Journal articles on the topic 'Fingerprints Classification Data processing'
To see the other types of publications on this topic, follow the link: Fingerprints Classification Data processing.
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 'Fingerprints Classification Data processing.'
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
van Duijvenbode, Jeroen R., Mike W. N. Buxton, and Masoud Soleymani Shishvan. "Performance Improvements during Mineral Processing Using Material Fingerprints Derived from Machine Learning—A Conceptual Framework." Minerals 10, no. 4 (April 18, 2020): 366. http://dx.doi.org/10.3390/min10040366.
Full textAbstract:
Material attributes (e.g., chemical composition, mineralogy, texture) are identified as the causative source of variations in the behaviour of mineral processing. That makes them suitable to act as key characteristics to characterise and classify material. Therefore, vast quantities of collected data describing material attributes could help to forecast the behaviour of mineral processing. This paper proposes a conceptual framework that creates a data-driven link between ore and the processing behaviour through the creation of material “fingerprints”. A fingerprint is a machine learning-based classification of measured material attributes compared to the range of attributes found within the mine’s mineral reserves. The outcome of the classification acts as a label for a machine learning model and contains relevant information, which may identify the root cause of measured differences in processing behaviour. Therefore, this class label can forecast the associated behaviour of mineral processing. Furthermore, insight is given into the confidence of available data originating from different analytical techniques. Taken together, this enhances the understanding of how differences in geology impact metallurgical plant performance. Targeted measurements at low-confidence unit processes and for specific attributes would upgrade the confidence in fingerprints and capabilities to predict plant performance.
2
Ibitayo, Faluyi Bamidele, Olowojebutu Akinyemi Olanrewaju, and Makinde Bukola Oyeladun. "A FINGERPRINT BASED GENDER DETECTOR SYSTEM USING FINGERPRINT PATTERN ANALYSIS." international journal of advanced research in computer science 13, no. 4 (August 20, 2022): 35–47. http://dx.doi.org/10.26483/ijarcs.v13i4.6885.
Full textAbstract:
Humans have distinctive and unique traits which can be used to distinguish them thus, acting as a form of identification. Biometrics identifies people by measuring some aspect of individual’s anatomy or physiology such as hand geometry or fingerprint which consists of a pattern of interleaved ridges and valleys. The aim of this research is to analyse humans fingerprint texture in order to determine their gender, and correlation of RTVTR and Ridge Count on gender detection. The study is to analyze the effectiveness of physical biometrics (thumbprint) in order to determine gender in humans. Humans have distinctive and unique traits which can be used to distinguish them thus, acting as a form of identification. Biometrics identify people by measuring some aspect of individual’s anatomy or physiology such as hand geometry or fingerprint which consists of a pattern of interleaved ridges and valleys. This work developed a system that determines human gender using fingerprint analysis trained with SVM+CNN (for gender classification). To build an accurate fingerprint based model for gender detection system using fingerprint pattern analysis, there are certain steps that must be taken, which include; Data collection (in conducting research, the first step is collecting data in the form of a set of fingerprint image), Pre-processing Data (before entering the training data, pre-processing data is performed, which is resize the fingerprint image 96x96 pixels). Training Data (in this processing the dataset will be trained using the Convolutional neural network and Support vector machine methodology. This training data processing is a stage where CNN + SVM are trained to obtained high accuracy from the classification conducted). Result Verification (after doing all the above process, at this stage, we will display the results of gender prediction based on fingerprint images in the application that has been making). SOCOFing database is made up of 6,000 fingerprint images from 600 African subjects. It contains unique attributes such as labels for gender, hand and finger name as well as synthetically altered versions with three different levels of alteration for obliteration, central rotation, and z-cut. The values for accuracy, sensitivity and precision using the CNN classifier at threshold 0.25 were 96%, 97.8% and 96.92% respectively. At threshold 0.45 the values were 96.3%, 97.6% and 97.6% respectively. At threshold 0.75 the values were 96.5%, 97.3% and 97.9% respectively. In case of the SVM classifier, at threshold 0.25 were 94.3%, 96.6% and 95.8% respectively. At threshold 0.45 the values were 94.5%, 96.4% and 96.2% respectively. At threshold 0.75 the values were 94.8%, 97.3% and 96.8% respectively. From the 600 fingerprints classified, it was observed that a total of 450 fingerprints were detected for male and 150 for female. Results were obtained for gender accuracy, sensitivity and precision through several thresholds to compare the two classifiers. However, it should be verified that the results obtained showed that the CNN classification yielded better accuracy, sensitivity and precision than SVM.
3
Dincă Lăzărescu, Andreea-Monica, Simona Moldovanu, and Luminita Moraru. "A Fingerprint Matching Algorithm Using the Combination of Edge Features and Convolution Neural Networks." Inventions 7, no. 2 (May 27, 2022): 39. http://dx.doi.org/10.3390/inventions7020039.
Full textAbstract:
This study presents an algorithm for fingerprint classification using a CNN (convolutional neural network) model and making use of full images belonging to four digital databases. The main challenge that we face in fingerprint classification is dealing with the low quality of fingerprints, which can impede the identification process. To overcome these restrictions, the proposed model consists of the following steps: a preprocessing stage which deals with edge enhancement operations, data resizing, data augmentation, and finally a post-processing stage devoted to classification tasks. Primarily, the fingerprint images are enhanced using Prewitt and Laplacian of Gaussian filters. This investigation used the fingerprint verification competition with four databases (FVC2004, DB1, DB2, DB3, and DB4) which contain 240 real fingerprint images and 80 synthetic fingerprint images. The real images were collected using various sensors. The innovation of the model is in the manner in which the number of epochs is selected, which improves the performance of the classification. The number of epochs is defined as a hyper-parameter which can influence the performance of the deep learning model. The number of epochs was set to 10, 20, 30, and 50 in order to keep the training time at an acceptable value of 1.8 s/epoch, on average. Our results indicate the overfitting of the model starting with the seventh epoch. The accuracy varies from 67.6% to 98.7% for the validation set, and between 70.2% and 75.6% for the test set. The proposed method achieved a very good performance compared to the traditional hand-crafted features despite the fact that it used raw data and it does not perform any handcrafted feature extraction operations.
4
Suryadibrata, Alethea, and Suryadi Darmawan Salim. "Klasifikasi Anjing dan Kucing menggunakan Algoritma Linear Discriminant Analysis dan Support Vector Machine." Ultimatics : Jurnal Teknik Informatika 11, no. 1 (August 30, 2019): 46–51. http://dx.doi.org/10.31937/ti.v11i1.1076.
Full textAbstract:
One of the factors driving technological development is the increase in computers ability to complete various jobs. One of them is doing image processing, which is widely used in our daily life, such as the use of fingerprints, face/iris recognition barcodes, medical needs, and various other uses. Classification is one of the applications of image processing that is used the most. One algorithm that can be used for the development of image classification systems is Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM). LDA is a feature extraction algorithm to find a subspace that separates classes well. SVM is a classification algorithm, based on the idea of finding a hyperplane that best divides a dataset into classes. In this study, LDA and SVM algorithms were tested on the dog and cat classification system, with the highest F- score calculation results being 0.69 with 200 training data and 50 testing data for cats and 0.64 with 200 training data and 30 testing data for dogs.
5
Chhabra, Megha, Manoj Kumar Shukla, and Kiran Kumar Ravulakollu. "Boosting the classification performance of latent fingerprint segmentation using cascade of classifiers." Intelligent Decision Technologies 14, no. 3 (September 29, 2020): 359–71. http://dx.doi.org/10.3233/idt-190105.
Full textAbstract:
Segmentation and classification of latent fingerprints is a young challenging area of research. Latent fingerprints are unintentional fingermarks. These marks are ridge patterns left at crime scenes, lifted with latent or unclear view of fingermarks, making it difficult to find the guilty party. The segmentation of lifted images of such finger impressions comes with some unique challenges in domain such as poor quality images, incomplete ridge patterns, overlapping prints etc. The classification of poorly acquired data can be improved with image pre-processing, feeding all or optimal set of features extracted to suitable classifiers etc. Our classification system proposes two main steps. First, various effective extracted features are compartmentalised into maximal independent sets with high correlation value, Second, conventional supervised technique based binary classifiers are combined into a cascade/stack of classifiers. These classifiers are fed with all or optimal feature set(s) for binary classification of fingermarks as ridge patterns from non-ridge background. The experimentation shows improvement in accuracy rate on IIIT-D database with supervised algorithms.
6
Mohammed Salih, Basna, Adnan Mohsin Abdulazeez, and Omer Mohammed Salih Hassan. "Gender Classification Based on Iris Recognition Using Artificial Neural Networks." Qubahan Academic Journal 1, no. 2 (May 31, 2021): 156–63. http://dx.doi.org/10.48161/qaj.v1n2a63.
Full textAbstract:
Biometric authentication is one of the most quickly increasing innovations in today's world; this promising technology has seen widespread use in a variety of fields, including surveillance services, safe financial transfers, credit-card authentication. in biometric verification processes such as gender, age, ethnicity is iris recognition technology is considered the most accurate compared to other vital features such as face, hand geometry, and fingerprints. Because the irises in the same person are not similar. In this work, the study of gender classification using Artificial Neural Networks (ANN) based on iris recognition. The eye image data were collected from the IIT Delhi IRIS Database. All datasets of images were processed using various image processing techniques using the neural network. The results obtained showed high performance in training and got good results in testing. ANN's training and testing process gave a maximum performance at 96.4% and 97% respectively.
