Based on the adaptive particle swarm algorithm and error backpropagation neural network, this paper proposes methods for different styles of music classification and migration visualization. This method has the advantages of simple structure, mature algorithm, and accurate optimization. It can find better network weights and thresholds so that particles can jump out of the local optimal solutions previously searched and search in a larger space. The global search uses the gradient method to accelerate the optimization and control the (...) real-time generation effect of the music style transfer, thereby improving the learning performance and convergence performance of the entire network, ultimately improving the recognition rate of the entire system, and visualizing the musical perception. This kind of real-time information visualization is an artistic expression form, in which artificial intelligence imitates human synesthesia, and it is also a kind of performance art. Combining traditional music visualization and image style transfer adds specific content expression to music visualization and time sequence expression to image style transfer. This visual effect can help users generate unique and personalized portraits with music; it can also be widely used by artists to express the relationship between music and vision. The simulation results show that the method has better classification performance and has certain practical significance and reference value. (shrink)

Preoperative diagnosis of gastric cancer and primary gastric lymphoma is challenging and has important clinical significance. Inspired by the inductive reasoning learning of the human brain, transfer learning can improve diagnosis performance of target task by utilizing the knowledge learned from the other domains (source domain). However, most studies focus on single-source transfer learning and may lead to model performance degradation when a large domain shift exists between the single-source domain and target domain. By simulating the multi-modal information learning and (...) transfer mechanism of human brain, this study designed a multisource transfer learning feature extraction and classification framework, which can enhance the prediction performance of the target model by using multisource medical data (domain). First, this manuscript designs a feature extraction network that takes the maximum mean difference based on the Wasserstein distance as an adaptive measure of probability distribution and extracts the domain-specific invariant representations between source and target domain data. Then, aiming at the random generation of parameters bringing uncertainties to prediction accuracy and generalization ability of extreme learning machine network, the 1-norm regularization is used to implement sparse constraints of the output weight matrix and improve the robustness of the model. Finally, some experiments are carried out on the data of two medical centers. The experimental results show that the area under curves (AUCs) of the method are 0.958 and 0.929 in the two validation cohorts, respectively. The method in this manuscript can provide doctors with a better diagnostic reference, which has certain practical significance. (shrink)

We show a number of improvements in the use of Hidden Conditional Random Fields for phone classification on the TIMIT and Switchboard corpora. We first show that the use of regularization effectively prevents overfitting, improving over other methods such as early stopping. We then show that HCRFs are able to make use of non-independent features in phone classification, at least with small numbers of mixture components, while HMMs degrade due to their strong independence assumptions. Finally, we successfully apply (...) Maximum a Posteriori adaptation to HCRFs, decreasing the phone classification error rate in the Switchboard corpus by around 1% – 5% given only small amounts of adaptation data. (shrink)

Transfer learning can improve the robustness of deep learning in the case of small samples. However, when the semantic difference between the source domain data and the target domain data is large, transfer learning easily introduces redundant features and leads to negative transfer. According the mechanism of the human brain focusing on effective features while ignoring redundant features in recognition tasks, a brain-like classification method based on adaptive feature matching dual-source domain heterogeneous transfer learning is proposed for the (...) preoperative aided diagnosis of lung granuloma and lung adenocarcinoma for patients with solitary pulmonary solid nodule in the case of small samples. The method includes two parts: (1) feature extraction and (2) feature classification. In the feature extraction part, first, By simulating the feature selection mechanism of the human brain in the process of drawing inferences about other cases from one instance, an adaptive selected-based dual-source domain feature matching network is proposed to determine the matching weight of each pair of feature maps and each pair of convolution layers between the two source networks and the target network, respectively. These two weights can, respectively, adaptive select the features in the source network that are conducive to the learning of the target task, and the destination of feature transfer to improve the robustness of the target network. Meanwhile, a target network based on diverse branch block is proposed, which made the target network have different receptive fields and complex paths to further improve the feature expression ability of the target network. Second, the convolution kernel of the target network is used as the feature extractor to extract features. In the feature classification part, an ensemble classifier based on sparse Bayesian extreme learning machine is proposed that can automatically decide how to combine the output of base classifiers to improve the classification performance. Finally, the experimental results (the AUCs were 0.9542 and 0.9356, respectively) on the data of two center data show that this method can provide a better diagnostic reference for doctors. (shrink)

This paper presents an in-depth analysis of tennis match scene classification using an adaptive Gaussian mixture model parameter estimation simulation algorithm. We divided the main components of semantic analysis into type of motion, distance of motion, speed of motion, and landing area of the tennis ball. Firstly, for the problem that both people and tennis balls in the video frames of tennis matches from the surveillance viewpoint are very small, we propose an adaptive Gaussian mixture model parameter (...) estimation algorithm, which has good accuracy and speed on small targets. Secondly, in this paper, we design a sports player tracking algorithm based on role division and continuously lock the target player to be tracked and output the player region. At the same time, based on the displacement information of the key points of the player’s body and the system running time, the distance and speed of the player’s movement are obtained. Then, for the problem that tennis balls are small and difficult to capture in high-speed motion, this paper designs a prior knowledge-based algorithm for predicting tennis ball motion and landing area to derive the landing area of tennis balls. Finally, this paper implements a prototype system for semantic analysis of real-time video of tennis matches and tests and analyzes the performance indexes of the system, and the results show that the system has good performance in real-time, accuracy, and stability. (shrink)

