Metal roof enclosure system is an important part of steel structure construction. In recent years, it has been widely used in large-scale public or industrial buildings such as stadiums, airport terminals, and convention centers. Affected by bad weather, various types of accidents on metal roofs frequently occurred, causing huge property losses and adverse effects. Because of wide span, long service life and hidden fault of metal roof, the manual inspection of metal roof has low efficiency, poor real-time performance, and it (...) is difficult to find hidden faults. On the basis of summarizing the working principle of metal roof and cause of accidents, this paper classifies the fault types of metal roofs in detail and establishes a metal roof monitoring and fault diagnosis system using distributed multisource heterogeneous sensors and Zigbee wireless sensor networks. Monitoring data from strain gauge, laser ranging sensor, and ultrasonic ranging sensor is utilized comprehensively. By extracting time domain feature, the data trend characteristics and correlation characteristics are analyzed and fused to eliminate erroneous data and find superficial faults such as sensor drift and network interruption. Aiming to the hidden faults including plastic deformation and bolt looseness, an SVM fault diagnosis algorithm based on RBF kernel function is designed and applied to diagnose metal roof faults. The experimental results show that the RBF-SVM algorithm can achieve high classification accuracy. (shrink)

Brain–machine interfaces are systems that allow the control of a device such as a robot arm through a person’s brain activity; such devices can be used by disabled persons to enhance their life and improve their independence. This paper is an extended version of a work that aims at discriminating between left and right imagined hand movements using a support vector machine classifier to control a robot arm in order to help a person to find an object in the environment. (...) The main focus here is to search for the best features that describe efficiently the electroencephalogram data during such imagined gestures by comparing two feature extraction methods, namely the continuous wavelet transform and the empirical modal decomposition, combined with the principal component analysis that were fed through a linear and radial basis function kernel SVM classifier. The experimental results showed high performance achieving an average accuracy across all the subjects of 92.75% with an RBF kernel SVM classifier using CWT and PCA compared to 80.25% accuracy obtained with EMD and PCA. The proposed system has been implemented and tested using data collected from five male subjects and it enabled the control of the robot arm in the right and the left direction. (shrink)

Multi-Task Learning tries to improve the learning process of different tasks by solving them simultaneously. A popular Multi-Task Learning formulation for SVM is to combine common and task-specific parts. Other approaches rely on using a Graph Laplacian regularizer. Here we propose a combination of these two approaches that can be applied to L1, L2 and LS-SVMs. We also propose an algorithm to iteratively learn the graph adjacency matrix used in the Laplacian regularization. We test our proposal with synthetic and real (...) problems, both in regression and classification settings. When the task structure is present, we show that our model is able to detect it, which leads to better results, and we also show it to be competitive even when this structure is not present. (shrink)

Support vector machines (SVMs) are being used increasingly in affective science as a data-driven classification method and feature reduction technique. Whereas traditional statistical methods typically compare group averages on selected variables, SVMs use a predictive algorithm to learn multivariate patterns that optimally discriminate between groups. In this review, we provide a framework for understanding the methods of SVM-based analyses and summarize the findings of seminal studies that use SVMs for classification or data reduction in the behavioral and neural study of (...) emotion and affective disorders. We conclude by discussing promising directions and potential applications of SVMs in future research in affective science. (shrink)

Neurodegenerative Parkinson's Disease (PD) is one of the common incurable diseases among the elderly. Clinical assessments are characterized as standardized means for PD diagnosis. However, relying on medical evaluation of a patient's status can be subjective to physicians' experience, making the assessment process susceptible to human errors. The use of ICT-based tools for capturing the status of patients with PD can provide more objective and quantitative metrics. In this vein, the Personalized Serious Game Suite (PGS) and intelligent Motor Assessment Tests (...) (iMAT), produced within the i-PROGNOSIS European project (www.i-prognosis.eu), are explored in the current study. More specifically, data from 27 patients with PD at Stage 1 (9) and Stage 3 (18) produced from their interaction with PGS/iMAT are analyzed. Five feature vector (FV) scenarios are set, including features from PGS or iMAT scores or their combination, after also taking into consideration the age of patients with PD. These FVs are fed into three machine learning classifiers, i.e., K-Nearest Neighbor (KNN), Support Vector Machines (SVM), and Random Forest (RF), to infer the stage of each patient with PD. A Leave-One-Out Cross-Validation (LOOCV) method is adopted for testing the classification performance. The experimental results show that a high (>90%) classification accuracy is achieved from both data sources (PGS/iMAT), justifying the effectiveness of PGS/iMAT to efficiently reflect the motor skill status of patients with PD and further potentiating PGS/iMAT enhancement with a machine learning a part to infer for the stage of patients with PD. Clearly, this integrated approach provides new opportunities for remote monitoring of the stage of patients with PD, contributing to a more efficient organization and set up of personalized interventions. (shrink)

Starting with the hypothesis that analogical reasoning consists of a search of semantic space, we used eye-tracking to study the time course of information integration in adults in various formats of analogies. The two main questions we asked were whether adults would follow the same search strategies for different types of analogical problems and levels of complexity and how they would adapt their search to the difficulty of the task. We compared these results to predictions from the literature. Machine learning (...) techniques, in particular support vector machines (SVMs), processed the data to find out which sets of transitions best predicted the output of a trial (error or correct) or the type of analogy (simple or complex). Results revealed common search patterns, but with local adaptations to the specifics of each type of problem, both in terms of looking-time durations and the number and types of saccades. In general, participants organized their search around source-domain relations that they generalized to the target domain. However, somewhat surprisingly, over the course of the entire trial, their search included, not only semantically related distractors, but also unrelated distractors, depending on the difficulty of the trial. An SVM analysis revealed which types of transitions are able to discriminate between analogy tasks. We discuss these results in light of existing models of analogical reasoning. (shrink)

