Extraction Of Various Features Research Articles

Device authentication for 5G terminals via Radio Frequency fingerprints

The development of wireless communication network technology has provided people with diversified and convenient services. However, with the expansion of network scale and the increase in the number of devices, malicious attacks on wireless communication are becoming increasingly prevalent, causing significant losses. Currently, wireless communication systems authenticate identities through certain data identifiers. However, this software-based data information can be forged or replicated. This article proposes the authentication of device identity using the hardware fingerprint of the terminal’s Radio Frequency (RF) components, which possesses properties of being genuine, unique, and stable, holding significant implications for wireless communication security. Through the collection and processing of raw data, extraction of various features including time-domain and frequency-domain features, and utilizing machine learning algorithms for training and constructing a legal fingerprint database, it is possible to achieve close to a 97% recognition accuracy for Fifth Generation (5G) terminals of the same model. This provides an additional and robust hardware-based security layer for 5G communication security, enhancing monitoring capability and reliability.

SOH estimation and RUL prediction of lithium batteries based on multidomain feature fusion and CatBoost model

AbstractIn this paper, a lithium‐ion battery State of Health (SOH) estimation algorithm is proposed based on the fusion of multidomain features and the application of a CatBoost model. The aim is to address the issue of low prediction accuracy in SOH caused by the utilization of single‐feature extraction techniques. The algorithm encompasses the extraction of various features from the original charge–discharge data, including time‐domain, frequency‐domain, entropy, and time‐series features. Following the evaluation of feature importance, a feature selection process is conducted to eliminate redundant features that provide a limited contribution to the predictive results. Subsequently, a multiple‐set discriminative correlation analysis is employed to integrate high‐dimensional features. To attain accurate predictions, the CatBoost model is further optimized through the utilization of a sparrow search algorithm. Experimental results demonstrate that the proposed algorithm achieves accurate SOH estimations within individual batteries, as evidenced by mean square error values consistently below 4e−4 and goodness‐of‐fit values exceeding or equal to 0.98. Additionally, the algorithm exhibits reliable prediction capabilities across different batteries operating under the same charge/discharge strategy. Comparative analysis indicates that the adoption of the multidomain feature fusion approach yields improved prediction accuracy in contrast to the utilization of a single feature extraction method.

Detection and Classification of Diabetic Retinopathy using Deep Learning

Detection of Diabetic Retinopathy at the early stages could significantly reduce the need for complicated and expensive surgeries. The availability of large datasets has fuelled research in this field. In this project, diabetic retinopathy is detected and classified into five stages: no DR, severe DR, Moderate DR, Proliferative DR, and mild DR. This is made possible with the help of various deep learning techniques. A trained model (ResNet-50 architecture) is used for the extraction of various features from the images. This model gives an accuracy of 0.47% in testing. The dataset used is the Aptos 2019 dataset which is available on Kaggle.

A review of wearable sensors based fall-related recognition systems

Falls are an important factor in significantly deteriorating quality of life of older adults, consequently leading to both physical and psychological harm. A wearable-based fall-related recognition system (WFRS) indeed facilitates the prediction, detection, and classification of fall events in helping fallers. Previous studies have provided a relatively comprehensive introduction to WFRSs from the perspective of sensor types and recognition algorithms. However, while these studies provide a clear technical direction, how to choose the appropriate technology for each phase of the experiment is a stumbling block for newly interested researchers. Accordingly, a comprehensive review article covering the mainstream technologies of WFRSs is imperative and meaningful. This review analyzes 48 state-of-the-art researches in WFRSs from three databases (i.e., IEEE Explorer, ScienceDirect, and MDPI) and introduces the pipeline techniques that consist of data acquisition, preprocessing, feature extraction, model training, and evaluation. Specifically, we first analyze the pros and cons of the use of different number of sensors for data collection. We then introduce the widely used preprocessing techniques including filtering and data augmentation. Afterwards, we detail the extraction of various features and illustrate methods for the selection, training, and evaluation of fall recognition models. We finally discuss factors affecting the overall performance of a model and offer suggestions for future research.

