Search

Advancements in wireless communication and automation have revolutionized mobility systems, notably through autonomous vehicles and unmanned aerial vehicles (UAVs). UAV spatial coordinates, determined via Global Positioning System (GPS) signals, are susceptible to cyberattacks due to unencrypted and unauthenticated transmissions with GPS spoofing being a significant threat. To mitigate these vulnerabilities, intrusion detection systems (IDSs) for UAVs have been developed and enhanced using machine learning (ML) algorithms. However, Adversarial Machine Learning (AML) has introduced new risks by exploiting ML models. This study presents a UAV-IDS employing AML methodology to enhance the detection and classification of GPS spoofing attacks. The key contribution is the development of an AML detection model that significantly improves UAV system robustness and security. Our findings indicate that the model achieves a detection accuracy of 98%, demonstrating its effectiveness in managing large-scale datasets and complex tasks. This study emphasizes the importance of physical layer security for enhancing IDSs in UAVs by introducing a novel detection model centered on an adversarial training defense method and advanced deep learning techniques. [ABSTRACT FROM AUTHOR]

Wireless physical layer authentication has emerged as a promising approach to wireless security. The topic of wireless node classification and recognition has experienced significant advancements due to the rapid development of deep learning techniques. The potential of using deep learning to address wireless security issues should not be overlooked due to its considerable capabilities. Nevertheless, the utilization of this approach in the classification of wireless nodes is impeded by the lack of available datasets. In this study, we provide two models based on a data-driven approach. First, we used generative adversarial networks to design an automated model for data augmentation. Second, we applied a convolutional neural network to classify wireless nodes for a wireless physical layer authentication model. To verify the effectiveness of the proposed model, we assessed our results using an original dataset as a baseline and a generated synthetic dataset. The findings indicate an improvement of approximately 19% in classification accuracy rate. [ABSTRACT FROM AUTHOR]

SQL injection attacks are one of the most common types of attacks on Web applications. These attacks exploit vulnerabilities in an application's database access mechanisms, allowing attackers to execute unauthorized SQL queries. In this study, we propose an architecture for detecting SQL injection attacks using a recurrent neural network autoencoder. The proposed architecture was trained on a publicly available dataset of SQL injection attacks. Then, it was compared with several other machine learning models, including ANN, CNN, decision tree, naive Bayes, SVM, random forest, and logistic regression models. The experimental results showed that the proposed approach achieved an accuracy of 94% and an F1-score of 92%, which demonstrate its effectiveness in detecting QL injection attacks with high accuracy in comparison to the other models covered in the study. [ABSTRACT FROM AUTHOR]

Adversarial machine learning is a recent area of study that explores both adversarial attack strategy and detection systems of adversarial attacks, which are inputs specially crafted to outwit the classification of detection systems or disrupt the training process of detection systems. In this research, we performed two adversarial attack scenarios, we used a Generative Adversarial Network (GAN) to generate synthetic intrusion traffic to test the influence of these attacks on the accuracy of machine learning-based Intrusion Detection Systems(IDSs). We conducted two experiments on adversarial attacks including poisoning and evasion attacks on two different types of machine learning models: Decision Tree and Logistic Regression. The performance of implemented adversarial attack scenarios was evaluated using the CICIDS2017 dataset. Also, it was based on a comparison of the accuracy of machine learning-based IDS before and after attacks. The results show that the proposed evasion attacks reduced the testing accuracy of both network intrusion detection systems models (NIDS). That illustrates our evasion attack scenario negatively affected the accuracy of machine learning-based network intrusion detection systems, whereas the decision tree model was more affected than logistic regression. Furthermore, our poisoning attack scenario disrupted the training process of machine learning-based NIDS, whereas the logistic regression model was more affected than the decision tree. [ABSTRACT FROM AUTHOR]

With the maturity of electronic science (e-science) the scientific applications are growing to be more complex composed of a set of coordinating tasks with complex dependencies among them referred to as workflows. For optimized execution of workflows in the Grid, the high level middleware services (like task scheduler, resource broker, performance steering service etc.) need in-advance estimates of workflow execution times. However, modeling and predicting workflow execution time in the Grid is complex due to several tasks in a workflow, their distributed execution on multiple heterogeneous Grid-sites, and dynamic behaviour of the shared Grid resources. In this paper, we describe a novel method based on radial basis function neural network to model and predict workflow execution time in the Grid. We model workflows execution time in terms of attributes describing workflow structure and execution runtime information. To further refine our models, we employ principle component analysis to eliminate attributes of lesser importance. We recommend a set of only 14 attributes (as compared with total 21) to effectively model workflow execution time. Our reduced set of attributes improves the prediction accuracy by $$16\%$$ . Results of our prediction experiments for three real-world scientific workflows are presented to show that our predictions are more accurate than the two best methods from related work so far. [ABSTRACT FROM AUTHOR]

