Search

In recent years, large language models (LLMs) have been employed significantly in different domains of computing education. Nevertheless, these models have been focused on essential adherence to their integration as coding assistants in computing education. However, attention has been switched to thoroughly examining and analyzing LLM behavior, particularly in computing education for programming tasks such as code generation, code explanation, and programming error message explanation. Therefore, it becomes imperative to understand their behavior to examine potential pitfalls. This article addresses this gap systematically and details how different LLM-based coding chatbots, such as ChatGPT, Codex, Copilot, and others, react to various coding inputs within computing education. To achieve this objective, we collected and analyzed articles from 2021 to 2024, and 72 studies were thoroughly examined. These objectives include investigating the existing limitations and challenges associated with utilizing these systems for coding tasks, assessing their responses to prompts containing coding syntax, examining the impact of their output on student learning, and evaluating their performance as debugging tools. The findings of this review highlight that it is premature to incorporate these systems into computing education due to their limitations that may limit their effectiveness as comprehensive coding assistants for computer science students. These limitations include issues with handling prompts containing code snippets, potential negative impacts on student learning, limited debugging capabilities, and other ineffectiveness. The finding also reports multiple research directions that can be considered in future research related to LLMs in computing education.

The Know Your Customer (KYC) process is a fundamental prerequisite for any financial institution’s compliance with the regulatory framework. Blockchain technology has emerged as a revolutionary solution to enhance the effectiveness of the KYC procedure. It ensures that the KYC process is transparent, secure, and immutable, thereby offering a robust solution to combat fraudulent activities. The potential of blockchain technology in revolutionizing the KYC process has been acknowledged globally. Blockchain technology provides a decentralized platform for storing customer data, enabling financial institutions to access the information seamlessly. Using ethereum blockchain technology in KYC procedures can enhance the efficiency of financial institutions, significantly reducing the time and cost associated with the process. This work aims to provide a viable and sustainable solution to the challenges that banks experience in implementing KYC procedures and onboarding new customers. The proposed solution involves the central bank maintaining a comprehensive register of all registered banks while closely monitoring their adherence to the existing regulations governing KYC and customer acquisition.

Human Action Recognition (HAR) is a vital area of computer vision with diverse applications in security, healthcare, and human-computer interaction. Addressing the challenges of HAR, particularly in dynamic and complex environments, is essential to advancing this field. The strength of the HADE framework is its carefully curated dataset, which was primarily derived from smartphone camera footage. This dataset encompasses a wide range of human actions captured in various settings, providing a robust foundation for training our novel HAR models, HADE I and HADE II. These models have been specifically designed and optimized for parallel processing on GPUs, showing significant improvements in the efficiency of both training and inference processes. Through a comprehensive evaluation, the HADE framework demonstrated a remarkable improvement in HAR accuracy, achieving 83.57% accuracy on our custom dataset. This marks a considerable enhancement over existing methodologies and underscores the efficacy of the HADE approach in accurately interpreting complex human actions. The framework’s potential applicability in healthcare in the domain of neurological patient care is particularly noteworthy, where it can aid in early detection and facilitate personalized treatment plans. Future research should focus on expanding the range of actions covered by HAR and exploring avenues for real-time processing. The introduction of the HADE framework not only makes a substantial contribution to the field of computer vision but also paves the way for its practical application across various sectors.

During the last few decades, agile methodologies have become the most widely used software development methods. Agile methodologies provide great customer satisfaction and fast product delivery at the low cost. The low cost and customer satisfaction make agile methods highly attractive. Agile methods were designed and used, in its early days, for small-scale projects. There are many challenges in applying agile methods for large-scale projects as determined by some previous studies. The objective of this research is to identify the practices of De-motivators in adopting agile projects at a large scale from management point of view by employing a systematic literature review (SLR).In the review process, a total of 72 practices were discovered. De-motivator factors have been identified and ranked, through the analytical hierarchical process, through SLR in our previous study (Abrar et al., 2020). Analytical hierarchical processing (AHP) is a well-known method used for multi-criteria decisions implemented by Satty (2023). In this study AHP is used to prioritize de-motivators and their categories based on their relative importance. The prioritized de-motivators and their categories provide a strong background to the software project manager and practitioners for adopting Agile Software Development in large-scale projects.