7
Hausdorf, Lena, Antje Fröhling, Oliver Schlüter, and Michael Klocke. "Analysis of the bacterial community within carrot wash water." Canadian Journal of Microbiology 57, no. 5 (May 2011): 447–52. http://dx.doi.org/10.1139/w11-013.
Full textAbstract:
Vegetables are washed after harvest to remove unwanted organic and inorganic particles, but wash water contaminated with certain pathogenic microorganisms can potentially contaminate produce. In this study, the microbial diversity of wash water was analyzed in samples taken from a carrot-processing facility. A 16S rRNA gene library with 427 clones was constructed and analyzed by amplified rDNA restriction analysis. For taxonomic classification, the 16S rRNA gene nucleotide sequences of 94 amplified rDNA restriction analysis fingerprints were determined. Each fingerprint indicates a distinct group of microorganisms. The nucleotide sequences were assigned to corresponding reference species. The most prevalent genus was Tolumonas , with 26% of the clones, followed by Acinetobacter and Flacobacterium , with 11% each. The latter two genera contain species that are known to cause nosocomial infections. The fourth most common genus was Arcobacter , comprising 9% of all clones. Some species of Arcobacter are considered to be emerging food pathogens, mainly associated with the contamination of meat products. So far, they have not been considered as contaminants of fresh produce. Based on the sequence data, an Arcobacter-specific PCR assay was developed to facilitate the detection of vegetable-associated Arcobacter strains.
8
Zhu, Qingchao, Qiqi Guo, Xiaoou Song, and Yue Zhang. "Research on combined radio frequency fingerprint identification model with limited samples." Journal of Physics: Conference Series 2284, no. 1 (June 1, 2022): 012014. http://dx.doi.org/10.1088/1742-6596/2284/1/012014.
Full textAbstract:
Abstract Aiming to solve the real problem of civilian aircraft identification, a novel combined radio frequency fingerprint (RFF) identification model is proposed, consisting of data analyzing processing, standard characteristic parameter database establishment, classification and optimization. In data analyzing processing step, discrimination was realized for wavelet coefficients, instantaneous phase, Hilbert huang transform energy spectrum, coefficients, time field envelope, probability density function, on basis of which, characteristic parameters were confirmed. In standard characteristic parameter database establishment step, a standard database was found through direct measurement method to avoid losing the RFF feature. In classification step, single character assortment rule and combined classifying rule were defined, with correlative concept and threshold concept. Finally, optimization for the model was realized by modifying parameters manually. Results show that, though hardware was limited and amount of samples were fewer, average identification rate is near to 69.75 percent, providing a theoretical reference for the real problem of identifying different aircrafts.
9
Jeon, Woosung, and Dongsup Kim. "FP2VEC: a new molecular featurizer for learning molecular properties." Bioinformatics 35, no. 23 (May 9, 2019): 4979–85. http://dx.doi.org/10.1093/bioinformatics/btz307.
Full textAbstract:
Abstract Motivation One of the most successful methods for predicting the properties of chemical compounds is the quantitative structure–activity relationship (QSAR) methods. The prediction accuracy of QSAR models has recently been greatly improved by employing deep learning technology. Especially, newly developed molecular featurizers based on graph convolution operations on molecular graphs significantly outperform the conventional extended connectivity fingerprints (ECFP) feature in both classification and regression tasks, indicating that it is critical to develop more effective new featurizers to fully realize the power of deep learning techniques. Motivated by the fact that there is a clear analogy between chemical compounds and natural languages, this work develops a new molecular featurizer, FP2VEC, which represents a chemical compound as a set of trainable embedding vectors. Results To implement and test our new featurizer, we build a QSAR model using a simple convolutional neural network (CNN) architecture that has been successfully used for natural language processing tasks such as sentence classification task. By testing our new method on several benchmark datasets, we demonstrate that the combination of FP2VEC and CNN model can achieve competitive results in many QSAR tasks, especially in classification tasks. We also demonstrate that the FP2VEC model is especially effective for multitask learning. Availability and implementation FP2VEC is available from https://github.com/wsjeon92/FP2VEC. Supplementary information Supplementary data are available at Bioinformatics online.
10
Beckmann, Manfred, David P. Enot, David P. Overy, Ian M. Scott, Paul G. Jones, David Allaway, and John Draper. "Metabolite fingerprinting of urine suggests breed-specific dietary metabolism differences in domestic dogs." British Journal of Nutrition 103, no. 8 (December 15, 2009): 1127–38. http://dx.doi.org/10.1017/s000711450999300x.
Full textAbstract:
Selective breeding of dogs has culminated in a large number of modern breeds distinctive in terms of size, shape and behaviour. Inadvertently, a range of breed-specific genetic disorders have become fixed in some pure-bred populations. Several inherited conditions confer chronic metabolic defects that are influenced strongly by diet, but it is likely that many less obvious breed-specific differences in physiology exist. Using Labrador retrievers and miniature Schnauzers maintained in a simulated domestic setting on a controlled diet, an experimental design was validated in relation to husbandry, sampling and sample processing for metabolomics. Metabolite fingerprints were generated from ‘spot’ urine samples using flow injection electrospray MS (FIE-MS). With class based on breed, urine chemical fingerprints were modelled using Random Forest (a supervised data classification technique), and metabolite features (m/z) explanatory of breed-specific differences were putatively annotated using the ARMeC database (http://www.armec.org). GC-MS profiling to confirm FIE-MS predictions indicated major breed-specific differences centred on the metabolism of diet-related polyphenols. Metabolism of further diet components, including potentially prebiotic oligosaccharides, animal-derived fats and glycerol, appeared significantly different between the two breeds. Analysis of the urinary metabolome of young male dogs representative of a wider range of breeds from animals maintained under domestic conditions on unknown diets provided preliminary evidence that many breeds may indeed have distinctive metabolic differences, with significant differences particularly apparent in comparisons between large and smaller breeds.
11
Hao, Zhanjun, Juan Niu, Xiaochao Dang, and Danyang Feng. "Wi-CAL: A Cross-Scene Human Motion Recognition Method Based on Domain Adaptation in a Wi-Fi Environment." Electronics 11, no. 16 (August 20, 2022): 2607. http://dx.doi.org/10.3390/electronics11162607.
Full textAbstract:
In recent years, research on Wi-Fi sensing technology has developed rapidly. This technology automatically senses human activities through commercial Wi-Fi devices, such as lying down, falling, walking, waving, sitting down, and standing up. Because the movement of human parts affects the transmission of Wi-Fi signals, resulting in changes in CSI. In the context of indoor monitoring of human health through daily behavior, we propose Wi-CAL. More precisely, CSI fingerprints were collected at six events in two indoor locations, and data enhancement technology Dynamic Time Warping Barycentric Averaging (DBA) was used to expand the data. Then the feature weighting algorithm and convolution layer are combined to select the most representative CSI data features of human action. Finally, a classification model suitable for multiple scenes was obtained by blending the softmax classifier and CORrelation ALignment (CORAL) loss. Experiments are carried out on public data sets and the data sets before and after the expansion collected in this paper. Through comparative experiments, it can be seen that our method can achieve good recognition performance.
12
Yin, Liang, Ruonan Yang, and Yuliang Yao. "Channel Sounding and Scene Classification of Indoor 6G Millimeter Wave Channel Based on Machine Learning." Electronics 10, no. 7 (April 1, 2021): 843. http://dx.doi.org/10.3390/electronics10070843.
Full textAbstract:
Millimeter wave, especially the high frequency millimeter wave near 100 GHz, is one of the key spectrum resources for the sixth generation (6G) mobile communication, which can be used for precise positioning, imaging and large capacity data transmission. Therefore, high frequency millimeter wave channel sounding is the first step to better understand 6G signal propagation. Because indoor wireless deployment is critical to 6G and different scenes classification can make future radio network optimization easy, we built a 6G indoor millimeter wave channel sounding system using just commercial instruments based on time-domain correlation method. Taking transmission and reception of a typical 93 GHz millimeter wave signal in the W-band as an example, four indoor millimeter wave communication scenes were modeled. Furthermore, we proposed a data-driven supervised machine learning method to extract fingerprint features from different scenes. Then we trained the scene classification model based on these features. Baseband data from receiver was transformed to channel Power Delay Profile (PDP), and then six fingerprint features were extracted for each scene. The decision tree, Support Vector Machine (SVM) and the optimal bagging channel scene classification algorithms were used to train machine learning model, with test accuracies of 94.3%, 86.4% and 96.5% respectively. The results show that the channel fingerprint classification model trained by machine learning method is effective. This method can be used in 6G channel sounding and scene classification to THz in the future.
13
Shinde, Krishna K., and C. N. Kayte. "Fingerprint Recognition Based on Deep Learning Pre-Train with Our Best CNN Model for Person Identification." ECS Transactions 107, no. 1 (April 24, 2022): 2209–20. http://dx.doi.org/10.1149/10701.2209ecst.
