Increase Classification Accuracy Research Articles

Implementation of art therapy assisted by the internet of medical things based on blockchain and fuzzy set theory

This work aims to improve the stability and efficiency of the Internet of Medical Things (IoMT), strengthen the security and privacy of personal information, and create a healthy and safe network environment. First, art therapy in the current medical environment is discussed, and the security defenses of the IoMT supporting art therapy are studied. Then, a security defense method for IoMT is proposed by combining basic Blockchain knowledge with the Fuzzy Sets Theory. Specifically, a Density-awarded Fuzzy C-means (DFCM) algorithm is developed to solve the clustering issue of unbalanced data sets. Besides, the Fuzzy Support Vector Machine (FSVM) model is used to classify data points far from the sample center to increase classification accuracy. In the simulation experiment, the DFCM algorithm achieves a pleasing clustering effect on the four data sets, involving the data sets with density changes and imbalanced sample points within the cluster. Moreover, the combination of DFCM and FSVM (DFCM-FSVM) for attack detection in the Internet of Things (IoT) realizes the optimal accuracy in the detection of different behaviors compared with similar algorithms; the detection accuracy of normal behavior, scheduled attack, gray hole attack, and black hole attack is 99.8%, 89.8%, 99.4%, and 91.5%, respectively. This work creatively proposes a hybrid intrusion detection method based on fuzzy theory. As the second line of defense in security protection, it plays a critical role and is suitable for the network environment of the perception layer. In conclusion, the attack detection method based on Blockchain combined with the Fuzzy Sets Theory can precisely identify potential attacks in abnormal data, which has important practical value for maintaining data security and the regular operation of the IoMT.

Supervised poststack 3D seismic data classification via multiscale and multilabel consistent feature reduction

Following the advancement of machine learning-based seismic feature classification techniques for complex reservoirs, the acquisition and analysis of reliable seismic samples involved in seismic facies analysis and network-based inversion have emerged as a current research hotspot in the field of intelligent seismic processing. Many investigations focus on the improvement of model classification algorithms and neural networks. However, creating and collecting labels for massive seismic data are highly time-consuming and laborious, and suffer from sample unreliability and category imbalance in the case of small-sample labels. To address such problems, a multiscale and multilabel consistent principal component analysis-linear discriminant analysis (PCA-LDA) algorithm to learn a robust feature discriminative dictionary for classification is presented. In addition to the automatic use of multilabels from well logs and core analysis, we have associated multiscale with well trajectory locations to enrich sample information and enhance the reliability of the samples during 3D sample acquisition. More specifically, we begin by proposing an approach for the automatic collection of multiscale multilabel 3D poststack seismic samples along the well track. Next, the multilabel sequence in the scan window is fed into the Boyer-Moore majority vote algorithm for sample segmentation, which constructs multilabel hierarchies for each sample. Then to enhance the model training bias due to small-sample label imbalance, we develop a novel label-shuffling balanced strategy, which obtains a complete database by filling random unduplicated augmented training samples (spatial and frequency-domain augmentation operations). Finally, the linear robustness decision-making space of PCA-LDA is obtained using the feature mapping space of PCA, as well as its visual representation. Experimental results on synthetic and field seismic data demonstrate that robust feature extraction with a trustworthy and complete multiscale and multilabel sample database increases classification accuracy.

A Comparison Between the Performance of Features Selection Techniques: Survey Study

Feature selection is one of the most popular and crucial methods of data processing used in different machine learning and data mining approaches to avoid high dimensionality and increase classification accuracy. Additionally, attribute selection aids in accelerating machine learning algorithms, improving prediction accuracy, data comprehension, decreasing data storage space, and minimizing the computational complexity of learning algorithms. For this reason, several feature selection approaches are used. To determine the essential feature or feature subsets needed to achieve classification objectives, several feature selection techniques have been suggested in the literature. In this research, different widely employed feature selection strategies have been evaluated by using different datasets to see how efficiently these techniques may be applied to achieve high performance of learning algorithms, which improves the classifier's prediction accuracy.