One approach to therapy and training for the restoration of damaged muscles and motor systems is rehabilitation. EEG-assisted Brain-Computer Interface (BCI) may assist in restoring or enhancing ‘lost motor abilities in the brain. Assisted by brain activity, BCI offers simple-to-use technology aids and robotic prosthetics. This systematic literature review aims to explore the latest developments in BCI and motor control for rehabilitation. Additionally, we have explored typical EEG apparatuses that are available for BCI-driven rehabilitative purposes. Furthermore, a comparison of significant studies in rehabilitation assessment using machine learning techniques has been summarized. The results of this study may influence policymakers’ decisions regarding the use of EEG equipment, particularly wireless devices, to implement BCI technology. Moreover, the literature review results offer suggestions for further study and new research areas. We plan to identify the additional characteristics of each EEG equipment and determine which one is most suited for each industry by measuring the user experience based on various devices in future research.

Finding the precise and accurate location of devices on road networks is challenging in remote areas with poor internet connectivity and Global Positioning System coverage. Navigation applications that completely depend on the internet and reference spatial data for location identification and mapping do not perform well in case of frequent internet disconnection. These reference spatial data sources have many associated challenges like large size, errors in data, and restricted access. To address these challenges, this paper provides an approach for localization and routing using self-generated reference data using likelihood estimation. According to the proposed approach, the trajectory information is used to create the reference data in the format of Comma Separated Values (CSV). This reference data is first analyzed for quality issues and then used for navigation purposes. Further for the localization Sugeno Fuzzy Model is used as a fuzzy inference system for the initial localization and subsequent mapping of the location. The proposed approach is validated using an Android application on seven predefined routes. According to the performed result analysis, the proposed fuzzy logic-based approach is able to provide location identification with 98.9 percent accuracy with a root mean square error value of 3 percent.

Neuropeptides (NPs) are a kind of neuromodulator/ neurotransmitter that works as signaling molecules in the central nervous system, and perform major roles in physiological and hormone regulation activities. Recently, machine learning-based therapeutic agents have gained the attention of researchers due to their high and reliable prediction results. However, the unsatisfactory performance of the existing predictors is due to their high execution cost and minimum predictive results. Therefore, the development of a reliable prediction is highly indispensable for scientists to effectively predict NPs. In this study, we presented an automatic and computationally effective model for identifying of NPs. The evolutionary information is formulated using a bigram position-specific scoring matrix (Bi-PSSM) and K-spaced bigram (KSB). Moreover, for noise reduction, a discrete wavelet transform (DWT) is utilized to form Bi-PSSM_DWT and KSB_DWT based high discriminative vectors. In addition, one-hot encoding is also employed to collect sequential features from peptide samples. Finally, a multi-perspective feature set of sequential and embedded evolutionary information is formed. The optimum features are chosen from the extracted features via Shapley Additive exPlanations (SHAP) by evaluating the contribution of the extracted features. The optimal features are trained via six classification models i.e., XGB, ETC, SVM, ADA, FKNN, and LGBM. The predicted labels of these learners are then provided to a genetic algorithm to form an ensemble classification approach. Hence, our model achieved a higher predictive accuracy of 94.47% and 92.55% using training sequences and independent sequences, respectively. Which is $\sim $ 3% highest predictive accuracy than present methods. It is suggested that our presented tool will be beneficial and may execute a substantial role in drug development and research academia. The source code and all datasets are publicly available at https://github.com/shahidawkum/Target-ensC_NP.