Full textAbstract:
In this article, we use pre-train VGG16, VGG19, and ResNet50 with ImageNet wights and our best CNN model to identify human fingerprint patterns. The system including pre-processing phase where the input fingerprint images first technique apply cropping and normalize for unwanted part remove of fingerprint images and normalize its dimension, second Image Enhancement for removing noise in to ridgelines, and last Canny Edge Detection technique for adjustment to smooth image with Gaussian to remove noise. Then apply one by one model on KVKR fingerprint dataset. Our best CNN model has automatically extracted features and RMSprop optimizer use for classification this features. This study performing experimental work of each pre-processed dataset and testing these three models with different dataset size of input train, test, and validation data. The VGG16 model got a better recognition accuracy than VGG19 and ResNet50 models.
14
Tzuan, Gabriel Tan Hong, Fazida Hanim Hashim, Thinal Raj, Aqilah Baseri Huddin, and Mohd Shaiful Sajab. "Oil Palm Fruits Ripeness Classification Based on the Characteristics of Protein, Lipid, Carotene, and Guanine/Cytosine from the Raman Spectra." Plants 11, no. 15 (July 26, 2022): 1936. http://dx.doi.org/10.3390/plants11151936.
Full textAbstract:
The capacity of palm oil production is directly affected by the ripeness of the fresh fruit bunches (FFB) upon harvesting. Conventional harvesting standards rely on rigid harvesting scheduling as well as the number of fruitlets that have loosened from the bunch. Harvesting is usually done every 10 to 14 days, and an FFB is deemed ready to be harvested if there are around 5 to 10 empty sockets on the fruit bunch. Technology aided by imaging techniques relies heavily on the color of the fruit bunch, which is highly dependent on the surrounding light intensities. In this study, Raman spectroscopy is used for ripeness classification of oil palm fruits, based on the molecular assignments extracted from the Raman bands between 1240 cm−1 and 1360 cm−1. The Raman spectra of 52 oil palm fruit samples which contain the fingerprints of different organic compounds were collected. Signal processing was applied to perform baseline correction and to reduce background noises. Characteristic data of the organic compounds were extracted through deconvolution and curve fitting processes. Subsequently, a correlation study between organic compounds was developed and eight hidden Raman peaks including protein, beta carotene, carotene, lipid, guanine/cytosine, chlorophyll-a, and tryptophan were successfully located. Through ANOVA statistical analysis, a total of six peak intensities from proteins through Amide III (β-sheet), beta-carotene, carotene, lipid, guanine/cytosine, and carotene and one peak location from lipid were found to be significant. An automated oil palm fruit ripeness classification system deployed with artificial neural network (ANN) using the seven signification features showed an overall performance of 97.9% accuracy. An efficient and accurate ripeness classification model which uses seven significant Raman peak features from the correlation analysis between organic compounds was successfully developed.
15
Radhi, Muna Abdul Hussain. "Human Identification Model Considering Biometrics Features." Journal La Multiapp 3, no. 4 (August 26, 2022): 198–206. http://dx.doi.org/10.37899/journallamultiapp.v3i4.692.
Full textAbstract:
In the medical field, brain classification is an effective technique for identifying a person through his brain print based on the hidden biometrics of high specificity included in the magnetic resonance images(MRI) of the brain, as this privacy strongly contributes to the issue of verification and identification of the person. In this paper, the brain print is extracted from the MRI obtained from 50 healthy people, which were passed through several pre-processing techniques in order to be used in the classification stage through convolutional neural network model, among those pre-classification stages, data collection after extracting the influential features for each image, which was based on linear discrimination analysis (LDA). The experimental results showed the importance of using LDA for feature extraction and adoption as input for K-NN and CNN classifiers. The classifiers proved successful in the classification if the features extracted with the help of LDA were adopted. Where CNN had the ability to classify with an accuracy of 99%, 82% for K-NN. The final stage in identifying a person through a brain fingerprint relied mainly on the model's success in classifying and predicting the remaining data in the testing stage.
16
Mitiche, Imene, Gordon Morison, Alan Nesbitt, Michael Hughes-Narborough, Brian Stewart, and Philip Boreham. "Imaging Time Series for the Classification of EMI Discharge Sources." Sensors 18, no. 9 (September 14, 2018): 3098. http://dx.doi.org/10.3390/s18093098.
Full textAbstract:
In this work, we aim to classify a wider range of Electromagnetic Interference (EMI) discharge sources collected from new power plant sites across multiple assets. This engenders a more complex and challenging classification task. The study involves an investigation and development of new and improved feature extraction and data dimension reduction algorithms based on image processing techniques. The approach is to exploit the Gramian Angular Field technique to map the measured EMI time signals to an image, from which the significant information is extracted while removing redundancy. The image of each discharge type contains a unique fingerprint. Two feature reduction methods called the Local Binary Pattern (LBP) and the Local Phase Quantisation (LPQ) are then used within the mapped images. This provides feature vectors that can be implemented into a Random Forest (RF) classifier. The performance of a previous and the two new proposed methods, on the new database set, is compared in terms of classification accuracy, precision, recall, and F-measure. Results show that the new methods have a higher performance than the previous one, where LBP features achieve the best outcome.
17
Putra, Kurnia Prima, Marwan Ramdhany Edy, M. Syahid Nur Wahid, Muhammad Fajar B, and Fadhlirrahman Baso. "FEATURES SIMPLIFICATION USING CUBIC BEZIER PROPERTIES FOR GAIT RECOGNITION ON SMARTPHONE." Journal of Embedded Systems, Security and Intelligent Systems 3, no. 1 (June 1, 2022): 11. http://dx.doi.org/10.26858/jessi.v3i1.33716.
Full textAbstract:
Smartphone is widely used around the world. It’s user authentication usually used pin code, pattern code, fingerprint and conventional login authentication. This kinds of authentication mechanism is intrusive because those mechanisms requires users to give exclusive interaction for user authentication during the process. One of authentication method which is non-intrusive during data collection is authentication by using gait. This mechanism classified as non-intrusive because this mechanism could gather biometric data without being noticed by the authentication subjects. Since it is non-intrusive, this mechanism allows re-authentications without bothering the authentication subjects. One of the recent gait recognition is using accelerometer on smartphone to measure and capture acceleration data on gait. This method extract step cycles in various length, map and interpolate the data into higher sample count, and then use each of mapped and interpolated data as feature using recognition. Regardless the classification or recognition method, using each mapped and interpolated data as features would result in high processing time during classification or recognition due to high feature count. In this research, we try to simplify the features of gait data with minimum data loss so it might give robust result with less latency by aligning cubic Bezier curve to step cycle data and extracting the Bezier properties.
18
Li, Guoming, Galen E. Erickson, and Yijie Xiong. "Individual Beef Cattle Identification Using Muzzle Images and Deep Learning Techniques." Animals 12, no. 11 (June 4, 2022): 1453. http://dx.doi.org/10.3390/ani12111453.
Full textAbstract:
Individual feedlot beef cattle identification represents a critical component in cattle traceability in the supply food chain. It also provides insights into tracking disease trajectories, ascertaining ownership, and managing cattle production and distribution. Animal biometric solutions, e.g., identifying cattle muzzle patterns (unique features comparable to human fingerprints), may offer noninvasive and unique methods for cattle identification and tracking, but need validation with advancement in machine learning modeling. The objectives of this research were to (1) collect and publish a high-quality dataset for beef cattle muzzle images, and (2) evaluate and benchmark the performance of recognizing individual beef cattle with a variety of deep learning models. A total of 4923 muzzle images for 268 US feedlot finishing cattle (>12 images per animal on average) were taken with a mirrorless digital camera and processed to form the dataset. A total of 59 deep learning image classification models were comparatively evaluated for identifying individual cattle. The best accuracy for identifying the 268 cattle was 98.7%, and the fastest processing speed was 28.3 ms/image. Weighted cross-entropy loss function and data augmentation can increase the identification accuracy of individual cattle with fewer muzzle images for model development. In conclusion, this study demonstrates the great potential of deep learning applications for individual cattle identification and is favorable for precision livestock management. Scholars are encouraged to utilize the published dataset to develop better models tailored for the beef cattle industry.
19
Mannu, Alberto, Ioannis K. Karabagias, Maria Enrica Di Pietro, Salvatore Baldino, Vassilios K. Karabagias, and Anastasia V. Badeka. "13C NMR-Based Chemical Fingerprint for the Varietal and Geographical Discrimination of Wines." Foods 9, no. 8 (August 2, 2020): 1040. http://dx.doi.org/10.3390/foods9081040.
