Search

The evolving healthcare domain necessitates an upgrade through digitization, integrating patient data, and advanced medical results. In the last couple of decades, advances in information and storage technologies in healthcare have produced vast amounts of data. The remarkable increases in data volumes, along with the enticing prospects and potential inherent in data analysis, have contributed to the concept of Big Data. There is a pressing need within the research community to analyze these large volumes of Big Data. To address this challenge, Big Data Analytics (BDA), the systematic process of examining large and complex datasets to uncover hidden patterns, correlations, and insights for informed decision-making, has emerged. It employs various methodologies and techniques to enable informed decision-making. This study delves into using Machine Learning (ML) in big data environments, explicitly utilizing the MLib library in Apache Spark to derive meaningful insights from diabetic healthcare dataset. The CDC’s Behavioral Risk Factor Surveillance System (BRFSS) was used to empirically demonstrate the advantages of integrating BDA with ML for medical decision-making in Big Data environments. The research finding highlighted the superior performance of Logistic Regression (LR) models compared to other models like Naive Bayes (NB), providing valuable insights for healthcare applications.

Personality analysis allows the experts to get insights into an individual’s conduct, vulnerabilities, and prospective capabilities. Some common methods employed for personality prediction include text analysis, social media data, facial expressions, and emotional speech extraction. Recently, some studies have utilized the big five model to predict personality traits using non-verbal cues (gaze score, body motion, head motion). However, these studies mostly target only three aspects of the big five mode. None of the studies so far have used non-verbal cues to target all five traits (extraversion, openness, neuroticism, agreeableness, and conscientiousness) of the Big Five model. In this paper, we propose a multi-modal system that predicts all five personality traits of the Big Five model using non-verbal cues (facial expressions, head poses, body poses), 44-item Big Five Inventory (BFI) questionnaire, and expert analysis. The facial expression module utilizes the Face Emotion Recognition Plus (FER+) dataset trained with Convolution Neural Network (CNN) model achieving 95.14% accuracy. Evaluating 16 subjects in verbal interaction with humanoid robot NAO, we combined questionnaire feedback, human-robot interaction data, and expert perspectives to deduce their Big Five traits. Findings reveal 100% accuracy in personality prediction via expert insights and the system, and 75% for the questionnaire-based approach.

Driver Drowsiness Detection (D3) is a challenging task as it requires analysis based on various behavioral and physiological signs such as health issues, mental stress, and exhaustion. Data analytics reveals that driver drowsiness is the reason for one-fifth of all traffic accidents worldwide. Thus, safety devices are valuable for alerting sleepy drivers regarding more danger that may occur. Constant real-time drowsiness detection in complex conditions and denoting is still an open issue. However, facing these challenges, this article proposed a technique called Driver Drowsiness Detection using Custom Deep Learning Model (D3-CDLM). This approach contains four different modules: In the given procedure the investigation and exploration include, 1) feature extraction and selection; 2) machine learning and ensemble methods; 3) deep learning; and 4) the combination of the two, Hybrid. The first operation computes HOG, which stands for Histogram of Oriented Gradient, which is rotation and illumination invariant and resistant to the information in the local areas. Then Principal Component Analysis or PCA is used to obtain the best or top HOG features that are used as inputs to machine learning and ensemble methods-based modules. For hard to learn facial features, transfer learning is also carried out, and a new 30-layer CNNs structure is proposed called CDLM. Finally, the hybrid module’s top features are investigated using the PCA control of the architecture in coordination with the proposed CDLM for detecting drowsiness. Empirical analysis that encompasses all districts were applied on Yawning Detection Dataset. The results reveal that the developed and designed deep learning and hybrid modules acquire better accuracy than the proposed and utilized machine learning-based module along with the compared existing approaches in the pertinent literature.