EEG based classification of children with learning disabilities using shallow and deep neural network

Learning disability (LD), a neurodevelopmental disorder that has severely impacted the lives of many children all over the world. LD refers to significant deficiency in children’s reading, writing, spelling, and ability to solve mathematical task despite having normal intelligence. This paper proposes a framework for early detection and classification of LD with non-LD children from rest electroencephalogram (EEG) signals using shallow and deep neural network. Twenty children with LD and twenty non-LD children (aged 8–16 years) participated in this study. Preprocessing the raw EEG signal, segmentation and extraction of various features from the alpha, beta, delta, and theta bands obtained using digital wavelet transform (DWT). Filter based feature selection method were employed for the selection of most relevant features that reduces the computation burden on models. Afterwards, these ranked accumulated features were evaluated separately by machine learning (ML) classifiers and neural network (shallow and deep) models to investigate the performance. The performance of the ML classifiers and one-hidden layer shallow neural network and 3-hidden layer deep neural network were compared. Experimental results showed that the most relevant features computed by ReliefF algorithm along with the shallow neural network based classifier attained the highest average and maximum classification accuracy of 95.8 % and 97.5 % respectively, which is greatest among the existing literatures. The efficient and automatic LD classification from EEG signal could aid in the development of computer-aided diagnosis systems for early detection.

GTFtools: a software package for analyzing various features of gene models.

Gene-centric bioinformatics studies frequently involve the calculation or the extraction of various features of genes such as splice sites, promoters, independent introns and untranslated regions (UTRs) through manipulation of gene models. Gene models are often annotated in gene transfer format (GTF) files. The features are essential for subsequent analysis such as intron retention detection, DNA-binding site identification and computing splicing strength of splice sites. Some features such as independent introns and splice sites are not provided in existing resources including the commonly used BioMart database. A package that implements and integrates functions to analyze various features of genes will greatly ease routine analysis for related bioinformatics studies. However, to the best of our knowledge, such a package is not available yet. We introduce GTFtools, a stand-alone command-line software that provides a set of functions to calculate various gene features, including splice sites, independent introns, transcription start sites (TSS)-flanking regions, UTRs, isoform coordination and length, different types of gene lengths, etc. It takes the ENSEMBL or GENCODE GTF files as input and can be applied to both human and non-human gene models like the lab mouse. We compare the utilities of GTFtools with those of two related tools: Bedtools and BioMart. GTFtools is implemented in Python and not dependent on any third-party software, making it very easy to install and use. GTFtools is freely available at www.genemine.org/gtftools.php as well as pyPI and Bioconda.

Early Termination of CU Partition Based on Boosting Neural Network for 3D-HEVC Inter-Coding

As an extension of the High Efficiency Video Coding (HEVC) standard, the 3D-HEVC needs to encode multiple texture videos and depth maps components. In the 3D-HEVC inter-coding test model, a large variety of Coding Unit (CU) sizes are adopted to select the one with the lowest Rate-Distortion (RD) cost as the best CU size. This technique provides the highest achievable coding efficiency, but it brings a huge computational complexity which limits 3D-HEVC from practical applications. In this paper, early termination of CU encoding is proposed to reduce the complexity caused by the CU size splitting process. The proposed algorithm is based on CU homogeneity and a boosting neural network clustering algorithm. The algorithm contained three main steps. The first step is for the extraction of various features from the original encoder. Then, the selection of the features, which had a high correlation with CU partition using a machine learning algorithm. In the second step, a boosting neural network model is used for training the selected features to derive the threshold values for our proposed algorithm. In the final step, an efficient early termination of CU splitting is released for texture videos and depth maps based on the extracted thresholds from the training model. The experimental results show that the proposed algorithm reduces a significant encoding time, while the loss in coding efficiency is negligible.

SUIP: An Android malware detection method based on data flow features

Currently static detection is the most commonly used in Android malware detection. Among them, the extraction of various features is particularly important. In analysing the data flow features of applications, researchers usually use taint analysis method to extract. However, this method lack intermediate process features. So in this paper, we analyse the features of Android components to obtain application data transfer features for complementing the application data flow features and build a more complete combination of data flow features. Based on this, we propose a new Android malicious application detection method—SUIP. This method complements the missing features based on taint analysis, and combines the LightGBM algorithm to build a detection model. Finally, we use the sample set in Virusshare for experiments. Compared with the traditional static detection method of Android malicious code, the result shows that our detection method has a high detection accuracy of 98.50%.