While often presented as promising assistive technologies for motor-impaired users, electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) remain barely used outside laboratories due to low reliability in real-life conditions. There is thus a need to design long-term reliable BCIs that can be used outside-of-the-lab by end-users, e.g., severely motor-impaired ones. Therefore, we propose and evaluate the design of a multi-class Mental Task (MT)-based BCI for longitudinal training (20 sessions over 3 months) of a tetraplegic user for the CYBATHLON BCI series 2019. In (...) this BCI championship, tetraplegic pilots are mentally driving a virtual car in a racing video game. We aimed at combining a progressive user MT-BCI training with a newly designed machine learning pipeline based on adaptive Riemannian classifiers shown to be promising for real-life applications. We followed a two step training process: the first 11 sessions served to train the user to control a 2-class MT-BCI by performing either two cognitive tasks (REST and MENTAL SUBTRACTION) or two motor-imagery tasks (LEFT-HAND and RIGHT-HAND). The second training step (9 remaining sessions) applied an adaptive, session-independent Riemannian classifier that combined all 4 MT classes used before. Moreover, as our Riemannian classifier was incrementally updated in an unsupervised way it would capture both within and between-session non-stationarity. Experimental evidences confirm the effectiveness of this approach. Namely, the classification accuracy improved by about 30% at the end of the training compared to initial sessions. We also studied the neural correlates of this performance improvement. Using a newly proposed BCI user learning metric, we could show our user learned to improve his BCI control by producing EEG signals matching increasingly more the BCI classifier training data distribution, rather than by improving his EEG class discrimination. However, the resulting improvement was effective only on synchronous (cue-based) BCI and it did not translate into improved CYBATHLON BCI game performances. For the sake of overcoming this in the future, we unveil possible reasons for these limited gaming performances and identify a number of promising future research directions. Importantly, we also report on the evolution of the user's neurophysiological patterns and user experience throughout the BCI training and competition. (shrink)

. NormalBoost is a new boosting algorithm which is capable of classifying a multi-dimensional binary class dataset. It adaptively combines several weak classifiers to form a strong classifier. Unlike many boosting algorithms which have high computation and memory complexities, NormalBoost is capable of classification with low complexity. The purpose of this paper is to present NormalBoost as a framework which establishes a platform to solve classification problems. The approach was tested with a dataset which was extracted automatically from (...) real-world traffic sign images. The dataset contains both images of traffic sign borders and speed limit pictograms. This framework involves the computation of Haar-like features of these images and then employs the NormalBoost classifier to classify these traffic signs. The total number of images which were classified was 6500 binary images. A -fold validation was invoked to check the validity of the classification which resulted in a classification rate of 98.4% and 98.9% being achieved for these two databases. This framework is distinguished by its invariance to in-plane rotation of the images under consideration. Experiments show that the classification rate remains almost constant when traffic sign images with different angles of rotations were tested. (shrink)

The VIA Classification of Character Strengths and Virtue has received substantial attention since its inception as a model of 24 dimensions of positive human functioning, but less so as a potential contributor to a psychological science on the nature of virtue. The current paper presents an overview of how this classification could serve to advance the science of virtue. Specifically, we summarize previous research on the dimensional versus categorical characterization of virtue, and on the identification of cardinal virtues. (...) We give particular attention to the three-dimensional model of cardinal virtues that includes moral, self-regulatory, and intellectual domains. We also discuss the possibility that these three clusters be treated as fundamental elements of a virtue model, meaning that they clearly and directly contribute to both individual and communal flourishing across various cultures. This discussion includes a summary of previous speculations about the evolution of adaptations underlying the human capacity for using behavioral repertoires associated with the three virtues, as well as discussing ways in which they simultaneously enhance community and individual, in the last case focusing particularly on evidence concerning mating potential. We then discuss the relationship between the evolutionary perspective on virtues and Aristotle’s concept of the reciprocity of the virtues. Finally, we provide speculations about the nature of practical wisdom. While accepting the potential value of future revisions to the VIA model, that model even under its current conditions has the potential to generate a number of intriguing and testable hypotheses about the nature of virtue. (shrink)

This paper presents a new boosting algorithm called NormalBoost which is capable of classifying a multi-dimensional binary class dataset. It adaptively combines several weak classifiers to form a strong classifier. Unlike many boosting algorithms which have high computation and memory complexities, NormalBoost is capable of classification with low complexity. Since NormalBoost assumes the dataset to be continuous, it is also noise resistant because it only deals with the means and standard deviations of each dimension. Experiments conducted to evaluate its (...) performance shows that NormalBoost performs almost the same as AdaBoost in the classification rate. However, NormalBoost performs 189 times faster than AdaBoost and employs a very little amount of memory when a dataset of 2 million samples with 50 dimensions is invoked. (shrink)

