Multi-class Support Vector Machine Research Articles

Hybrid deep models for parallel feature extraction and enhanced emotion state classification

Emotions play a vital role in recognizing a person’s thoughts and vary significantly with stress levels. Emotion and stress classification have gained considerable attention in robotics and artificial intelligence applications. While numerous methods based on machine learning techniques provide average classification performance, recent deep learning approaches offer enhanced results. This research presents a hybrid deep learning model that extracts features using AlexNet and DenseNet models, followed by feature fusion and dimensionality reduction via Principal Component Analysis (PCA). The reduced features are then classified using a multi-class Support Vector Machine (SVM) to categorize different types of emotions. The proposed model was evaluated using the DEAP and EEG Brainwave datasets, both well-suited for emotion analysis due to their comprehensive EEG signal recordings and diverse emotional stimuli. The DEAP dataset includes EEG signals from 32 participants who watched 40 one-minute music videos, while the EEG Brainwave dataset categorizes emotions into positive, negative, and neutral based on EEG recordings from participants exposed to six different film clips. The proposed model achieved an accuracy of 95.54% and 97.26% for valence and arousal categories in the DEAP dataset, respectively, and 98.42% for the EEG Brainwave dataset. These results significantly outperform existing methods, demonstrating the model’s superior performance in terms of precision, recall, F1-score, specificity, and Mathew correlation coefficient. The integration of AlexNet and DenseNet, combined with PCA and multi-class SVM, makes this approach particularly effective for capturing the intricate patterns in EEG data, highlighting its potential for applications in human-computer interaction and mental health monitoring, marking a significant advancement over traditional methods.

Deep Learning-Enabled Dynamic Model for Nutrient Status Detection of Aquaponically Grown Plants

Developing models to assess the nutrient status of plants at various growth stages is challenging due to the dynamic nature of plant development. Hence, this study encoded spatiotemporal information of plants within a single time-series model to precisely assess the nutrient status of aquaponically cultivated lettuce. In particular, the long short-term memory (LSTM) and deep autoencoder (DAE) approaches were combined to classify aquaponically grown lettuce plants according to their nutrient status. The proposed approach was validated using extensive sequential hyperspectral reflectance measurements acquired from lettuce leaves at different growth stages across the growing season. A DAE was used to extract distinct features from each sequential spectral dataset time step. These features were used as input to an LSTM model to classify lettuce grown across a gradient of nutrient levels. The results demonstrated that the LSTM outperformed the convolutional neural network (CNN) and multi-class support vector machine (MCSVM) approaches. Also, features selected by the DAE showed better performance compared to features extracted using both genetic algorithms (GAs) and sequential forward selection (SFS). The hybridization of deep autoencoder and long short-term memory (DAE-LSTM) obtained the highest overall classification accuracy of 94%. The suggested methodology presents a pathway to automating the process of nutrient status diagnosis throughout the entire plant life cycle, with the LSTM technique poised to assume a pivotal role in forthcoming time-series analyses for precision agriculture.

RanBALL: An Ensemble Random Projection Model for Identifying Subtypes of B-cell Acute Lymphoblastic Leukemia.

As the most common pediatric malignancy, B-cell acute lymphoblastic leukemia (B-ALL) has multiple distinct subtypes characterized by recurrent and sporadic somatic and germline genetic alterations. Identification of B-ALL subtypes can facilitate risk stratification and enable tailored therapeutic approaches. Existing methods for B-ALL subtyping primarily depend on immunophenotypic, cytogenetic and genomic analyses, which would be costly, complicated, and laborious in clinical practice applications. To overcome these challenges, we present RanBALL (an Ensemble Ran dom Projection-Based Model for Identifying B -Cell A cute L ymphoblastic L eukemia Subtypes), an accurate and cost-effective model for B-ALL subtype identification based on transcriptomic profiling only. RanBALL leverages random projection (RP) to construct an ensemble of dimension-reduced multi-class support vector machine (SVM) classifiers for B-ALL subtyping. Results based on 100 times 5-fold cross validation tests for >1700 B-ALL patients demonstrated that the proposed model achieved an accuracy of 93.35%, indicating promising prediction capabilities of RanBALL for B-ALL subtyping. The high accuracies of RanBALL suggested that our model could effectively capture underlying patterns of transcriptomic profiling for accurate B-ALL subtype identification. We believe RanBALL will facilitate the discovery of B-ALL subtype-specific marker genes and therapeutic targets, and eventually have consequential positive impacts on downstream risk stratification and tailored treatment design.