Covering Arrays ML HPO for Static Malware Detection

Malware classification is a well-known problem in computer security. Hyper-parameter optimisation (HPO) using covering arrays (CAs) is a novel approach that can enhance machine learning classifier accuracy. The tuning of machine learning (ML) classifiers to increase classification accuracy is needed nowadays, especially with newly evolving malware. Four machine learning techniques were tuned using cAgen, a tool for generating covering arrays. The results show that cAgen is an efficient approach to achieve the optimal parameter choices for ML techniques. Moreover, the covering array shows a significant promise, especially cAgen with regard to the ML hyper-parameter optimisation community, malware detectors community and overall security testing. This research will aid in adding better classifiers for static PE malware detection.

An Improved Explainable Point Cloud Classifier (XPCC)

Classification of objects from 3-D point clouds has become an increasingly relevant task across many computer-vision applications. However, few studies have investigated explainable methods. In this article, a new prototype-based and explainable classification method called eXplainable point cloud classifier (XPCC) is proposed. The XPCC method offers several advantages over previous explainable and nonexplainable methods. First, the XPCC method uses local densities and global multivariate generative distributions. Therefore, the XPCC provides comprehensive and interpretable object-based classification. Furthermore, the proposed method is built on recursive calculations, thus, is computationally very efficient. Second, the model learns continuously without the need for complete retraining and is domain transferable. Third, the proposed XPCC expands on the underlying learning method explainable deep neural networks (xDNN), and is specific to 3-D. As such, the following three new layers are added to the original xDNN architecture: 1) the 3-D point cloud feature extraction, 2) the global compound prototype weighting, and 3) the SoftMax function. Experiments were performed with the ModelNet40 benchmark, which demonstrated that XPCC is the only one to increase classification accuracy relative to the base algorithm when applied to the same problem. In addition, this article proposes a novel prototype-based visual representation that provides model- and object-based explanations. The prototype objects are superimposed to create a prototypical class representation of their data density within the feature space, called the compound prototype cloud. They allow a user to visualize the explainable aspects of the model and identify object regions that contribute to the classification in a human-understandable way.

Breast Cancer Prediction Using Fine Needle Aspiration Features and Upsampling with Supervised Machine Learning.

Breast cancer is one of the most common invasive cancers in women and it continues to be a worldwide medical problem since the number of cases has significantly increased over the past decade. Breast cancer is the second leading cause of death from cancer in women. The early detection of breast cancer can save human life but the traditional approach for detecting breast cancer disease needs various laboratory tests involving medical experts. To reduce human error and speed up breast cancer detection, an automatic system is required that would perform the diagnosis accurately and timely. Despite the research efforts for automated systems for cancer detection, a wide gap exists between the desired and provided accuracy of current approaches. To overcome this issue, this research proposes an approach for breast cancer prediction by selecting the best fine needle aspiration features. To enhance the prediction accuracy, several feature selection techniques are applied to analyze their efficacy, such as principal component analysis, singular vector decomposition, and chi-square (Chi2). Extensive experiments are performed with different features and different set sizes of features to investigate the optimal feature set. Additionally, the influence of imbalanced and balanced data using the SMOTE approach is investigated. Six classifiers including random forest, support vector machine, gradient boosting machine, logistic regression, multilayer perceptron, and K-nearest neighbors (KNN) are tuned to achieve increased classification accuracy. Results indicate that KNN outperforms all other classifiers on the used dataset with 20 features using SVD and with the 15 most important features using a PCA with a 100% accuracy score.

Point Cloud Classification by Domain Adaptation Using Recycling Max Pooling and Cutting Plane Identification.