Detection of cyber‐threats in the smart grid Supervisory Control and Data Acquisition (SCADA) is still remains one of the complex and essential processes need to be highly concentrated in present times. Typically, the SCADA is more prone to the security issues due to their environmental problems and vulnerabilities. Therefore, the proposed work intends to design a new detection approach by integrating the optimization and classification models for smart grid SCADA security. In this framework, the min‐max normalization is performed at first for noise removal and attributes arrangement. Here, the correlation estimation mechanism is mainly deployed to reduce the dimensionality of features by choosing the relevant features used for attack prediction. Moreover, the optimal features are selected by using the optimal solution provided by the Holistic Harris Hawks Optimization (H3O). Finally, the Perceptron Stochastic Neural Network (PSNN) is utilized to categorize the normal and attacking data flow in the network with minimal processing time and complexity. By using the combination of proposed H3O‐PSNN technique, the detection accuracy is improved up to 99% for all datasets used in this study, and also other measures such as precision to 99.2%, recall to 99%, f1‐score to 99.2% increased, when compared to the standard techniques. [ABSTRACT FROM AUTHOR]

As the amount of historical data available in the legal arena has grown over time, industry specialists are driven to gather, compile, and analyze this data in order to forecast court case rulings. However, predicting and justifying court rulings while using judicial facts is no easy task. Currently, previous research on forecasting court outcomes using small experimental datasets yielded a number of unanticipated predictions utilizing machine learning (ML) models and conventional methodologies for categorical feature encoding. The current work proposes forecasting court judgments using a hybrid neural network model, namely a long short-term memory (LSTM) network with a CNN, in order to effectively forecast court rulings using historic judicial datasets. By prioritizing and choosing features that scored the highest in the provided legal data set, only the most pertinent features were picked. After that, the LSTM+CNN model was utilized to forecast lawsuit verdicts. In contrast to previous related experiments, this composite model's testing results were promising, showing 92.05 percent accuracy, 93 percent precision, 94 percent recall, and a 93 percent F1-score. [ABSTRACT FROM AUTHOR]

In Internet of Things (IoT) environments, privacy and security are among some of the significant challenges. Recently, several studies have attempted to apply blockchain technology to increase IoT network security. However, the lightweight feature of IoT devices commonly fails to meet computational intensive requirements for blockchain-based security models. In this work, we propose a mechanism to address this issue. We design an IoT blockchain architecture to store device identity information in a distributed ledger. We propose a Blockchain of Things (BCoT) Gateway to facilitate the recording of authentication transactions in a blockchain network without modifying existing device hardware or applications. Furthermore, we introduce a new device recognition model that is suitable for blockchain-based identity authentication, where we employ a novel feature selection method for device traffic flow. Finally, we develop the BCoT Sentry framework as a reference implementation of our proposed method. Experiment results verify the feasibility of our proposed framework. [ABSTRACT FROM AUTHOR]

Epilepsy is a nervous system disorder. Encephalography (EEG) is a generally utilized clinical approach for recording electrical activity in the brain. Although there are a number of datasets available, most of them are imbalanced due to the presence of fewer epileptic EEG signals compared with non-epileptic EEG signals. This research aims to study the possibility of integrating local EEG signals from an epilepsy center in King Abdulaziz University hospital into the CHB-MIT dataset by applying a new compatibility framework for data integration. The framework comprises multiple functions, which include dominant channel selection followed by the implementation of a novel algorithm for reading XLtek EEG data. The resulting integrated datasets, which contain selective channels, are tested and evaluated using a deep-learning model of 1D-CNN, Bi-LSTM, and attention. The results achieved up to 96.87% accuracy, 96.98% precision, and 96.85% sensitivity, outperforming the other latest systems that have a larger number of EEG channels. [ABSTRACT FROM AUTHOR]