Research on ELoran Demodulation Algorithm Based on Multiclass Support Vector Machine

Demodulation and decoding are pivotal for the eLoran system’s timing and information transmission capabilities. This paper proposes a novel demodulation algorithm leveraging a multiclass support vector machine (MSVM) for pulse position modulation (PPM) of eLoran signals. Firstly, the existing demodulation method based on envelope phase detection (EPD) technology is reviewed, highlighting its limitations. Secondly, a detailed exposition of the MSVM algorithm is presented, demonstrating its theoretical foundations and comparative advantages over the traditional method and several other methods proposed in this study. Subsequently, through comprehensive experiments, the algorithm parameters are optimized, and the parallel comparison of different demodulation methods is carried out in various complex environments. The test results show that the MSVM algorithm is significantly superior to traditional methods and other kinds of machine learning algorithms in demodulation accuracy and stability, particularly in high-noise and -interference scenarios. This innovative algorithm not only broadens the design approach for eLoran receivers but also fully meets the high-precision timing service requirements of the eLoran system.

A LiDAR-Based Recommendation System to Improve Sitting Posture Respecting Privacy.

Poor posture is becoming more widespread due to the rising number of jobs that require workers to sit for extended hours. Maintaining proper leg positioning is essential for good overall posture and long-term health. However, current monitoring methods involve multiple sensors and cameras, leading to discomfort and privacy concerns. This paper presents a privacy-preserving recommendation system using Light Detection and Ranging (LiDAR) to monitor leg positions. The system captures the horizontal leg outline at knee height and extracts domain-specific features, while a stacked autoencoder reproduces the latent representation of the leg outline. The system comprises three modules, including one-class and multi-class support vector machines, to identify 15 leg positions and reject unrecognized ones. Data from 30 healthy volunteers during work activities trained the system. When tested on new participants, the system achieved an accuracy of over 98%. In addition to monitoring leg positions while respecting privacy and ergonomics, our system alerts workers about poor leg positions and generates intuitive dashboards with posture statistics that help safety engineers identify at-risk workers and body parts. This offers a promising solution for improving desk workers' posture and reducing long-term health issues, respecting privacy.

Deep Feature Extraction with SVM Classifier for Brain Tumor Classification

Recently, methods for classifying brain tumors have used Deep Learning (DL), in particular, Convolutional Neural Networks (CNNs), to obtain promising results. Unlike conventional Machine Learning (ML) algorithms, CNNs can automatically extract features from images; they do not, however, need the extraction regarding hand-crafted features. Many obstacles reduce the accuracy of brain tumor classification systems; to address such obstacles, we propose a DL-based feature extraction method for brain tumor classification. A total of two pretrained CNNs, VggNet-16 and ResNet-18, are applied as deep feature extractors in the scheme to accomplish deep feature extraction. Contrast Limited Adaptive Histogram Equalization (CLAHE) technique has been first used for enhancing the images. Second, each separately pretrained CNN, VggNet-16 and ResNet-18, is used for extracting the deep features from Magnetic Resonance Imaging (MRI). Lastly, a Multiclass Support Vector Machines (Multiclass -SVM) classifier is used to complete a classification task. Tests conducted on the aforementioned datasets: the effectiveness of the suggested approach is demonstrated by the CE-MRI Figshare, the REMBRANDT, and the Brain Tumor Classification, where the pre-trained CNN models and SVM classifier enhance performance. Specifically, the pretrained CNN with SVM approach produces accuracy ranging from 95.28% to 98.62% across all data-sets.

Classification of exercise fatigue levels by multi-class SVM from ECG and HRV.