Cartoon movies are a primary source of entertainment for children. However, concerns arise when these movies inadvertently expose children to violent scenes. This paper addresses the challenge of detecting subtle instances of violence within cartoon movies. The main difficulty in this task is the sequential nature of movies, where a sequence of frames must be considered in their given order. Existing methods have not effectively addressed the issue. In this study, we tackled this challenge by employing a sequential model. The research comprises three key steps. Initially, a histogram technique was implemented to select key frames from the video sequences. Subsequently, a Convolutional Neural Network (CNN) was utilized to extract prominent features from these selected key frames. In the third phase, the acquired features were utilized to train a sequential model using sequence-based learning. The model was then refined through transfer learning, using a dataset containing scenes devoid of violence, as well as scenes depicting varying forms of violence, including bloodshed, fights, gunshots, and explosions. A significant contribution of this study is the meticulous categorization of violent scenes into four distinct types, allowing for further investigation into the diverse effects of different violence categories. Furthermore, the study introduces an innovative approach by integrating a dense layer into the sequential model to enhance final classification. The trained model’s performance was comprehensively evaluated using metrics such as F1 score, precision, accuracy, and recall. To validate the effectiveness of the proposed model, it was benchmarked against state-of-the-art methods. This study presents an innovative deep-learning methodology for the identification of violent scenes in cartoon movies. Its potential applications encompass a wide range, including safeguarding children from inappropriate content.

Computer viruses, malicious, and other hostile attacks can affect a computer network. Intrusion detection is a key component of network security as an active defence technology. Traditional intrusion detection systems struggle with issues like poor accuracy, ineffective detection, a high percentage of false positives, and an inability to handle new types of intrusions. To address these issues, we propose a deep learning-based novel method to detect cybersecurity vulnerabilities and breaches in cyber-physical systems. The proposed framework contrasts the unsupervised and deep learning-based discriminative approaches. This paper presents a generative adversarial network to detect cyber threats in IoT-driven IICs networks. The results demonstrate a performance increase of approximately 95% to 97% in terms of accuracy, reliability, and efficiency in detecting all types of attacks with a dropout value of 0.2 and an epoch value of 25. The output of well-known state-of-the-art DL classifiers achieved the highest true rate (TNR) and highest detection rate (HDR) when detecting the following attacks: (BruteForceXXS, BruteForceWEB, DoS_Hulk_Attack, and DOS_LOIC_HTTP_Attack) on the NSL-KDD, KDDCup99, and UNSW-NB15 datasets. It also maintained the confidentiality and integrity of users’ and systems’ sensitive information during the training and testing phases.

In the era of non-volatile memories, the racetrack memory is a promising technology to pack hundreds of bits in a magnetic nanowire. A solid-state read head is grown alongside the nanowire to sense individual bits which are pushed across the head by a shifting force. However, the probabilistic nature of this shifting movement inflicts positional errors. Therefore, robust and low-cost error correcting codes are essential for a reliable alternative in on-chip memories and storage applications. Recent works focus on Varshamov-Tenengolts (VT) codes which can correct all single bit insertions and deletions. However, VT codes are incapable of detecting multiple deletions/insertions. Because a positional error corrupts multiple data words, multi-bit positional error detection is critical for racetrack memories. In this article, we propose a novel positional single error correction and double error detection (P-SECDED) code in the context of racetrack memories with a single read head. In particular, we adopt a postamble-based approach where a VT-encoded codeword appends a carefully selected bit-pattern, stored on the racetrack. We rigorously analyze the limitations of the postamble method, and deduce a criterion for postamble selection. We further provide a methodology to optimize this postamble selection in order to correct all single-bit errors and as much of two-bit errors as possible. Finally, we prove that all incurable two-bit errors are successfully detected. To the best of our knowledge, this work is the first attempt to provide P-SECDED fault-tolerance to three-dimensional racetrack memories which cannot afford multiple read heads.

Neural network models are black boxes in nature. The mechanics behind these black boxes are practically unexplainable. Having the insight into patterns identified by these algorithms can help unravel important properties of the subject in query. These artificial intelligence based algorithms are used in every domain for prediction. This research focuses on patterns formed in network traffic that can be leveraged to identify videos streaming over the network. The proposed work uses a sufficient input subset (SIS) model on two separate video identification techniques to understand and explain the patterns detected by the techniques. The first technique creates the fingerprints of videos on a period-based algorithm to handle variable bitrate inconsistencies. These fingerprints are passed to a convolutional Neural Network (CNN) for pattern recognition. The second technique is based on traffic pattern plot identification that creates a graph of packet size with respect to time for each stream before passing that to a CNN as an image. For model explainability, a sufficient input subset (SIS) model is used to identify features that are sufficient to reach the same prediction under a certain threshold of confidence by the model. The generated SIS of each input sample is clustered using DBSCAN, K-Means, and cosine-based Hierarchical clustering. The clustered SIS highlight the common patterns for each class. The SIS patterns learnt by each model of three individual videos are discussed. Furthermore, these patterns are used to investigate misclassification and provide a rationale behind it to justify the working of the classifier model.

