Support Vector Machine System Research Articles

The prediction of thermal sensation in building using support vector machine and extreme gradient boosting

The building has great potential for energy savings as one of the locations that humans often occupy. In addition to energy efficiency, humans must consider environmental sustainability and the comfort of the building's occupants. Conditioning of indoor air quality, including those related to thermal comfort, continues to be pursued to be more economical, one of which is to utilize the prediction of occupants' thermal sensations. The prediction results can be utilized to adjust room air conditions more economically. This paper proposes using extreme gradient boosting (XGBoost) and support vector machine (SVM) to predict the thermal sensation in the building. The built environment parameters are preprocessed, and the thermal sensation is predicted by intelligent systems. The ten variables that most influence the level of accuracy of this thermal sensation prediction system are thermal preference vote, indoor operative temperature, Griffith's neutral temperature, indoor globe temperature, mean radiant temperature, Indoor air temperature, predicted mean vote, and outdoor mean temperature. SVM with four features, XGBoost and XGBoost with hyperparameter tuning, achieve an accuracy of 99.45%, 97.81%, and 98.08%, respectively. Regarding computational complexity, training an SVM system with the same number of features requires a shorter time than XGBoost training. The same thing also happened with the test of the SVM system, which required a shorter time compared to the time for the examination of the XGBoost system.

Random access memory page caching: a strategy for enhancing shared virtual memory multicomputer systems performance

This study examines a modified approach to optimizing the performance of support vector machine (SVM)-type multicomputer systems through a distinct type of caching method that allocates space in the random access memory (RAM) of a computing node for caching pages. The article extensively describes research on enhancing the performance of the SVM system through memory page caching in RAM at the hardware level by implementing the SVM system based on field-programmable gate arrays (FPGA). A systematic comparative evaluation highlights a discernible enhancement in system performance relative to systems not equipped with the revised caching algorithm. These findings could prove instrumental for subsequent studies focused on optimizing the performance of SVM systems, providing empirical data to inform future investigations and potential applications in multicomputer system performance enhancement.

A comparison of data augmentation methods in voice pathology detection

To distinguish pathological voices from healthy voices, automatic voice pathology detection systems can be built using machine learning (ML) and deep learning (DL) techniques. To fully exploit such systems, large quantities of training data are typically required. The amount of training data is, however, small in the area of pathological voice, and therefore data augmentation (DA) becomes a potential technology to artificially increase the quantity of training data. This study presents a systematic comparison between various DA methods in the detection of pathological voice, including three time domain methods (noise addition, pitch shifting and time stretching), one time–frequency domain method (SpecAugment), and two vocoder-based methods (harmonic-to-noise ratio (HNR) modification and glottal pulse length modification). Detection systems were built using four popular spectral feature representations (static mel-frequency cepstral coefficients (MFCCs), dynamic MFCCs, spectrogram and mel-spectrogram). As classifiers, two widely used ML models (support vector machine (SVM) and random forest (RF)) and two DL models (long short-term memory (LSTM) network and convolutional neural network (CNN) with 1-dimensional (1-D) and 2-dimensional (2-D) architectures) were used. These systems were trained using a small number of training samples from two popular databases of pathological voice (HUPA and SVD) to find the best feature/classifier combination for each database. As a result, one ML-based detection system (mel-spectrogram/SVM for HUPA and SVD) and two DL-based detection systems (dynamic MFCCs/2-D CNN for HUPA and mel-spectrogram/2-D CNN for SVD) were selected for the comparison of the DA methods. The results show that by using DA in the system training, detection accuracy increased compared to the baseline systems that were trained without using DA. This improvement in accuracy was, however, clearly larger for the 2D-CNN system than for the SVM system. Furthermore, all six DA methods improved accuracy of the 2-D CNN system compared to the baseline system for both databases. The highest improvements were achieved using the time–frequency domain SpecAugment DA method, which improved accuracy by 1.5% and 3.8% (absolute) for the HUPA and SVD database, respectively.