Amyloid proteins (AMYs) are usually an aggregate of insoluble fibrous that have major pathogenic effects on various tissues. However, its abnormal deposition may lead to several diseases i.e., Parkinson’s, Alzheimer’s, and type 2 diabetes. In addition, AMYs form amyloid aggregates when they are in a misfolded state. Therefore, it is crucial to accurately predict AMYs and their pathogenic characteristics. Various computational predictors have been presented for the accurate prediction of AMYs. Although, the effectiveness of these predictors is unsatisfactory due to their low generalization abilities and high training cost. In this attempt, we proposed an intelligent computational predictor for the accurate prediction of AMYs. The novel embedded evolutionary features are gathered using K-separated bigrams, and the Filter method into the evolutionary descriptors. Moreover, DDE-based enhanced frequency coupling information are gathered from the Amyloid sequences. Additionally, a multi-model vector is obtained by combining the features of the applied formulation techniques. To reduce the computational cost of the proposed model, the eXtreme Gradient Boosting-Recursive Feature Elimination (XGB-RFE) based high-ranked features are selected from the heterogeneous vector. In the next part, the optimal features are evaluated via several learners, i.e., XGBoost (XGB), Light Gradient Boosted Machine (LGBM), Support Vector Machine (SVM), Adaboost (ada), and Extra Trees classifier (ETC),. The proposed model reported an improved predictive prediction accuracy of 93.10% using training sequences and 89.67% using independent sequences, respectively. Which is $\sim 4$ % higher training accuracy than existing predictors. It is anticipated that our predictive approach will be useful for scientists and might play a key role in drug development and academic research.

A tremendous amount of unstructured data, such as comments, opinions, and other sorts of data is generated in real-time with the growth of web 2.0. Due to the unstructured nature of the data, building an accurate predictive model for sentiment analysis remains challenging. While various DNN architectures have been applied to sentiment analysis with encouraging results, they treat various features equally and suffer from high-dimensional feature space. Moreover, state-of-the-art methods cannot properly utilize semantic and sentiment knowledge to extract meaningful relevant contextual sentiment features. This paper proposes a sentiment and context-aware hybrid DNN model with an attention mechanism that intelligently learns and highlights salient features of relevant sentiment context in the text. We first use integrated wide coverage sentiment lexicons to identify text sentiment features then leverage bidirectional encoder representation from transformers to produce sentiment-enhanced word embeddings for text semantic extraction. After that, the proposed approach adapts the BiLSTM to capture both word order/contextual text semantic information and the long-dependency relation in the word sequence. Our model also employs an attention mechanism to assign weights to features and give greater significance to salient features in the word sequence. Finally, CNN is utilized to reduce the dimensionality of feature space and extract the local key features for sentiment analysis. The effectiveness of the proposed model is evaluated on real-world benchmark datasets demonstrating that the proposed model significantly improves the accuracy of existing text sentiment classification.

Sentiment analysis has been instrumental in developing artificial intelligence when applied to various domains. However, most sentiments and emotions are temporal and often exist in a complex manner. Several emotions can be experienced at the same time. Instead of recognizing only categorical information about emotions, there is a need to understand and quantify the intensity of emotions. The proposed research intends to investigate a quantum-inspired approach for quantifying emotional intensities in runtime. The inspiration comes from manifesting human cognition and decision-making capabilities, which may adopt a brief explanation through quantum theory. Quantum state fidelity was used to characterize states and estimate emotion intensities rendered by subjects from the Amsterdam Dynamic Facial Expression Set (ADFES) dataset. The Quantum variational classifier technique was used to perform this experiment on the IBM Quantum Experience platform. The proposed method successfully quantifies the intensities of joy, sadness, contempt, anger, surprise, and fear emotions of labelled subjects from the ADFES dataset.

Diabetic retinopathy (DR) is a disease that damages retinal blood vessels and leads to blindness. Usually, colored fundus shots are used to diagnose this irreversible disease. The manual analysis (by clinicians) of the mentioned images is monotonous and error-prone. Hence, various computer vision hands-on engineering techniques are applied to predict the occurrences of the DR and its stages automatically. However, these methods are computationally expensive and lack to extract highly nonlinear features and, hence, fail to classify DR’s different stages effectively. This paper focuses on classifying the DR’s different stages with the lowest possible learnable parameters to speed up the training and model convergence. The VGG16, spatial pyramid pooling layer (SPP) and network-in-network (NiN) are stacked to make a highly nonlinear scale-invariant deep model called the VGG-NiN model. The proposed VGG-NiN model can process a DR image at any scale due to the SPP layer’s virtue. Moreover, the stacking of NiN adds extra nonlinearity to the model and tends to better classification. The experimental results show that the proposed model performs better in terms of accuracy, computational resource utilization compared to state-of-the-art methods.