Recent years have seen a lot of interest in the study of chaotic structures and their accompanying cryptography frameworks. In this research, we came up with a new way to encrypt images that used the chaos and a modified block cipher named the SHARK cipher. The new algorithm looks at the creation of random sequences as a problem that needs to be solved in the best way possible, and then it uses the Duffing chaotic map to get even better random sequences. Chaos has been combined with a revised edition of the SHARK structure to make the algorithm design more robust with increased confusion and diffusion. The offered algorithm includes a complex encryption and decryption structure with minimal time consumption for secure data transmission. The proposed algorithm is verified with the encryption of some standard images of different sizes. Numerous analyses have been performed to see how well the algorithm works against a variety of assaults, and the outcomes show that the cryptosystem has a good level of robustness. The comparative results are also performed in this work, which guarantees the excellent performance of our cryptosystem. The system is also subjected to chosen-plaintext and chosen-ciphertext attacks which implies that it can resist many classical cryptographic attacks. Therefore, our cryptosystem is robust enough to use for image encryption. [ABSTRACT FROM AUTHOR]

Based on the improved BP neural network, this paper establishes an adaptive online controlling model and adopts the model to optimize the controlling accuracies in discrete nonlinear dynamic systems and inverted pendulum systems. To avoid the local minimum problem of the BP neural network's objective function in the training process, this paper proposes a neural network training method based on the quasi-Newton method (BFGS) optimization algorithm. Compared with other control methods, the neural network-based inverted pendulum control method proposed in this paper has higher control accuracy. Through the control simulation of its power system uses a discrete control method and the control of the inverted pendulum model system, this paper verifies the validity and good control has significantly improved the control method. [ABSTRACT FROM AUTHOR]

This investigation sought to understand whether performance in naturalistic virtual reality tasks for cognitive assessment relates to the cognitive domains that are supposed to be measured. The Shoe Closet Test (SCT) was developed based on a simple visual search task involving attention skills, in which participants have to match each pair of shoes with the colors of the compartments in a virtual shoe closet. The interaction within the virtual environment was made using the Microsoft Kinect. The measures consisted of concurrent paper-and-pencil neurocognitive tests for global cognitive functioning, executive functions, attention, psychomotor ability, and the outcomes of the SCT. The results showed that the SCT correlated with global cognitive performance as measured with the Montreal Cognitive Assessment (MoCA). The SCT explained one third of the total variance of this test and revealed good sensitivity and specificity in discriminating scores below one standard deviation in this screening tool. These findings suggest that performance of such functional tasks involves a broad range of cognitive processes that are associated with global cognitive functioning and that may be difficult to isolate through paper-and-pencil neurocognitive tests. [ABSTRACT FROM AUTHOR]

Sophisticated educational technologies are evolving rapidly, and online courses are becoming more easily available, generating interest in innovating lightweight data-driven adaptive approaches that foster responsive teaching and improving the overall learning experience. However, in most existing adaptive educational systems, the black-box modeling of learner and instructional models based on the views of a few designers or experts tended to drive the adaptation of learning content. However, different sources of uncertainty could affect these views, including how accurately the proposed adaptive educational methods actually assess student responses and the corresponding uncertainties associated with how students receive and comprehend the resulting instruction. E-learning environments contain high levels of linguistic uncertainties, whereby students can interpret and act on the same terms, words, or methods (e.g., course difficulty, length of study time, or preferred learning style) in various ways according to varying levels of motivation, pre-knowledge, cognition, and future plans. Thus, one adaptive instructional model does not fit the needs of all students. Basing the instruction model on determining learners' interactions within the learning environment in interpretable and easily read white-box models is crucial for adapting the model to students' needs and understanding how learning is realized. This paper presents a new zSlices-based type-2 fuzzy-logic-based system that can learn students' preferred knowledge delivery needs based on their characteristics and current levels of knowledge to generate an adaptive learning environment. We have evaluated the proposed system's efficiency through various large-scale, real-world experiments involving 1871 students from King Abdulaziz University. These experiments demonstrate the proposed zSlices type-2 fuzzy-logic-based system's capability for handling linguistic uncertainties to produce better performance, particularly in terms of enhanced student performance and improved success rates compared with interval type-2 fuzzy logic, type-1 fuzzy systems, adaptive, instructor-led systems, and non-adaptive systems. [ABSTRACT FROM AUTHOR]