The study of the emotion-inducing function of music education is an important part of the basic theoretical research of music education, which influences the positioning of the basic nature and value attributes of music education, and at the same time, it also plays a practical role in the teaching practice of music education. In this paper, music education plays the role of “healthy psychology” with the help of the characteristic of “emotionality”. It takes music as a means of inducing individual (...) emotions, and explores the ways of inducing and measuring emotions in specific music emotion-inducing operations. In the experimental process of inducing emotions by European religious music, the non-linear and non-smooth EEG signals were decomposed into a series of eigenmodal functions with different oscillation frequencies using the empirical modal decomposition adaptively. Then, multi-dimensional information such as waveform difference, phase difference, and normalized energy of the eigenmodal functions are extracted as emotional features. Based on the extracted features, SVM is utilized for emotion recognition. In terms of the mean values of emotion evoking intensity of religious music, “sense of calm” (M=5.51) evoked the highest intensity, followed by “sense of transcendence” (M=5.4). “Nostalgia” (M=5.13) evoked a slightly weaker intensity, and ‘Power’ (M=4.26) had the lowest intensity, while religious music evoked significantly more emotions than secular music (p. (shrink)

A significant portion of the world’s text is tagged by readers on social bookmarking websites. Credit attribution is an inherent problem in these corpora because most pages have multiple tags, but the tags do not always apply with equal specificity across the whole document. Solving the credit attribution problem requires associating each word in a document with the most appropriate tags and vice versa. This paper introduces Labeled LDA, a topic model that constrains Latent Dirichlet Allocation by defining a one-to-one (...) correspondence between LDA’s latent topics and user tags. This allows Labeled LDA to directly learn word-tag correspondences. We demonstrate Labeled LDA’s improved expressiveness over traditional LDA with visualizations of a corpus of tagged web pages from del.icio.us. Labeled LDA outperforms SVMs by more than 3 to 1 when extracting tag-specific document snippets. As a multi-label text classifier, our model is competitive with a discriminative baseline on a variety of datasets. (shrink)

Impostor syndrome or Impostor phenomenon is a belief that a person thinks their success is due to luck or external factors, not their abilities. This psychological trait is present in certain groups like women. In this paper, we propose a neutrosophic trait measure to represent the psychological concept of the trait-anti trait using refined neutrosophic sets. This study analysed a group of 200 undergraduate students for impostor syndrome, perfectionism, introversion and self-esteem: after the COVID pandemic break in 2021. Data labelling (...) was carried out using these neutrosophic trait measures. Machine learning models like Support Vector Machine(SVM), K-nearest neighbour (K-NN), and random forest were used to model the data; SVM provided the best accuracy of 92.15%. (shrink)

Walt Disney’s movie, The Pagemaster (1994) begins on a dark and stormy night, with a young boy stumbling into an immense, gothic-styled library for refuge from the rain. Once inside, he is soon carried away by a tumultuous river of coloured paints, transformed into an animated characterization of himself, and thrust into an animated world of literature, where he battles Captain Hook, flees Moby Dick, and participates in other classic tales of adventure, horror, and fantasy. -/- Adults might understand the (...) film as a fanciful description of how they feel when reading a lively book. Although they would probably not imagine themselves tagging along with the animated characters like a 4th musketeer, they might very well claim that they enter a fiction through the viewpoint of one or more of the characters, experiencing, imaginatively, mental images of the sights, sounds, smells, and movements that the character would experience. Under this description, the reader would be forming multi- modal images that would correspond directly to what the literary characters are doing, thinking, and experiencing. When a fictional hero whips out his sword and slashes a rope in half, the reader might form a visual image of the hero’s determined face, an auditory image of the sound of the whizzing sword, and a motor image of an extended arm movement. I call such an imitative participation, by use of mental images in any modality, a simulation. -/- I suggest that this imitative experiencing of a fiction through the production of multi-modal imagery - a simulation - is not the only way in which readers might engage a literary text. In this paper I explore the hypothesis that readers might use their own bodily processes - those of the somato-viscero-motor system (SVM) for a non-imitative activity that I call a reinterpretation and that the reinterpretation might make a distinctive contribution to the reading process. As an example of a simulation and a reinterpretation, take the SVM experience of the reader’s breathing. A simulation would occur if the text describes a character who is taking deep breaths of air and the reader creates a mental image representing the experience of breathing. In this case, the reader’s mental image of breathing would stand for a property of the literary work - the fictional experience of breathing. -/- By contrast to the simulation, a reinterpretation would occur if the text describes a character who is gazing at long, wispy clouds that extend outward from a horizon and the reader uses his own experience of breathing to stand for the visual sense of looking at a long, continuous expanse of filmy white: the reader’s actual breathing would stand for a property of the literary work - the fictional experience of seeing. Breathing is not the same as seeing. This should help clarify the following definition. -/- I hypothesize that a reinterpretation occurs when the reader becomes aware of some component of the SVM system and reinterprets it as a property of the literary work that is not the same as that particular SVM process. The SVM experience is projected into the literary work. (shrink)

Cancer is fast becoming an alarming cause of human death. However, it has been reported that if the disease is detected at an early stage, diagnosed, treated appropriately, the patient has better chances of survival long life. Machine learning technique with feature-selection contributes greatly to the detecting of cancer, because an efficient feature-selection method can remove redundant features. In this paper, a Fuzzy Preference-Based Rough Set (FPRS) blended with Support Vector Machine (SVM) has been applied in order to predict cancer (...) biomarkers for biological and gene expression datasets. Biomarkers are determined by deploying three models of FPRS, namely, Fuzzy Upward Consistency (FUC), Fuzzy Downward Consistency (FLC), and Fuzzy Global Consistency (FGC). The efficiency of the three models with SVM on five datasets is exhibited, and the biomarkers that have been identified from FUC models have been reported. (shrink)