Rapid Identification of Foodborne Pathogens in Limited Resources Settings Using a Handheld Raman Spectroscopy Device

Rapid and precise methods to detect pathogens are paramount in ensuring food safety and selecting appropriate disinfection treatments. Raman spectrometry is a promising technology being investigated for detecting pathogens and achieving rapid, culture-free, and label-free methods. Nonetheless, previous Raman techniques require additional steps, including the preparation of slides that could introduce significant variability. In this study, we investigated the capability of a Raman handheld device for rapid identification of monocultures of Listeria monocytogenes, Salmonella Typhimurium, Escherichia coli O157:H7, and Staphylococcus aureus, and the combination of co-cultures in BHI broth suspension by utilising principal component analysis (PCA) and support vector machine (SVM) classification of Raman spectra. The detection method accurately identified monocultures (0.93 ± 0.20), achieving good discrimination after 24 h of bacterial growth. However, the PCA–SVM system was less accurate for classifying co-cultures (0.67 ± 0.35). These results show that this method requires an isolation step followed by biomass enrichment (>8 log10 CFU/mL) for accurate identification. The advantage of this technology is its simplicity and low-cost preparation, achieving high accuracy in monocultures in a shorter time than conventional culture-dependent methods.

Exploration of temporal dynamics of frequency domain linear prediction cepstral coefficients for dialect classification

Speakers exhibit dialectal traits in speech at sub-segmental, segmental, and supra-segmental levels. Any feature representation for dialect classification should appropriately represent these dialectal traits. Traditional segmental features such as mel-frequency cepstral coefficients (MFCCs) fail to represent sub-segmental and supra-segmental dialectal traits. This study proposes to use frequency domain linear prediction cepstral coefficients (FDLPCCs) for dialect classification inspired by its long temporal summarization during pole estimation. The i-vectors and x-vectors derived from both baseline (MFCCs, linear prediction cepstral coefficients (LPCCs), perceptual LPCCs (PLPCCs), RASTA filtered PLPCCs (PLPCC-R) and proposed (FDLPCC) features are used for identifying the dialects with support vector machine (SVM) and feed-forward neural network (FFNN) as classifiers. Proposed FDLPCC features have shown to perform better than baseline features such as MFCCs and PLPCC-Rs (best among LPCCs variants) by an absolute improvement of 3.4% and 3.9% (in unweighted average recall (UAR)), with i-vector + SVM system and 1.6% and 4.6% (in UAR), i-vector + FFNN system respectively. It is also found that there exists a complementary information between the proposed and baseline features. Furthermore current studies are compared with previous studies and it is found that performances of current studies are better than previous studies.

RESEARCH ON SHIP ENGINE ROOM MONITORING AND FAULT DIAGNOSIS SYSTEM BASED ON LABVIEW

The structure of marine engine room system is complex, with many fault sources and abundant symptom parameters. There is no simple correspondence between faults and symptoms, but they are interrelated and intricate. The existing fault diagnosis of ship engine room is mostly based on expert system, but the bottleneck of knowledge acquisition, lack of learning ability and the complexity and efficiency of the expert system are restricting its further development. In order to overcome the above shortcomings of expert system, the support vector machine (SVM) is introduced into the expert system, and the support vector machine (SVM) is used to solve the problem of small sample self-learning ability and high-dimensional space self-adaptation ability. The expert system is used to achieve the automatic knowledge acquisition and rapid logical reasoning. Knowledge base management and maintenance, symbolic reasoning and related explanations, and give full play to the advantages of both SVM and expert system. Finally, the fault diagnosis of marine diesel engine booster system is introduced as an example. The MATLAB Script is used to call the MATLAB SVM analysis toolkit, and the combination of SVM and expert system is used to diagnose the fault.