The super packed functionalities and artificial intelligence (AI)-powered applications have made the Android operating system a big player in the market. Android smartphones have become an integral part of life and users are reliant on their smart devices for making calls, sending text messages, navigation, games, and financial transactions to name a few. This evolution of the smartphone community has opened new horizons for malware developers. As malware variants are growing at a tremendous rate every year, there is an urgent need to combat against stealth malware techniques. This paper proposes a visualization and machine learning-based framework for classifying Android malware. Android malware applications from the DREBIN dataset were converted into grayscale images. In the first phase of the experiment, the proposed framework transforms Android malware into fifteen different image sections and identifies malware files by exploiting handcrafted features associated with Android malware images. The algorithms such as Gray Level Co-occurrence Matrix-based (GLCM), Global Image deScripTors (GIST), and Local Binary Pattern (LBP) are used to extract the handcrafted features from the image sections. The extracted features were further classified using machine learning algorithms like K-Nearest Neighbors, Support Vector Machines, and Random Forests. In the second phase of the experiment, handcrafted features were fused with CNN features to form the feature fusion strategy. The classification performance was evaluated against every malware image file section. The results obtained using the Feature Fusion strategy are compared with handcrafted features results. The experiment results conclude to the fact that Feature Fusion-SVM model is most suited for the identification and classification of Android malware using the certificate and Android Manifest (CR + AM) malware images. It attained an high accuracy of 93.24%.

Nanoscale devices, also called nanomachines, form communication networks and cooperate with each other so that they can be used to perform complicated tasks. Such networks of nanodevices, named nanonetworks, envisioned to serve the functionality and performance of today’s Internet. This paper presents a comparative review of the state-of-the-art electromagnetic (EM) nanonetworks highlighting their potentials and challenges in a comprehensive manner. We first introduce the promising areas of applications of nanonetworks; therein, we explain how it can be useful in biomedical fields, environmental domains, consumer products, military systems, and on-chip wireless communications. Then, the survey focuses on the basic principles of fundamental physical layer issues enabling nanonetworks; the discussion includes frequency bands, modulation and demodulation, and EM properties of nanoparticles. Subsequently, the study provides an overview of transmission characteristics including channels, channel coding, and energy constraint nature of nanonetworks. Furthermore, we provide an in-depth discussion on nanoantenna highlighting its variants and their characteristics; give an overview of network layer issues; and discuss the security issues in EM nanonetworks. The study argues that despite the significant recent development of EM communication as one of the most desired modes of nano communications, the limited capabilities of nanomachines introduce a new set of challenges and unique requirements and pose unseen characteristics that need to be deliberately addressed. On that, the review finally provides a critical discussion on the applicability of EM mode for nano communication networks highlighting the future challenges with a set of perspectives of possible solutions.

A cloudlet is an emerging computing paradigm that is designed to meet the requirements and expectations of the Internet of things (IoT) and tackle the conventional limitations of a cloud (e.g., high latency). The idea is to bring computing resources (i.e., storage and processing) to the edge of a network. This article presents a taxonomy of cloudlet applications, outlines cloudlet utilities, and describes recent advances, challenges, and future research directions. Based on the literature, a unique taxonomy of cloudlet applications is designed. Moreover, a cloudlet computation offloading application for augmenting resource-constrained IoT devices, handling compute-intensive tasks, and minimizing the energy consumption of related devices is explored. This study also highlights the viability of cloudlets to support smart systems and applications, such as augmented reality, virtual reality, and applications that require high-quality service. Finally, the role of cloudlets in emergency situations, hostile conditions, and in the technological integration of future applications and services is elaborated in detail.

Face segmentation represents an active area of research within the bio-metric community in particular and the computer vision community in general. Over the last two decades, methods for face segmentation have received increasing attention due to their diverse applications in several human-face image analysis tasks. Although many algorithms have been developed to address the problem, face segmentation is still a challenge not being completely solved, particularly for images taken in wild, unconstrained conditions. In this paper, we present a comprehensive review of face segmentation, focusing on methods for both the constrained and unconstrained environmental conditions. The article illustrates the advantages and disadvantages of previously proposed methods in state-of-the-art (SOA). The approaches presented comprise the seminal works on face segmentation and culminating in SOA approaches of the deep learning architecture. An extensive comparison of the previous approaches is intuitively presented, with a discussion of the potential directions for future research on the topic. We believe this comprehensive review and recap will contribute to a number of application domains, and will augment the knowledge of the research community.