Among the various physiological signals, electrocardiogram (ECG) is a valid criterion for the classification of various exercise fatigue. In this study, we combine features extracted by deep neural networks with linear features from ECG and heart rate variability (HRV) for exercise fatigue classification. First, the ECG signals are converted into 2-D images by using the short-term Fourier transform (STFT), and image features are extracted by the visual geometry group (VGG) . The extracted image and linear features of ECG and HRV are sent to the different types of classifiers to distinguish distinct exercise fatigue level. To validate performance, the proposed methods are tested on (i) an open-source EPHNOGRAM dataset and (ii) a self-collected dataset (n = 51). The results reveal that the classification based on the concatenated features has the highest accuracy, and the calculation time of the system is also significantly reduced. This demonstrates that the proposed novel hybrid approach can be used to assist in improving the accuracy and timeliness of exercise fatigue classification in a real-time exercise environment. The experimental results show that the proposed method outperforms other recent state-of-the-art methods in terms of accuracy 96.90%, sensitivity 96.90%, F1-score of 0.9687 in EPHNOGRAM and accuracy 92.17%, sensitivity 92.63%, F1-score of 0.9213 in self-collected dataset.

Early Glaucoma Detection using LSTM-CNN integrated with Multi Class SVM

Early Glaucoma Detection using LSTM-CNN integrated with Multi Class SVM

Application of near-infrared spectroscopy as at line method for the evaluation of histamine in tuna fish (Thunnus albacares)

The assessment of histamine levels in fishery products has emerged as a paramount issue in the context of global food safety, given its profound implications for human health and the consequential impact on food quality and trade. Histamine intoxication, stemming from the ingestion of foods containing heightened histamine levels, results from the bacterial decarboxylation of histidine under conditions of improper handling, processing, or storage. This study endeavors to provide a thorough examination of histamine contamination in frozen-thawed tuna (Thunnus albacares) samples, employing an integrated approach that combines near-infrared spectroscopy (NIRS) with advanced machine learning techniques. One hundred and one samples were considered, and a systematic fortification process was applied to obtain samples with 4 histamine concentrations (0; 50; 150; 250 mg/kg); the fortification levels were confirmed by the LC-MS/MS analysis. Subsequently, NIRS spectra were collected and chemometric analyses, including modified partial least squares regression (MPLS) and support vector machine (SVM), were employed for quantitative and qualitative evaluation, respectively. Histamine quantification through MPLS utilizing the full spectrum exhibited good predictive performance in cross-validation and in hold-out validation (R2CV = 0.88; R2P = 0.74, respectively), confirming the potential of NIRS for estimating histamine levels in tuna. SVM classification models, both binary (presence/absence) and multiclass (four levels), demonstrated high accuracy (100% and 93%, respectively). The study highlights the effectiveness of NIRS combined with machine learning for rapid and accurate histamine detection in frozen-thawed tuna, offering a non-destructive, environmentally friendly alternative to traditional methods. This approach holds significant promise for food business operators and regulatory authorities, enhancing product safety, quality control, and decision-making processes related to histamine contamination in the seafood industry.

Triangulating text relationship in literary retranslation: The Great Gatsby in Chinese

Abstract In the scenario of literary retranslation, the presence of a previous translation necessarily has influence on retranslators. Systemic analyses of relevant features are needed to reveal the potential influence that an earlier translation exerts on a later one and the strategies the latter takes as a response. Starting with the assumption that a distinctive translation can be identified with a set of consistent features, this study examines the relationship between translations with The Great Gatsby and its nine Chinese versions as a case in point, with a novel method of corpus triangulation. For the discovery of the most effective set of distinctive features, a multi-class Support Vector Machine algorithm is applied on twenty-one linguistic features related to vocabulary, grammar, and textuality for the classification of samples from the nine versions. A principal components analysis then follows to verify the multi-dimensionality of a translation and the intertwinement of its features. Finally, further aided with a sentiment analysis, we examine the faithfulness of translations and their distances from each other. Through cross-validation, this study finds: (1) With the shared source text, different translations show a certain, and in some pairs striking, degree of resemblance both in terms of linguistic features and in the sentiment-based narrative plot; (2) the dependency relation between retranslations and earlier ones is usually manifested in measurable linguistic features; (3) linguistic features of a text are normally combined in a complicated manner and features of different categories inextricably intertwined; (4) the trend of proximity proposed by the Retranslation Hypothesis is discernible in the retranslations; and (5) cross-validation between the examination of linguistic features and sentiment analysis proves to be an effective approach for measuring the distance between translations and the closeness of a translation to the original.