Semi-Automated Glioblastoma Tumor Detection based on Different Classifiers using Magnetic Resonance Spectroscopy

Purpose: Glioblastoma Multiform (GBM) is one of the most common and deadly malignant brain tumors. Surgery is the primary treatment, and careful surgery can minimize recurrence odds. Magnetic Resonance Imaging (MRI) imaging with Magnetic Resonance Spectroscopy (MRS) is used to diagnose various types of tumors in the Central Nervous System (CNS). In this study, several classification methods were used to separate tumor and healthy tissue. Materials and Methods: This study examined the MRI and MRS results of seven people enrolled in this study in 2018. The data was obtained with a prescription from a neurologist and neurosurgeon. Choline (Cho) and N-Acetylaspartate (NAA) metabolite signals were selected as the reference signal after preprocessing and removing the water signal. With the support of 3 radiologists, each tumor and healthy vesicles were identified for every patient. Then, tumor and healthy voxels were separated based on Multilayer Perceptron (MLP), linear Support Vector Machine (SVM), Gaussian SVM, and Fuzzy system using the obtained values and four different methods. Results: Data extracted from Cho and NAA metabolites were fed into MLP, linear SVM, Gaussian and Fuzzy SVM as input, and the amounts of accuracy, sensitivity, and specificity were determined for each method. The maximum accuracy for training mode and test mode was equal to 89.7% and 87%, respectively, specific to classification using Gaussian SVM. The results also showed that the classification accuracy can be significantly increased by increasing the number of fuzzy membership functions from 2 to 6. Conclusion: The results of this study suggested that a more complex classification system, such as SVM with a Gaussian kernel and fuzzy system can be more efficient and reliable when it comes to separating tumor tissue from healthy tissues from MRS data.

Proposing WPOD-NET combining SVM system for detecting car number plate

<span lang="EN-US">Nowadays, there are many smart parking lots using plate detection system to control in/out vehicles. However, the disadvantages of systems are a fixed environment and necessity of manual labor and requirement of checkpoints in entrances. To solve the problems, a novel algorithm for wide-angle detecting car number plate using warped planar object detection (WPOD-NET) and a modified support vector machine (SVM) system is proposed. Comparing to other models, the proposal improves not only the range of detection angle but also the accuracy of detecting in shady conditions. The results show that the accuracy of proposal model is up to 95.1% with 1000 testing images in various scenarios.</span>

Automated caries detection with smartphone color photography using machine learning

Untreated caries is significant problem that affected billion people over the world. Therefore, the appropriate method and accuracy of caries detection in clinical decision-making in dental practices as well as in oral epidemiology or caries research, are required urgently. The aim of this study was to introduce a computational algorithm that can automate recognize carious lesions on tooth occlusal surfaces in smartphone images according to International Caries Detection and Assessment System (ICDAS). From a group of extracted teeth, 620 unrestored molars/premolars were photographed using smartphone. The obtained images were evaluated for caries diagnosis with the ICDAS II codes, and were labeled into three classes: "No Surface Change" (NSC); "Visually Non-Cavitated" (VNC); "Cavitated" (C). Then, a two steps detection scheme using Support Vector Machine (SVM) has been proposed: "C versus (VNC + NSC)" classification, and "VNC versus NSC" classification. The accuracy, sensitivity, and specificity of best model were 92.37%, 88.1%, and 96.6% for "C versus (VNC + NSC)," whereas they were 83.33%, 82.2%, and 66.7% for "VNC versus NSC." Although the proposed SVM system required further improvement and verification, with the data only imaged from the smartphone, it performed an auspicious potential for clinical diagnostics with reasonable accuracy and minimal cost.

Detection of Malicious Primary User Emulation Based on a Support Vector Machine for a Mobile Cognitive Radio Network Using Software-Defined Radio