Ontic structural realism constitutes a promising take on scientific realism, one that avoids the well‐known issues that realist stances have with underdetermination and theory change. In its most radical versions, ontic structural realism proposes a type of eliminativism about theoretical entities, ascribing ontological commitment only to the structures, and not to the objects appearing in our theories. More moderate versions of ontic structural realism have also been proposed, allowing for ‘thin’ objects in the ontology. This work connects these takes on (...) structural realism with the independent notion that there are two categorically different kinds of scientific theories, namely those that deal with interactions and those that deal with structural constraints – what are known as interaction and framework theories, respectively. By taking this classification seriously, one can arrive at a selective version of ontic structural realism which is better adapted to our scientific knowledge, in which eliminativist ontic structural realism constitutes a natural fit to framework theories, whereas the moderate version is connected to interaction theories. (shrink)

In recent years, neural networks have attracted much attention in the machine learning and the deep learning technologies. Bio-inspired functions and intelligence are also expected to process efficiently and improve existing technologies. In the visual pathway, the prominent features consist of nonlinear characteristics of squaring and rectification functions observed in the retinal and visual cortex networks, respectively. Further, adaptation is an important feature to activate the biological systems, efficiently. Recently, to overcome short-comings of the deep learning techniques, orthogonality for the (...) weights in the networks has been developed for the signal propagation and the efficient optimization of the learning. In this paper, bio-inspired asymmetric networks with nonlinear characteristics are proposed, which are derived from the retinal networks in the biological visual pathway. The asymmetric network proposed here was verified to detect the movement of the object, efficiently in our previous studies. This paper shows a new characteristic of the adaptive orthogonality in the asymmetric networks. First, it is shown that the asymmetric network with nonlinear characteristics is effective for generating orthogonality. Second, the proposed asymmetric network with Gabor filters is compared with the conventional energy model from the point of the orthogonality characteristics. Finally, the asymmetric networks with nonlinear characteristics can generate the extended orthogonal bases in independent subspaces, which are useful for classification and efficient learning. (shrink)

To improve the safety and the performance of operators involved in risky and demanding missions, human-machine cooperation should be dynamically adapted, in terms of dialogue or function allocation. To support this reconfigurable cooperation, a crucial point is to assess online the operator’s ability to keep performing the mission. The article explores the concept of Operator Functional State, then it proposes to operationalize this concept on the specific activity of drone swarm monitoring, carried out by 22 participants on simulator SUSIE. With (...) the aid of supervised learning methods, physiological and contextual are classified into three classes, corresponding to different levels of OFS. This classification would help for adapting the countermeasures to the situation faced by operators. (shrink)

Accurate prediction of battery quality using early-cycle data is critical for battery, especially lithium battery in microgrid networks. To effectively predict the lifetime of lithium-ion batteries, a time series classification method is proposed that classifies batteries into high-lifetime and low-lifetime groups using features extracted from early-cycle charge-discharge data. The proposed method is based on a smooth localized complex exponential model that can extract battery features from time-frequency maps and self-adaptively select the time-frequency resolution to maximize the discrepancy of data (...) from the two groups. A smooth localized complex exponential periodogram is then calculated to obtain the time-frequency decomposition of the whole time series data for further classification. The experimental results show that, by using battery features extracted from the first 128 charge-discharge processes, the proposed method can accurately classify batteries into high-lifetime and low-lifetime groups, with classification accuracy and specificity as high as 95.12% and 92.5%, respectively. (shrink)

Computer vision research involving street and road detection methods usually focuses on driving assistance and autonomous vehicle systems. In this context, street segmentation occurs in real-time, based on images centered on the street. This work, on the other hand, uses street segmentation for urban planning research to classify pavement types of a city or region, which is particularly important for developing countries. For this application, it is needed a dataset with images from various locations for each street. These images are (...) not necessarily centered on the street and include challenges that are not common in street segmentation datasets, such as mixed pavement types and the presence of faults and holes on the street. We implemented a multi-class version of a state-of-the-art segmentation algorithm and adapted it to perform street pavement classification, handling navigation along streets and angle variation to increase the accuracy of the classification. A data augmentation approach is also proposed to use preliminary results from the test instances as new ground truth and increase the amount of training data. A dataset with more than 300,000 images from 773 streets from a Brazilian city was built. Our approach achieved a precision of 0.93, showing the feasibility of the proposed application. (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)

A critical comparative analysis of howfarmers and scientists classify and manage soilsreveals fundamental differences as well assimilarities. In the past, the study of local soilknowledge has been predominantly targeted atdocumenting how farmers classified their soils incontrast to understanding how such classificatoryknowledge was made use of in actually managing soilsfor sustaining production. Often, classificatorydesigns – being cognitive and linguistic in nature –do not reflect the day-to-day actions in farming.Instead of merely describing local soil classificationin relation to scientific criteria, understanding howdifferent types (...) of ethnolinguistic soil categories arerelated to crops, climate, subsistence needs,fertility, market demand, and cultural norms of thesociety would be far more effective in focusingresearch and development efforts. (shrink)