Judgments concerning animals have arisen across a variety of established practice areas. There is, however, no publicly available repository of judgments concerning the emerging practice area of animal protection law. This has hindered the identification of individual animal protection law judgments and comprehension of the scale of animal protection law made by courts. Thus, we detail the creation of an initial animal protection law repository using natural language processing and machine learning techniques. This involved domain expert classification of 500 judgments (...) according to whether or not they were concerned with animal protection law. 400 of these judgments were used to train various models, each of which was used to predict the classification of the remaining 100 judgments. The predictions of each model were superior to a baseline measure intended to mimic current searching practice, with the best performing model being a support vector machine (SVM) approach that classified judgments according to term frequency—inverse document frequency (TF-IDF) values. Investigation of this model consisted of considering its most influential features and conducting an error analysis of all incorrectly predicted judgments. This showed the features indicative of animal protection law judgments to include terms such as ‘welfare’, ‘hunt’ and ‘cull’, and that incorrectly predicted judgments were often deemed marginal decisions by the domain expert. The TF-IDF SVM was then used to classify non-labelled judgments, resulting in an initial animal protection law repository. Inspection of this repository suggested that there were 175 animal protection judgments between January 2000 and December 2020 from the Privy Council, House of Lords, Supreme Court and upper England and Wales courts. (shrink)

With the development of modern information technology, the flipped classroom teaching mode came into being. It has gradually become one of the hotspots of contemporary educational circles and has been applied to various disciplines at the same time. The domestic research on the flipped classroom teaching mode is still in the exploratory stage. The application of flipped classroom teaching mode is still in the exploratory stage. It also has many problems, such as low class efficiency, poor teacher-student interaction, outdated teaching (...) modes, not student-centered, etc., which lead to poor students’ enthusiasm for learning. Therefore, the current English flipped classroom teaching mode still needs to be tested and revised in practice. Combined with emotion recognition technology, this paper analyzes speech emotion recognition, image emotion recognition, and audition emotion recognition technology and conducts a revision test for the current English flipped classroom teaching mode. It uses the SVM algorithm for one-to-one method and dimension discretization for emotion recognition, and finds that the recognition results after different dimension classification recognition are improved for each emotion. Among them, the recognition rate of different dimension classification recognition methods is 2.6% higher than that of one-to-one method. This shows that under the same conditions, the emotion recognition technology of different dimension classification recognition methods is higher. (shrink)

The article is devoted to the analysis of gender and age specifics of determining value-motivational trends of volunteering. The purpose of the research is to reveal the specifics of socio-psychological factors of volunteering, and, above all, the role and place of age and gender of the volunteer. The research was implemented by filling out an individual volunteer questionnaire. The sample of the research consisted of 302 volunteers aged 17 to 80 years from more than 15 cities of Ukraine. In particular, (...) it is shown that depending on what motivational trends dominate in an individual profile of the SVM volunteer, and, therefore, direct his/her individual activity, the resource of readiness that is implemented in rendering aid, is specifically related to them. In addition, it was found that the meaningfulness of activity on giving help can exhaust own high indicators in the relationship to the implementation of various motivational trends. In turn, it is also shown that individual value-motivational trends to be sensitive on age and gender. The identified features of the gender and age of the volunteer are an important component in the system of factors of the socio-psychological conditioning of volunteering activity. This allows it is to link the specifics of their impact with the characteristics of value-motivational trends, the motivational potential of which is realized by volunteers on giving to help. (shrink)

BackgroundThe Basal ganglia (BG) played a crucial role in the brain-level mechanisms of chronic pain disorders. However, the functional changes of BG in chronic prostatitis/chronic pelvic pain syndrome (CP/CPPS) are still poorly understood. This study investigated the BG subregions’ resting-state functional connectivity (rs-FC) in CP/CPPS patients compared with healthy controls.MethodsTwenty eight patients with CP/CPPS and 28 age- and education-matched healthy males underwent clinical measurements and 3T brain MR imaging, including T1-weighted structural images and resting-state functional imaging. The data were analyzed (...) by the seeded-based rs-FC analysis. Then, a machine learning method was applied to assess the feasibility of detecting CP/CPPS patients through the changed rs-FC.ResultsCompared with healthy males, patients presented decreased rs-FC between the BG subregions and right middle cingulate cortex, and correlated with pain (r = 0.51, p-uncorrected = 0.005) and urinary symptoms (r = –0.4, p-uncorrected = 0.034). The left superior temporal gyrus and right supramarginal gyrus showed decreased rs-FC with the BG subregions as well. The area under the receiver operating characteristic curve of 0.943 (accuracy = 80%, F1-score = 80.6%) was achieved for the classification of CP/CPPS patients and healthy males with support vector machine (SVM) based on the changed rs-FC.ConclusionThese findings provide evidence of altered BG subregions’ rs-FC in CP/CPPS, which may contribute to our understanding of the BG’s role in CP/CPPS. (shrink)

The objective of this work is to propose ten efficient scaling techniques for the Wisconsin Diagnosis Breast Cancer dataset using the support vector machine. These scaling techniques are efficient for the linear programming approach. SVM with proposed scaling techniques was applied on the WDBC dataset. The scaling techniques are, namely, arithmetic mean, de Buchet for three cases p = 1,2, and ∞, equilibration, geometric mean, IBM MPSX, and Lp-norm for three cases p = 1,2, and ∞. The experimental results show (...) that the equilibration scaling technique overcomes the benchmark normalization scaling technique used in many commercial solvers. Finally, the experimental results also show the effectiveness of the grid search technique which gets the optimal parameters for the SVM classifier. (shrink)

