Basit Qureshi

The ongoing shift toward 6G-enabled healthcare IoT is making privacy-preserving collaborative intelligence a practical requirement rather than a research luxury. Federated Learning (FL) is a natural fit for this setting, yet it remains vulnerable when untrusted devices participate in training, as attackers can inject poisoned updates, distort aggregation, or increase the risk of sensitive information leakage. In this paper, we present TAWB-SFL, a trust-aware framework that combines Split Federated Learning (SFL), blockchain, and edge intelligence to build a secure intrusion detection pipeline for healthcare IoT. The proposed design splits the deep model across the device and edge: lightweight CNN layers on IoT nodes extract spatial patterns from patient-related data, while an edge-side BiLSTM models temporal behavior to identify attacks. SFL keeps raw data on devices, blockchain smart contracts handle device registration/authentication and provide auditable logging of update transactions, and trust scores are used to weight client contributions during aggregation. To support frequent and timely update commitments, we further adopt the TAWB-SFL consensus design to reduce latency and improve scalability. Experimental results on the ToN-IoT and IoT-Healthcare datasets achieve 99.9% detection accuracy with a consensus time of 250 ms, indicating that the proposed approach can deliver accurate threat detection while enabling low-latency, accountable model updates in 6G healthcare IoT environments.

The development of wireless communication technology has led to an exponential growth in the Healthcare Internet of Things (H-IoT). Sensors and actuators are used in smart medical devices to collect data about the human body, which is then sent to the fog layer for analysis. However, H-IoT devices present security and Quality of Service (QoS) concerns because of their critical nature, complexity, and dynamic features, which make them incompatible with conventional network topologies. Furthermore, reducing superfluous data and identifying effective fog nodes are difficult tasks. We provide a novel Software-Defined Networking (SDN)- driven Deep Learning (DL) approach to develop a secure, intelligent, and efficient framework for smart H-CIoT networks in order to address the aforementioned challenges. In this method, we have first considered SDN architecture as a promising solution since it allows for reconfiguration over static network infrastructure and manages the distributed architecture of intelligent H-CIoT networks by keeping the data and control planes apart. Secondly, a security module based on Bidirectional Long Short-Term Memory (BiLSTM) is implemented to recognize various forms of attacks within the H-CIoT network. Third, the past medical records of the patients are used to train the DL model. It then makes an informed decision about whether to send the data to the fog layer. The CNN approach is also included in the suggested framework to choose the best fog node. The simulation results indicate that the proposed framework achieved an accuracy of 99.59%, an F1-score of 99.53%, a latency of 3 ms, energy consumption of 55W, and a probability of 0.92%. It outperforms the baseline and current methods with improvements of 5% in accuracy, 4% in F1-score, 10 ms in latency, 25 W in energy consumption, and 0.66% in probability, respectively.

Single-board computers (SBCs) are emerging as an efficient and economical solution for fog and edge computing, providing localized big data processing with lower energy consumption. Newer and faster SBCs deliver improved performance while still maintaining a compact form factor and cost-effectiveness. In recent times, researchers have addressed scheduling issues in Hadoop-based SBC clusters. Despite their potential, traditional Hadoop configurations struggle to optimize performance in heterogeneous SBC clusters due to disparities in computing resources. Consequently, we propose modifications to the scheduling mechanism to address these challenges. In this paper, we leverage the use of node labels introduced in Hadoop 3+ and define a Frugality Index that categorizes and labels SBC nodes based on their physical capabilities, such as CPU, memory, disk space, etc. Next, an adaptive configuration policy modifies the native fair scheduling policy by dynamically adjusting resource allocation in response to workload and cluster conditions. Furthermore, the proposed frugal configuration policy considers prioritizing the reduced tasks based on the Frugality Index to maximize parallelism. To evaluate our proposal, we construct a 13-node SBC cluster and conduct empirical evaluation using the Hadoop CPU and IO intensive microbenchmarks. The results demonstrate significant performance improvements compared to native Hadoop FIFO and capacity schedulers, with execution times 56% and 22% faster than the best_cap and best_fifo scenarios. Our findings underscore the effectiveness of our approach in managing the heterogeneous nature of SBC clusters and optimizing performance across various hardware configurations.

Efficient resource allocation is crucial in clusters with frugal Single-Board Computers (SBCs) possessing limited computational resources. These clusters are increasingly being deployed in edge computing environments in resource-constrained settings where energy efficiency and cost-effectiveness are paramount. A major challenge in Hadoop scheduling is load balancing, as frugal nodes within the cluster can become overwhelmed, resulting in degraded performance and frequent occurrences of out-of-memory errors, ultimately leading to job failures. In this study, we introduce an Adaptive Multi-criteria Selection for Efficient Resource Allocation (AMS-ERA) in Frugal Heterogeneous Hadoop Clusters. Our criterion considers CPU, memory, and disk requirements for jobs and aligns the requirements with available resources in the cluster for optimal resource allocation. To validate our approach, we deploy a heterogeneous SBC-based cluster consisting of 11 SBC nodes and conduct several experiments to evaluate the performance using Hadoop wordcount and terasort benchmark for various workload settings. The results are compared to the Hadoop-Fair, FOG, and IDaPS scheduling strategies. Our results demonstrate a significant improvement in performance with the proposed AMS-ERA, reducing execution time by 27.2%, 17.4%, and 7.6%, respectively, using terasort and wordcount benchmarks.