Full textAbstract:
A fast, economic, and eco-friendly methodology for the wine variety and geographical origin differentiation using 13C nuclear magnetic resonance (NMR) data in combination with machine learning was developed. Wine samples of different grape varieties cultivated in different regions in Greece were subjected to 13C NMR analysis. The relative integrals of the 13C spectral window were processed and extracted to build a chemical fingerprint for the characterization of each specific wine variety, and then subjected to factor analysis, multivariate analysis of variance, and k-nearest neighbors analysis. The statistical analysis results showed that the 13C NMR fingerprint could be used as a rapid and accurate indicator of the wine variety differentiation. An almost perfect classification rate based on training (99.8%) and holdout methods (99.9%) was obtained. Results were further tested on the basis of Cronbach’s alpha reliability analysis, where a very low random error (0.30) was estimated, indicating the accuracy and strength of the aforementioned methodology for the discrimination of the wine variety. The obtained data were grouped according to the geographical origin of wine samples and further subjected to principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA). The PLS-DA and variable importance in projection (VIP) allowed the determination of a chemical fingerprint characteristic of each geographical group. The statistical analysis revealed the possibility of acquiring useful information on wines, by simply processing the 13C NMR raw data, without the need to determine any specific metabolomic profile. In total, the obtained fingerprint can be used for the development of rapid quality-control methodologies concerning wine.
20
Yang, Shangyi, Chao Sun, and Youngok Kim. "Indoor 3D Localization Scheme Based on BLE Signal Fingerprinting and 1D Convolutional Neural Network." Electronics 10, no. 15 (July 22, 2021): 1758. http://dx.doi.org/10.3390/electronics10151758.
Full textAbstract:
Indoor localization schemes have significant potential for use in location-based services in areas such as smart factories, mixed reality, and indoor navigation. In particular, received signal strength (RSS)-based fingerprinting is used widely, given its simplicity and low hardware requirements. However, most studies tend to focus on estimating the 2D position of the target. Moreover, it is known that the fingerprinting scheme is computationally costly, and its positioning accuracy is readily affected by random fluctuations in the RSS values caused by fading and the multipath effect. We propose an indoor 3D localization scheme based on both fingerprinting and a 1D convolutional neural network (CNN). Instead of using the conventional fingerprint matching method, we transform the 3D positioning problem into a classification problem and use the 1D CNN model with the RSS time-series data from Bluetooth low-energy beacons for classification. By using the 1D CNN with the time-series data from multiple beacons, the inherent drawback of RSS-based fingerprinting, namely, its susceptibility to noise and randomness, is overcome, resulting in enhanced positioning accuracy. To evaluate the proposed scheme, we developed a 3D positioning system and performed comprehensive tests, whose results confirmed that the scheme significantly outperforms the conventional common spatial pattern classification algorithm.
21
Shi, Chenjun, Ji Zhu, Mingqian Xu, Xu Wu, and Yan Peng. "An Approach of Spectra Standardization and Qualitative Identification for Biomedical Materials Based on Terahertz Spectroscopy." Scientific Programming 2020 (October 21, 2020): 1–8. http://dx.doi.org/10.1155/2020/8841565.
Full textAbstract:
Terahertz time-domain spectroscopy (THz-TDS) systems are widely used to obtain fingerprint spectra of many different biomedical substances, and thus the identification of different biological materials, medicines, or dangerous chemicals can be realized. However, the spectral data for the same substance obtained from different THz-TDS systems may have distinct differences because of differences in system errors and data processing methods, which leads to misclassification and errors in identification. To realize the exact and fast identification of substances, spectral standardization is the key issue. In this paper, we present detailed disposal methods and execution processes for the spectral standardization and substance identification, including feature extracting, database searching, and fingerprint spectrum matching of unknown substances. Here, we take twelve biomedical compounds including different biological materials, medicines, or dangerous chemicals as examples. These compounds were analyzed by two different THz-TDS systems, one of which is a commercial product and the other is our verification platform. The original spectra from two systems showed obvious differences in their curve shapes and amplitudes. After wavelet transform, cubic spline interpolation, and support vector machine (SVM) classification with an appropriate kernel function, the spectra from two systems can be standardized, and the recognition rate of qualitative identification can be up to 99.17%.
22
Fu, Ao, Huanchun Mei, Hong Zhou, Li Zhao, Meilan Yuan, and Yong Jiang. "Classification of Fish Sauce Origin by Means of Electronic Nose Fingerprint and Gas Chromatography-Mass Spectrometry of Volatile Compounds." Current Analytical Chemistry 16, no. 2 (February 11, 2020): 166–75. http://dx.doi.org/10.2174/1573411014666180626160745.
Full textAbstract:
Background: Volatile compounds in fish sauce may vary due to the species of fish, ingredients, processing period, temperature, and even the preference of people in each area. It is necessary to study a method of distinguishing the origins of fish sauce. The aims of this paper are to introduce a method to classification of fish sauce origin by means of electronic nose fingerprint and gas chromatography- mass spectrometry of volatile compounds and the two artificial neural networks are used to predict the origins of fish sauce. Methods: Headspace sampling-solid phase microextraction combined with gas chromatography-mass spectrometric analysis and electronic nose were used to analysze volatile compounds in different origins of fish sauce, and these dates predicted the origins of fish sauce by artificial neural networks. Results: 94 volatile compounds were identified by Automatic mass spectral deconvolution and identification system, out of which 44 are from Guangdong, 53 from our laboratory, 51 from Vietnam, 47 and 45 from Thailand. Then electronic nose was applied to identify the origin of fish sauce, and the data were analyzed using principal component analysis and load analysis. The fish sauce from different origin can be classified well on the PCA plot. Lastly, two artificial neural networks are used to predict the origins of fish sauce, and the accuracy rates of radial basis and gradient descent both are 93.33%. Conclusion: That illustrates that we can provide a quick method to distinguish fish sauce products of different origins. These results indicated that the combinations of multiple analysis and identification methods could make up the limitations of a single method, enhance the accuracy of identification, and provide useful information for product development.
23
Oh, Jiwon, Heesu Hwang, Yoonmi Nam, Myeong-Il Lee, Myeong-Jin Lee, Wonseok Ku, Hye-Won Song, et al. "Machine Learning-Assisted Gas-Specific Fingerprint Detection/Classification Strategy Based on Mutually Interactive Features of Semiconductor Gas Sensor Arrays." Electronics 11, no. 23 (November 24, 2022): 3884. http://dx.doi.org/10.3390/electronics11233884.
Full textAbstract:
A high-performance machine learning-assisted gas sensor strategy based on the integration of supervised and unsupervised learning with a gas-sensitive semiconductor metal oxide (SMO) gas sensor array is introduced. A 4-SMO sensor array was chosen as a test sensor system for detecting carbon monoxide (CO) and ethyl alcohol (C2H5OH) mixtures using 15 different combinations. Gas sensing detection/classification was performed with different numbers of gas sensor and machine learning algorithms. K-Means clustering was successfully employed to rationally identify the similarity features of targeted gases among 4 different groups, i.e., matrix gas, two single-component gases, and one two-gas mixture, based on only unlabeled voltage-based gas sensing information. Detailed classification was performed through a multitude of supervised algorithms, i.e., 2-layer artificial neural networks (ANNs), 4-layer deep neural networks (DNNs), 1-dimensional convolutional neural networks (1D CNNs), and 2-dimensional CNNs (2D CNNs). The numerical-based DNNs and image-based CNNs are shown to be excellent approaches for gas detection and classification, as indicated by the highest accuracy and lowest loss indicators. Through the analysis of the influence of the number of sensors on the arrayed gas sensor system, the application of machine learning methodology to an arrayed gas sensor system demonstrates four unique features, i.e., a data augmentation methodology, machine learning approach of combining K-means clustering and neural networks, and a systematic approach to optimized sensor combinations, potentially leading to the practical sensor networks based on chemical sensors. Even two SMO sensor combinations are shown to be highly effective in gas discrimination against diverse gas environments assisted through numeric-based DNNs and image-based 1D CNNs, overcoming the simple clustering proposed through the unsupervised K-means clustering.
24
Currà, Antonio, Riccardo Gasbarrone, Giuseppe Bonifazi, Silvia Serranti, Francesco Fattapposta, Carlo Trompetto, Lucio Marinelli, Paolo Missori, and Eugenio Lendaro. "Near-Infrared Transflectance Spectroscopy Discriminates Solutions Containing Two Commercial Formulations of Botulinum Toxin Type A Diluted at Recommended Volumes for Clinical Reconstitution." Biosensors 12, no. 4 (April 6, 2022): 216. http://dx.doi.org/10.3390/bios12040216.
Full textAbstract:
Botulinum neurotoxin type A (BoNT-A) is the active substance in pharmaceutical preparations widely used worldwide for the highly effective treatment of various disorders. Among the three commercial formulations of BoNT-A currently available in Italy for neurological indications, abobotulinum A toxin (Dysport®, Ipsen SpA, Milano, Italy) and incobotulinum A toxin (Xeomin®, Merz Pharma Italia srl, Milano, Italy) differ in the content of neurotoxin, non-toxic protein, and excipients. Clinical applications of BoNT-A adopt extremely diluted solutions (10−6 mg/mL) for injection in the target body district. Near-infrared spectroscopy (NIRS) and chemometrics allow rapid, non-invasive, and non-destructive methods for qualitative and quantitative analysis. No data are available to date on the chemometric analysis of the spectral fingerprints acquired from the diluted commercial formulations of BoNT-A. In this proof-of-concept study, we tested whether NIRS can categorize solutions of incobotulinum A toxin (lacking non-toxic proteins) and abobotulinum A toxin (containing non-toxic proteins). Distinct excipients in the two formulations were also analyzed. We acquired transmittance spectra in the visible and short-wave infrared regions (350–2500 nm) by an ASD FieldSpec 4™ Standard-Res Spectrophotoradiometer, using a submerged dip probe designed to read spectra in transflectance mode from liquid samples. After preliminary spectra pre-processing, principal component analysis was applied to characterize the spectral features of the two BoNT-A solutions and those of the various excipients diluted according to clinical standards. Partial least squares-discriminant analysis was used to implement a classification model able to discriminate the BoNT-A solutions and excipients. NIRS distinguished solutions containing distinct BoNT-A commercial formulations (abobotulinum A toxin vs. incobotulinum A toxin) diluted at recommended volumes for clinical reconstitution, distinct proteins (HSA vs. incobotulinum A toxin), very diluted solutions of simple sugars (lactose vs. sucrose), and saline or water. Predictive models of botulinum toxin formulations were also performed with the highest precision and accuracy.