Deep models have been studied in point cloud classification for the applications of autonomous driving and robotics. One challenging issue is that the point cloud of the same object could be discrepantly captured depending on sensors. Such a difference is the main cause of the domain gap. The deep models trained with one domain of point clouds may not work well with other domains because of such a domain gap. A technique to reduce domain inconsistency is domain adaptation. In this paper, we propose an unsupervised domain adaptation with two novel schemes. First, to improve unreliable pseudo-label assignment, we introduce a voting-based procedure based on the recycling max pooling module, which involves self-paced learning. It helps to increase the training stability of the models. Second, to learn the geometrical characteristics of point clouds in unfamiliar settings, we propose a training method of cutting plane identification, which works in an unsupervised way. Testing with the popular point cloud dataset of PointDA-10 and Sim-to-Real, experiments show that our method increase classification accuracy by 6.5%-points on average, ModelNet and ShapeNet as the source domain and ScanNet, and ScanObjectNN as the target domain. From an ablation study, it was observed that each method contributes to improving the robustness of domain adaptation.

INCREASING THE SPATIAL ACCURACY OF THE LAND USE MAP USING FUSION OF OPTICAL AND RADAR IMAGES OF SENTINEL AND GOOGLE EARTH ENGINE

Abstract. Nowadays, exact and real-time land use and land cover (LULC) maps are imperative to supply precise data for energetic observing, arranging and arrive administration. With the appearance of cloud computing frameworks, time arrangement includes extraction methods, and machine learning classifiers, unused openings emerge in more precise and larger-scale LULC mapping. In this research, the aim is to obtain a land use map with a spatial resolution of 10 meters by combining Sentinel-1 radar images and Sentinel-2 optical images. The processing was done in Google Earth Engine cloud computing system. Also, in this research, NDVI map and NDBI map were used to increase classification accuracy. Classification was done using the decision tree method and in eleven classes. To evaluate the classification accuracy and the final map, randomly collected points were used in the study area. The results of the comparison of the ground collection points and the final classified map showed that the classification accuracy in this study was around 94%. The results obtained from such as research can be optimally used in urban planning and crisis management.

Fusing Multiple Land Cover Products Based on Locally Estimated Map-Reference Cover Type Transition Probabilities

There are a variety of land cover products generated from remote-sensing images. However, misclassification errors in individual products and inconsistency among them undermine their utilities for research and other applications. While it is worth developing advanced pattern classifiers and utilizing the images of finer spatial, temporal, and/or spectral resolution for increased classification accuracy, it is also sensible to increase map classification accuracy through effective map fusion by exploiting complementarity among multi-source products over a study area. This paper presents a novel fusion method that works by weighting multiple source products based on their map-reference cover type transition probabilities, which are predicted using random forest for individual map pixels. The proposed method was tested and compared with three alternatives: consensus-based weighting, random forest, and locally modified Dempster–Shafer evidential reasoning, in a case study, over Shaanxi province, China. For this case study, three types of land cover products (GlobeLand30, FROM-GLC, and GLC_FCS30) of two nominal years (2010 and 2020) were used as the base maps for fusion. Reference sample data for model training and testing were collected following a robust stratified random sampling design that allows for augmenting reference data flexibly. Accuracy assessments show that overall accuracies (OAs) of fused land cover maps have been improved (1~9% in OAs), with the proposed method outperforming other methods by 2~8% in OAs. The proposed method does not need to have the base products’ classification systems harmonized beforehand, thus being robust and highly recommendable for fusing land cover products.

Fine-grained age-matching improves atrophy-based detection of mild cognitive impairment more than amyloid-negative reference subjects

IntroductionIn clinical practice, differentiating between age-related gray matter (GM) atrophy and neurodegeneration-related atrophy at early disease stages, such as mild cognitive impairment (MCI), remains challenging. We hypothesized that fined-grained adjustment for age effects and using amyloid-negative reference subjects could increase classification accuracy. MethodsT1-weighted magnetic resonance imaging (MRI) data of 131 cognitively normal (CN) individuals and 91 patients with MCI from the Alzheimer’s disease neuroimaging initiative (ADNI) characterized concerning amyloid status, as well as 19 CN individuals and 19 MCI patients from an independent validation sample were segmented, spatially normalized and analyzed in the framework of voxel-based morphometry (VBM). For each participant, statistical maps of GM atrophy were computed as the deviation from the GM of CN reference groups at the voxel level. CN reference groups composed with different degrees of age-matching, and mixed and strictly amyloid-negative CN reference groups were examined regarding their effect on the accuracy in distinguishing between CN and MCI. Furthermore, the effects of spatial smoothing and atrophy threshold were assessed. ResultsApproaches with a specific reference group for each age significantly outperformed all other age-adjustment strategies with a maximum area under the curve of 1.0 in the ADNI sample and 0.985 in the validation sample. Accounting for age in a regression-based approach improved classification accuracy over that of a single CN reference group in the age range of the patient sample. Using strictly amyloid-negative reference groups improved classification accuracy only when age was not considered. ConclusionOur results demonstrate that VBM can differentiate between age-related and MCI-associated atrophy with high accuracy. Crucially, age-specific reference groups significantly increased accuracy, more so than regression-based approaches and using amyloid-negative reference groups.