Heating, Ventilation, and Air Conditioning (HVAC) systems account for 59% of energy consumption in domestic buildings and 36% in non-domestic buildings. According to a study, around 39% of occupants are dissatisfied with indoor temperature in non-domestic buildings. To maintain thermal comfort and indoor air quality, HVAC systems are widely used in non-domestic buildings. This research aims to develop energy-efficient control techniques for HVAC systems while ensuring indoor thermal comfort. Three control strategies, namely EnergyPlus model-based Model Predictive Control (MPC), Sliding Mode Control (SMC), and simple ON/OFF control, are employed and compared at the Department of Electrical and Computer Engineering, COMSATS University Islamabad, Lahore Campus. Furthermore, a machine learning-based Predicted Mean Vote (PMV)-based temperature setpoint estimator is designed to ensure occupant thermal comfort. The control techniques estimate the temperature setpoints and supply air temperature of the Variable Air Volume (VAV) system to control indoor room temperature. The energy consumption and indoor thermal comfort of the building are compared under different control techniques. The results show that MPC with PMV-based setpoints consumes 17.20% less energy during winters and 14.67% less energy during summers than a simple ON/OFF controller.

Information-centric networking (ICN) and its fruition, the named data networking (NDN) is a paradigm shift from host-centric address-based communication architecture to the content-centric name-based one. ICN intends to resolve various major issues faced by today’s internet architecture such as privacy, security, consistent routing, and mobility, to name a few. With the massive increase of mobile data traffic in today’s era, mobility is one of the major concerns in networking. On the one hand, ICN realization i.e., the NDN follows a pull-based communication model and natively supports the consumer (end-user) mobility in wired networks by maintaining the forwarding states on intermediate nodes. Nevertheless, the mobile consumer nodes confront issues in wireless networking environments such as excessive energy consumption as a result of request flooding, content retrieval delays due to intermittent connectivity, and bandwidth consumption due to the broadcasting nature of the wireless medium, among others. The producer (content-generator) mobility, on the other hand, was not initially supported in the original architectural design of NDN for both wired and wireless networks. Therefore, to efficiently address the degradation issues incurred by mobile consumer/producer nodes, a plethora of mobility management schemes have been proposed over the recent few years. In this paper, we provided a detailed survey on the existing research efforts—in the context of producer, consumer, and hybrid mobility, that have been proposed in the literature. Moreover, we outlined various research directions considering the role of mobility in futuristic technologies such as artificial intelligence-enabled smart networks, software-defined networking, edge computing, vehicular-fog computing, autonomous driving, semantic communication, and resource-constrained Internet of Things.

Precise and timely diagnosis of Covid-19 and pneumonia is crucial for effective treatment. However, the traditional RT-PCR method is time-consuming, costly, and prone to incorrect results. To address these limitations, a deep ensemble strategy is proposed as a promising alternative to provide more accurate and reliable outcomes. The strategy comprises three main stages: i) pre-processing, ii) salient feature extraction, and iii) training and classification. In the pre-processing step, the authors resize the images to the desired input shape. Data augmentation techniques, such as zooming, nearest full mode, rotation, and flipping, are employed to augment the dataset, thereby improving the training accuracy of the proposed approach. Additionally, the proposed method leverages the capabilities of VGG-16, DenseNet-201, and Efficient-B0 models using transfer-learning techniques to extract deep features from the images. These salient features are then passed through proposed fully connected layers and ensemble classifiers to predict the probability of the given classes. Extensive experiments were conducted on a chest X-ray image dataset, demonstrating that the proposed system outperforms contemporary techniques in terms of precision, recall, F1-score, and accuracy (acc). The proposed method obtained 97% of acc, while 96%, 95%, and 97% pre, rec, and F1-score respectively. In conclusion, this study presents a valuable contribution to medical image diagnosis using an AI-based deep ensemble strategy. The proposed approach offers a promising solution for accurate and efficient diagnosis of Covid-19 and pneumonia, assisting healthcare professionals in making informed decisions for optimal treatment outcomes.