In intelligent transportation system, smart vehicles are equipped with a variety of sensing devices those offer various multimedia applications and services related to smart driving assistance, weather forecasting, traffic congestion information, road safety alarms, and many entertainment and comfort-related applications. These smart vehicles produce a massive amount of multimedia related data that required fast and real-time processing which cannot be fully handled by the standalone onboard computing devices due to their limited computational power and storage capacities. Therefore, handling such multimedia applications and services demanded changes in the underlaying networking and computing models. Recently, the integration of vehicles with cloud computing is emerged as a challenging computing paradigm. However, there are certain challenges related to multimedia contents processing, (i.e., resource cost, fast service response time, and quality of experience) that severely affect the performance of vehicular communication. Thus, in this paper, we propose an efficient resource allocation and computation framework for vehicular multimedia cloud computing to overcome the aforementioned challenges. The performance of the proposed scheme is evaluated in terms of quality of experience, service response time, and resource cost by using the Cloudsim simulator.

Facial expressions convey exhaustive information about human emotions and the most interactive way of social collaborations, despite differences in ethnicity, culture, and geography. Due to cultural differences, the variations in facial structure, facial appearance, and facial expression representation are the main challenges to the facial expression recognition system. These variations necessitate the need for multicultural facial expression analysis. This study presents several computational algorithms to handle these variations to get high expression recognition accuracy. We propose an artificial neural network-based ensemble classifier for multicultural facial expression analysis. The facial images from the Japanese female facial expression database, Taiwanese facial expression image database, and RadBoud faces database are combined to form a multi-culture facial expression dataset. The participants in the multicultural dataset originate from four ethnic regions including Japanese, Taiwanese, Caucasians, and Moroccans. Local binary pattern, uniform local binary pattern, and principal component analysis are applied for facial feature representation. Experimental results prove that facial expressions are innate and universal across all cultures with minor variations.

The prevalence of diabetes is rising globally. Diabetes patients need continuous monitoring, and to achieve this objective, they have to be engaged in their healthcare management process. Mobile health (MH) is an information and communications technology trend to empower chronically ill patients in a smart environment. Discussing the current state of MH technologies is required in order to address their limitations. Existing review articles have evaluated the MH literature based on applicability and level of adoption by patients and healthcare providers. Most of these reviews asserted that MH apps and research have not reached a stable level yet. To the best of our knowledge, there is no clear description of solutions to these problems. In addition, no one has investigated and analyzed MH in its contextual environment in a detailed way. We conducted a comprehensive survey of MH research on diabetes management articles published between 2011 and September 27, 2017. In this survey, we discuss current challenges in MH, along with research gaps, opportunities, and trends. Our literature review searched three academic databases (ScienceDirect, IEEE Xplore, and SpringerLink). A total of 60 articles were analyzed, with 30% from ScienceDirect, 38% from IEEE Xplore, and 32% from SpringerLink. MH was analyzed in the context of the electronic health record (EHR) ecosystem. We consider dimensions such as clinical decision support systems, EHRs, cloud computing, semantic interoperability, wireless body area networks, and big data analytics. We propose specific metrics to analyze and evaluate MH from each of these dimensions. A comprehensive analysis of the literature from this viewpoint is valuable for both theoretical and developmental progress. This paper provides a critical analysis of challenges that have not been fully met and highlights directions for future research that could improve MH applicability.