25
Tegou, Thomas, Ilias Kalamaras, Markos Tsipouras, Nikolaos Giannakeas, Kostantinos Votis, and Dimitrios Tzovaras. "A Low-Cost Indoor Activity Monitoring System for Detecting Frailty in Older Adults." Sensors 19, no. 3 (January 22, 2019): 452. http://dx.doi.org/10.3390/s19030452.
Full textAbstract:
Indoor localization systems have already wide applications mainly for providing localized information and directions. The majority of them focus on commercial applications providing information such us advertisements, guidance and asset tracking. Medical oriented localization systems are uncommon. Given the fact that an individual’s indoor movements can be indicative of his/her clinical status, in this paper we present a low-cost indoor localization system with room-level accuracy used to assess the frailty of older people. We focused on designing a system with easy installation and low cost to be used by non technical staff. The system was installed in older people houses in order to collect data about their indoor localization habits. The collected data were examined in combination with their frailty status, showing a correlation between them. The indoor localization system is based on the processing of Received Signal Strength Indicator (RSSI) measurements by a tracking device, from Bluetooth Beacons, using a fingerprint-based procedure. The system has been tested in realistic settings achieving accuracy above 93% in room estimation. The proposed system was used in 271 houses collecting data for 1–7-day sessions. The evaluation of the collected data using ten-fold cross-validation showed an accuracy of 83% in the classification of a monitored person regarding his/her frailty status (Frail, Pre-frail, Non-frail).
26
Farkas, József, and István Dalmadi. "Near infrared and fluorescence spectroscopic methods and electronic nose technology for monitoring foods." Progress in Agricultural Engineering Sciences 5, no. 1 (December 1, 2009): 1–29. http://dx.doi.org/10.1556/progress.5.2009.1.
Full textAbstract:
There is a clear need for application of proper methods for measuring food quality and safety in the globalized food-webs. Numerous instrumental methods have been established in the course of the 20th century and are developing further, together with data analysis techniques, for such purposes. Among them, near-infrared and fluorescence spectroscopic methods and chemical sensor arrays called electronic noses show particular promise for rapid, non-destructive, non-invasive and cost-effective ways for assessing changes and enhancing control during processing and storage of foods. Their key advantages as analytical tools are 1) their relatively high speed of analysis, 2) the lack of a need to carry out complex sample preparation or processing, 3) their relatively low cost, and 4) their suitability for on-line monitoring or quality control. The present survey attempts to demonstrate examples from the above areas, limiting itself mainly to monitoring some quality indices which contribute to the functionality or acceptability of foods as affected by alternative processing technologies, or loss of freshness/microbial safety, or developing spoilage during storage and marketing. These instrumental methods are correlative techniques: they must be calibrated first against (traditional) reference properties, and the instrumental data are evaluated with the help of chemometric methods. Near-infrared (NIR) spectroscopy can be used in either the reflectance or the transmittance mode. NIR spectra transformed to mathematical derivatives allows subtle spectrum changes to be resolved. Selected examples from the extensive NIRS literature relate to assessment of the quality of frozen fish, predicting cooking loss of chicken patties, detecting complex physico-chemical changes of minced meat as a function of the intensity of high hydrostatic pressure treatment, comparing changes of NIR spectrometric “fingerprints” caused by gamma radiation or high pressure pasteurization of liquid egg white. Changes of NIR spectra reflect several parameters which suit the evaluation of loss of freshness, and onset of spoilage of various foods. NIR spectroscopy shows an application potential for rapid detection of bacterial or mould contamination. It may serve as a tool for detecting initial stages of mobilization processes during germination of cereal grains, or even for GMO screening. Spectrofluorometic measurements have shown potential, e.g. to monitor lipid oxidation and development of meat rancidity, to differentiate between raw and processed milks, and to monitor fish and egg freshness. Electronic noses containing chemical sensor arrays offer a rapid method for evaluation of head-space volatiles of food samples, important for characterizing quality and safety. Such gas sensors may be able to classify storage time, and determine spoilage, either earlier or at the same time as the human senses, or “sniffing out” bacterial pathogens or (toxigenic) fungal growth on certain foods. Electronic nose sensing is also a promising method for detecting quality changes of fruit- and vegetable products non-destructively. In relation to some examples to be presented in the paper, certain software developments as qualitative classification tools made by Hungarian scientists will be pointed out.
27
Dodson, C. T. J., John Soldera, and Jacob Scharcanski. "Some Information Geometric Aspects of Cyber Security by Face Recognition." Entropy 23, no. 7 (July 9, 2021): 878. http://dx.doi.org/10.3390/e23070878.
Full textAbstract:
Secure user access to devices and datasets is widely enabled by fingerprint or face recognition. Organization of the necessarily large secure digital object datasets, with objects having content that may consist of images, text, video or audio, involves efficient classification and feature retrieval processing. This usually will require multidimensional methods applicable to data that is represented through a family of probability distributions. Then information geometry is an appropriate context in which to provide for such analytic work, whether with maximum likelihood fitted distributions or empirical frequency distributions. The important provision is of a natural geometric measure structure on families of probability distributions by representing them as Riemannian manifolds. Then the distributions are points lying in this geometrical manifold, different features can be identified and dissimilarities computed, so that neighbourhoods of objects nearby a given example object can be constructed. This can reveal clustering and projections onto smaller eigen-subspaces which can make comparisons easier to interpret. Geodesic distances can be used as a natural dissimilarity metric applied over data described by probability distributions. Exploring this property, we propose a new face recognition method which scores dissimilarities between face images by multiplying geodesic distance approximations between 3-variate RGB Gaussians representative of colour face images, and also obtaining joint probabilities. The experimental results show that this new method is more successful in recognition rates than published comparative state-of-the-art methods.
28
Mekruksavanich, Sakorn, and Anuchit Jitpattanakul. "Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing." Sensors 21, no. 22 (November 12, 2021): 7519. http://dx.doi.org/10.3390/s21227519.
Full textAbstract:
Smartphones as ubiquitous gadgets are rapidly becoming more intelligent and context-aware as sensing, networking, and processing capabilities advance. These devices provide users with a comprehensive platform to undertake activities such as socializing, communicating, sending and receiving e-mails, and storing and accessing personal data at any time and from any location. Nowadays, smartphones are used to store a multitude of private and sensitive data including bank account information, personal identifiers, account passwords and credit card information. Many users remain permanently signed in and, as a result, their mobile devices are vulnerable to security and privacy risks through assaults by criminals. Passcodes, PINs, pattern locks, facial verification, and fingerprint scans are all susceptible to various assaults including smudge attacks, side-channel attacks, and shoulder-surfing attacks. To solve these issues, this research introduces a new continuous authentication framework called DeepAuthen, which identifies smartphone users based on their physical activity patterns as measured by the accelerometer, gyroscope, and magnetometer sensors on their smartphone. We conducted a series of tests on user authentication using several deep learning classifiers, including our proposed deep learning network termed DeepConvLSTM on the three benchmark datasets UCI-HAR, WISDM-HARB and HMOG. Results demonstrated that combining various motion sensor data obtained the highest accuracy and energy efficiency ratio (EER) values for binary classification. We also conducted a thorough examination of the continuous authentication outcomes, and the results supported the efficacy of our framework.
29
Chang, Zhuo, Lin Wang, Binbin Li, and Wenyuan Liu. "MetaEar: Imperceptible Acoustic Side Channel Continuous Authentication Based on ERTF." Electronics 11, no. 20 (October 20, 2022): 3401. http://dx.doi.org/10.3390/electronics11203401.
Full textAbstract:
With the development of ubiquitous mobile devices, biometrics authentication has received much attention from researchers. For immersive experiences in AR (augmented reality), convenient continuous biometric authentication technologies are required to provide security for electronic assets and transactions through head-mounted devices. Existing fingerprint or face authentication methods are vulnerable to spoof attacks and replay attacks. In this paper, we propose MetaEar, which harnesses head-mounted devices to send FMCW (Frequency-Modulated Continuous Wave) ultrasonic signals for continuous biometric authentication of the human ear. CIR (channel impulse response) leveraged the channel estimation theory to model the physiological structure of the human ear, called the Ear Related Transfer Function (ERTF). It extracts unique representations of the human ear’s intrinsic and extrinsic biometric features. To overcome the data dependency of Deep Learning and improve its deployability in mobile devices, we use the lightweight learning approach for classification and authentication. Our implementation and evaluation show that the average accuracy can reach about 96% in different scenarios with small amounts of data. MetaEar enables one to handle immersive deployable authentication and be more sensitive to replay and impersonation attacks.