Neural Network Fusion Processing and Inverse Mapping to Combine Multisensor Satellite Data and Analyze the Prominent Features

In the last decade, the increase of active and passive earth observation satellites has provided us with more remote sensing data. This fact has led to enhanced interest in the fusion of different satellite data since some of the satellites have properties complementary to others. Fusion techniques can improve the estimation in areas of interest by using the complementary information and inferring unknown parameters. They also have the potential to provide high-resolution detailed classification maps. Thus, we propose a neural network, which combines and analyzes the data obtained from synthetic aperture radar (SAR) and optical sensors to provide high-resolution classification maps. The neural network employs a novel activation function to construct a neural network explainability method termed as inverse mapping for prominent feature analysis. By applying inverse mapping to the data-fusion neural network, we can understand which input features are the prominent contributors for which classification outputs. Inverse mapping realizes backward signal flow based on teacher-signal backpropagation dynamics, which is consistent with its forward processing. It performs the contribution analysis of the data pixel-by-pixel and class-by-class. In this paper, we focus on earthquake damage detection by dealing with SAR and optical sensor data of the 2018 Sulawesi earthquake in Indonesia. The fusion-based results show increased classification accuracy compared to the results of independent sensors. Moreover, we observe that inverse mapping shows reasonable explanations in a consistent manner. It also indicates the contributions of features different from straightforward counterparts, namely pre- and post-seismic features, in the detection of particular classes.

Network Intrusion Detection Based on Feature Selection and Hybrid Metaheuristic Optimization

Applications of internet-of-things (IoT) are increasingly being used in many facets of our daily life, which results in an enormous volume of data. Cloud computing and fog computing, two of the most common technologies used in IoT applications, have led to major security concerns. Cyberattacks are on the rise as a result of the usage of these technologies since present security measures are insufficient. Several artificial intelligence (AI) based security solutions, such as intrusion detection systems (IDS), have been proposed in recent years. Intelligent technologies that require data preprocessing and machine learning algorithm-performance augmentation require the use of feature selection (FS) techniques to increase classification accuracy by minimizing the number of features selected. On the other hand, metaheuristic optimization algorithms have been widely used in feature selection in recent decades. In this paper, we proposed a hybrid optimization algorithm for feature selection in IDS. The proposed algorithm is based on grey wolf (GW), and dipper throated optimization (DTO) algorithms and is referred to as GWDTO. The proposed algorithm has a better balance between the exploration and exploitation steps of the optimization process and thus could achieve better performance. On the employed IoT-IDS dataset, the performance of the proposed GWDTO algorithm was assessed using a set of evaluation metrics and compared to other optimization approaches in the literature to validate its superiority. In addition, a statistical analysis is performed to assess the stability and effectiveness of the proposed approach. Experimental results confirmed the superiority of the proposed approach in boosting the classification accuracy of the intrusion in IoT-based networks.