This paper presents an automatic content-based image retrieval (CBIR) system for brain tumors on T1-weighted contrast-enhanced magnetic resonance images (CE-MRI). The key challenge in CBIR systems for MR images is the semantic gap between the low-level visual information captured by the MRI machine and the high-level information perceived by the human evaluator. The traditional feature extraction methods focus only on low-level or high-level features and use some handcrafted features to reduce this gap. It is necessary to design a feature extraction framework to reduce this gap without using handcrafted features by encoding/combining low-level and high-level features. Deep learning is very powerful for feature representation that can depict low-level and high-level information completely and embed the phase of feature extraction in self-learning. Therefore, we propose a deep convolutional neural network VGG19-based novel feature extraction framework and apply closed-form metric learning to measure the similarity between the query image and database images. Furthermore, we adopt transfer learning and propose a block-wise fine-tuning strategy to enhance the retrieval performance. The extensive experiments are performed on a publicly available CE-MRI dataset that consists of three types of brain tumors (i.e., glioma, meningioma, and pituitary tumor) collected from 233 patients with a total of 3064 images across the axial, coronal, and sagittal views. Our method is more generic, as we do not use any handcrafted features; it requires minimal preprocessing, tested as robust on fivefold cross-validation, can achieve a fivefold mean average precision of 96.13%, and outperforms the state-of-the-art CBIR systems on the CE-MRI dataset.

In traditional learning environments, it is easy for a teacher to get an accurate and deep understanding about how students are learning and undertaking tasks. This results in teacher understanding about each student’s learning preferences and behavior, which exhibits, for instance, students’ learning styles and affective states. On the other hand, identification of learning styles and affective states in web-based learning environments is quite challenging. The existing approaches for the identification of learning styles such as questionnaire is not without limitations. Similarly, affective states identification approaches mentioned in the literature indicate several shortcomings. This paper proposes an automatic approach for the identification of learning styles and affective states in web-based Learning Management Systems (LMSs). The unique feature of this approach is that it is generic in nature. Using this approach, the students learning styles and affective states are calculated automatically from their learning preferences and behavior within a course. Evaluation of this approach was performed by following a study with 81 students. The results of the study were then compared with the learning styles and affective states questionnaires, which demonstrate that the suggested approach is more appropriate for the identification of learning styles and affective states. Therefore, using this approach, a tool (AsLim) has been developed and can be used by the teachers for the identification of learning styles and affective states of their students.

Diabetes is a serious chronic disease. The importance of clinical decision support systems (CDSSs) to diagnose diabetes has led to extensive research efforts to improve the accuracy, applicability, interpretability, and interoperability of these systems. However, this problem continues to require optimization. Fuzzy rule-based systems are suitable for the medical domain, where interpretability is a main concern. The medical domain is data-intensive, and using electronic health record data to build the FRBS knowledge base and fuzzy sets is critical. Multiple variables are frequently required to determine a correct and personalized diagnosis, which usually makes it difficult to arrive at accurate and timely decisions. In this paper, we propose and implement a new semantically interpretable FRBS framework for diabetes diagnosis. The framework uses multiple aspects of knowledge-fuzzy inference, ontology reasoning, and a fuzzy analytical hierarchy process (FAHP) to provide a more intuitive and accurate design. First, we build a two-layered hierarchical and interpretable FRBS; then, we improve this by integrating an ontology reasoning process based on SNOMED CT standard ontology. We incorporate FAHP to determine the relative medical importance of each sub-FRBS. The proposed system offers numerous unique and critical improvements regarding the implementation of an accurate, dynamic, semantically intelligent, and interpretable CDSS. The designed system considers the ontology semantic similarity of diabetes complications and symptoms concepts in the fuzzy rules' evaluation process. The framework was tested using a real data set, and the results indicate how the proposed system helps physicians and patients to accurately diagnose diabetes mellitus.