Mobile cognitive radio networks provide a new platform to implement and adapt wireless cellular communications, increasing the use of the electromagnetic spectrum by using it when the primary user is not using it and providing cellular service to secondary users. In these networks, there exist vulnerabilities that can be exploited, such as the malicious primary user emulation (PUE), which tries to imitate the primary user signal to make the cognitive network release the used channel, causing a denial of service to secondary users. We propose a support vector machine (SVM) technique, which classifies if the received signal is a primary user or a malicious primary user emulation signal by using the signal-to-noise ratio (SNR) and Rényi entropy of the energy signal as an input to the SVM. This model improves the detection of the malicious attacker presence in low SNR without the need for a threshold calculation, which can lead to false detection results, especially in orthogonal frequency division multiplexing (OFDM) where the threshold is more difficult to estimate because the signal limit values are very close in low SNR. It is implemented on a software-defined radio (SDR) testbed to emulate the environment of mobile system modulations, such as Gaussian minimum shift keying (GMSK) and OFDM. The SVM made a previous learning process to allow the SVM system to recognize the signal behavior of a primary user in modulations such as GMSK and OFDM and the SNR value, and then the received test signal is analyzed in real-time to decide if a malicious PUE is present. The results show that our solution increases the detection probability compared to traditional techniques such as energy or cyclostationary detection in low SNR values, and it detects malicious PUE signal in MCRN.

Hardware-Efficient VLSI Design for Cascade Support Vector Machine with On-Chip Training and Classification Capability

Local processing of machine learning algorithms like support vector machine (SVM) is preferred over the cloud for many real-time embedded applications. However, such embedded systems often have stringent energy constraints besides throughput and accuracy requirements. Hence, hardware-efficient design to compute SVM is critical to enable these applications. In this paper, a hardware-efficient SVM learning unit is proposed using reduced number of multiplications and approximate computing techniques. These design techniques helped the learning unit to achieve 46.97% and 35.72% reductions in area and power when compared with those of the design using full multipliers. The proposed SVM learning unit supports on-chip training and classification. Energy-efficient dual-core, quad-core and octa-core cascade SVM systems were developed using the proposed SVM learning unit to expedite the on-chip training process. The runtime and energy efficiency of the cascade SVM systems improved with an increase in the number of cores. Interestingly, an average speedup of 421x in training time and a remarkable energy reduction of 24,497x were observed for the octa-core cascade SVM system when compared with the software SVM solution running on Intel Core i5-5257U processor. Moreover, the proposed octa-core cascade SVM system showed 73.75% and 65.78% lower area and power, respectively, than those of state-of-the-art cascade SVM architecture.

A Support Vector Machine-Firefly Algorithm for Movie Opinion Data Classification

The sentiment analysis used in this study is the process of classifying text into two classes, namely negative and positive classes. The classification method used is Support Vector Machine (SVM). The successful classification of the SVM method depends on the soft margin coefficient C, as well as the σ parameter of the kernel function. Therefore we need a combination of SVM parameters that are appropriate for classifying film opinion data using the SVM method. This study uses the Firefly method as an SVM parameter optimization method. The dataset used in this study is public opinion data on several films. The results of this study indicate that the Firefly Algorithm (FA) can be used to find optimal parameters in the SVM classifier. This is evidenced by the results of SVM system testing using 2179 data with nine SVM parameter combinations resulting in 85% highest accuracy, while the FA-SVM system with nine population and generation combinations produces the highest accuracy of 88%. The second test results using 1200 data using the same combination as the one test, the SVM method produces the highest accuracy of 87%, while the FA-SVM method produces the highest accuracy of 89%.

Using Computer Images to identify the pathology of Tooth and the application of SVM Systems in Dentistry

Objective: The research aimed to use both CAD and CBST systems and apply them on SVM computer to images to discover the caries in tooth. Materials and Methods: Datasets from different complexities were evaluated using ensemble -SVM algorithm. Depending on sequences and resolutions dataset, the limitation of intra-class variations, to reach significant inter-class variations and background related to the action. We follow the original setup for a pre-defined set of folds. Average accuracy over all classes is reported as performance measure. Results: Images data that was gathered were and using Support Vector Machine (SVM) learning algorithms were proving to end with accurate models based on large feature spaces which were provided by huge dimensional input spaces. Hypothesis space linear functions was used in a high dimensional feature space and combining it with algorithm to optimize and eventually implement it. Conclusion: Dental CAD ans SVM systems are by now capable to speed up the diagnostic procedure and offer a helpful second opinion in doubtful cases.