30
A. Ali, Bushra, and Ekbal H. Ali. "HUMAN IDENTIFICATION SYSTEM BASED ON BRAINPRINT USING MACHINE LEARNING ALGORITHMS." Journal of Engineering and Sustainable Development 26, no. 2 (March 1, 2022): 13–22. http://dx.doi.org/10.31272/jeasd.26.2.2.
Full textAbstract:
In the medical field, due to the development of neuroimaging, several new methods of the biometric field have been attending and favorable candidates for the identification of people. These methods are part of "covert biometrics" that involve the use of measures of clinical and medical images to identify them. The prime motivation to use an invisible (Hidden biometric) is the fact that attacks of a system can be very hard to deal with. This privacy strongly contributes to the increased strongest in the topic of person's verification and identification. In this article, he extracted a brain signature, called a "brain fingerprint" from brain (MRI) Magnetic Resonance Image, obtained from 30 healthy subjects as images (1739), these real data sets from Yarmok Medical Hospital. These brainprint in this work are considered to be a hallmark of the brain. The objective of this proposed work which is design a robust, accurate human identification using human brain print, the brain classification based on several phases, included Data acquisition, Feature extraction processing depend on linear discrimination analysis (LDA) to gain important and interesting features of every image calculated by (number of features in the class). The proposed system shows rise detection precision with the features extracted based on LDA with automatical classifier learning by K nearest neighbor (K-NN) and logistic regression (LR) from the LDA method gained with the LR algorithm of (93%) while LDA method gained (91%) with K-NN.
31
Nguyen, Huong Thu, and Long The Nguyen. "Fingerprints Classification through Image Analysis and Machine Learning Method." Algorithms 12, no. 11 (November 11, 2019): 241. http://dx.doi.org/10.3390/a12110241.
Full textAbstract:
The system that automatically identifies the anthropometric fingerprint is one of the systems that interact directly with the user, which every day will be provided with a diverse database. This requires the system to be optimized to handle the process to meet the needs of users such as fast processing time, almost absolute accuracy, no errors in the real process. Therefore, in this paper, we propose the application of machine learning methods to develop fingerprint classification algorithms based on the singularity feature. The goal of the paper is to reduce the number of comparisons in automatic fingerprint recognition systems with large databases. The combination of using computer vision algorithms in the image pre-processing stage increases the calculation time, improves the quality of the input images, making the process of feature extraction highly effective and the classification process fast and accurate. The classification results on 3 datasets with the criteria for Precision, Recall, Accuracy evaluation and ROC analysis of algorithms show that the Random Forest (RF) algorithm has the best accuracy (≥96.75%) on all 3 databases, Support Vector Machine (SVM) has the best results (≥95.5%) 2 / 3 databases.
32
Duan, Jiajun, Yigang He, Xiaoxin Wu, Hui Zhang, and Wenjie Wu. "Anti-Interference Deep Visual Identification Method for Fault Localization of Transformer Using a Winding Model." Sensors 19, no. 19 (September 25, 2019): 4153. http://dx.doi.org/10.3390/s19194153.
Full textAbstract:
The idea of Ubiquitous Power Internet of Things (UPIoTs) accelerates the development of intelligent monitoring and diagnostic technologies. In this paper, a diagnostic method suitable for power equipment in an interference environment was proposed based on the deep Convolutional Neural Network (CNN): MobileNet-V2 and Digital Image Processing (DIP) methods to conduct fault identification process: including fault type classification and fault localization. A data visualization theory was put forward in this paper, which was applied in frequency response (FR) curves of transformer to obtain dataset. After the image augmentation process, the dataset was input into the deep CNN: MobileNet-V2 for training procedures. Then a spatial-probabilistic mapping relationship was established based on traditional Frequency Response Analysis (FRA) fault diagnostic method. Each image in the dataset was compared with the fingerprint values to get traditional diagnosing results. Next, the anti-interference abilities of the proposed CNN-DIP method were compared with that of the traditional one while the magnitude of the interference gradually increased. Finally, the fault tolerance of the proposed method was verified by further analyzing the deviations between the wrong diagnosing results with the corresponding actual labels. Experimental results showed that the proposed deep visual identification (CNN-DIP) method has a higher diagnosing accuracy, a stronger anti-interference ability and a better fault tolerance.
33
Hana Kusumaputri, Farah, Suryo Adhi Wibowo, and Yuti Malinda. "Identifikasi Individu Berdasarkan Pola Citra Rugae Palatina Menggunakan Adaptive Neuro Fuzzy Inference System (ANFIS)." Jurnal Ilmiah FIFO 12, no. 2 (March 5, 2021): 156. http://dx.doi.org/10.22441//fifo.2020.v12i2.005.
Full textAbstract:
Abstract Indonesia is a country that is in an area prone to natural disasters, such as volcanic eruptions, earthquakes, tsunamis, and others. These natural disasters often cause many victims to die. To identify the victims' identities, an identification process is needed. The identification method most commonly used today is using fingerprints, teeth, and DNA. However, this identification method still has some shortcomings. At present a more effective alternative method is offered by utilizing the palatine rugae pattern. Rugae palatina has individual characteristics and is resistant to all kinds of damage. So that Rugae palatina has the potential to be used in the process of individual identification. In this research, application of palatine rugae image processing application will be developed with data recording, image registration, feature extraction using Principal Component Analysis (PCA) method, and palatine rugae pattern classification using Adaptive Neuro Fuzzy Inference System (ANFIS) method. The expected output from this final project is a system that is able to identify individuals by utilizing the palatine rugae pattern. To get good and effective parameters for system performance, periodic testing is carried out. The sampling procedure uses original photographs directly taken from the palatine rugae, so that it will facilitate the identification process. Keyword: ANFIS, ANN, Fuzzy Logic, PCA, rugae palatina Abstrak Negara Indonesia merupakan negara yang berada di daerah rawan bencana alam, seperti erupsi gunung merapi, gempa bumi, tsunami, dan lain-lain. Bencana alam tersebut seringkali menyebabkan korban meninggal dalam jumlah yang banyak. Untuk mengenali identitas para korban tersebut diperlukannya proses identifikasi. Metode identifikasi yang paling sering digunakan saat ini yaitu menggunakan sidik jari, gigi, dan DNA. Namun, metode identifikasi tersebut masih mempunyai beberapa kekurangan. Saat ini ditawarkan metode alternatif yang lebih efektif yaitu dengan memanfaatkan pola rugae palatina. Rugae palatina memiliki sifat yang individual dan tahan terhadap segala macam kerusakan. Sehingga Rugae palatina memiliki potensi untuk digunakan dalam proses identifikasi individu. Dalam penelitian ini akan dikembangkan aplikasi pengolahan sampel citra rugae palatina dengan proses perekaman data, registrasi citra, ekstrasi ciri menggunakan metode Principal Component Analysis (PCA), dan klasifikasi pola rugae palatina menggunakan metode Adaptive Neuro Fuzzy Inference System (ANFIS). Keluaran yang diharapkan dari penelitian ini adalah sebuah sistem yang mampu mengidentifikasi individu dengan memanfaatkan pola rugae palatina. Untuk mendapatkan parameter yang baik dan efektif terhadap performansi sistem, maka dilakukan pengujian secara berkala. Prosedur pegangambilan sampel menggunakan foto asli yang secara langsung diambil dari rugae palatina, sehingga akan mempermudah proses identifikasi. Kata kunci: ANFIS, ANN, Fuzzy Logic, PCA, rugae palatina
34
Saeed, Fahman, Muhammad Hussain, and Hatim A. Aboalsamh. "Automatic Fingerprint Classification Using Deep Learning Technology (DeepFKTNet)." Mathematics 10, no. 8 (April 12, 2022): 1285. http://dx.doi.org/10.3390/math10081285.
Full textAbstract:
Fingerprints are gaining in popularity, and fingerprint datasets are becoming increasingly large. They are often captured utilizing a variety of sensors embedded in smart devices such as mobile phones and personal computers. One of the primary issues with fingerprint recognition systems is their high processing complexity, which is exacerbated when they are gathered using several sensors. One way to address this issue is to categorize fingerprints in a database to condense the search space. Deep learning is effective in designing robust fingerprint classification methods. However, designing the architecture of a CNN model is a laborious and time-consuming task. We proposed a technique for automatically determining the architecture of a CNN model adaptive to fingerprint classification; it automatically determines the number of filters and the layers using Fukunaga–Koontz transform and the ratio of the between-class scatter to within-class scatter. It helps to design lightweight CNN models, which are efficient and speed up the fingerprint recognition process. The method was evaluated two public-domain benchmark datasets FingerPass and FVC2004 benchmark datasets, which contain noisy, low-quality fingerprints obtained using live scan devices and cross-sensor fingerprints. The designed models outperform the well-known pre-trained models and the state-of-the-art fingerprint classification techniques.
