Search

Abstract The educational landscape is witnessing a transformation with the integration of Educational Technology (Edutech). As educational institutions adopt digital platforms and tools, the generation of Educational Big Data (EBD) has significantly increased. Research indicates that educational institutions produce massive data, including student enrollment records, academic performance metrics, attendance records, learning activities, and interactions within digital learning environments. This influx of data needs efficient processing to derive actionable insights and enhance the learning experience. Real-time data processing has a critical part in educational environments to support various functions such as personalized learning, adaptive assessment, and administrative decision-making. However, there may be challenges in sending large amounts of educational data to cloud servers, i.e., latency, cost and network congestion. These challenges make it more difficult to provide educators and students with timely insights and services, which reduces the efficiency of educational activities. This paper proposes a Regional Computing (RC) paradigm designed specifically for big data management in education to address these issues. In this case, RC is established within educational regions and intended to decentralize data processing. To reduce dependency on cloud infrastructure, these regional servers are strategically located to collect, process, and store big data related to education regionally. Our investigation results show that RC significantly reduces latency to 203.11 ms for 2,000 devices, compared to 707.1 ms in Cloud Computing (CC). It is also more cost-efficient, with a total cost of just 1.14 USD versus 5.36 USD in the cloud. Furthermore, it avoids the 600% congestion surges seen in cloud setups and maintains consistent throughput under high workloads, establishing RC as the optimal solution for managing EBD.

This paper conducts a thorough comparative analysis of optimization algorithms for an unconstrained convex optimization problem. It contrasts traditional methods like Gradient Descent (GD) and Nesterov Accelerated Gradient (NAG) with modern techniques such as Adaptive Moment Estimation (Adam), Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP). Through empirical experiments, convergence speed, solution accuracy and robustness, is evaluated providing insights to aid algorithm selection. The convergence dynamics of convex optimization, is explored analyzing classical algorithms and contemporary neural network (NN) methodologies. The study concludes with a comparative assessment of these algorithms performance metrics and their respective strengths and weaknesses.

Abstract Background Anomaly detection is crucial in healthcare data due to challenges associated with the integration of smart technologies and healthcare. Anomaly in electronic health record can be associated with an insider trying to access and manipulate the data. This article focuses around the anomalies under different contexts. Methodology This research has proposed methodology to secure Electronic Health Records (EHRs) within a complex environment. We have employed a systematic approach encompassing data preprocessing, labeling, modeling, and evaluation. Anomalies are not labelled thus a mechanism is required that predicts them with greater accuracy and less false positive results. This research utilized unsupervised machine learning algorithms that includes Isolation Forest and Local Outlier Factor clustering algorithms. By calculating anomaly scores and validating clustering through metrics like the Silhouette Score and Dunn Score, we enhanced the capacity to secure sensitive healthcare data evolving digital threats. Three variations of Isolation Forest (IForest)models (SVM, Decision Tree, and Random Forest) and three variations of Local Outlier Factor (LOF) models (SVM, Decision Tree, and Random Forest) are evaluated based on accuracy, sensitivity, specificity, and F1 Score. Results Isolation Forest SVM achieves the highest accuracy of 99.21%, high sensitivity (99.75%) and specificity (99.32%), and a commendable F1 Score of 98.72%. The Isolation Forest Decision Tree also performs well with an accuracy of 98.92% and an F1 Score of 99.35%. However, the Isolation Forest Random Forest exhibits lower specificity (72.84%) than the other models. Conclusion The experimental results reveal that Isolation Forest SVM emerges as the top performer showcasing the effectiveness of these models in anomaly detection tasks. The proposed methodology utilizing isolation forest and SVM produced better results by detecting anomalies with less false positives in this specific EHR of a hospital in North England. Furthermore the proposal is also able to identify new contextual anomalies that were not identified in the baseline methodology.

Abstract Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.

Abstract Background Healthcare programs and insurance initiatives play a crucial role in ensuring that people have access to medical care. There are many benefits of healthcare insurance programs but fraud in healthcare continues to be a significant challenge in the insurance industry. Healthcare insurance fraud detection faces challenges from evolving and sophisticated fraud schemes that adapt to detection methods. Analyzing extensive healthcare data is hindered by complexity, data quality issues, and the need for real-time detection, while privacy concerns and false positives pose additional hurdles. The lack of standardization in coding and limited resources further complicate efforts to address fraudulent activities effectively. Methodolgy In this study, a fraud detection methodology is presented that utilizes association rule mining augmented with unsupervised learning techniques to detect healthcare insurance fraud. Dataset from the Centres for Medicare and Medicaid Services (CMS) 2008-2010 DE-SynPUF is used for analysis. The proposed methodology works in two stages. First, association rule mining is used to extract frequent rules from the transactions based on patient, service and service provider features. Second, the extracted rules are passed to unsupervised classifiers, such as IF, CBLOF, ECOD, and OCSVM, to identify fraudulent activity. Results Descriptive analysis shows patterns and trends in the data revealing interesting relationship among diagnosis codes, procedure codes and the physicians. The baseline anomaly detection algorithms generated results in 902.24 seconds. Another experiment retrieved frequent rules using association rule mining with apriori algorithm combined with unsupervised techniques in 868.18 seconds. The silhouette scoring method calculated the efficacy of four different anomaly detection techniques showing CBLOF with highest score of 0.114 followed by isolation forest with the score of 0.103. The ECOD and OCSVM techniques have lower scores of 0.063 and 0.060, respectively. Conclusion The proposed methodology enhances healthcare insurance fraud detection by using association rule mining for pattern discovery and unsupervised classifiers for effective anomaly detection.