Background: Despite the multisensory nature of perception, previous research on emotions has been focused on unimodal emotional cues with visual stimuli. To the best of our knowledge, there is no evidence on the extent to which incongruent emotional cues from visual and auditory sensory channels affect pupil size. Aims: To investigate the effects of audiovisual emotional information perception on the physiological and affective response, but also to determine the impact of mismatched cues in emotional perception on these physiological indexes. Method: Pupil size, electrodermal activity and affective subjective responses were recorded while 30 participants were exposed to visual and auditory stimuli with varied emotional content in three different experimental conditions: pictures and sounds presented alone (unimodal), emotionally matched audio-visual stimuli (bimodal congruent) and emotionally mismatched audio-visual stimuli (bimodal incongruent). Results: The data revealed no effect of emotional incongruence on physiological and affective responses. On the other hand, pupil size covaried with skin conductance response (SCR), but the subjective experience was partially dissociated from autonomic responses. Conclusion: Emotional stimuli are able to trigger physiological responses regardless of valence, sensory modality or level of emotional congruence. [ABSTRACT FROM AUTHOR]

In supervised prediction problems, the response attribute depends on certain explanatory attributes. Some real problems require the response attribute to represent ordinal values that should increase with some of the explaining attributes. They are called classification problems with monotonicity constraints. In this paper, we aim at formalizing the approach to nested generalized exemplar learning with monotonicity constraints, proposing the monotonic nested generalized exemplar learning (MoNGEL) method. It accomplishes learning by storing objects in $${\mathbb {R}}^n$$ , hybridizing instance-based learning and rule learning into a combined model. An experimental analysis is carried out over a wide range of monotonic data sets. The results obtained have been verified by non-parametric statistical tests and show that MoNGEL outperforms well-known techniques for monotonic classification, such as ordinal learning model, ordinal stochastic dominance learner and k-nearest neighbor, considering accuracy, mean absolute error and simplicity of constructed models. [ABSTRACT FROM AUTHOR]

In recent years, educational institutions have worked hard to automate their work using more trending technologies that prove the success in supporting decision-making processes. Most of the decisions in educational institutions rely on rating the academic research profiles of their staff. An enormous amount of scholarly data is produced continuously by online libraries that contain data about publications, citations, and research activities. This kind of data can change the accuracy of the academic decisions, if linked with the local data of universities. The linked data technique in this study is applied to generate a link between university semantic data and a scientific knowledge graph, to enrich the local data and improve academic decisions. As a proof of concept, a case study was conducted to allocate the best academic staff to teach a course regarding their profile, including research records. Further, the resulting data are available to be reused in the future for different purposes in the academic domain. Finally, we compared the results of this link with previous work, as evidence of the accuracy of leveraging this technology to improve decisions within universities. [ABSTRACT FROM AUTHOR]

In the field of protein engineering, the function and structure of proteins are key to understanding cellular mechanisms, biological evolution, and biodiversity. With the advancement of high-throughput sequencing technologies, we have accumulated a vast amount of protein sequence data, yet the protein properties and functional information contained within these data have not been fully deciphered. Predicting protein properties is crucial for revealing how proteins function within complex biological systems and also offers possibilities for the early diagnosis of diseases and the development of new drugs. However, due to the complexity of protein properties and functions, traditional experimental methods face significant challenges in terms of cost, time, and accuracy. In recent years, machine learning techniques have become a powerful tool for addressing these challenges due to their ability to learn patterns and relationships from large-scale data. Machine learning methods have demonstrated outstanding performance in areas such as protein structure prediction, function annotation, interaction recognition, and physicochemical property prediction. This survey reviews the application of machine learning in protein property prediction. Current research progress, challenges in the field, and future development directions have been discussed, highlighting the significance and potential of machine learning methods in advancing protein science research and applications. • Comprehensive review of machine learning methods. • Deep learning innovations in protein science, especially from 2019 to 2023. • Role of pre-trained models in protein property prediction. • Integration of advanced machine learning techniques in protein property prediction. • Representation learning from protein sequences and structures. [ABSTRACT FROM AUTHOR]