35
Wang, Yongchang, Laurence G. Hassebrook, and Daniel L. Lau. "Data Acquisition and Processing of 3-D Fingerprints." IEEE Transactions on Information Forensics and Security 5, no. 4 (December 2010): 750–60. http://dx.doi.org/10.1109/tifs.2010.2062177.
Full text
36
Militello, Carmelo, Leonardo Rundo, Salvatore Vitabile, and Vincenzo Conti. "Fingerprint Classification Based on Deep Learning Approaches: Experimental Findings and Comparisons." Symmetry 13, no. 5 (April 26, 2021): 750. http://dx.doi.org/10.3390/sym13050750.
Full textAbstract:
Biometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs), tested on two fingerprint databases—namely, PolyU and NIST—and comparisons to other results presented in the literature in order to establish the type of classification that allows us to obtain the best performance in terms of precision and model efficiency, among approaches under examination, namely: AlexNet, GoogLeNet, and ResNet. We present the first study that extensively compares the most used CNN architectures by classifying the fingerprints into four, five, and eight classes. From the experimental results, the best performance was obtained in the classification of the PolyU database by all the tested CNN architectures due to the higher quality of its samples. To confirm the reliability of our study and the results obtained, a statistical analysis based on the McNemar test was performed.
37
Yang, Jun-Ho, and Jack J. Yoh. "Forensic Discrimination of Latent Fingerprints Using Laser-Induced Breakdown Spectroscopy (LIBS) and Chemometric Approaches." Applied Spectroscopy 72, no. 7 (March 23, 2018): 1047–56. http://dx.doi.org/10.1177/0003702818765183.
Full textAbstract:
A novel technique is reported for separating overlapping latent fingerprints using chemometric approaches that combine laser-induced breakdown spectroscopy (LIBS) and multivariate analysis. The LIBS technique provides the capability of real time analysis and high frequency scanning as well as the data regarding the chemical composition of overlapping latent fingerprints. These spectra offer valuable information for the classification and reconstruction of overlapping latent fingerprints by implementing appropriate statistical multivariate analysis. The current study employs principal component analysis and partial least square methods for the classification of latent fingerprints from the LIBS spectra. This technique was successfully demonstrated through a classification study of four distinct latent fingerprints using classification methods such as soft independent modeling of class analogy (SIMCA) and partial least squares discriminant analysis (PLS-DA). The novel method yielded an accuracy of more than 85% and was proven to be sufficiently robust. Furthermore, through laser scanning analysis at a spatial interval of 125 µm, the overlapping fingerprints were reconstructed as separate two-dimensional forms.
38
Dionson, Mary Gift D., and El Jireh P. Bibangco. "Inception-V3 Architecture in Dermatoglyphics-Based Temperament Classification." Philippine Social Science Journal 3, no. 2 (November 16, 2020): 173–74. http://dx.doi.org/10.52006/main.v3i2.164.
Full textAbstract:
Personality classification is one of the areas of behavioral psychology that focuses on categorizing individuals. Different factors constitute the main currents of human personality. These factors turned out to be complicated and sometimes yield a biased result. Meanwhile, the entire human body reflects the character of its possessor more accurately than any set of questionnaires. Dermatoglyphics is the scientific study of fingerprints. Fingerprint patterns and ridge density are the viable bases in the classification of the personality of an individual. This uniqueness has expanded through research confirming parents' ability to identify their children's unique potentials through fingerprint analysis. Bridging the gap between computer science and psychology is one of the biggest challenges of the study. Exploring the possibilities revolves around image processing, where fingerprints served as image input and a deep learning convolutional neural network model implemented in the Inception-v3 architecture is used to analyze and classify different fingerprint patterns finally associate with the classified prints to its corresponding temperament type.
39
Suwarno, Sri. "Gender Classification Based on Fingerprint Using Wavelet and Multilayer Perceptron." Sinkron 8, no. 1 (January 1, 2023): 139–44. http://dx.doi.org/10.33395/sinkron.v8i1.11925.
Full textAbstract:
Fingerprint-based gender classification is beneficial for speeding up the fingerprint identification of criminals, accident victims, and natural disaster victims that are difficult to be recognized based on their physical characteristics. The biggest obstacle to digitally classifying fingerprints is the image's poor quality. Some methods have been developed to improve image quality through various preprocessing, such as noise removal, background segmentation, thinning, and binarization. However, as these processes increase the classification time, some methods have been developed to classify fingerprints without preprocessing. One of them that has shown excellent success is CNN (Convolutional Neural Network). The method does not require preprocessing, but the computation time is very long and requires large amounts of training data. This study proposed a new method that did not need any preprocessing by using wavelet decomposition combined with the max-pooling process to generate features. Firstly, the fingerprint image was decomposed with a Haar wavelet of 4 levels, and each level was followed by a max-pooling process with a 2´2 filter. After that, the resulting feature was used as training data for the Multilayer Perceptron (MLP) network. In this study, the training data was a dataset from NIST (National Institute of Standart and Technology), with 750 fingerprints consisting of male and female fingerprints, each as many as 375. The method could produce a total accuracy of 80.1%.
40
Ezin, Eugène C. "Pyramidal Structure Algorithm for Fingerprint Classification Based on Artificial Neural Networks." Journal of Advanced Computational Intelligence and Intelligent Informatics 14, no. 1 (January 20, 2010): 63–68. http://dx.doi.org/10.20965/jaciii.2010.p0063.
Full textAbstract:
Feature extraction plays a primary role in pattern recognition classification. Many context-based and problem-based algorithms have been proposed providing good performance in high-quality fingerprint imaging but fail when declining with poor-quality fingerprints. The pyramidal algorithm we present in this paper operates on an image matrix layer for extracting features from ink-and-paper fingerprints. The effectiveness of the pyramidal algorithm compared to the consolidation algorithm is demonstrated using a backpropagation neural network experiment to test preprocessed data.
41
Barbosa, Sergio, Javier Saurina, Lluís Puignou, and Oscar Núñez. "Classification and Authentication of Paprika by UHPLC-HRMS Fingerprinting and Multivariate Calibration Methods (PCA and PLS-DA)." Foods 9, no. 4 (April 13, 2020): 486. http://dx.doi.org/10.3390/foods9040486.
Full textAbstract:
In this study, the feasibility of non-targeted UHPLC-HRMS fingerprints as chemical descriptors to address the classification and authentication of paprika samples was evaluated. Non-targeted UHPLC-HRMS fingerprints were obtained after a simple sample extraction method and C18 reversed-phase separation. Fingerprinting data based on signal intensities as a function of m/z values and retention times were registered in negative ion mode using a q-Orbitrap high-resolution mass analyzer, and the obtained non-targeted UHPLC-HRMS fingerprints subjected to unsupervised principal component analysis (PCA) and supervised partial least squares regression-discriminant analysis (PLS-DA) to study sample discrimination and classification. A total of 105 paprika samples produced in three different regions, La Vera PDO and Murcia PDO, in Spain, and the Czech Republic, and all of them composed of samples of at least two different taste varieties, were analyzed. Non-targeted UHPLC-HRMS fingerprints demonstrated to be excellent sample chemical descriptors to achieve the authentication of paprika production regions with 100% sample classification rates by PLS-DA. Besides, the obtained fingerprints were also able to perfectly discriminate among the different paprika taste varieties in all the studied cases, even in the case of the different La Vera PDO paprika tastes (sweet, bittersweet, and spicy) which are produced in a very small region.
42
Kirfel, Alexander, Tobias Scheer, Norbert Jung, and Christoph Busch. "Robust Identification and Segmentation of the Outer Skin Layers in Volumetric Fingerprint Data." Sensors 22, no. 21 (October 27, 2022): 8229. http://dx.doi.org/10.3390/s22218229.
Full textAbstract:
Despite the long history of fingerprint biometrics and its use to authenticate individuals, there are still some unsolved challenges with fingerprint acquisition and presentation attack detection (PAD). Currently available commercial fingerprint capture devices struggle with non-ideal skin conditions, including soft skin in infants. They are also susceptible to presentation attacks, which limits their applicability in unsupervised scenarios such as border control. Optical coherence tomography (OCT) could be a promising solution to these problems. In this work, we propose a digital signal processing chain for segmenting two complementary fingerprints from the same OCT fingertip scan: One fingerprint is captured as usual from the epidermis (“outer fingerprint”), whereas the other is taken from inside the skin, at the junction between the epidermis and the underlying dermis (“inner fingerprint”). The resulting 3D fingerprints are then converted to a conventional 2D grayscale representation from which minutiae points can be extracted using existing methods. Our approach is device-independent and has been proven to work with two different time domain OCT scanners. Using efficient GPGPU computing, it took less than a second to process an entire gigabyte of OCT data. To validate the results, we captured OCT fingerprints of 130 individual fingers and compared them with conventional 2D fingerprints of the same fingers. We found that both the outer and inner OCT fingerprints were backward compatible with conventional 2D fingerprints, with the inner fingerprint generally being less damaged and, therefore, more reliable.
43
Alsharman, Nesreen, Adeeb Saaidah, Omar Almomani, Ibrahim Jawarneh, and Laila Al-Qaisi. "Pattern Mathematical Model for Fingerprint Security Using Bifurcation Minutiae Extraction and Neural Network Feature Selection." Security and Communication Networks 2022 (April 16, 2022): 1–16. http://dx.doi.org/10.1155/2022/4375232.