Deep learning has found widespread application in diabetic retinopathy (DR) screening, primarily for lesion detection. However, this approach encounters challenges such as information loss due to convolutional operations, shape uncertainty, and the high similarity between different lesions types. These factors collectively hinder the accurate segmentation of lesions. In this research paper, we introduce a novel dual-branch U-Net architecture, referred to as Dual-Branch (DB)-U-Net, tailored to address the intricacies of small-scale lesion segmentation. Our approach involves two branches: one employs a U-Net to capture the shared characteristics of lesions, while the other utilizes a modified U-Net, known as U2Net, equipped with two decoders that share a common encoder. U2Net is responsible for generating probability maps for lesion segmentation as well as corresponding boundary segmentation. DB U-Net combines the outputs of U2Net and U-Net as a dual branch, concatenating their segmentation maps to produce the final result. To mitigate the challenge of imbalanced data, we employ the Dice loss as a loss function. We evaluate the effectiveness of our approach on publicly available datasets, including DDR, IDRiD, and E-Ophtha. Our results demonstrate that DB U-Net achieves AUPR values of 0.5254 and 0.7297 for Microaneurysms and soft exudates segmentation, respectively, on the IDRiD dataset. These results outperform other models, highlighting the potential clinical utility of our method in identifying retinal lesions from retinal fundus images.

Green energy can help in protecting the environment. Moreover, its continuous supply increases the quality of life and indeed the economic development of a country. The power sector in Pakistan is continuously under stress due to the imbalance between the demand and supply of energy. Pakistan has abundant renewable energy resources, i.e., solar, hydro, wind, etc., which are the main elements of green energy. This study first evaluates the existing power sector in Pakistan. Then, we proposed a peer-to-peer energy trading framework that helps in reducing the stress on the power sector in Pakistan by meeting the local energy demands of the consumers with the help of local energy generation. In the proposed peer-to-peer energy trading market, a novel method for determining the uniform energy trading price is proposed. This proposed pricing method increases the utilities of the market participants i.e., saving in energy bills for consumers and profitability for the sellers. The proposed study assumes that solar energy is provided from the energy producer side. Solar energy penetration on various ratios starting from 14% to 35% is tested on environment and consumer satisfaction levels. We conducted comprehensive experiments to validate the proposed method and the results suggest that a 35% penetration of solar in each subdivision can be helpful to decrease the current stress on Pakistans’ power sector. Furthermore, it also helps in reducing the carbon emission footprint.

In most of the medical treatments, intravenous catheterization is considered as a first crucial phase, in which health practitioners find the superficial vein to conduct blood sampling or medication procedures. In some patients these veins are hard to localize due to different physiological characteristics such as dark skin tone, scars, vein depth etc., which mostly results in multiple attempts for needle insertion. This causes pain, delayed treatment, bleeding, and even infections. To reduce these risks, an automated veins detection method is needed that can efficiently segment the veins and produce realistic results for cannulation purposes. For this purpose, many imaging modalities such as Photoacoustic, Trans-illumination, ultrasound, Near-Infrared etc. are used. Among these modalities Near-Infrared (NIR) imaging modality is considered most suitable due to its lower cost and non-ionizing nature. Over the past few years, subcutaneous veins localization using NIR have attracted increasing attention in the field of health care and biomedical engineering. Therefore, the proposed research work is based on NIR images for forearm subcutaneous veins segmentation. This paper presents a deep learning-based approach called Generative Adversarial Networks (GAN) for segmentation/localization of forearm veins. GANs have shown exciting results in the medical imaging field recently. These are used for unsupervised feature learning and image-to-image translation applications. These networks generate realistic results by learning data mapping from one state to another. Since GANs can produce state of the art results, therefore we have proposed a Pix2Pix GAN for segmentation of forearm veins. The proposed algorithm is trained and tested on forearm subcutaneous veins image dataset. The proposed model outperforms traditional approaches with the mean accuracy and sensitivity, values obtained are 0.971 and 0.862 respectively. The dice coefficient and Intersection over Union (IoU) score are respectively 0.962 and 0.936 which are better than the state-of-the-art methods.