The emergence of online enterprises spread across continents has given rise to the need for managing the tacit knowledge and expertise of employees. Scenarios that includes the intention of the employer to find tacit expertise and knowledge of an employee that is not documented or self-disclosed have been addressed in this article. In today’s world management of tacit knowledge has become important for the organizations. Recent studies have also proposed hosting tacit knowledge management module over cloud for large global enterprises. There are many conceptual frameworks for the acquisition and processing of the tacit knowledge. This article has proposed a reputation based approach utilizing social interactions of employees to identify the expert based on the tacit knowledge. The existing reputation-based approaches towards expertise ranking in enterprises utilize PageRank, Normal distribution, and the Hidden Markov model for expertise ranking. These models suffer negative referral, collusion, reputation inflation, and dynamism. However, the authors have proposed a Bayesian-based approach utilizing the beta probability distribution reputation model for employee ranking in enterprises that can be hosted as a cloud service for the employees of the enterprise. The experimental results reveal improved performance compared to previous techniques in terms of mean average error (MAE) for the three data sets. The proposed scheme is able to differentiate categories of interactions in a dynamic context. The results reveal that the technique is independent of the rating pattern and density of data.

Smart devices in smart cities face the dual challenge of requiring real-time data processing and storing that data permanently on the cloud for future use. This creates a significant conflict between the need for immediate responsiveness and the demands of long-term storage. While Cloud Computing (CC) offers a viable platform for processing and storing this data, it introduces delays, longer response times, and network congestion issues. Internet of Things (IoT) devices require real-time responses, but their data must also be available for subsequent analysis and decision-making. Although edge and fog computing paradigms have been developed to address these issues, they suffer from limited resources and scalability challenges, making them inadequate for the above needs. A hybrid paradigm is often proposed to address the limitations of both cloud and edge computing. However, synchronization between cloud and edge can introduce delays, negatively affecting overall performance. The proposed framework, Regional Computing (RC), addresses big data challenges in smart cities by providing an intermediate solution between edge (limited power) and cloud (distant) computing. RC manages data during peak hours, alleviating congestion on the public network. The collected data is subsequently offloaded to cloud servers for long-term storage and detailed analysis. Preliminary findings are very encouraging, indicating substantial enhancements in reducing network congestion, minimizing delays, and lowering costs.

This research paper presents the development and analysis of a multifaceted smart grid prototype. It combines various technologies for the smart grid operation. The first technology is environmental analysis of smart grid and solar panel cleaning. Secondly, radio-frequency identification (RFID)-based security and access control system has been integrated for smart grid. The third component is internet of things (IoT)-based energy monitoring and load management. For environmental analysis sensors such as temperature, humidity, light-dependent resistor, and flame sensors are connected to a NodeMCU controller for real time monitoring. Moreover, IoT based solar cleaning system is developed in the form of prototype with the help of Blynk and servo motor. The second component of prototype is smart security system which is developed with the help of Arduino and RFID module to facilitate secure access control. The third part of prototype employs voltage and current sensors with an ESP32 microcontroller and the Blynk application for real-time energy consumption analysis. This setup enables remote monitoring of voltage, power dynamics, and consumption patterns in a smart grid. It also offers an IoT based solution for load management and load shedding within the smart grid. The complete prototype overall demonstrates a comprehensive approach to 1) smart grid management, 2) environmental analysis, 3) security, and 4) energy monitoring.

Abstract Database code fragments exist in software systems by using Structured Query Language (SQL) as the standard language for relational databases. Traditionally, developers bind databases as backends to software systems for supporting user applications. However, these bindings are low‐level code and implemented to persist user data, so Object Relational Mapping (ORM) frameworks take place to abstract database access details. Both approaches are prone to problematic database code fragments that negatively impact the quality of software systems. We survey problematic database code fragments in the literature and examine antipatterns that occur in low‐level database access code using SQL and high‐level counterparts ORM frameworks. We also study problematic database code fragments in different and popular software architectures such as Service‐Oriented Architecture, Microservice Architecture, and Model View Controller. We create a novel categorization of both SQL schema and query antipatterns in terms of performance, maintainability, portability, and data integrity.