Combining the communicative language competence model and the perspective of multimodal research, this research proposes a research framework for oral communicative competence under the multimodal perspective. This not only truly reflects the language communicative competence but also fully embodies the various contents required for assessment in the basic attributes of spoken language. Aiming at the feature sparseness of the user evaluation matrix, this paper proposes a feature weight assignment algorithm based on the English spoken category keyword dictionary and user search (...) records. The algorithm is mainly based on the self-built English oral category classification dictionary and converts the user’s query vector into a user-English-speaking type vector. Through the calculation rules proposed in this paper, the target user’s preference score for a specific type of spoken English is obtained, and this score is assigned to the unrated item of the original user’s feature matrix as the initial starting score. At the same time, in order to solve the problem of insufficient user similarity calculation accuracy, a user similarity calculation algorithm based on “Synonyms Cilin Extended Edition” and search records is proposed. The algorithm introduces “Synonyms Cilin” to calculate the correlation between the semantic items, vocabulary, and query vector in the user query record to obtain the similarity between users and finally gives a user similarity calculation that integrates user ratings and query vectors method. For the task of Chinese grammar error correction, this article uses two methods of predicting the relationship between words in the corpus, Word2Vec and GloVe, to train the word vectors of different dimensions and use the word vectors to represent the text features of the experimental samples, avoiding sentences brought by word segmentation. On the basis of word vectors, the advantages and disadvantages of CNN, LSTM, and SVM models in this shared task are analyzed through experimental data. The comparative experiment shows that the method in this paper has achieved relatively good results. (shrink)

Computer vision is widely used in manufacturing, sports, medical diagnosis, and other fields. In this article, a multifeature fusion error action expression method based on silhouette and optical flow information is proposed to overcome the shortcomings in the effectiveness of a single error action expression method based on the fusion of features for human body error action recognition. We analyse and discuss the human error action recognition method based on the idea of template matching to analyse the key issues that (...) affect the overall expression of the error action sequences, and then, we propose a motion energy model based on the direct motion energy decomposition of the video clips of human error actions in the 3 Deron action sequence space through the filter group. The method can avoid preprocessing operations such as target localization and segmentation; then, we use MET features and combine with SVM to test the human body error database and compare the experimental results obtained by using different feature reduction and classification methods, and the results show that the method has the obvious comparative advantage in the recognition rate and is suitable for other dynamic scenes. (shrink)

The study investigates the possibility of applying texture analysis (TA) for testing Duchenne Muscular Dystrophy (DMD) therapies. The work is based on the Golden Retriever Muscular Dystrophy (GRMD) canine model, in which 3 phases of canine growth and/or dystrophy development are identified: the first phase (0–4 months of age), the second phase (from over 4 to 6 months), and the third phase (from over 6 months to death). Two differentiation problems are posed: (i) the first phase vs. the second phase (...) and (ii) the second phase vs. the third phase. Textural features are derived from T2-weighted Magnetic Resonance Imaging (MRI) images. In total, 37 features provided by 8 different TA methods (statistical, filter-based, and model-based) have been tested. The work focuses on finding such textural features that evolve along with the dog’s growth. These features are indicated by means of statistical analyses and eliminated from further investigation, as they may disturb the correct assessment of response to treatment in dystrophy. The relative importance of each remaining feature is then assessed with the use of the Monte Carlo (MC) procedure. Furthermore, feature selection based on the MC procedure is employed to find the optimal subset of age-independent features. Finally, three classifiers are used for evaluating different sets of textural features: Adaptive Boosting (AB), back-propagation Neural Network (NN), and nonlinear Support Vector Machines (SVM). The best subsets of age-independent features ensure 80.0% and 78.5% of correctly identified phases of dystrophy progression, for the first (i) and second (ii) differentiation problem respectively. (shrink)

The output stability of the photovoltaic system is directly affected by temperature change of PV panels. In this paper, a novel temperature prediction method of PV panels with support vector machine is proposed, which can solve the temperature prediction problem in a complex environment. In order to optimize parameters of SVM, a Pigeon-Inspired Optimization method is given. Meanwhile, the delay factor is added to improve the PIO algorithm for avoiding the problem of local optimum. Moreover, a multisensor monitoring system of (...) PV is established, and the collected data of temperature are used to train and verify the accuracy of the model. Finally, the proposed method is evaluated using synthetic and actual data sets. Simulation results show that the DFPIO-SVM can obtain better predictive performance. (shrink)

In the tourism industry, the sales of local specialties is an important part, and the package design and integrity of the specialties are very important. This paper first introduced the support vector machine (SVM) algorithm that was used for detecting defects on the surface of paper packages. Then, the design of red wind packages was briefly described, and the simulation experiment was carried out on SVM algorithm using red wine packages with different degrees of surface defects. Proper parameters were tested (...) using the k-fold cross-validation method. The results demonstrated that the properties of paper improved the value of packages and the SVM algorithm had better accuracy than artificial recognition in recognizing different degrees of defects on the surface of packages. In conclusion, this paper describes the application of paper in packages and provides an effective method for the defection of defects on the surface of packages. This study provides an effective references to the improvement of package values and the enhancement of package integrity. (shrink)