Fault Diagosis of CHB Inverter Using Machine Learning

Renewable energy has gained popularity due to depleting natural resources and escalating fossil fuel and nuclear pollution. Power electronic engineers design grid-connected power conversion systems. MLIs provide more power and solutions. Cascaded H-Bridge (CHB) MLIs start with two or more 3L single-phase H-bridge inverters. Each H-bridge may produce three separate voltage levels. Combining the separated dc voltage sources produces a stepped output voltage with a step size equal to the magnitude of the connected sources. The present work develops a method for detecting and resolving switch failures in a three-phase CHB inverter, ensuring system dependability and allowing for system redundancy. The recommended approach uses Wavelet transform to extract features, then Decision Tree classifier to detect and characterise defects. Increased classification accuracy shows the DT-based fault diagnosis system's efficiency in identifying inverter switch faults.

Feature Selection Method Using Multi-Agent Reinforcement Learning Based on Guide Agents

In this study, we propose a method to automatically find features from a dataset that are effective for classification or prediction, using a new method called multi-agent reinforcement learning and a guide agent. Each feature of the dataset has one of the main and guide agents, and these agents decide whether to select a feature. Main agents select the optimal features, and guide agents present the criteria for judging the main agents' actions. After obtaining the main and guide rewards for the features selected by the agents, the main agent that behaves differently from the guide agent updates their Q-values by calculating the learning reward delivered to the main agents. The behavior comparison helps the main agent decide whether its own behavior is correct, without using other algorithms. After performing this process for each episode, the features are finally selected. The feature selection method proposed in this study uses multiple agents, reducing the number of actions each agent can perform and finding optimal features effectively and quickly. Finally, comparative experimental results on multiple datasets show that the proposed method can select effective features for classification and increase classification accuracy.

USTW Vs. STW: A Comparative Analysis for Exam Question Classification based on Bloom’s Taxonomy

Bloom’s Taxonomy (BT) is widely used in educational institutions to produce high-quality exam papers to evaluate students’ knowledge at different cognitive levels. However, manual question labeling takes a long time, and not all evaluators are familiar with BT. The researchers worked to automate the exam question classification process based on BT as a solution. Enhancement in term weighting is one of the ways to increase classification accuracy while working with text data. However, all the past work on the term weighting in exam question classification focused on unsupervised term weighting (USTW) schemes. The supervised term weighting (STW) schemes showed effectiveness in text classification but were not addressed in past studies of exam question classification. As a result, this study focused on the effectiveness of STW in classifying exam questions using BT. Hence, this research performed a comparative analysis between the USTW schemes and STW for exam question classification. The STW schemes used in this study are TF-ICF, TF-IDF-ICF, and TF-IDF-ICSDF, whereas the USTW schemes used for comparison are TF-IDF, ETF-IDF, and TFPOS-IDF. This study used Support Vector Machines (SVM), Na¨ıve Bayes (NB), and Multilayer Perceptron (MLP) to train the model. Accuracy and F1 score were used in this study to evaluate the classification result. The experiment result showed that overall, the STW scheme TF-ICF outperformed all the other schemes, followed by the USTW scheme ETF-IDF. Both the ETF-IDF and TFPOS-IDF outperformed standard TFIDF. The outcome of this study indicates the future research direction where the combination of STW and USTW schemes may increase the Accuracy of BT-based exam question classification.

A Bayesian Network for the Classification of Human Motion as Observed by Distributed Radar

In this article, a statistical model of human motion as observed by a network of radar sensors is presented where knowledge on the position and heading of the target provides information on the observation conditions of each sensor node. Sequences of motions are estimated from measurements of instantaneous Doppler frequency, which captures informative micromotions exhibited by the human target. A closed-form Bayesian estimation algorithm is presented that jointly estimates the state of the target and its exhibited motion class which are described by a hidden Markov model. To correct errors in the estimated motion class distribution introduced by faulty modeling assumptions, calibration of the probability distribution and measurement likelihood is performed by isotonic regression. It is shown, by modeling sensor observation conditions and by isotonic calibration of the measurement likelihood that a cognitive resource management system is able to increase classification accuracy by 5 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\%}$</tex-math></inline-formula> –10 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\%}$</tex-math></inline-formula> while utilizing sensor resources in accordance with defined mission objectives.