Automatic Parkinson’s Disease Diagnosis with Wearable Sensor Technology for Medical Robot

The clinical diagnosis of Parkinson’s disease (PD) has been the subject of medical robotics research. Currently, a hot research topic is how to accurately assess the severity of Parkinson’s disease patients and enable medical robots to better assist patients in the rehabilitation process. The walking task on the Unified Parkinson’s Disease Rating Scale (UPDRS) is a well-established diagnostic criterion for PD patients. However, the clinical diagnosis of PD is determined based on the clinical experience of neurologists, which is subjective and inaccurate. Therefore, in this study, an automated diagnostic method for PD based on an improved multiclass support vector machine (MCSVM) is proposed in which wearable sensors are used. Kinematic analysis was performed to extract gait features, both spatiotemporal and kinematic, from the installed IMU and pressure sensors. Comparison experiments of three different kernel functions and linear trajectory experiments were designed. The experimental results show that the accuracies of the three kernel functions of the proposed improved MCSVM are 92.43%, 93.45%, and 95.35%. The simulation trajectories of the MCSVM are the closest to the real trajectories, which shows that the technique performs better in the clinical diagnosis of PD.

Asymmetric lesion detection with geometric patterns and CNN-SVM classification

In dermoscopic images, which allow visualization of surface skin structures not visible to the naked eye, lesion shape offers vital insights into skin diseases. In clinically practiced methods, asymmetric lesion shape is one of the criteria for diagnosing Melanoma. Initially, we labeled data for a non-annotated dataset with symmetrical information based on clinical assessments. Subsequently, we propose a supporting technique—a supervised learning image processing algorithm—to analyze the geometrical pattern of lesion shape, aiding non-experts in understanding the criteria of an asymmetric lesion. We then utilize a pre-trained convolutional neural network (CNN) to extract shape, color, and texture features from dermoscopic images for training a multiclass support vector machine (SVM) classifier, outperforming state-of-the-art methods from the literature. In the geometry-based experiment, we achieved a 99.00 % detection rate for dermatological asymmetric lesions. In the CNN-based experiment, the best performance is found 94 % Kappa Score, 95 % Macro F1-score, and 97 % weighted F1-score for classifying lesion shapes (Asymmetric, Half-Symmetric, and Symmetric).

Wavelet scattering and multiclass support vector machine (WS_MSVM) for effective fault classification in transformers: a real-time experimental approach

The dependable operation of the protective system is affected by residual magnetism and magnetic bias during the activation of the transformer. Challenges arise in distinguishing between inrush current and fault current when the transformer circuit breaker switching angle and remnant flux attain specific values. This situation can lead to a lack of sensitivity or failure in the operation of the transformer protection system. Thus, this paper proposes an effective approach for classifying different faults in transformers (internal and non-internal faults) using wavelet scattering and multiclass support vector machine (MSVM) technique (WS_MSVM). The wavelet scattering method begins by transmitting the data through a sequence of wavelet transforms, nonlinear operations, and averaging processes. This series of operations aims to generate low-variance representations of time series data. Wavelet time scattering produces signal representations that remain unaffected by shifts in the input signal, while still preserving the ability to distinguish between internal and non-internal faults. Internal faults are those occurring within the zones of the current transformer (CT) connected on both sides of the transformer. On the other hand, non-internal faults consist of magnetizing inrush current, sympathetic inrush current, and external faults (faults occurring outside the CT zones). The efficacy of the proposed WS_SVM is evaluated on the real-time experimental results obtained from the differential path of a laboratory transformer. The experimental data generated over one power frequency cycle under diverse operating conditions is employed in MATLAB to assess the effectiveness of the proposed WS_SVM algorithm.