We investigate and classify the notion of final derivability of two basic inconsistency-adaptive logics. Specifically, the maximal complexity of the set of final consequences of decidable sets of premises formulated in the language of propositional logic is described. Our results show that taking the consequences of a decidable propositional theory is a complicated operation. The set of final consequences according to either the Reliability Calculus or the Minimal Abnormality Calculus of a decidable propositional premise set is in general undecidable, (...) and can be -complete. These classifications are exact. For first order theories even finite sets of premises can generate such consequence sets in either calculus. (shrink)

The first classification of general types of transition between phases of matter, introduced by Paul Ehrenfest in 1933, lies at a crossroads in the thermodynamical study of critical phenomena. It arose following the discovery in 1932 of a suprising new phase transition in liquid helium, the “lambda transition,” when W. H. Keesom and coworkers in Leiden, Holland observed a λhaped “jump” discontinuity in the curve giving the temperature dependence of the specific heat of helium at a critical value. This (...) apparent jump led Ehrenfest to introduce a classification of phase transitions on the basis of jumps in derivatives of the free energy function. This classification was immediately applied by A.J. Rutgers to the study of the transition from the normal to superconducting state in metals. Eduard Justi and Max von Laue soon questioned the possibility of its class of “second-order phase transitions” -- of which the “lambda transition was believed to be the arche type -- but C.J. Gorter and H.B.G. Casimir used an “order parameter to demonstrate their existence in superconductors. As a crossroads of study, the Ehrenfest classification was forced to undergo a slow, adaptive evolution during subsequent decades. During the 1940s the classification was increasingly used in discussions of liquid-gas, order-disorder, paramagnetic-ferromagnetic and normal-super-conducting phase transitions. Already in 1944 however, Lars Onsagers solution of the Ising model for two-dimensional magnets was seen to possess a derivative with a logarithmic divergence rather than a jump as the critical point was approached. In the 1950s, experiments further revealed the lambda transition in helium to exhibit similar behavior. Rather than being a prime example of an Ehrenfest phase transition, the lambda transition was seen to lie outside the Ehrenfest classification. The Ehrenfest scheme was then extended to include such singularities, most notably by A. Brain Pippard in 1957, with widespread acceptance. During the 1960s these logarithmic infinities were the focus of the investigation of “scaling” by Leo Kadanoff, B. Widom and others. By the 1970s, a radically simplified binary classification of phase transitions into “first-order” and “continuous” transitions was increasingly adopted. (shrink)

In adaptive sports (also known as Para sports, disability sports, or Paralympic sports), athletes are assigned to classes that indicate their functional potential, regardless of talent, training, or experience. The aim of the present study among wheelchair basketball athletes (n = 141) was to explore the role of functional classification as a potential stressor. Specifically, we looked into the anecdotal relationship between classification and athletes' concern about “performing in accordance with one's class”. Based on a serial mediation (...) research model, we examined the links between functional classification and three outcome variables (i.e., cognitive worry, somatic arousal, and game performance) through the mediator variables of perceived competitive demands and sport-specific self-efficacy. Unexpectedly, we did not find any evidence of a classification effect on either the mediator variables or competitive anxiety. However, we did find positive correlations between functional classification and athletes' contribution to their team's score, which align with research supporting the proportionality and the validity of the functional classification system. Moreover, regardless of classification, mediation analyses revealed an indirect link between perceived competitive demands and cognitive worry through sport-specific self-efficacy. These findings suggest that, regardless of classification, athletes' self-efficacy may be increased by managing their appraisals of competitive demands and that their cognitive worries may be reduced by self-efficacy interventions. (shrink)

The study of film adaptations, particularly those coming from literature, has been growing at a rapid rate during the last years due to the amount of adaptations coming from both mainstream and independent film industries. The focus of these studies though is generally addressed to best sellers where the literary style is clearly adaptable to the screen; however, there are cases where the adaptive process has resulted in an entirely different outcome. Naked Lunch, written by William Burroughs and adapted (...) to screen by David Cronenberg, represents a bold change if compared with other novels turned into films. The purpose of this article is to descriptively analyse the literary style in order to understand how it has been represented and adapted into Cronenberg’s film. The analysis will be performed helped with computer-based tools to support statements, using the novel itself as corpus and adding theoretical ideas from Leech and Short’s perspectives. The results suggest that the author’s corrosive, sexually-fuelled claustrophobic style has been translated following three patterns in terms of adaptation theory, although Burroughs, in the hands of Cronenberg, becomes an almost new classification of adaptation, not only adding literary features to the film, but also distinguishable core moments of the writer’s life to the final product. The analysis conducted encourages the study of other uncommon adaptations from literary authors in order to understand the adaptive process followed by filmmakers. (shrink)