For a better detection in Network information security monitoring system, the author proposes a method based on adaptive depth detection. A deep belief network was designed and implemented, and the intrusion detection system model was combined with a support vector machine. The data set adopts the NSL-KDD network communication data set, and this data set is authoritative in the security field. Redundant cleaning, data type conversion, normalization, and other processing operations are performed on the data set. Using the data conversion (...) method based on the probability mass function probability mass function coding, a standard data set with low redundancy and low dimensionality can be obtained. Research indicates that when the batch size reaches 64, the accuracy of the test set reaches its maximum value. As the batch size increases, the accuracy first increases and then decreases. When the batch size continues to increase, the model will inevitably fall into the local optimal state, resulting in the degradation of the detection performance of the system. In terms of the false alarm rate, the DBN-SVM model is also the highest; however, it is only 10.73%. Under the premise of increasing the detection rate, the false alarm rate is improved; for the overall detection performance of the model, it is within an acceptable range. In terms of accuracy, the DBN-SVM model also scored the highest. The accuracy rate is the ratio of normal and correct classification for intrusion detection. It can explain the detection ability of the model. In summary, the overall detection ability of the DBN-SVM model is the best. The good classification ability to use SVM is proved, and the classification of low-dimensional features is expected to increase the detection rate of the system. (shrink)

This abstract presents a novel brain-computer interface (BCI) framework to control a prosthetic leg, for the rehabilitation of patients suffering from locomotive disorders, using functional near-infrared spectroscopy (fNIRS). fNIRS signals corresponding to walking intention and rest are used to initiate and stop the gait cycle and a nonlinear proportional derivative computed torque controller (PD-CTC) with gravity compensation is used to control torques of hip and knee joints for minimization of position error. The brain signals of walking intention and rest tasks (...) are acquired from primary motor cortex in the left hemisphere for nine subjects. After acquiring brain signals, in order to remove motion artifacts and physiological noises, the performance of six different filters i.e. Kalman, Wiener, Gaussian, hemodynamic response filter (hrf), Band-pass and finite impulse response, is evaluated. Afterwards, six different features are extracted from oxygenated hemoglobin signals and their different combinations were used for classification. The classification performance of five different classifiers i.e. artificial neural network, quadratic discriminant analysis, linear discriminant analysis (LDA), Naïve Bayes and support vector machine (SVM) is used. The classification accuracies obtained from SVM using hrf filter are significantly higher (p < 0.005) than the other combinations of classifier and filters. These accuracies are 77.5%, 72.5%, 68.3%, 74.2%, 73.3%, 80.8%, 65%, 76.7%, and 86.7% for all nine subjects. The control commands generated using classifier initiate and stop the gait cycle of the prosthetic leg whose knee and hip torques are controlled using PD-CTC to minimize position error. The proposed scheme can be effectively used for neurofeedback training and rehabilitation of lower limb amputation of paralyzed patients. (shrink)

Emotion recognition plays an important role in intelligent human–computer interaction, but the related research still faces the problems of low accuracy and subject dependence. In this paper, an open-source software toolbox called MindLink-Eumpy is developed to recognize emotions by integrating electroencephalogram and facial expression information. MindLink-Eumpy first applies a series of tools to automatically obtain physiological data from subjects and then analyzes the obtained facial expression data and EEG data, respectively, and finally fuses the two different signals at a decision (...) level. In the detection of facial expressions, the algorithm used by MindLink-Eumpy is a multitask convolutional neural network based on transfer learning technique. In the detection of EEG, MindLink-Eumpy provides two algorithms, including a subject-dependent model based on support vector machine and a subject-independent model based on long short-term memory network. In the decision-level fusion, weight enumerator and AdaBoost technique are applied to combine the predictions of SVM and CNN. We conducted two offline experiments on the Database for Emotion Analysis Using Physiological Signals dataset and the Multimodal Database for Affect Recognition and Implicit Tagging dataset, respectively, and conducted an online experiment on 15 healthy subjects. The results show that multimodal methods outperform single-modal methods in both offline and online experiments. In the subject-dependent condition, the multimodal method achieved an accuracy of 71.00% in the valence dimension and an accuracy of 72.14% in the arousal dimension. In the subject-independent condition, the LSTM-based method achieved an accuracy of 78.56% in the valence dimension and an accuracy of 77.22% in the arousal dimension. The feasibility and efficiency of MindLink-Eumpy for emotion recognition is thus demonstrated. (shrink)

. This paper illustrates the applications of various ensemble methods for enhanced classification accuracy. The case in point is the Pima Indian Diabetic Dataset. The computational model comprises of two stages. In the first stage, k-means clustering is employed to identify and eliminate wrongly classified instances. In the second stage, a fine tuning in the classification was effected. To do this, ensemble methods such as AdaBoost, bagging, dagging, stacking, decorate, rotation forest, random subspace, MultiBoost and grading were invoked along with (...) five chosen base classifiers, namely support vector machine, radial basis function network, decision tree J48, naïve Bayes and Bayesian network. The k-fold cross validation technique is adopted. Computational experiments with the proposed method showed an improvement of 16.14% to 22.49% in the classification accuracy compared to literature survey. Among the ensemble methods tried, MultiBoost ensemble with SVM classifier and grading ensemble with naïve Bayes showed the best performance followed by MultiBoost, stacking and grading ensemble with Bayesian classifier, rotation forest ensemble with RBF and grading and rotation forest ensemble with J48. This investigation conclusively proves the significance of cascading k-means clustering with ensemble methods in the enhanced accuracy in categorization of diabetic dataset. (shrink)