Dengesiz Makine Öğrenimi Teknikleri Kullanılarak Fonokardiyografi Sinyallerinin Sınıflandırılması

Cardiovascular diseases, which involve heart and blood vessel dysfunctions, cause a higher number of deaths than any other disease in the world. Throughout history, many approaches have been developed to analyze cardiovascular health by diagnosing such conditions. One of the methodologies is recording and analyzing heart sounds to distinguish normal and abnormal functioning of the heart, which is called Phonocardiography. With the emergence of machine learning applications in healthcare, this process can be automated via the extraction of various features from phonocardiography signals and performing classification with several machine learning algorithms. Many studies have been conducted to extract time and frequency domain features from the phonocardiography signals by segmenting them first into individual heart cycles, and then by classifying them using different machine learning and deep learning approaches. In this study, various time and frequency domain features have been extracted using the complete signal rather than just segments of it. Random Forest algorithm was found to be the most successful algorithm in terms of accuracy as well as recall and precision.

Time-frequency analysis and fuzzy-based detection of heat-stressed sleep EEG spectra.

Nowadays, sleep disorders are contemplated as the major issue in the human lives. The current work aims at extraction of time-frequency information from recorded dataset and provides an efficient sleep stage detection method. Recordings of brain signal namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) were carried out under defined clinical condition for the classification of sleep EEG. Subsequent upon the extraction of various features from the raw EEG data, neuro-fuzzy system is trained to classify the sleep stages into three major classes namely awake, slow wave sleep (SWS), and rapid eye movement sleep (REM). This classification would enable medical professionals to diagnose sleep related disorders accurately. The results obtained clearly indicate that the mean performance for SWS stage is profound as compared to REM and awake stage. Specificity and sensitivity of the proposed method are obtained as 95.4% and 80%, respectively. The average accuracy of the system employing neuro-fuzzy approach is found to be 90.6% in which SWS stage was best detected among the other stages of sleep EEG.Graphical abstract.

Extractive Text Summarization for Sports Articles using Statistical Method

The past decade has endorsed a great rise in Artificial Intelligence. Text summarization which comes under AI has been an important research area that identifies the relevant sentences from a piece of text. By Text Summarization, we can get short and precise information by preserving the contents of the text. This paper presents an approach for generating a short and precise extractive summary for the given document of text. A statistical method for extractive text summarization of sports articles using extraction of various features is discussed in this paper. The features taken are TF-ISF, Sentence Length, Sentence Position, Sentence to Sentence cohesion, Proper noun, Pronoun. Each sentence is given a score known as the predictive score is calculated and the summary for the given document of text is given based on the predictive score or also known as the rank of the sentence. The accuracy is checked using the BBC Sports Article dataset and sports articles of various newspapers like the New York Times, CNN. The precision of 73% is acquired when compared with System Generated Summary (SGS) and manual summary, on an average.

Hard exudate based severity assessment of diabetic macular edema from retinal fundus images

Diabetic macular edema (DME) is a consequence of diabetic retinopathy characterised by the abnormal accumulation of fluid and protein deposit in the macula region of the retina. Prior disclosure of even a trivial trace of DME is essential as it could consequently lead to blurred vision. DME can be diagnosed by the presence of exudates (glossy lesions) in the retinal fundus images. In this work, OD and macula are detected using morphological operation and hard exudates are segmented. Exudates are classified using early treatment diabetic retinopathy standard as normal, moderate or severe cases. The proposed work also incorporates the extraction of various features from the retinal fundus image. Various textural and exudate features are extracted and fed to a classifier to detect DME. Experiments are performed on a publically available database. Performance is evaluated with metrics like accuracy, sensitivity, specificity and accuracy. The results obtained are promising.

Fake currency detection using image processing

The advancement of color printing technology has increased the rate of fake currency note printing and duplicating the notes on a very large scale. Few years back, the printing could be done in a print house, but now anyone can print a currency note with maximum accuracy using a simple laser printer. As a result the issue of fake notes instead of the genuine ones has been increased very largely. India has been unfortunately cursed with the problems like corruption and black money. And counterfeit of currency notes is also a big problem to it. This leads to design of a system that detects the fake currency note in a less time and in a more efficient manner. The proposed system gives an approach to verify the Indian currency notes. Verification of currency note is done by the concepts of image processing. This article describes extraction of various features of Indian currency notes. MATLAB software is used to extract the features of the note. The proposed system has got advantages like simplicity and high performance speed. The result will predict whether the currency note is fake or not.