MOX-NET: Multi-stage deep hybrid feature fusion and selection framework for monkeypox classification

Background:Monkeypox virus has quickly expanded throughout several nations, raising serious public health concerns. Lack of precautionary measures raises concerns about the possibility of global pandemic. As a result, early detection of monkeypox is essential for efficient diagnosis and treatment before broad community transmission. Artificial intelligence (AI) and machine learning (ML) have recently shown tremendous promise in early monkeypox diagnosis using image-based diagnoses methods. But, challenges such as low contrast lesions, overloaded datasets, high memory complexity, and redundant feature extraction still need to be addressed. Methods:This work proposes a coalesced CAD system for monkeypox classification using a deep learning framework. The proposed approach includes multiple stages: First, the given dataset images are pre-processed by a proposed fusion-based contrast enhancement method. Second, six pre-trained deep learning models i.e., Vision Transformers (ViT), Shifted Windows (Swin) Transformers, ResNet-50, ResNet-101, EfficientNetV2, and ConvNeXt-V2 are modified and transfer learning is used for training. Third, from all the deep learning networks, the deep feature vectors are acquired and integrated through the convolutional sparse image decomposition fusion strategy. Subsequently, an entropy-controlled firefly feature selection approach is applied to identify the most suitable features for classification. Lastly, the multi-class support vector machine is utilized to classify the input data based on the selected features. Results:The proposed algorithm utilized the MSLID dataset and obtained an accuracy of 98.64% which is better than other state-of-the-art works. Conclusions:Experimental outcomes reveals that the proposed monkeypox classification algorithm outperforms well-established existing algorithms in both visual and quantitative evaluations, resulting in improved accuracy.

TO-LAB model: Real time Touchless Lung Abnormality detection model using USRP based machine learning algorithm.

Due to the increasing prevalence of respiratory diseases and the importance of early diagnosis. The need for non-invasive and touchless medical diagnostic solutions has become increasingly crucial in modern healthcare to detect lung abnormalities. Existing methods for lung abnormality detection often rely on invasive and time-consuming procedures limiting their effectiveness in real-time diagnosis. This work introduces a novel Touchless Lung Abnormality (TO-LAB) detection model utilizing universal software radio peripherals (USRP) and machine learning algorithms. The TO-LAB model integrates a blood pressure meter and an RGB-D depth-sensing camera to gather individual data without physical contact. Heart rate (HR) is analyzed through image conversion to IPPG signals, while blood pressure (BP) is obtained via analog conversion from the blood pressure meter. This touchless imaging setup facilitates the extraction of essential signal features crucial for respiratory pattern analysis. Advanced computer vision algorithms like Mel-frequency cepstral coefficients (MFCC) and Principal Component Analysis (PCA) process the acquired data to focus on breathing abnormalities. These features are then combined and inputted into a machine learning-based Multi-class SVM for breathing activity analysis. The Multi-class SVM categorizes breathing abnormalities as normal, shallow, or elevated based on the fused features. The efficiency of this TO-LAB model is evaluated with the simulated and real-time data. According to the findings, the proposed TO-LAB model attains the maximum accuracy of 96.15% for real time data; however, the accuracy increases to 99.54% for simulated data for the efficient classification of breathing abnormalities. From this analysis, our model attains better results in simulated data but it declines the accuracy while processing with real-time data. Moreover, this work has a significant medical impact since it presents a solution to the problem of gathering enough data during the epidemic to create a realistic model with a large dataset.

Vision-based Human Activity Recognition Using Local Phase Quantization

Human activity recognition (HAR) has been the most active and interesting area of research in recent years due to its wide range of applications in the field, such as healthcare, security and surveillance, robotics, gaming, entertainment, etc. However, recognizing vision-based human activity is still a challenging as input sequences may have cluttered background, illumination conditions, occlusions, degradation of video quality, blurring, etc. In the literature, several state-of-the-art methods have been trained and tested on different datasets but have yet to perform adequately to a certain extent. Moreover, extracting potential features and combining appropriate methods is one of the most challenging tasks in realistic video. This paper proposes an efficient frequency-based blur-invariance local phase quantization feature extractor and multiclass SVM classifier that overcomes these challenges. The feature is invariant towards camera motion, misfocused optics, movements in the scene, and environmental conditions. The proposed feature vector is then fed to the classifier to recognize human activities. The experiment has conducted on two publicly available datasets, UCF101 and HMDB51, and has achieved 99.79% and 98.67% accuracies, respectively. The approach has also outperformed the existing state-of-the-art approaches in terms of computational cost without compromising the accuracy of HAR.