Bathymetry retrieval from optical images with spatially distributed support vector machines

This paper presents a spatially distributed support vector machine (SVM) system for estimating shallow water bathymetry from optical satellite images. Unlike the traditional global models that make predictions from a unified global model for the entire study area, our system uses locally trained SVMs and spatially weighted votes to make predictions. By using IKONOS-2 multi-spectral image and airborne bathymetric LiDAR water depth samples, we developed a spatially distributed SVM system for bathymetry estimates. The distributed model outperformed the global SVM model in predicting bathymetry from optical satellite images, and it worked well at the scenarios with a low number of training data samples. The experiments showed the localized model reduced the bathymetry estimation error by 60% from RMSE of 1.23 m to 0.48 m. Different from the traditional global model that underestimates water depth near shore and overestimates water depth offshore, the spatially distributed SVM system did not produce regional prediction bias and its prediction residual exhibited a random pattern. Our model worked well even if the sample density was much lower: The model trained with 10% of the samples was still able to obtain similar prediction accuracy as the global SVM model with the full training set.

Survey on SVM and their application in image classification

Life of any living being is impossible if it does not have the ability to differentiate between various things, objects, smell, taste, colors, etc. Human being is a good ability to classify the object easily such as different human face, images. This is time of the machine so we want that machine can do all the work like as a human, this is part of machine learning. Here this paper discusses the some important technique for the image classification. What are the techniques through which a machine can learn for the image classification task as well as perform the classification task with efficiently. The most known technique to learn a machine is SVM. Support Vector machine (SVM) has evolved as an efficient paradigm for classification. SVM has a strongest mathematical model for classification and regression. This powerful mathematical foundation gives a new direction for further research in the vast field of classification and regression. Over the past few decades, various improvements to SVM has appeared, such as twin SVM, Lagrangian SVM, Quantum Support vector machine, least square support vector machine, etc., which will be further discussed in the paper, led to the creation of a new approach for better classification accuracy. For improving the accuracy as well as performance of SVM, we must aware of how a kernel function should be selected and what are the different approaches for parameter selection. This paper reviews the different computational model of SVM and key process for the SVM system development. Furthermore provides survey on their applications for image classification.

Symtosis: A liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm

Background and ObjectiveFatty Liver Disease (FLD) - a disease caused by deposition of fat in liver cells, is predecessor to terminal diseases such as liver cancer. The machine learning (ML) techniques applied for FLD detection and risk stratification using ultrasound (US) have limitations in computing tissue characterization features, thereby limiting the accuracy. MethodsUnder the class of Symtosis for FLD detection and risk stratification, this study presents a Deep Learning (DL)-based paradigm that computes nearly seven million weights per image when passed through a 22 layered neural network during the cross-validation (training and testing) paradigm. The DL architecture consists of cascaded layers of operations such as: convolution, pooling, rectified linear unit, dropout and a special block called inception model that provides speed and efficiency. All data analysis is performed in optimized tissue region, obtained by removing background information. We benchmark the DL system against the conventional ML protocols: support vector machine (SVM) and extreme learning machine (ELM). ResultsThe liver US data consists of 63 patients (27 normal/36 abnormal). Using the K10 cross-validation protocol (90% training and 10% testing), the detection and risk stratification accuracies are: 82%, 92% and 100% for SVM, ELM and DL systems, respectively. The corresponding area under the curve is: 0.79, 0.92 and 1.0, respectively. We further validate our DL system using two class biometric facial data that yields an accuracy of 99%. ConclusionDL system shows a superior performance for liver detection and risk stratification compared to conventional machine learning systems: SVM and ELM.

Development of a Support Vector Machine - Based Image Analysis System for Focal Liver Lesions Classification in Magnetic Resonance Images