Extraction of Various Features of ECG Signal

Extraction of Various Features of ECG Signal

Mapping curbstones in airborne and mobile laser scanning data

The high point densities obtained by today's laser scanning systems enable the extraction of various features which are traditionally mapped by photogrammetry or land surveying. While significant progress has been made in the extraction of buildings and trees from dense point clouds, little research has been performed on the extraction of roads. In this paper it is analysed to what extent road sides can be mapped in point clouds of high point density. In urban areas curbstones are often used to separate the road surface from the adjacent pavement. These curbstones are mapped in a three step procedure. First, the locations with small height jumps near the terrain surface are detected. Second, midpoints of high and low points on either side of the height jump are generated, put in a sequence to obtain a polygonal chain describing the approximate curbstone location. A sigmoidal function is then fitted to all points near the polygonal chain to increase the accuracy. Third, small gaps between nearby and collinear line segments are closed. GPS measurements were taken to analyse the performance of the road side detection. The analysis showed that the completeness in airborne laser scanning (ALS) data varying between 53% and 92% is higher than that in mobile laser scanning (MLS) data ranging from 54% to 83%, depending on the amount of parked cars occluding the curbstones. The RMS value in the comparison with the GPS points measured from ground survey was 0.11m in ALS data and 0.06m in MLS data, respectively.

Classification of RBC And WBC in Peripheral Blood Smear Using KNN

The objective of the paper is to present the blood cells classification method to develop an automatic differential blood count system. The counting and analysis of blood cells provides a huge amount of information to the pathologist , for finding the disease and its treatment. The proposed system consists of two automatic steps : segmentation of blood cells and classification. For classification, feature vector is created by extraction of various features from the segmented blood cells. Experimental results have shown the effectiveness of system.

Using genetic algorithms and k-nearest neighbour for automatic frequency band selection for signal classification

The classification of signals is usually based on the extraction of various features that subsequently will be used as an input to a classifier. These features are extracted as a result of the experts’ prior knowledge, which may often involve a lack of the information necessary for an accurate classification in all cases. This study proposes a new technique, in which a genetic algorithm is used to automatically extract frequency-domain features from a set of signals, with no need of prior knowledge. This allows, first, to achieve greater accuracy in the classification of signals, and, secondly, to discover new data on the signals to be classified. This system was used to solve a well-known problem: classification of electroencephalogram (EEG) signals, and its results show a better performance in comparison with other works on the same problem.

Feature selection for sleep/wake stages classification using data driven methods

This paper focuses on the problem of selecting relevant features extracted from human polysomnographic (PSG) signals to perform accurate sleep/wake stages classification. Extraction of various features from the electroencephalogram (EEG), the electro-oculogram (EOG) and the electromyogram (EMG) processed in the frequency and time domains was achieved using a database of 47 night sleep recordings obtained from healthy adults in laboratory settings. Multiple iterative feature selection and supervised classification methods were applied together with a systematic statistical assessment of the classification performances. Our results show that using a simple set of features such as relative EEG powers in five frequency bands yields an agreement of 71% with the whole database classification of two human experts. These performances are within the range of existing classification systems. The addition of features extracted from the EOG and EMG signals makes it possible to reach about 80% of agreement with the expert classification. The most significant improvement on classification accuracy is obtained on NREM sleep stage I, a stage of transition between sleep and wakefulness.

Computerized detection of masses in digital mammograms: Investigation of feature-analysis techniques

Mammographic screening of asymptomatic women has shown effectiveness in the reduction of breast cancer mortality. We are developing a computerized scheme for the detection of mammographic masses as an aid to radiologists in mammographic screening programs. Possible masses on digitized screen/film mammograms are initially identified using a nonlinear bilateral-subtraction technique, which is based on asymmetric density patterns occurring in corresponding portions of right and left mammograms. In this study, we analyze the characteristics of actual masses and nonmass detections to develop feature-analysis techniques with which to reduce the number of nonmass (ie, false-positive) detections. These feature-analysis techniques involve (1) the extraction of various features (such as area, contrast, circularity and border-distance based on the density and geometric information of masses in both processed, and original breast images), and (2) tests of the extracted features to reduce nonmass detections. Cumulative histograms of both actual-mass detections and nonmass detections are used to characterize extracted features and to determine the cutoff values used in the feature tests. The effectiveness of the feature-analysis techniques is evaluated in combination with the computerized detection scheme that uses the nonlinear bilateral-subtraction technique using free-response receiver operating characteristic analysis and 77 patient cases (308 mammograms). Results show that the feature-analysis techniques effectively improve the performance of the computerized detection scheme: about 35% false-positive detections were eliminated without loss in sensitivity when the feature-analysis techniques were used.