PurposeThyroid-associated ophthalmopathy is a vision threatening autoimmune and inflammatory orbital disease, and has been reported to be associated with a wide range of structural and functional abnormalities of bilateral hemispheres. However, whether the interhemisphere functional connectivity of TAO patients is altered still remain unclear. A new technique called voxel-mirrored homotopic connectivity combined with support vector machine method was used in the present study to explore interhemispheric homotopic functional connectivity alterations in patients with TAO.MethodsA total of 21 TAO patients and 21 (...) wellmatched healthy controls, respectively, underwent functional magnetic resonance imaging scanning in the resting state. We evaluated alterations in the resting state functional connectivity between hemispheres by applying VMHC method and then selected these abnormal brain regions as seed areas for subsequent study using FC method. Furthermore, the observed changes of regions in the VMHC analysis were chosen as classification features to differentiate patients with TAO from HCs through support vector machine method.ResultsThe results showed that compared with HCs, TAO patients showed significantly lower VMHC values in the bilateral postcentral gyrus, lingual gyrus, calcarine, middle temporal gyrus, middle occipital gyrus and angular. Moreover, significantly decreased FC values were found between the right postcentral gyrus/lingual gyrus/calcarine and left lingual gyrus/cuneus/superior occipital gyrus, left postcentral gyrus/lingual gyrus/calcarine and right lingual gyrus/ middle temporal gyrus, right middle temporal gyrus and left cerebellum-8/lingual gyrus/middle occipital gyrus/supplementary motor area, left middle temporal gyrus and right middle occipital gyrus, right middle occipital gyrus/angular and left middle temporal pole. The SVM classification model achieved good performance in differentiating TAO patients from HCs.ConclusionThe present study revealed that the altered interhemisphere interaction and integration of information involved in cognitive and visual information processing pathways including the postcentral gyrus, cuneus, cerebellum, angular, widespread visual cortex and temporal cortex in patients with TAO relative to HC group. VMHC variability had potential value for accurately and specifically distinguishing patients with TAO from HCs. The new findings may provide novel insights into the neurological mechanisms underlying visual and cognitive disorders in patients with TAO. (shrink)

The most prominent form of human communication and interaction is speech. It plays an indispensable role for expressing emotions, motivating, guiding, and cheering. An ill-intentioned speech can mislead people, societies, and even a nation. A misguided speech can trigger social controversy and can result in violent activities. Every day, there are a lot of speeches being delivered around the world, which are quite impractical to inspect manually. In order to prevent any vicious action resulting from any misguided speech, the development (...) of an automatic system that can efficiently detect suspicious speech has become imperative. In this study, we have presented a framework for acquisition of speech along with the location of the speaker, converting the speeches into texts and, finally, we have proposed a system based on long short-term memory which is a variant of recurrent neural network to classify speeches into suspicious and nonsuspicious. We have considered speeches of Bangla language and developed our own dataset that contains about 5000 suspicious and nonsuspicious samples for training and validating our model. A comparative analysis of accuracy among other machine learning algorithms such as logistic regression, SVM, KNN, Naive Bayes, and decision tree is performed in order to evaluate the effectiveness of the system. The experimental results show that our proposed deep learning-based model provides the highest accuracy compared to other algorithms. (shrink)

The number of scientific publications is growing exponentially. Research articles cite other work for various reasons and, therefore, have been studied extensively to associate documents. It is argued that not all references carry the same level of importance. It is essential to understand the reason for citation, called citation intent or function. Text information can contribute well if new natural language processing techniques are applied to capture the context of text data. In this paper, we have used contextualized word embedding (...) to find the numerical representation of text features. We further investigated the performance of various machine-learning techniques on the numerical representation of text. The performance of each of the classifiers was evaluated on two state-of-the-art datasets containing the text features. In the case of the unbalanced dataset, we observed that the linear Support Vector Machine achieved 86% accuracy for the “background” class, where the training was extensive. For the rest of the classes, including “motivation,” “extension,” and “future,” the machine was trained on less than 100 records; therefore, the accuracy was only 57 to 64%. In the case of a balanced dataset, each of the classes has the same accuracy as trained on the same size of training data. Overall, SVM performed best on both of the datasets, followed by the stochastic gradient descent classifier; therefore, SVM can produce good results as text classification on top of contextual word embedding. (shrink)

Significant research has been devoted to detecting people in images and videos. In this paper we describe a human de- tection method that augments widely used edge-based fea- tures with texture and color information, providing us with a much richer descriptor set. This augmentation results in an extremely high-dimensional feature space (more than 170,000 dimensions). In such high-dimensional spaces, classical machine learning algorithms such as SVMs are nearly intractable with respect to training. Furthermore, the number of training samples is much (...) smaller than the dimensionality of the feature space, by at least an order of magnitude. Finally, the extraction of features from a densely sampled grid structure leads to a high degree of multicollinearity. To circumvent these data characteristics, we employ Partial Least Squares (PLS) analysis, an effi- cient dimensionality reduction technique, one which pre- serves significant discriminative information, to project the data onto a much lower dimensional subspace (20 dimen- sions, reduced from the original 170,000). Our human de- tection system, employing PLS analysis over the enriched descriptor set, is shown to outperform state-of-the-art tech- niques on three varied datasets including the popular INRIA pedestrian dataset, the low-resolution gray-scale Daim- lerChrysler pedestrian dataset, and the ETHZ pedestrian dataset consisting of full-length videos of crowded scenes. (shrink)

A smooth rotated hyperbola model for support vector machine (SVM) is proposed. The method is based on the approximation property of the hyperbola to its asymptotic lines. The rotated hyperbola model has the least error on approximating the plus function when the angle between the two asymptotic lines is 135 degree. Experimental result shows that compared with other smooth methods, the rotated hyperbola function support vector machine (RHSSVM) reduces the compute time and can efficiently handle large scale and high dimensional (...) programs. (shrink)

This article puts forward a novel smooth rotated hyperbola model for support vector machine (RHSSVM) for classification. As is well known, the Support vector machine (SVM) is based on Statistical Learning Theory and performs its high precision on data classification. However, the objective function is non-differentiable at the zero point. Therefore the fast algorithms cannot be used to train and test the SVM. To deal with it, the proposed method is based on the approximation property of the hyperbola to its (...) asymptotic lines. Firstly, we describe the development of RHSSVM from the basic linear SVM optimization programming. Then we extend the linear model to non-linear model. We prove the solution of RHSSVM is convergent, unique, and global optimal. We show how RHSSVM can be practically implemented. At last, the theoretical analysis illustrates that compared with other three typical models, the rotated hyperbola model has the least error on approximating the plus function. Meanwhile, computer simulations show that the RHSSVM can reduce the consuming time at most 54.6% and can efficiently handle large scale and high dimensional programming. -/- . (shrink)