Diagnosis of deadly diseases, such as liver fibrosis, is very important. Clinical decision support systems (CDSSs) based on patient's historical medical data and accurate AI techniques can aid physicians in their decision-making process. The task of arriving at an accurate and timely diagnosis decision is always complex because of the dynamic, vagueness, and uncertainty associated with this disease. Fuzzy logic can perfectly handle these issues. In recent years, two of the most interesting techniques are a fuzzy analytical hierarchy process (FAHP) and an adaptive neuro-fuzzy inference system (ANFIS). The FAHP is popular for dealing with uncertainty in multi-criteria decision-making, and the ANFIS is popular in learning fuzzy inference system from data based on artificial neural networks. To the best of our knowledge, these two methods have not been used to model CDSSs in fibrosis stage detection domain. In this paper, we develop a CDSS based on a case comparison of the effectiveness of the FAHP and the ANFIS in the medical diagnosis of the fibrosis disease. We carefully design and implement two frameworks based on these two techniques. Diagnostic real data of 119 cases infected by chronic viral hepatitis C from the Liver Institute at Mansoura University in Egypt are used to train and test both the FAHP and ANFIS. Criteria and subcriteria weights are based on opinions of two domain experts. The ANFIS model is designed using trial and error based on the analysis of various experiments. Results are later compared with the diagnostic conclusions of medical expert and other three medical and fuzzy techniques. The comparison results show that these two techniques can successfully be employed in designing a diagnostic CDSS system for fibrosis diagnosis. The two techniques achieve a classification accuracy of 93.3%. The results confirm the efficiency and effectiveness of both methods. Therefore, both the FAHP and ANFIS are viable approaches in modeling CDSS for diagnosis of a liver fibrosis stage.

The volume of adult content on the world wide web is increasing rapidly. This makes an automatic detection of adult content a more challenging task, when eliminating access to ill-suited websites. Most pornographic webpage-filtering systems are based on n-gram, naïve Bayes, K-nearest neighbor, and keyword-matching mechanisms, which do not provide perfect extraction of useful data from unstructured web content. These systems have no reasoning capability to intelligently filter web content to classify medical webpages from adult content webpages. In addition, it is easy for children to access pornographic webpages due to the freely available adult content on the Internet. It creates a problem for parents wishing to protect their children from such unsuitable content. To solve these problems, this paper presents a support vector machine (SVM) and fuzzy ontology-based semantic knowledge system to systematically filter web content and to identify and block access to pornography. The proposed system classifies URLs into adult URLs and medical URLs by using a blacklist of censored webpages to provide accuracy and speed. The proposed fuzzy ontology then extracts web content to find website type (adult content, normal, and medical) and block pornographic content. In order to examine the efficiency of the proposed system, fuzzy ontology, and intelligent tools are developed using Protégé 5.1 and Java, respectively. Experimental analysis shows that the performance of the proposed system is efficient for automatically detecting and blocking adult content.

Demand side management (DSM) will play a significant role in the future smart grid by managing loads in a smart way. DSM programs, realized via home energy management systems for smart cities, provide many benefits; consumers enjoy electricity price savings and utility operates at reduced peak demand. In this paper, evolutionary algorithms-based (binary particle swarm optimization, genetic algorithm, and cuckoo search) DSM model for scheduling the appliances of residential users is presented. The model is simulated in time of use pricing environment for three cases: 1) traditional homes; 2) smart homes; and 3) smart homes with renewable energy sources. Simulation results show that the proposed model optimally schedules the appliances resulting in electricity bill and peaks reductions.

The recent technology of human voice capture and interpretation has spawned the social robot to convey information and to provide recommendations. This technology helps people obtain information about a particular topic after giving an oral query to a humanoid robot. However, most of the search engines are keyword-matching mechanism-based, and the existing full-text query search engines are inadequate at retrieving relevant information from various oral queries. With only predefined words and sentence-based recommendations, a social robot may not suggest the correct items, if items retrieved along with the information are not predefined. In addition, the available conventional ontology-based systems cannot extract precise data from webpages to show the correct results. In this regard, we propose a merged ontology and support vector machine (SVM)-based information extraction and recommendation system. In the proposed system, when a humanoid robot receives an oral query from a disabled user, the oral query changes into a full-text query, the system mines the full-text query to extract the disabled user's needs, and then converts the query into the correct format for a search engine. The proposed system downloads a collection of information about items (city features, diabetes drugs, and hotel features). The SVM identifies the relevant information on the item and removes anything irrelevant. Merged ontology-based sentiment analysis is then employed to find the polarity of the item for recommendation. The system suggests items with a positive polarity term to the disabled user. The intelligent model and merged ontology were designed by employing Java and Protégé Web Ontology Language 2 software, respectively. Experimentation results show that the proposed system is highly productive when analyzing retrieved information, and provides accurate recommendations.