Bioinformatics is a subject that studies life phenomena by using mathematical and information science theories and techniques. Its main tasks, such as DNA sequence comparison, protein structure prediction and cell metabolism analysis, can be regarded as complex optimization problems with different characteristics. Evolutionary computing is a kind of global optimization algorithm inspired by nature. Over the years, scholars have accumulated fruitful results in solving complex optimization problems such as large-scale, dynamic, multi-modal, multi-objective and multi-constrained problems by using Evolutionary Computation algorithms, and have successfully applied to the above optimization tasks in bioinformatics. This paper mainly summarizes the work of Evolutionary Computation technologies in bioinformatics from 2019 to 2023 at multiple levels, including Genomics, Proteomics, metabolomics and molecular networks related optimization tasks, as well as further applications in disease diagnosis and drug development. • Recent works on Evolutionary Computation technologies in Bioinformatics from 2019 to 2023. • Optimization tasks in Bioinformatics from genotype to phenotype. • Evolutionary Computation technologies from Genomics, Proteomics, Metabolomics and Molecular Networks level respectively. • Downstream applications such as disease diagnosis and drug discovery. [ABSTRACT FROM AUTHOR]

The 5th generation (5G) wireless networks propose to address a variety of usage scenarios, such as enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). Due to the exponential increase in the user equipment (UE) devices of wireless communication technologies, 5G and beyond networks (B5G) expect to support far higher user density and far lower latency than currently deployed cellular technologies, like long-term evolution-Advanced (LTE-A). However, one of the critical challenges for B5G is finding a clever way for various channel access mechanisms to maintain dense UE deployments. Random access channel (RACH) is a mandatory procedure for the UEs to connect with the evolved node B (eNB). The performance of the RACH directly affects the performance of the entire network. Currently, RACH uses a uniform distribution-based (UD) random access to prevent a possible network collision among multiple UEs attempting to access channel resources. However, in a UD-based channel access, every UE has an equal chance to choose a similar contention preamble close to the expected value, which causes an increase in the collision among the UEs. Therefore, in this paper, we propose a Poisson process-based RACH (2PRACH) alternative to a UD-based RACH. A Poisson process-based distribution, such as exponential distribution, disperses the random preambles between two bounds in a Poisson point method, where random variables occur continuously and independently with a constant parametric rate. In this way, our proposed 2PRACH approach distributes the UEs in a probability distribution of a parametric collection. Simulation results show that the shift of RACH from UD-based channel access to a Poisson process-based distribution enhances the reliability and lowers the network's latency. [ABSTRACT FROM AUTHOR]

Upon the working principles of the human neocortex, the Hierarchical Temporal Memory model has been developed which is a proposed theoretical framework for sequence learning. Both categorical and numerical types of data are handled by HTM. Semantic Folding Theory (SFT) is based on HTM to represent a data stream for processing in the form of sparse distributed representation (SDR). For natural language perception and production, SFT delivers a solid structural background for semantic evidence description to the fundamentals of the semantic foundation during the phase of language learning. Anomalies are the patterns from data streams that do not follow the expected behavior. Any stream of data patterns could have a number of anomaly types. In a data stream, a single pattern or combination of closely related patterns that diverges and deviates from standard, normal, or expected is called a static (spatial) anomaly. A temporal anomaly is a set of unexpected changes between patterns. When a change first appears, this is recorded as an anomaly. If this change looks a number of times, then it is set to a "new normal" and terminated as an anomaly. An HTM system detects the anomaly, and due to continuous learning nature, it quickly learns when they become the new normal. A robust anomalous behavior detection framework using HTM-based SFT for improving decision-making (SDR-ABDF/P2) is a proposed framework or model in this research. The researcher claims that the proposed model would be able to learn the order of several variables continuously in temporal sequences by using an unsupervised learning rule. [ABSTRACT FROM AUTHOR]

In recent years, accumulating evidences have shown that microRNA (miRNA) plays an important role in the exploration and treatment of diseases, so detection of the associations between miRNA and disease has been drawn more and more attentions. However, traditional experimental methods have the limitations of high cost and time- consuming, a computational method can help us more systematically and effectively predict the potential miRNA-disease associations. In this work, we proposed a novel network embedding-based heterogeneous information integration method to predict miRNA-disease associations. More specifically, a heterogeneous information network is constructed by combining the known associations among lncRNA, drug, protein, disease, and miRNA. After that, the network embedding method Learning Graph Representations with Global Structural Information (GraRep) is employed to learn embeddings of nodes in heterogeneous information network. In this way, the embedding representations of miRNA and disease are integrated with the attribute information of miRNA and disease (e.g. miRNA sequence information and disease semantic similarity) to represent miRNA-disease association pairs. Finally, the Random Forest (RF) classifier is used for predicting potential miRNA-disease associations. Under the 5-fold cross validation, our method obtained 85.11% prediction accuracy with 80.41% sensitivity at the AUC of 91.25%. In addition, in case studies of three major Human diseases, 45 (Colon Neoplasms), 42 (Breast Neoplasms) and 44 (Esophageal Neoplasms) of top-50 predicted miRNAs are respectively verified by other miRNA-disease association databases. In conclusion, the experimental results suggest that our method can be a powerful and useful tool for predicting potential miRNA-disease associations. [ABSTRACT FROM AUTHOR]