Research on muscle fatigue of upper limb in overhead static work

To explore the muscle fatigue features of upper limb at different heights in overhead static work, an experiment was conducted to obtain the surface electromyography (sEMG) of subjects and their subjective fatigue state based on Borg CR-10 scale. The processing methods of time domain and frequency domain features of sEMG were studied and the multiclass support vector machine (SVM) was used to identify the state of muscle fatigue. By analyzing the muscular contribution, the correlation of subjective ratings and objective muscle fatigue features, ranking order of muscle fatigue accumulation, and muscular fatigue classification and identification, the results show that the muscles contribute above 10% on average are the biceps, deltoid and trapezius, and their cumulative contribution exceeds 70%; and the ranking orders of muscle fatigue accumulation in three heights are H3>H2>H1 for biceps and trapezius and H2>H3>H1 for deltoid; and with the time increase of overhand static operation, the muscle fatigue of upper limb gradually accumulates, resulting in the value of time domain features increases and the frequency domain features decreases, and their changes are consistent; and the accuracy of multiclass SVM is above 90% for identifying muscle fatigue of upper limb in overhead static work.

Gear fault diagnosis based on bidimensional time-frequency information theoretic features and error-correcting output codes: A multi-class support vector machine

Gear fault diagnosis based on bidimensional time-frequency information theoretic features and error-correcting output codes: A multi-class support vector machine

Activity recognition based on spatio-temporal features with transfer learning

<span lang="EN-US">Human action recognition (HAR) has gathered significant attention recently due to its high demand in various application domains. We explore different CNN architectures for extracting Spatio-Temporal features. In addition to spatial correlation in 2D images, video actions also own the temporal domain attributes. Many research attempts addressed simple activity recognition, but complex activity recognition is still challenging. In the proposed work, the concept of transfer learning consists of two pre-trained networks, ResNet50 and VGG16, which are used to extract Spatiotemporal features and are later fused using the averaging method. Pre-processed frames are considered for the pre-trained network, the pre-processing consists of frame extraction, resizing, and contrast enhancement. The fused features are trained using a multiclass non-linear SVM classifier that achieved an accuracy of 89.71% on the UCF-101 database.</span>

Firefly Algorithm for SVM Multi-class Optimization on Soybean Land Suitability Analysis

Soybean is the primary source of vegetable protein nutrition, containing fat and vitamins that Indonesian people widely consume. The decline in soybean production in Indonesia every year is due to the reduced area of soybean cultivation, thereby increasing dependence on imports from other countries. Land suitability maps can provide directions for priority locations for soybean cultivation based on land characteristics and weather to produce optimal production. The SVM multi-class algorithm has been applied to classify land suitability data to create a land suitability map but has yet to obtain optimal accuracy, especially for sigmoid kernels. The objective of this study is to enhance the performance of the sigmoid kernel SVM by utilizing the firefly algorithm. The study focuses on evaluating the suitability of soybean cultivation in Bogor and Grobogan Regencies. The results of the tests indicate that the firefly algorithm-optimized SVM (FA-SVM) significantly improves accuracy compared to the SVM without optimization. The accuracy achieved by FA-SVM is 89.95%, while the SVM without optimization only achieves an accuracy of 65.99%. The best parameters produced by the firefly algorithm are C=2.33 and σ=0.45 obtained from firefly customization, and the number of generations is 10. Based on this, the optimization algorithm can be used to produce an optimal model. The best optimal model obtained can be used as a guide for priority locations/areas for soybean cultivation by farming communities, so as to produce maximum soybean productivity.