Classifying Gait Alterations Using an Instrumented Smart Sock and Deep Learning

This article presents a noninvasive method of classifying gait patterns associated with various movement disorders and/or neurological conditions, utilizing unobtrusive, instrumented socks and a deep-learning network. Seamless instrumented socks were fabricated using three accelerometer-embedded yarns, positioned at the toe (hallux), above the heel, and on the lateral malleolus. Human trials were conducted on 12 able-bodied participants, an instrumented sock was worn on each foot. Participants were asked to complete seven trials consisting of their typical gait and six different gait types that mimicked the typical movement patterns associated with various movement disorders and neurological conditions. Four neural networks and an SVM were tested to ascertain the most effective method of automatic data classification. The bi-long short-term memory (LSTM) generated the most accurate results and illustrates that the use of three accelerometers per foot increased classification accuracy compared to a single accelerometer per foot by 11.4%. When only a single accelerometer was utilized for classification, the ankle accelerometer generated the most accurate results in comparison to the other two. The network was able to correctly classify five different gait types: stomp (100%), shuffle (66.8%), diplegic (66.6%), hemiplegic (66.6%), and “normal walking” (58.0%). The network was incapable of correctly differentiating foot slap (21.2%) and steppage gait (4.8%). This work demonstrates that instrumented textile socks incorporating three accelerometer yarns were capable of generating sufficient data to allow a neural network to distinguish between specific gait patterns. This may enable clinicians and therapists to remotely classify gait alterations and observe changes in gait during rehabilitation.

New methods for analysing circulating cell‐free mitochondrial DNA

Trauma, ischemia, inflammatory stress and environmental conditions can cause tissue injury and damage. This damage spurs the release of cellular components and debris into the extracellular environment, including damage associated molecular pattern (DAMP) molecules. These DAMPs are sensed by pattern recognition receptors that activate a cellular damage response to the pathological insult. Mitochondrial components have recently been recognised as potent DAMPs.1, 2 The mitochondrial genome shares features with bacterial genomes, due to their shared origin. Therefore, when mitochondrial DNA (mtDNA) is released into the extracellular space it is recognised as a foreign molecule and initiates an innate immune response.1, 2 Not only have DAMP molecules been of interest in studying the relationships between cellular damage and immune responses, but emerging evidence suggests that DAMPs may serve as ‘liquid biopsies’ to indicate tissue damage or disease status. For example, plasma levels of circulating cell-free mtDNA (ccf-mtDNA) can be isolated and quantified easily using quantitative real-time PCR (qPCR). The results of many studies suggest that there are higher levels of ccf-mtDNA after trauma, acute myocardial infarction, sepsis and in some inflammatory conditions.3 A recent systematic review examined published articles on utilising ccf-mtDNA as a predictor of mortality in critically ill patients.4 The authors noted that in their analysis there are inconsistencies in ccf-mtDNA isolation methods and quantification. For example, most often qPCR primers were designed against subunits of the NADH dehydrogenase (MT-ND, MT-ND1, MT-ND2 or MT-ND6).4 However, some studies use one primer set, others use multiple primer sets and some use primer sets recognising different genes in the mitochondrial genome. This may explain the discrepancies in the findings linking ccf-mtDNA to mortality in some studies but not in all. Therefore, there is a need for the development of technologies that improve upon these current methods to quantify ccf-mtDNA. Daly and colleagues recently developed a protocol that provides a new approach to analysing plasma ccf-mtDNA.5 In their approach, they utilised a target bait-capture kit consisting of biotinylated RNA probes complementary to the entire mitochondrial genome. First, the biotinylated probes bind to mitochondrial sequences and then are enriched, pooled, and sequenced on a standard Illumina instrument. Second, a Workflow Description Language-based computational pipeline aligns the reads to both the nuclear and mitochondrial genome and then custom programs call mitochondrial and nuclear coverage, insert fragment size and mtDNA variants. Nuclear genomes contain sequences of mitochondrial origin, called nuclear mitochondrial DNA segments (NUMTs). NUMT pseudogenes can also be enriched using these methods. Therefore, to exclude the possibility that reads are from the nuclear genome, this method excludes sequences that aligned to both nuclear and mitochondrial genomes. This approach may underestimate the mtDNA levels but increases classification accuracy. In fact, this protocol was shown to enrich for mean coverage of the mtDNA genome compared to whole genome sequencing. Therefore, this protocol allows for the simultaneous quantification of mtDNA levels across the entire mitochondrial genome, differentiation of fragment lengths, and the identification of mtDNA variants.5 The authors utilised their protocol to investigate ccf-mtDNA in comparison to clinical phenotypes of injury and severity scores in a cohort of 30 trauma patients.5 There were no significant differences in ccf-mtDNA abundance between patients with non-severe or severe injuries. The ccf-mtDNA fragment length was significantly shorter in patients with major trauma and in patients where acute lung injury occurred after admission compared to non-severe injury patients. There were also mtDNA variants that were discovered that were associated with various clinical scores of injuries and severity in this cohort. Therefore, the authors utilised samples from this trauma cohort to validate that their protocol can be implemented to examined mtDNA levels, fragment length, and variants.5 This technological advance has advantages over the standard qPCR methods, as the entire mitochondrial genome can be analysed in one protocol. However, additional experiments and validation studies should be performed to directly compare the sensitivity and accuracy of this protocol versus the standard qPCR methods. Nevertheless, these methods will give scientists an additional tool to examine ccf-mtDNA in relation to tissue damage or disease status. This work was funded by the Intramural Research Program of the National Institute on Aging, National Institutes of Health. The authors declare no conflict of interest.