Meeting electricity demand by the generation of electricity from locally distributed energy sources has gained much success over the years. Among different frameworks for such renewable generation and consumption, peer-to-peer (P2P) markets have proved to be an efficient solution. As the pricing mechanism is an integral part of P2P markets, optimal price determination for electricity trading that ensures the profitability of the participants is the key to success in such markets. In addition to profitability, the pricing mechanism should be able to incorporate users’ reserved prices and grid supply uncertainty to be implementable in developing countries. To achieve this objective and based on participants’ preferences, an effective game-theoretic model is proposed to formulate the trading pairs among consumers and sellers. Then, keeping in view the participants’ reserved prices for electricity trading, an effective and novel method based on the game-theoretic approach is proposed to determine the electricity price in the direct P2P electricity market. The proposed model is evaluated on a market having 22 participants. Among these, 11 participants act as electricity consumers, and the other 11 act as sellers. Simulation results show that the proposed algorithm is more effective as it further reduces the electricity bills for consumers from 5% to 8% and increases the revenues of sellers from 13% to 15% as compared to other proposed mid-range auction and uniform pricing models.

The online retrieval of clothes-related images is crucial because finding the exact items, like the query image from a large amount of data, is highly challenging. However, significant clothes image variations degrade visual search retrieval accuracy. Another problem with retrieval accuracy is the high dimensions of feature vectors obtained from pre-trained deep CNN models. This research aims to enhance clothes retrieval training and test accuracy by using two different means. Initially, features are extracted using the modified AlexNet (M-AlexNet) with slight modification. The ReLU activation function is replaced with a self-regularized Mish activation function because of its non-monotonic nature. The M-AlexNet with Mish is trained on the CIFAR-10 dataset using the SoftMax classifier. Another contribution is to reduce the dimensions of feature vectors obtained from M-AlexNet. The dimensions of features are reduced by selecting the top $k$ -ranked features and removing some of the different features using the proposed Joint Shannon’s Entropy Pearson Correlation Coefficient (JSE-PCC) technique to enhance the clothes retrieval performance. To calculate the efficacy of suggested methods, the comparison is performed with other deep CNN models such as baseline AlexNet, VGG-16, VGG-19, and ResNet50 on DeepFashion2, MVC, and the proposed Clothes Image Dataset (CID). Extensive experiments indicate that AlexNet with Mish attains 85.15%, 82.04%, and 83.65% accuracy on DeepFashion2, MVC, and 83.65% on CID datasets. Hence, M-AlexNet and the proposed feature selection technique surpassed the results with a margin of 5.11% on DeepFashion2, 1.95% on MVC, and 3.51% on CID datasets.

Dynamic coverage is one of the fundamental problems in multi-agent systems (MASs), and is related to optimal placement of nodes to observe a physical space. In a typical coverage problem, a set of targets are required to be monitored. The problem becomes more challenging when the targets are allowed to move as well. Efficient coverage control by mobile agents in a specific area poses many challenges, such as optimal coverage of all targets, dynamic redeployment of agents as targets change their location, trajectory control of each agent during redeployment and determining the number of mobile agents to cover specific targets. In particular, for dynamic coverage problems, agents are deployed to provide coverage to the mobile targets and the agents dynamically redeploy themselves in such a way that they provide maximum coverage to targets not only when they are stationary but also when they are in motion. In many scenarios, such as disaster recovery or public event coverage, dynamic behavior of agents to reach to the next optimal position, plays an important role in determining the performance of the system. In this paper, we propose an augmented Lagrangian based algorithm, which provides a mechanism to control the trajectory of agents to reach the optimal position. By adjusting the gain parameters of the proposed algorithm, we achieve negligible overshoot in response to fast dynamics that is not possible by using conventional Lagrangian. Also, the proposed algorithm is close to the optimal trajectory. Thus, by using the proposed algorithm, we can improve the dynamic performance without compromising the optimal deployment of the agents. The numerical evaluation results show significant improvement in dynamic performance for an example scenario of an MAS.