The classification frameworks for fault diagnosis of rolling element bearings in rotating machinery are mostly based on analysis in a single time-frequency domain, where sensitive features are not completely extracted. To solve this problem, a new fault diagnosis technique is proposed in the mixed domain, based on the crossover-mutation chaotic particle swarm optimization support vector machine. Firstly, fault features are generated using techniques in the time domain, the frequency domain, and the time-frequency domain. Secondly, the weighted maximum relevance minimum redundancy (...) algorithm is adopted to reduce the dimension of the feature set and to establish the representative feature set. Thirdly, a new crossover-mutation strategy is suggested to reduce the local minima in optimization, and an optimization disturbance is added. Finally, the support vector machine is optimized using the improved chaotic particle swarm to improve fault classification diagnosis. The effectiveness of the proposed new bearing fault diagnostic technique is verified by experimental tests under different bearing conditions. Test results showed that the bearing fault classification accuracy of CMCPSO-SVM in the mixed domain was much higher than those in a single feature domain. (shrink)

Neuromarketing has gained attention to bridge the gap between conventional marketing studies and electroencephalography -based brain-computer interface research. It determines what customers actually want through preference prediction. The performance of EEG-based preference detection systems depends on a suitable selection of feature extraction techniques and machine learning algorithms. In this study, We examined preference detection of neuromarketing dataset using different feature combinations of EEG indices and different algorithms for feature extraction and classification. For EEG feature extraction, we employed discrete wavelet transform (...) and power spectral density, which were utilized to measure the EEG-based preference indices that enhance the accuracy of preference detection. Moreover, we compared deep learning with other traditional classifiers, such as k-nearest neighbor, support vector machine, and random forest. We also studied the effect of preference indicators on the performance of classification algorithms. Through rigorous offline analysis, we investigated the computational intelligence for preference detection and classification. The performance of the proposed deep neural network outperforms KNN and SVM in accuracy, precision, and recall; however, RF achieved results similar to those of the DNN for the same dataset. (shrink)

_Introduction:_ Clinically relevant information can go uncaptured in the conventional scoring of a verbal fluency test. We hypothesize that characterizing the temporal aspects of the response through a set of time related measures will be useful in distinguishing those with MCI from cognitively intact controls. _Methods:_ Audio recordings of an animal fluency test administered to 70 demographically matched older adults (mean age 90.4 years), 28 with mild cognitive impairment (MCI) and 42 cognitively intact (CI) were professionally transcribed and fed into (...) an automatic speech recognition (ASR) system to estimate the start time of each recalled word in the response. Next, we semantically cluster participant generated animal names and through a novel set of time-based measures, we characterize the semantic search strategy of subjects in retrieving words from animal name clusters. This set of time-based features along with standard count-based features (e.g., number of correctly retrieved animal names) were then used in a machine learning algorithm trained for distinguishing those with MCI from CI controls. _Results:_ The combination of both count-based and time-based features, automatically derived from the test response, achieved 77% on AUC-ROC of the support vector machine (SVM) classifier, outperforming the model trained only on the raw test score (AUC, 65%), and well above the chance model (AUC, 50%). _Conclusion:_ This approach supports the value of introducing time-based measures to the assessment of verbal fluency in the context of this generative task differentiating subjects with MCI from those with intact cognition. (shrink)

An effective approach is introduced to predict the magnitude of reservoir-triggered earthquake, based on support vector machines and fuzzy support vector machines methods. The main influence factors on RTE, including lithology, rock mass integrity, fault features, tectonic stress state, and seismic activity background in reservoir area, are categorized into 11 parameters and quantified by using analytical hierarchy process. Dataset on 100 reservoirs in China, including the 48 well-documented cases of RTE, are collected and used to train and validate the prediction (...) models established with SVM and FSVM, respectively. Through numerical tests, it is found that both the SVM and FSVM models are effective in the prediction of the magnitude of RTE with high accuracy, provided that sufficient samples are collected. While the results of FSVM which is extended from SVM by introducing a fuzzy membership to reduce the influence of noises or outliers are found to be slightly less accurate than those of SVM in the current analysis of RTE cases. The reason might be attributed to the high discreteness of the sample data in the current study. (shrink)

For the safe and economical construction of embankment dams, the mechanical behaviour of the rockfill materials used in the dam’s shell must be analyzed. The characterization of rockfill materials with specified shear strength is difficult and expensive due to the presence of particles greater than 500 mm in diameter. This work investigates the feasibility of using an extreme gradient boosting computing paradigm to estimate the shear strength of rockfill materials. To train and validate the proposed XGBoost model, a total of (...) 165 databases obtained from the literature are chosen. The XGBoost model was compared against support vector machine, adaptive boosting, random forest, and K-nearest neighbor models described in the literature. XGBoost beats SVM, RF, AdaBoost, and KNN models in terms of performance evaluation metrics such as coefficient of determination, Nash–Sutcliffe coefficient, and error in the root mean square ratio to the standard deviation of the measured data. The results demonstrated that the XGBoost model has the highest prediction performance with, followed by the SVM model with, RF, the AdaBoost model with and the KNN model with. A sensitivity analysis has been conducted to ascertain the impact of each investigated input parameter. This study demonstrates that the established XGBoost model for estimating the shear strength of rockfill materials is reliable. (shrink)