Processing data streams arriving at high speed requires the development of models that can provide fast and accurate predictions. Although deep neural networks are the state-of-the-art for many machine learning tasks, their performance in real-time data streaming scenarios is a research area that has not yet been fully addressed. Nevertheless, much effort has been put into the adaption of complex deep learning (DL) models to streaming tasks by reducing the processing time. The design of the asynchronous dual-pipeline DL framework allows (...) making predictions of incoming instances and updating the model simultaneously, using two separate layers. The aim of this work is to assess the performance of different types of DL architectures for data streaming classification using this framework. We evaluate models such as multi-layer perceptrons, recurrent, convolutional and temporal convolutional neural networks over several time series datasets that are simulated as streams at different speeds. In addition, we evaluate how the different architectures react to concept drifts typically found in evolving data streams. The obtained results indicate that convolutional architectures achieve a higher performance in terms of accuracy and efficiency, but are also the most sensitive to concept drifts. (shrink)

As an important component to promote the development of affective brain–computer interfaces, the study of emotion recognition based on electroencephalography (EEG) has encountered a difficult challenge; the distribution of EEG data changes among different subjects and at different time periods. Domain adaptation methods can effectively alleviate the generalization problem of EEG emotion recognition models. However, most of them treat multiple source domains, with significantly different distributions, as one single source domain, and only adapt the cross-domain marginal distribution while ignoring the (...) joint distribution difference between the domains. To gain the advantages of multiple source distributions, and better match the distributions of the source and target domains, this paper proposes a novel multi-source joint domain adaptation (MSJDA) network. We first map all domains to a shared feature space and then align the joint distributions of the further extracted private representations and the corresponding classification predictions for each pair of source and target domains. Extensive cross-subject and cross-session experiments on the benchmark dataset, SEED, demonstrate the effectiveness of the proposed model, where more significant classification results are obtained on the more difficult cross-subject emotion recognition task. (shrink)

Humans excel in categorization. Yet from a computational standpoint, learning a novel probabilistic classification task involves severe computational challenges. The present paper investigates one way to address these challenges: assuming class-conditional independence of features. This feature independence assumption simplifies the inference problem, allows for informed inferences about novel feature combinations, and performs robustly across different statistical environments. We designed a new Bayesian classification learning model that incorporates varying degrees of prior belief in class-conditional independence, learns whether or not (...) independence holds, and adapts its behavior accordingly. Theoretical results from two simulation studies demonstrate that classification behavior can appear to start simple, yet adapt effectively to unexpected task structures. Two experiments—designed using optimal experimental design principles—were conducted with human learners. Classification decisions of the majority of participants were best accounted for by a version of the model with very high initial prior belief in class-conditional independence, before adapting to the true environmental structure. Class-conditional independence may be a strong and useful default assumption in category learning tasks. (shrink)

The philosophy of medicine and psychiatry has considered the defining of disease, illness, and disorder an important project for over three decades. Within this literature, accounts based on adaptive "functions" have been prominent, particularly in the DSM nosology. In response to this trend, Jerome Wakefield has presented a view of mental disorder as "harmful dysfunction." In this view, "harm" contributes the value-element to disorder concepts, while "dysfunction" implies a value-free foundation as long as the latter is grounded in evolutionary (...) biology. In a critical review of Wakefield's and others' functionalist arguments for disorder concepts, we make four major points. We recommend a shift away from the definition of value-free disorder concepts, instead emphasizing the analysis of the logical features and the value commitments in nosological categories. (shrink)

Deep Learning has been widely used for tackling challenging natural language processing tasks over the recent years. Similarly, the application of Deep Neural Networks in legal analytics has increased significantly. In this survey, we study the early adaptation of Deep Learning in legal analytics focusing on three main fields; text classification, information extraction, and information retrieval. We focus on the semantic feature representations, a key instrument for the successful application of deep learning in natural language processing. Additionally, we share (...) pre-trained legal word embeddings using the word2vec model over large corpora, comprised legislations from UK, EU, Canada, Australia, USA, and Japan among others. (shrink)

A passive brain–computer interface based upon functional near-infrared spectroscopy brain signals is used for earlier detection of human drowsiness during driving tasks. This BCI modality acquired hemodynamic signals of 13 healthy subjects from the right dorsolateral prefrontal cortex of the brain. Drowsiness activity is recorded using a continuous-wave fNIRS system and eight channels over the right DPFC. During the experiment, sleep-deprived subjects drove a vehicle in a driving simulator while their cerebral oxygen regulation state was continuously measured. Vector phase analysis (...) was used as a classifier to detect drowsiness state along with sleep stage-based threshold criteria. Extensive training and testing with various feature sets and classifiers are done to justify the adaptation of threshold criteria for any subject without requiring recalibration. Three statistical features along with six VPA features were used. The average accuracies for the five classifiers are 90.9% for discriminant analysis, 92.5% for support vector machines, 92.3% for nearest neighbors, 92.4% for both decision trees, and ensembles over all subjects’ data. Trajectory slopes of CORE vector magnitude and angle: m and m are the best-performing features, along with ensemble classifier with the highest accuracy of 95.3% and minimum computation time of 40 ms. The statistical significance of the results is validated with a p-value of less than 0.05. The proposed passive BCI scheme demonstrates a promising technique for online drowsiness detection using VPA along with sleep stage classification. (shrink)