We consider a demand response program in which a block of apartments receive a discount from their electricity supplier if they ensure that their aggregate load from air conditioning does not exceed a predetermined threshold. The goal of the participants is to obtain the discount, while ensuring that their individual temperature preferences are also satisfied. As such, the apartments need to collectively optimise their use of air conditioning so as to satisfy these constraints and minimise their costs. Given an optimal cooling profile that secures the discount, the problem that the apartments face then is to divide the total discounted cost in a fair way. To achieve this, we take a coalitional game approach and propose the use of the Shapley value from cooperative game theory, which is the normative payoff division mechanism that offers a unique set of desirable fairness properties. However, applying the Shapley value in this setting presents a novel computational challenge. This is because its calculation requires, as input, the cost of every subset of apartments, which means solving an exponential number of collective optimisations, each of which is a computationally intensive problem. To address this, we propose solving the optimisation problem of each subset suboptimally, to allow for acceptable solutions that require less computation. We show that, due to the linearity property of the Shapley value, if suboptimal costs are used rather than optimal ones, the division of the discount will be fair in the following sense: each apartment is fairly "rewarded" for its contribution to the optimal cost and, at the same time, is fairly "penalised" for its contribution to the discrepancy between the suboptimal and the optimal costs. Importantly, this is achieved without requiring the optimal solutions. [ABSTRACT FROM AUTHOR]

Information and Communication Technologies (ICTs) have grown exponentially in the education context and the use of digital products by children is increasing. As a result, teachers are taking advantage of ICTs to include mobile devices such as Tablets or Smartphones inside the classroom as playful support material to motivate children during their learning. Designing an interactive experience for a child with a special need such as a hearing impairment is a great challenge. In this article, two interactive systems are depicted, using a non-traditional interaction, by the following stages: analysis, design and implementation, with the participation of children with cochlear implant in the Institute of Blind and Deaf Children of Valle del Cauca, Colombia and the ASPAS Institute, Mallorca, Spain, who evaluated both interactive systems, PHONOMAGIC and CASETO. Positive results were obtained, showing that the use of real objects can greatly influence the environment in which children interact with the game, allowing them to explore and manipulate the objects supporting their teaching-learning processes. [ABSTRACT FROM AUTHOR]

E-learning platforms facilitate the interaction between students and instructors while mitigating temporal or spatial constraints. Nevertheless, such platforms require measuring the degree of students' engagement with the delivered course content and teaching style. Such information is highly valuable for evaluating the quality of the teaching and altering the teaching delivery style in massively crowded online learning platforms. When the number of learners is high, it is essential to attain overall engagement and feedback, yet doing so is highly challenging due to the high levels of uncertainties related to students and the learning context. To handle these uncertainties more robustly, we present a method based on type-2 fuzzy logic utilizing visual RGB-D features, including head pose direction and facial expressions captured from Kinect v2, a low-cost but robust 3D camera, to measure the engagement degree of students in both remote and on-site education. This system augments another self-learning type-2 fuzzy logic system that helps teachers with recommendations of how to adaptively vary their teaching methods to suit the level of students and enhance their instruction delivery. This proposed dynamic e-learning environment integrates both on-site and distance students as well as teachers who instruct both groups of students. The rules are learned from the students' and teachers' learning/teaching behaviors, and the system is continuously updated to give the teacher the ability to adapt the delivery approach to varied learners' engagement levels. The efficiency of the proposed system has been tested through various real-world experiments in the University of Essex iClassroom among a group of thirty students and six teachers. These experiments demonstrate the capabilities-compared to type-1 fuzzy systems and non-adaptive systems-of the proposed interval type-2 fuzzy logic-based system to handle the uncertainties and improve average learners' motivations to engage during learning. [ABSTRACT FROM AUTHOR]