Purpose: The design and implementation of a computer-based image analysis system employing the support vector machine (SVM) classifier system for the classification of Focal Liver Lesions (FLLs) on routine non-enhanced, T2-weighted Magnetic Resonance (MR) images. Materials and Methods: The study comprised 92 patients; each one of them has undergone MRI performed on a Magnetom Concerto (Siemens). Typical signs on dynamic contrast-enhanced MRI and biopsies were employed towards a three class categorization of the 92 cases: 40-benign FLLs, 25-Hepatocellular Carcinomas (HCC) within Cirrhotic liver parenchyma and 27-liver metastases from Non-Cirrhotic liver. Prior to FLLs classification an automated lesion segmentation algorithm based on Marcov Random Fields was employed in order to acquire each FLL Region of Interest. 42 texture features derived from the gray-level histogram, co-occurrence and run-length matrices and 12 morphological features were obtained from each lesion. Stepwise multi-linear regression analysis was utilized to avoid feature redundancy leading to a feature subset that fed the multiclass SVM classifier designed for lesion classification. SVM System evaluation was performed by means of leave-one-out method and ROC analysis. Results: Maximum accuracy for all three classes (90.0%) was obtained by means of the Radial Basis Kernel Function and three textural features (Inverse- Different-Moment, Sum-Variance and Long-Run-Emphasis) that describe lesion's contrast, variability and shape complexity. Sensitivity values for the three classes were 92.5%, 81.5% and 96.2% respectively, whereas specificity values were 94.2%, 95.3% and 95.5%. The AUC value achieved for the selected subset was 0.89 with 0.81 - 0.94 confidence interval. Conclusion: The proposed SVM system exhibit promising results that could be utilized as a second opinion tool to the radiologist in order to decrease the time/cost of diagnosis and the need for patients to undergo invasive examination.

A Comparative Study between SVM and Fuzzy Inference System for the Automatic Prediction of Sleep Stages and the Assessment of Sleep Quality

This paper compares two supervised learning algorithms for predicting the sleep stages based on the human brain activity. The first step of the presented work regards feature extraction from real human electroencephalography (EEG) data together with its corresponding sleep stages that are utilized for training a support vector machine (SVM), and a fuzzy inference system (FIS) algorithm. Then, the trained algorithms are used to predict the sleep stages of real human patients. Extended comparison results are demonstrated which indicate that both classifiers could be utilized as a basis for an unobtrusive sleep quality assessment.

Automatic detection of articulations disorders from children’s speech preliminary study

Automatic Detection of Articulations Disorders from children’s speech is the major interest for the diagnosis and monitoring of articulations disorders therapy. In this work, acoustic features LPC (Linear prediction cepstrum) have been used with the two most commonly used classifier GMM-UBM (Gaussian mixture model-universal background model) and SVM (Support Vector Machines). We have used the idea of stacking the means of the GMM-UBM model to form a mean super vector and introduce the resulting super vector to SVM system. The main contribution of this paper is the used of automatic speaker recognition to detect the articulation disorder from the children speech and the investigation of the performance gained using a hybrid strategy between GMM-UBM and SVM systems. Series of experiments will be conducted; demonstrations of results from different experiments will be presented, tested and evaluated. Indeed we have found that this method is effective and robust.

Automatic Check Digits Recognition for Arabic Using Multi-Scale Features, HMM and SVM Classifiers

We propose in this work two Automatic Arabic (Indian) digits recognition systems using a real-life dataset of 3000 bank checks. The systems extracts features from training-set images of 7390 isolated digits (0-9). These features are multi-scale in which they capture narrow, intermediate, and large-scale qualities of the image. The gradient features correspond to the narrow scale, the structural features correspond to the intermediate scale, and the concavity features correspond to the large-scale. These features are employed by two different statistical classifiers; Hidden Markov Models (HMM) and Support Vector Machines (SVM). The two independent recognition systems utilize the proficient CENPARMI Arabic bank check database for training and testing. In order to select the optimal parameters for feature extraction and for the HMM classifier, the CENPARMI training dataset is divided into training and verification subsets. After adapting the two systems’ parameters, they are tested on unobserved 3035 digit images. The average recognition rates for the HMM and SVM systems are 97.86% and 99.04%, respectively. The presented systems provides state-of-the-art recognition results on the CENPARMI database, as they reported a higher recognition rates when compared to twelve previously published systems, especially for the SVM system. After analyzing the classification errors, the authors conclude that some of these errors are inevitable as they are most probably attributed to errors in labeling the original database, distinct writing styles of certain digits, and genuine faults.