One of the important measures of quality of education is the performance of students in academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and to improve their performance ahead of time using data mining techniques. In this paper, we developed a student performance prediction model that predicts the performance of high school students for the next semester for five courses. We modeled our prediction system as (...) a multi-label classification task and used support vector machine (SVM), Random Forest (RF), K-nearest Neighbors (KNN), and Multi-layer perceptron (MLP) as base-classifiers to train our model. We further improved the performance of the prediction model using a state-of-the-art partitioning scheme to divide the label space into smaller spaces and used Label Powerset (LP) transformation method to transform each labelset into a multi-class classification task. The proposed model achieved better performance in terms of different evaluation metrics when compared to other multi-label learning tasks such as binary relevance and classifier chains. (shrink)

High-dimensional data analysis has become the most challenging task nowadays. Dimensionality reduction plays an important role here. It focuses on data features, which have proved their impact on accuracy, execution time, and space requirement. In this study, a dimensionality reduction method is proposed based on the convolution of input features. The experiments are carried out on minimal preprocessed nine benchmark datasets. Results show that the proposed method gives an average 38% feature reduction in the original dimensions. The algorithm accuracy is (...) tested using the decision tree, support vector machine, and K-nearest neighbor classifiers and evaluated with the existing principal component analysis algorithm. The average increase in accuracy is 8.06 for DT, 5.80 for SVM, and 18.80 for the KNN algorithm. The most significant characteristic feature of the proposed model is that it reduces attributes, leading to less computation time without loss in classifier accuracy. (shrink)

Detecting Intrusions and anomalies is becoming much more challenging with new attacks popping out over a period of time. Achieving better accuracies by applying benchmark classifier algorithms used for identifying intrusions and anomalies have several hidden data mining challenges. Although neglected by many research findings, one of the most important and biggest challenges is the similarity or membership computation. Another challenge that cannot be simply neglected is the number of features that attributes to dimensionality. This research aims to come up (...) with a new membership function to carry similarity computation that can be helpful for addressing feature dimensionality issues. In principle, this work is aimed at introducing a novel membership function that can help to achieve better classification accuracies and eventually lead to better intrusion and anomaly detection. Experiments are performed on KDD dataset with 41 attributes and also KDD dataset with 19 attributes. Recent approaches CANN and CLAPP have showed new approaches for intrusion detection. The proposed classifier is named as UTTAMA. UTTAMA performed better to both CANN and CLAPP approaches w.r.t overall classifier accuracy. Another promising outcome achieved using UTTAMA is the U2R and R2L attack accuracies. The importance of proposed approach is that the accuracy achieved using proposed approach outperforms CLAPP, CANN, SVM, KNN and other existing classifiers. (shrink)

We employ the support vector machine classifier, over different types of kernels, to investigate whether observable variables of individuals and their household information are able to describe their consumption decision of film at theaters in Brazil. Using a very big dataset of 340,000 individuals living in metropolitan areas of a whole large developing economy, we performed a Knowledge Discovery in Databases to classify the film consumers, which results in 80% instances correctly classified. To reduce the degrees of freedom for SVM (...) and to learn the more important determinants of film consumption, we apply the Linear Discriminant Analysis that allows us to identify the key determinants of this consumption. The main individual characteristics are age, education, income, and preferences for cultural goods. Regarding the main geographic characteristics, these are the timing of sample, population concentration, and supply of movie theaters. The results point to an ineffective policy for the sector at the time investigated. (shrink)

Suspended sediment modeling is an important subject for decision-makers at the catchment level. Accurate and reliable modeling of suspended sediment load is important for planning, managing, and designing of water resource structures and river systems. The objective of this study was to develop artificial intelligence- based ensemble methods for modeling SSL in Katar catchment, Ethiopia. In this paper, three single AI-based models, that is, support vector machine, adaptive neurofuzzy inference system, feed-forward neural network, and one conventional multilinear regression modes, were (...) used for SSL modeling. Besides, four different ensemble methods, neural network ensemble, ANFIS ensemble, weighted average ensemble, and simple average ensemble, were developed by combining the outputs of the four single models to improve their predictive performance. The study used two-year discharge and SSL data for training and verification of the applied models. Determination coefficient and root mean square error were used to evaluate the performances of the developed models. Based on the performance measure results, the ANFIS model provides higher efficiency than the other developed single models. Out of all developed ensemble models, the nonlinear ANFIS model combination method was found to be the most accurate method and could increase the efficiency of SVM, MLR, ANFIS, and FFNN models by 19.02%, 37%, 9.73%, and 16.3%, respectively, at the verification stage. Overall, the proposed ensemble models in general and the AI-based ensemble in particular provide excellent performance in SSL estimation. (shrink)

The quality and quantity of training data are crucial to the performance of a deep-learning-based brain-computer interface system. However, it is not practical to record EEG data over several long calibration sessions. A promising time- and cost-efficient solution is artificial data generation or data augmentation. Here, we proposed a DA method for the motor imagery EEG signal called brain-area-recombination. For the BAR, each sample was first separated into two ones by left/right brain channels, and the artificial samples were generated by (...) recombining the half-samples. We then designed two schemas corresponding to the single- and multi-subject scenarios. Extensive experiments using the classifier of EEGnet were conducted on two public datasets under various training set sizes. In both schemas, the BAR method can make the EEGnet have a better performance of classification. To make a comparative investigation, we selected two common DA methods, and the BAR method beat them. Further, using the proposed BAR for augmentation, EEGnet achieved up to 8.3% improvement than a typical decoding algorithm CSP-SVM, note that both the models were trained on the augmented dataset. This study shows that BAR usage can significantly improve the classification ability of deep learning to MI-EEG signals. To a certain extent, it may promote the development of deep learning technology in the field of BCI. (shrink)