Helpfulness of online reviews serves multiple needs of different Web users. Several types of factors can drive reviews' helpfulness. This study focuses on uninvestigated factors by looking at not just the quantitative factors (such as the number of concepts), but also qualitative aspects of reviewers (including review types such as the regular, comparative and suggestive reviews and reviewer helpfulness) and builds a conceptual model for helpfulness prediction. The set of 1500 reviews were randomly collected from TripAdvisor.com across multiple hotels for analysis. A set of four hypotheses were used to test the proposed model. Our results suggest that the number of concepts contained in a review, the average number of concepts per sentence, and the review type contribute to the perceived helpfulness of online reviews. The regular reviews were not statistically significant predictors of helpfulness. As a result, review types and concepts have a varying degree of impact on review helpfulness. The findings of this study can provide new insights to e-commerce retailers in understanding the importance of helpfulness of reviews. [ABSTRACT FROM AUTHOR]

The recent years have witnessed significant progress in the automation of human behavior recognition using machine vision in order to realize intelligent environments which are capable of detecting users' actions and gestures so that the needed services can be provided automatically and instantly for maximizing the user comfort and safety as well as minimizing energy. However, the majority of traditional human behavior machine vision-based recognition approaches rely on assumptions (such as known spatial locations and temporal segmentations) or computationally expensive approaches (such as sliding window search through a spatio-temporal volume). Hence, it is difficult for such methods to scale up and handle the high uncertainty levels and complexities available in real-world applications. This paper proposes a novel fuzzy machine vision-based framework for efficient humans' behavior recognition. A model-based feature set is utilized to extract visual feature cues including silhouette slices and movement speed from the human silhouette in video sequences which are analyzed as inputs by the proposed fuzzy system. We have employed fuzzy c-means clustering to learn the membership functions of the proposed fuzzy system. The behavior recognition was implemented via selecting the best candidate's behavior category with the highest output degree as the recognized behavior. We have successfully tested our system on the publicly available Weizmann human action dataset where our fuzzy-based system produced an average recognition accuracy of 94.03 %, which outperformed the traditional non-fuzzy systems based on hidden Markov models and other state-of-the-art approaches which were applied on the Weizmann dataset. [ABSTRACT FROM AUTHOR]

Within the last two decades, the paradigm of Computing With Words (CWW) has been gaining more attention. Mainly, CWW has an exciting vision which tries to tackle the problem of human intelligence by taking the human mind as a role model. The human intelligence has been investigated by various disciplines including psychology, philosophy, neuroscience, linguistics, computer science, and cognitive sciences. Notably, it is not a straightforward task to map the human’s brain reasoning into computer processes. In this paper, we propose to facilitate such mapping by investigating a key element, which is to identify the step-by-step formation of perceptual judgments. Herein, we first introduce an approach that employs general type-2 fuzzy logic to dynamically model the human perceptions based on the human experience. This approach can be regarded as a step to enable the CWW vision. We have deployed the proposed approach in real-world settings and we will present two sets of real-world experiments which were conducted in the intelligent apartment (iSpace) in the University of Essex. The first set of experiments demonstrates the results of the proposed approach for the adaptive modeling of ambient luminance perception. In the second set of experiments, we show that our approach performs better in the rule base evaluation processing time and in output accuracy with comparison to an interval type-2 fuzzy logic system. [ABSTRACT FROM AUTHOR]

Self-interacting proteins (SIPs) is of paramount importance in current molecular biology. There have been developed a number of traditional biological experiment methods for predicting SIPs in the past few years. However, these methods are costly, time-consuming and inefficient, and often limit their usage for predicting SIPs. Therefore, the development of computational method emerges at the times require. In this paper, we for the first time proposed a novel deep learning model which combined natural language processing (NLP) method for potential SIPs prediction from the protein sequence information. More specifically, the protein sequence is de novo assembled by k-mers. Then, we obtained the global vectors representation for each protein sequences by using natural language processing (NLP) technique. Finally, based on the knowledge of known self-interacting and non-interacting proteins, a multi-grained cascade forest model is trained to predict SIPs. Comprehensive experiments were performed on yeast and human datasets, which obtained an accuracy rate of 91.45% and 93.12%, respectively. From our evaluations, the experimental results show that the use of amino acid semantics information is very helpful for addressing the problem of sequences containing both self-interacting and non-interacting pairs of proteins. This work would have potential applications for various biological classification problems. [ABSTRACT FROM AUTHOR]