we concentrate on digital evidence collection and management systems, which can be achieved by an integrated data fusion model with the help of an improved brain storm optimization (IBSO) algorithm. Here, we consider several multimedia data’s for evidence purposes, i.e. text, image, speech, physiological signals, and video. Then, we introduce a recurrent multiplicative neuron with a deep neural network (RM-DNN) for data de-duplication in evidence collection, which avoids repeated and redundant data. After that, we design a multistage dynamic neural network (MDNN) for sentimental analysis to decide what type of crime has transpired and classify the action on it. Finally, the accuracy, precision, recall, F1-score, G-mean, and area under the curve of our proposed HDL-DFI model implemented with the standard benchmark database and its fallouts are compared to current state-of-the-art replicas (AUC). The results of our experiments show that the computation time of the proposed model HDL-DFI is 20% and 25% lower than the previous model’s for uploading familiar and unfamiliar files, 22% and 29% lower for authentication generation, 23% and 31% lower for the index service test scenario, and 24.097% and 32.02% lower for familiarity checking.