Deep Learning has been widely used for tackling challenging natural language processing tasks over the recent years. Similarly, the application of Deep Neural Networks in legal analytics has increased significantly. In this survey, we study the early adaptation of Deep Learning in legal analytics focusing on three main fields; text classification, information extraction, and information retrieval. We focus on the semantic feature representations, a key instrument for the successful application of deep learning in natural language processing. Additionally, we share (...) pre-trained legal word embeddings using the word2vec model over large corpora, comprised legislations from UK, EU, Canada, Australia, USA, and Japan among others. (shrink)

In recent years, many school librarians have been scrambling to build and expand their graphic novel collections to meet the large and growing demand for these materials. For the purposes of this study, the term graphic novels refers to volumes in which the content is provided through sequential art, including fiction, nonfiction, and biographical material. As the library field has not yet arrived at a set of best practices or guidelines for institutions working to classify and catalog graphic novels, this (...) study seeks to record the ways in which school librarians are handling these materials as well as issues and questions at the forefront of their minds. A survey of school librarians in the United States revealed that almost all of them collect fiction and nonfiction graphic novels, while 67% collect manga. Most respondents indicated that they are partly or solely responsible for the cataloging and classification decisions made in their media centers. For classification purposes, most have elected to create separate graphic novel collections to house their fictional graphic novels. Some include nonfiction graphic novels in this section, while others create a nonfiction graphic novel collection nearby or shelve nonfiction graphic novels with other items that deal with similar subject matter. Many school librarians express uncertainty about how best to catalog and classify longer series, adapted classics, superhero stories, and the increasing number and variety of inventive titles that defy categorization. They also struggle with inconsistent vendor records and past practices and suffer from a lack of full confidence in their knowledge of how to best classify and catalog graphic novels so that they are both searchable in the library catalog and easily accessible on the shelves. (shrink)

The article deals with Russian scientific classifications (GRNTI, VAK) of computer science in comparison with Western scien­tific classifications Fields of Science and Technology (FOS) and Universal Decimal Classification (UDS). The author analyzes the basics and principles of these classifications, identifies their strong and weak points as well as their influence on the devel­opment of computer sciences. She also provides some recom­mendations on adjustments of Russian scientific classifications aiming to make them more flexible and adaptive to the faster scientific (...) and technological development and interdisciplinary cooperation. (shrink)

Changing and often class-dependent non-stationarities of signals are a big challenge in the transfer of common findings in cognitive workload estimation using Electroencephalography (EEG) from laboratory experiments to realistic scenarios or other experiments. Additionally, it often remains an open question whether actual cognitive workload reflected by brain signals was the main contribution to the estimation or discriminative and class-dependent muscle and eye activity, which can be secondary effects of changing workload levels. Within this study, we investigated a novel approach to (...) spatial filtering based on beamforming adapted to changing settings. We compare it to no spatial filtering and Common Spatial Patterns (CSP). We used a realistic maneuvering task, as well as an auditoryn-backsecondary task on a tugboat simulator as two different conditions to induce workload changes on professional tugboat captains. Apart from the typical within condition classification, we investigated the ability of the different classification methods to transfer between then-backcondition and the maneuvering task. The results show a clear advantage of the proposed approach over the others in the challenging transfer setting. While no filtering leads to lowest within-condition normalized classification loss on average in two scenarios (22 and 10%), our approach using adaptive beamforming (30 and 18%) performs comparably to CSP (33 and 15%). Importantly, in the transfer from one to another setting, no filtering and CSP lead to performance around chance level (45 to 53%), while our approach in contrast is the only one capable of classifying in all other scenarios (34 and 35%) with a significant difference from chance level. The changing signal composition over the scenarios leads to a need to adapt the spatial filtering in order to be transferable. With our approach, the transfer is successful due to filtering being optimized for the extraction of neural components and additional investigation of their scalp patterns revealed mainly neural origin. Interesting findings are that rather the patterns slightly change between conditions. We conclude that the approaches with low normalized loss depend on eye and muscle activity which is successful for classification within conditions, but fail in the classifier transfer since eye and muscle contributions are highly condition-specific. (shrink)

This article analyzes India’s Traditional Knowledge Digital Library (TKDL) as a potential intervention in the administration of patent law. The TKDL is a database including a vast body of traditional medical knowledge from India, aiming to prevent the patenting and misappropriation of that knowledge. This article contextualizes the TKDL in relation to documentation theory as well as to existing research on the uses of databases to protect traditional knowledge. It explores the TKDL’s potential consequences for India’s traditional medical knowledge and (...) the wider implications that traditional knowledge databases can have for the safeguarding of traditional knowledge in general. The article concludes that on the one hand the TKDL bridges the gap between the main branches of Indian traditional medicine and the formal knowledge system of International Patent Classifications. Furthermore, it has also inspired revisions of the International Patent Classification system, which makes it better adapted to incorporate traditional medical knowledge. On the other hand, critical research on traditional knowledge documentation argues that traditional knowledge databases, like the TKDL, can decontextualize the knowledge they catalogue and dispossess its original owners. The TKDL, however, also fits into a national, Indian agenda of documenting and modernizing traditional medicine that predates the formation of the TKDL by several decades and challenges the dichotomy between traditional and scientific knowledge systems that originally motivated the formation of the TKDL. (shrink)