Online learning environments (OLE) including learning management systems (LMS) and massive open online courses (MOOCs) are gaining popularity as the best modern alternate solutions available for education in the current era. The luxury to learn irrespective of geographical and temporal restrictions makes it an attractive resource. At the start of 2020, the global pandemic enforced social distance practice worldwide, changing the work environment dynamics, leaving options like online trading, work from home, and online education. Online learning environments gained particular attention in the educational sector, where users could access the online learning resources to fulfil their academic requirements during the lockdown. From massively available content such as MOOC, learners are overwhelmed with the available choices. In this scenario, recommender systems (RS) come to the rescue to help the learner make appropriate choices for completing the enrolled course. There is tremendous scope and a multitude of opportunities available for researchers to focus on this domain. An exhaustive analysis is required to spotlight the opportunities in this realm. Various studies have been performed to provide such solutions in multiple areas of the MOOC recommendation systems (MOOCRS) such as course recommendation, learner peer recommendation, resource recommendations, to name a few. This is a compendious study into the research conducted in this area, identifying 670 articles out of 116 selected for analysis published from 2013 to 2021. It also highlights multiple areas in MOOC, where the recommendation is required, as well as technologies used by other researchers to provide solutions over time.

This paper proposes a novel improved polar bear optimization (IPBO) algorithm and employs it along with polar bear optimization (PBO) and chaotic population-based variants of polar bear optimization algorithm to solve combined economic emission dispatch (CEED) problem. PBO is a meta-heuristic technique inspired by the hunting mechanisms of polar bears in harsh arctic regions based only on their sense of sight. Polar bears in nature exhibits hunting of prey not only on their sight but also on their keen sense of smell. Hence, a novel improved variant of PBO which enhances its operation by equipping it with tracking capabilities utilizing polar bears sense of smell has been proposed in this study. The validity of novel IPBO is tested through 5 benchmark functions and 140 units Korean ED problem. Furthermore, the impact of different population initialization methods is also observed on the capabilities of conventional PBO. The proposed chaotic population based PBO, improved PBO (IPBO) and PBO are employed to solve IEEE 3 unit and 6-unit CEED problem. CEED is a multi-objective power system optimization problem with conflicting objectives of cost and emission. The simulations performed undertake each objective individually as well as collectively. The results achieved by each technique are analyzed statistically through Wilcoxon rank sum test (WRST), probability density function and cumulative density function. Both the statistical and numerical analysis of results showcase the strength of each solution technique as well as their ability to improve cost and emissions in the solution of CEED problem.

The botnet attack is a multi-stage and the most prevalent cyber-attack in the Internet of Things (IoT) environment that initiates with scanning activity and ends at the distributed denial of service (DDoS) attack. The existing studies mostly focus on detecting botnet attacks after the IoT devices get compromised, and start performing the DDoS attack. Similarly, the performance of most of the existing machine learning based botnet detection models is limited to a specific dataset on which they are trained. As a consequence, these solutions do not perform well on other datasets due to the diversity of attack patterns. Therefore, in this work, we first produce a generic scanning and DDoS attack dataset by generating 33 types of scan and 60 types of DDoS attacks. In addition, we partially integrated the scan and DDoS attack samples from three publicly-available datasets for maximum attack coverage to better train the machine learning algorithms. Afterwards, we propose a two-fold machine learning approach to prevent and detect IoT botnet attacks. In the first fold, we trained a state-of-the-art deep learning model, i.e., ResNet-18 to detect the scanning activity in the premature attack stage to prevent IoT botnet attacks. While, in the second fold, we trained another ResNet-18 model for DDoS attack identification to detect IoT botnet attacks. Overall, the proposed two-fold approach manifests 98.89% accuracy, 99.01% precision, 98.74% recall, and 98.87% f1-score to prevent and detect IoT botnet attacks. To demonstrate the effectiveness of the proposed two-fold approach, we trained three other ResNet-18 models over three different datasets for detecting scan and DDoS attacks and compared their performance with the proposed two-fold approach. The experimental results prove that the proposed two-fold approach can efficiently prevent and detect botnet attacks as compared to other trained models.