Full textAbstract:
Biometric based access control is becoming increasingly popular in the current era because of its simplicity and user-friendliness. This eliminates identity recognition manual work and enables automated processing. The fingerprint is one of the most important biometrics that can be easily captured in an uncontrolled environment without human cooperation. It is important to reduce the time consumption during the comparison process in automated fingerprint identification systems when dealing with a large database. Fingerprint classification enables this objective to be accomplished by splitting fingerprints into several categories, but it still poses some difficulties because of the wide intraclass variations and the limited interclass variations since most fingerprint datasets are not categories. In this paper, we propose a classification and matching fingerprint model, and the classification classifies fingerprints into three main categories (arch, loop, and whorl) based on a pattern mathematical model using GoogleNet, AlexNet, and ResNet Convolutional Neural Network (CNN) architecture and matching techniques based on bifurcation minutiae extraction. The proposed model was implemented and tested using MATLAB based on the FVC2004 dataset. The obtained result shows that the accuracy for classification is 100%, 75%, and 43.75% for GoogleNet, ResNet, and AlexNet, respectively. The time required to build a model is 262, 55, and 28 seconds for GoogleNet, ResNet, and AlexNet, respectively.
44
Li, Huixing, Yan Xue, and Xiancai Zeng. "Investigation of Biometric Identification Technology Based on biological Fingerprints and Facial Features." E3S Web of Conferences 267 (2021): 02035. http://dx.doi.org/10.1051/e3sconf/202126702035.
Full textAbstract:
Biometric identification is largely dependent on feature extraction technology. As feature extraction techniques are increasingly mature, scholars have gradually turned their attention to the relevant problems between biometric characteristics. This paper reviews the characteristic extraction method of face and fingerprint analyzes the feature classification extraction method based on empirical knowledge and the depth learning-based computer logic sampling extraction method and compares existing solutions from the angle of image processing. Based on feature extraction, it will have prospected in the future biometric identification model of progress.
45
Karsch, Nicholas, Hendrik Schulte, Thomas Musch, and Christoph Baer. "A Novel Localization System in SAR-Demining Applications Using Invariant Radar Channel Fingerprints." Sensors 22, no. 22 (November 10, 2022): 8688. http://dx.doi.org/10.3390/s22228688.
Full textAbstract:
In this paper, we present a novel two dimensional (2D) frequency-modulated continuous-wave (FMCW) localization method for handheld systems based on the extraction of distinguishable subchannel fingerprints. Compared with other concepts, only one subdivided radar source channel is needed in order to instantly map a one-dimensional measurement to higher-dimensional space coordinates. The additional information of the detected target is implemented with low-cost hardware component features, which exhibit distinguishable space-dependent fingerprint codes. Using the given a priori information of the hardware thus leads to a universally applicable extension for low-cost synthetic aperture radar (SAR)-demining purposes. In addition to the description of the system concept and its requirements, the signal processing steps and the hardware components are presented. Furthermore, the 2D localization accuracy of the system and the classification accuracy of the frequency-coded fingerprints are described in a defined test environment to proof the operational reliability of the realized setup, reaching a classification accuracy of 94.7% and an averaged localization error of 4.9 mm.
46
Huang, Chao, Jin He, and Ji Yong Zhao. "Artificial Immune Network in the Recognition of Yunnan Herbal Medicine." Advanced Materials Research 718-720 (July 2013): 2353–58. http://dx.doi.org/10.4028/www.scientific.net/amr.718-720.2353.
Full textAbstract:
Concerning simple and unscientific of Yunnan herbal medicine identification method, a kind of identification method based on Artificial Immune Network was proposed in this paper. Using high performance liquid chromatography extracts fingerprints from Yunnan herbal medicine,and then the data of fingerprints were trained by the Artificial Immune Network. In comparison with the traditional K-means algorithm,the experiment results show that Artificial Immune Network has higher classification and recognition ability.
47
Amante, Eleonora, Eugenio Alladio, Rebecca Rizzo, Daniele Di Corcia, Pierre Negri, Lia Visintin, Michela Guglielmotto, Elena Tamagno, Marco Vincenti, and Alberto Salomone. "Untargeted Metabolomics in Forensic Toxicology: A New Approach for the Detection of Fentanyl Intake in Urine Samples." Molecules 26, no. 16 (August 18, 2021): 4990. http://dx.doi.org/10.3390/molecules26164990.
Full textAbstract:
The misuse of fentanyl, and novel synthetic opioids (NSO) in general, has become a public health emergency, especially in the United States. The detection of NSO is often challenged by the limited diagnostic time frame allowed by urine sampling and the wide range of chemically modified analogues, continuously introduced to the recreational drug market. In this study, an untargeted metabolomics approach was developed to obtain a comprehensive “fingerprint” of any anomalous and specific metabolic pattern potentially related to fentanyl exposure. In recent years, in vitro models of drug metabolism have emerged as important tools to overcome the limited access to positive urine samples and uncertainties related to the substances actually taken, the possible combined drug intake, and the ingested dose. In this study, an in vivo experiment was designed by incubating HepG2 cell lines with either fentanyl or common drugs of abuse, creating a cohort of 96 samples. These samples, together with 81 urine samples including negative controls and positive samples obtained from recent users of either fentanyl or “traditional” drugs, were subjected to untargeted analysis using both UHPLC reverse phase and HILIC chromatography combined with QTOF mass spectrometry. Data independent acquisition was performed by SWATH in order to obtain a comprehensive profile of the urinary metabolome. After extensive processing, the resulting datasets were initially subjected to unsupervised exploration by principal component analysis (PCA), yielding clear separation of the fentanyl positive samples with respect to both controls and samples positive to other drugs. The urine datasets were then systematically investigated by supervised classification models based on soft independent modeling by class analogy (SIMCA) algorithms, with the end goal of identifying fentanyl users. A final single-class SIMCA model based on an RP dataset and five PCs yielded 96% sensitivity and 74% specificity. The distinguishable metabolic patterns produced by fentanyl in comparison to other opioids opens up new perspectives in the interpretation of the biological activity of fentanyl.
48
Schablitzki, T., J. Rogal, and R. Drautz. "Topological fingerprints for intermetallic compounds for the automated classification of atomistic simulation data." Modelling and Simulation in Materials Science and Engineering 21, no. 7 (September 18, 2013): 075008. http://dx.doi.org/10.1088/0965-0393/21/7/075008.
Full text
49
Levasseur, Marceau, Téo Hebra, Nicolas Elie, Vincent Guérineau, David Touboul, and Véronique Eparvier. "Classification of Environmental Strains from Order to Genus Levels Using Lipid and Protein MALDI-ToF Fingerprintings and Chemotaxonomic Network Analysis." Microorganisms 10, no. 4 (April 17, 2022): 831. http://dx.doi.org/10.3390/microorganisms10040831.
Full textAbstract:
During the last two decades, MALDI-ToF mass spectrometry has become an efficient and widely-used tool for identifying clinical isolates. However, its use for classification and identification of environmental microorganisms remains limited by the lack of reference spectra in current databases. In addition, the interpretation of the classical dendrogram-based data representation is more difficult when the quantity of taxa or chemotaxa is larger, which implies problems of reproducibility between users. Here, we propose a workflow including a concurrent standardized protein and lipid extraction protocol as well as an analysis methodology using the reliable spectra comparison algorithm available in MetGem software. We first validated our method by comparing protein fingerprints of highly pathogenic bacteria from the Robert Koch Institute (RKI) open database and then implemented protein fingerprints of environmental isolates from French Guiana. We then applied our workflow for the classification of a set of protein and lipid fingerprints from environmental microorganisms and compared our results to classical genetic identifications using 16S and ITS region sequencing for bacteria and fungi, respectively. We demonstrated that our protocol allowed general classification at the order and genus level for bacteria whereas only the Botryosphaeriales order can be finely classified for fungi.
50
Singh, Sharad Pratap, Shahanaz Ayub, and J. P. Saini. "Analysis and comparison of normal and altered fingerprint using artificial neural networks." International Journal of Knowledge-based and Intelligent Engineering Systems 25, no. 2 (July 26, 2021): 243–49. http://dx.doi.org/10.3233/kes-210068.
Full textAbstract:
Fingerprint matching is based on the number of minute matches between two fingerprints. Implementation mainly includes image enhancement, segmentation, orientation histogram, etc., extraction (completeness) and corresponding minutiae. Finally, a matching score is generated that indicates whether two fingerprints coincide with the help of coding with MATLAB to find the matching score and simulation of Artificial Neural Network extending the feedback of the network. Using the artificial neural network tool, an important advantage is the similarity index between the sample data or unknown data. A neural network is a massively parallel distributed processor consisting of simple processing units that have a natural property to store knowledge and computer experiences are available for use. A fingerprint comparison essentially consists of two fingerprints to generate a fingerprint match score the match score is used to determine whether the two impressions they are of the same finger. The decision is made this study shows the comparison of normal and altered fingerprints using MATLAB coding and data used to study in the self-generated data using biometric scanner also the open source data available on the web is used for finding out matching score or similarity index, The study shows that there is hardly any matching between normal and altered fingerprints of the same person.