This article puts forward a novel class of Bézier smooth semi-supervised support vector machines(BS4VMs) for classification. As is well known, semi-supervised support vector machine is introduced for dealing with quantities of unlabeled data in the real world. Labeled data is utilized to train the algorithm and then adapting it to classify the unlabeled data. However, the objective semi-supervised function is not differentiable globally. It is required to endure heavy burden in solving two quadratic programming problems with inversion matrix operation. (...) To solve this problem, the interpolation Bézier functions for replacing the non-smooth term have been investigated. Firstly, the development of the novel BS4VMs classifier is introduced. Then, the non-linear model and convergence analysis are presented. To show how the BS4VMs can be practically implemented, experiments on synthetic and real data sets are offered. The theoretical analysis and experiments comparisons clearly illustrate the BS4VMs are superior to the proposed methods in both cross-validation classification accuracy and calculating time. (shrink)

Parkinson’s Disease can be treated with the use of microelectrode recording and stimulation. This paper presents a data stream classifier that analyses raw data from micro-electrodes and decides whether the measurements were taken from the subthalamic nucleus (STN) or not. The novelty of the proposed approach is based on the fact that distances based on raw data are used. Two distances are investigated in this paper, i.e. Normalized Compression Distance (NCD) and Lempel-Ziv Jaccard Distance (LZJD). No new features needed to (...) be extracted due to the fact that in the case of high-dimensional data the process is extremely time-consuming. The k-nearest neighbour (k-NN) was chosen as the classifier due to its simplicity, which is essential in data stream classification. Results obtained from classifiers based on k-NN: k-NN, k-NN were compared with Probabilistic Approximate Window (k-NN with PAW); k-NN with Probabilistic Approximate Window and Adaptive Windowing (k-NN with PAW and ADWIN); and Self Adjusting Memory k-NN (SAM k-NN), which use the proposed distances, with the performance of the same classifiers but using standard Euclidean distance. Prequential accuracy was chosen as the performance measure. The results of the experiments performed with the described approach are in most cases better, i.e. the performance measures for kNN classifiers that use NCD and LZJD distances are better by up to 8.5 per cent and 14 per cent, respectively. Moreover, the proposed approach performs better when compared with other stream classification algorithms, i.e. Hoeffding Tree, Naive Bayes, and Leveraging Bagging. In the discussed case, an improvement of classification rate of up to 17.9 per cent when using Lempel-Ziv Jaccard Distance instead of the Euclidean was noted. (shrink)

Geoengineering is typically defined as a techno-scientific response to climate change that differs from mitigation and adaptation, and that includes diverse individual technologies, which can be classified as either solar radiation management or carbon dioxide removal. We analyse the representation of geoengineering on Wikipedia as a way of opening up this dominating, if contested, model for further debate. We achieve this by contrasting the dominating model as presented in the encyclopaedic article texts with the patterns of hyper-link associations between the (...) articles. Two datasets were created tracing the geoengineering construct on Wikipedia, shedding light on its boundary with its context, as well as on its internal structure. The analysis shows that the geoengineering category tends to be associated on Wikipedia primarily with atmospheric solar radiation management rather than land-based carbon dioxide removal type technologies. The results support the notion that the dominant model of defining and classifying geoengineering technology has been beneficial for solar radiation management type technologies more than for land-based carbon dioxide removal ones. The article also demonstrates that controversy mapping with Wikipedia data affords analysis that can open up dominating definitions and classifications of technologies, and offer resistance to their frequent naturalising and decontextualising tendencies. This work is in line with recent work on digital sociology, but the article contributes a new methodology and reports on the first empirical application of controversy mapping using Wikipedia data to a technology. (shrink)

The British Museum, based in Montague House, Bloomsbury, opened its doors on 15 January 1759, as the world's first state-owned public museum. The Museum's collection mostly originated from Sir Hans Sloane, whose vast holdings were purchased by Parliament shortly after his death. The largest component of this collection was objects of natural history, including a herbarium made up of 265 bound volumes, many of which were classified according to the late seventeenth-century system of John Ray. The 1750s saw the emergence (...) of Linnaean binomial nomenclature, following the publication of Carl Linnaeus'Species Plantarum andSystema Naturae. In order to adopt this new system for their collections, the Trustees of the British Museum chose to employ the Swedish naturalist and former student of Linnaeus, Daniel Solander to reclassify the collection. Solander was ordered to devise a new system for classifying and cataloguing Sloane's natural history collection, which would allow both Linnaeans and those who followed earlier systems to access it. Solander's work was essential for allowing the British Museum to realize its aim of becoming a public centre of learning, adapting the collection to reflect the diversity of classificatory practices which were existent by the 1760s. This task engaged Solander until 1768, when he received an offer from Joseph Banks to accompany him on HMSEndeavourto the Pacific. (shrink)