Impact of feature reduction techniques on classification accuracy of machine learning techniques in leg rehabilitation

The scientific community has recently shown a lot of interest in biometric-based person recognition systems. It is a dynamic technology that tries to recognize biometrics automatically, swiftly, precisely, and consistently. Gait recognition is a sort of biometric classification that concentrates on identifying persons utilizing personal measurements and correlations, including trunk and limb size, in addition to spatial data connected to innate patterns in people's motions. The purpose of this study is to highlight how important it is to use feature reduction strategies to increase classification accuracy. Two of these approaches are employed in this work: Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). To classify foot disease, six machine learning techniques are deployed as classifiers. These classifiers are Random Forest (RF), Naïve Bayes (NB), K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree (DT), and Stochastic Gradient Descent (SGD) for the purpose of determining which classifier performs best in classifying leg rehabilitation data. Experimental results using the EMG dataset in Lower Limb indicate that the classification accuracy reached 99% with a time not exceeding a few seconds.

Optimized Intelligent Classifier for Early Breast Cancer Detection Using Ultra-Wide Band Transceiver.

Breast cancer is the most common cancer diagnosed in women and the leading cause of cancer-related deaths among women worldwide. The death rate is high because of the lack of early signs. Due to the absence of a cure, immediate treatment is necessary to remove the cancerous cells and prolong life. For early breast cancer detection, it is crucial to propose a robust intelligent classifier with statistical feature analysis that considers parameter existence, size, and location. This paper proposes a novel Multi-Stage Feature Selection with Binary Particle Swarm Optimization (MSFS-BPSO) using Ultra-Wideband (UWB). A collection of 39,000 data samples from non-tumor and with tumor sizes ranging from 2 to 7 mm was created using realistic tissue-like dielectric materials. Subsequently, the tumor models were inserted into the heterogeneous breast phantom. The breast phantom with tumors was imaged and represented in both time and frequency domains using the UWB signal. Consequently, the dataset was fed into the MSFS-BPSO framework and started with feature normalization before it was reduced using feature dimension reduction. Then, the feature selection (based on time/frequency domain) using seven different classifiers selected the frequency domain compared to the time domain and continued to perform feature extraction. Feature selection using Analysis of Variance (ANOVA) is able to distinguish between class-correlated data. Finally, the optimum feature subset was selected using a Probabilistic Neural Network (PNN) classifier with the Binary Particle Swarm Optimization (BPSO) method. The research findings found that the MSFS-BPSO method has increased classification accuracy up to 96.3% and given good dependability even when employing an enormous data sample.