Neuromorphic computing offers parallel data processing and low energy consumption and can be useful to replace conventional von Neumann computing. Memristors are two-terminal devices with varying conductance that can be used as synaptic arrays in hardware-based neuromorphic devices. In this research, we extensively investigate the analog symmetric multi-level switching characteristics of zinc tin oxide (ZTO)-based memristor devices for neuromorphic systems. A ZTO semiconductor layer is introduced between a complementary metal-oxide-semiconductor (CMOS) compatible Ni top electrode and a highly doped poly-Si bottom electrode. A variety of bio-realistic synaptic features are demonstrated, including long-term potentiation (LTP), long-term depression (LTD), and spike timing-dependent plasticity (STDP). The Ni/ZTO/Si device in which the adjustment of the number of states in conductance is realized by applying different pulse schemes is highly suitable for hardware-based neuromorphic applications. We evaluate the pattern recognition accuracy by implementing a system-level neural network simulation with ZTO-based memristor synapses. The density of states (DOS) and charge density plots reveal that oxygen vacancies in ZTO assist in generating resistive switching in the Ni/ZTO/Si device. The proposed ZTO-based memristor composed of metal-insulator-semiconductor (MIS) structure is expected to contribute to future neuromorphic applications through further studies.

Electroencephalography-based sleepiness detection system (ESDS) is a brain-computer interface that evaluates a driver's sleepiness level directly from cerebral activity. The goals of ESDS research are to estimate and produce a timely warning to prevent declines in performance efficiency and to inhibit sleepiness-related accidents. We first, review different types of measures used in sleepiness detection systems (SDSs) and presents their advantages and drawbacks. Second, the review includes several techniques proposed in ESDSs to optimize the number of EEG electrodes, increasing the sleepiness level resolution and incorporation of circadian information. Finally, the review discusses future direction that can be considered in the development of ESDS.

Human brain has a complex structure with the billions of neurons, so it is a difficult and challenging task to predict the behavior of human brain. Different methods and classifiers are used to measure and classify the brain activities with higher accuracy and reliability. In this paper, instead of using mostly used classifier (support vector machine), prediction of the brain activity is done by estimating the match score densities. This method is based on likelihood ratio test which helps in finding the optimal combination of match scores. The distributions of match scores are modeled for different classes based on density score fusion in which the densities of different classes are estimated from the training data set and match scores are found by fusing the estimated densities with the testing data. The fusion is done with the data extracted from distributed activation patterns using multivariate pattern analysis (MVPA) against a visual task. MVPA is an intense strategy which helps in better understanding of the human brain. The match score-based technique is used in different biometric systems but never been used for the prediction of brain activity. In order to test the performance of proposed method, prediction accuracy is compared with the support vector machine using two data sets of different modalities, one is electroencephalography (EEG) and the other is functional magnetic resonance imaging (fMRI). The results show that the proposed method predicts the novel data with improved accuracy of 66.1% and 69.3% compared with support vector machine which have 64.15% and 65.7% for fMRI and EEG data sets, respectively.

Driving distraction is a topic of great interest in the transport safety-research community, because it is now a primary cause of road accidents. A recent report has revealed that distraction is more alarming than previously thought, and a suitable measurement to effectively detect distraction is required. Most agree that driving distraction actually comprises the simultaneous interaction of two or more types of distraction. The purpose of this paper is, therefore, to determine the promising method for measuring visual cognitive distraction. We discuss the five common measurement methods for visual and cognitive driving distraction, which include driving performance, driver physical measures, driver biological measures, subjective reports, and hybrid measures. Hybrid measurement of driver's physical measures (e.g., eye movement) and driver's biological measures (e.g., electroencephalogram) is better than other methods at detecting types of visual cognitive distraction. This new perspective on measurement methods will help the field of transport safety to determine the best means of detecting and measuring the effect of visual cognitive distraction.