Due to the non-invasiveness and high precision of electroencephalography, the combination of EEG and artificial intelligence is often used for emotion recognition. However, the internal differences in EEG data have become an obstacle to classification accuracy. To solve this problem, considering labeled data from similar nature but different domains, domain adaptation usually provides an attractive option. Most of the existing researches aggregate the EEG data from different subjects and sessions as a source domain, which ignores the assumption that the (...) source has a certain marginal distribution. Moreover, existing methods often only align the representation distributions extracted from a single structure, and may only contain partial information. Therefore, we propose the multi-source and multi-representation adaptation for cross-domain EEG emotion recognition, which divides the EEG data from different subjects and sessions into multiple domains and aligns the distribution of multiple representations extracted from a hybrid structure. Two datasets, i.e., SEED and SEED IV, are used to validate the proposed method in cross-session and cross-subject transfer scenarios, experimental results demonstrate the superior performance of our model to state-of-the-art models in most settings. (shrink)

Calibration errors are inevitable and should not be ignored during the estimation of item parameters. Items with calibration error can affect the measurement results of tests. One of the purposes of the current study is to investigate the impacts of the calibration errors during the estimation of item parameters on the measurement accuracy, average test length, and test efficiency for variable-length cognitive diagnostic computerized adaptive testing. The other purpose is to examine the methods for reducing the adverse effects of (...) calibration errors. Simulation results show that calibration error has negative effect on the measurement accuracy for the deterministic input, noisy “and” gate model, and the reduced reparameterized unified model; the average test lengths is shorter, and the test efficiency is overestimated for items with calibration errors; the compensatory reparameterized unified model is less affected by the calibration errors, and the classification accuracy, average test length, and test efficiency are slightly stable in the CRUM framework; methods such as improving the quality of items, using large calibration sample to calibrate the parameters of items, as well as using cross-validation method can reduce the adverse effects of calibration errors on CD-CAT. (shrink)

Maximum deviation global discrimination index is a new item selection method for cognitive diagnostic computerized adaptive testing that allows for attribute coverage balance. We developed the maximum limitation global discrimination index from MDGDI, which allows for both attribute coverage balance and item exposure control. MLGDI can realize the attribute coverage balance and exposure control of the item. Our simulation study aimed to evaluate the performance of our new method against maximum global discrimination index, modified maximum GDI, standardized weighted deviation (...) GDI, and constraint progressive with SWDGDI. The results indicated that under the condition of realizing the attribute coverage balance, MDGDI had the highest attribute classification accuracy; when the selection strategy accommodated the practical constraints of the attribute coverage balance and item exposure control, MLGDI had the highest attribute classification accuracy; adding the item exposure control mechanism to the item selection method reduces the classification accuracy of the attributes of the item selection method; and compared with GDI, MMGDI, SWDGDI, CP_SWDGDI, and MDGDI, MLGDI can better achieve the attribute-coverage requirement, control item exposure rate, and attribute correct classification rate. (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)

Life strategy in personal dimension could be identified as a complex phenomenon, which includes main key dimensions and categories that characterize person’s life and behavior. Life strategy is a way of life self-determining, self-establishing, self-expression and self-organizing as well as the ability to bring living conditions according with personality own values and individual uniqueness. The student life strategies directly connected with higher education. Author’s sociological research examines the main features of life strategies of modern Ukrainian students. In the article, the (...) author's typology of the main types of life strategies of students is proposed. The tipology reflects the crucial connection with the appropriate understanding of the place and role of higher education: career-pragmatic, universal education, and adaptive-conformist. (shrink)

Life strategy in personal dimension could be identified as a complex phenomenon, which includes main key dimensions and categories that characterize person’s life and behavior. Life strategy is a way of life self-determining, self-establishing, self-expression and self-organizing as well as the ability to bring living conditions according with personality own values and individual uniqueness. The student life strategies directly connected with higher education. Author’s sociological research examines the main features of life strategies of modern Ukrainian students. In the article, the (...) author's typology of the main types of life strategies of students is proposed. The tipology reflects the crucial connection with the appropriate understanding of the place and role of higher education: career-pragmatic, universal education, and adaptive-conformist. (shrink)

The article reconstructs attempts to create scientifically coherent, internationally agreed-upon diagnostics for mild forms of schizophrenia throughout the 20th century. A particular focus here lies on what became known as bland—or sluggish—schizophrenia, a particular term coined in the USSR, which became known for its frequent use in internationally contested diagnoses of human rights activists. The argument follows the diagnosis of sluggish schizophrenia from its inception in a highly productive and equally international psychiatric community of the early 20th century pioneered by (...) prominent Soviet scholar Andrey Snezhnevsky and through its epistemic detachment and content-related transformation in the highly isolated Soviet psychiatric community since the interwar period. This transformation is analyzed with help of the case study on the International Classification of Diseases (ICD). Released by the World Health Organization, the ICD—and in particular its ninth revision—played a crucial role in the attempt to legitimize sluggish schizophrenia. The comparative study of four presumably identical ICD-passages from three languages helps reconstructing how internationally accorded terms would become adapted to the Soviet societal and political realities. The ultimate aim of the attempted adaptation, the article claims, was to provide the elsewhere contested diagnostic term “sluggish” schizophrenia with additional legitimacy per authority of the WHO and, thus, much needed credibility for domestic, and often political, use. (shrink)