Efficient resource allocation is crucial in clusters with frugal Single-Board Computers (SBCs) possessing limited computational resources. These clusters are increasingly being deployed in edge computing environments in resource-constrained settings where energy efficiency and cost-effectiveness are paramount. A major challenge in Hadoop YARN scheduling is load-balancing, as frugal nodes within the cluster can become overwhelmed, resulting in degraded performance and frequent occurrences of out-of-memory errors, ultimately leading to job failures. In this study, we introduce an Adaptive Multi-criteria Selection for Efficient Resource Allocation (AMS-ERA) in Frugal Heterogeneous Hadoop Clusters. Our criterion considers CPU, memory and disk requirements for jobs and aligns the requirements with available resources in the cluster for optimal resource allocation. To validate our approach, we deploy a heterogeneous SBC-based cluster consisting of 11 SBC nodes and conduct several experiments to evaluate the performance using Hadoop wordcount and terasort benchmark for various workload settings. The results are compared to the Hadoop-Fair, FOG and IDaPS scheduling strategies. Our results demonstrate a significant improvement in performance with the proposed AMS-ERA, reducing execution time by 27.2%, 17.4% and 7.6% respectively using terasort and wordcount benchmarks.

The application of Artificial intelligence for teaching and learning in the academic sphere is a trending subject of interest in computing education. ChatGPT, as an AI-based tool, provides various advantages, such as heightened student involvement, cooperation, accessibility, and availability. This paper addresses the prospects and obstacles associated with utilizing ChatGPT as a tool for learning and assessment in undergraduate Computer Science curriculum in particular to teaching and learning fundamental programming courses. Students having completed the course work for a Data Structures and Algorithms (a sophomore-level course) participated in this study. Two groups of students were given programming challenges to solve within a short period of time. The control group (group A) had access to textbooks and notes of programming courses, however, no Internet access was provided. Group B students were given access to ChatGPT and were encouraged to use it to help solve the programming challenges. The challenge was conducted in a computer lab environment using Programming Contest Control (PC2) environment which is widely used in ACM International Collegiate Programming Contest (ICPC). Each team of students addresses the problem by writing executable code that satisfies a certain number of test cases. Student teams were scored based on their performance in terms of the number of successfully passed test cases. Results show that students using ChatGPT had an advantage in terms of earned scores, however, there were inconsistencies and inaccuracies in the submitted code consequently affecting the overall performance. After a thorough analysis, the paper’s findings indicate that incorporating AI in higher education brings about various opportunities and challenges. Nonetheless, universities can efficiently manage these apprehensions by adopting a proactive and ethical stance toward the implementation of such tools.

Advancements in technology have revolutionized communication on social media platforms, where reviews and comments greatly influence product selection. Current opinion mining methods predominantly focus on textual content, overlooking the rich information within customer-posted images, termed here as Multus-Medium. This research introduces an innovative deep learning approach, Multus Medium Opinion Mining (MMOM), capitalizing on both text and image data for comprehensive product review analysis. MMOM employs an integrated model of Bidirectional Long Short-Term Memory (BiLSTM) and embedded Convolutional Neural Network (CNN), incorporating architectures of GoogleNet and VGGNet, thus enabling efficient extraction and fusion of textual and visual features. This synergistic approach enables data collection, preprocessing, feature extraction, fusion strategy-based feature vector generation, and subsequent product recommendation. Performance evaluation on two diverse real-world datasets name as “flicker8k” and “t4sa”. These datasets show substantial improvement over existing methods. MMOM outperforms standard benchmark models, achieving an accuracy, F1 score and ROC over fliker8k are 90.38%, 88.75% and 93.08%, whereas for twitter dataset are 88.54%, 86.34%, and 92.26% respectively, the accuracy of purposed model is 7.34% and 9.54% higher than the other two mentioned techniques. These statistics highlight the robustness and applicability of MMOM across various domains. The compelling results underscore the potential of MMOM, providing a more holistic and precise approach to opinion mining in the era of social media product reviews. This research, product recommendation helps the customer to make purchasing decision. Last but not the least, the purposed scheme can further be expanded in any other sentiment task like hospital recommendation system, crop farming recommendation and medical diagnostic system etc.

Machine Learning (ML) such as Artificial Neural Network (ANN), Deep learning, Recurrent Neural Networks (RNN), Alex Net and ResNet can be consider as a broad research direction in the identification and classification of critical diseases. CNN and its particular variant usually named as U-Net Segmentation has made a revolutionary advancement in the classification of medical diseases, specifically retinal diseases. However, because of the feature extraction complexity, U-Net has a significant flaw of high memory and CPU consumption, while moving the whole feature map to the related decoder. Furthermore, it can be concatenated to the unsampled decoder feature map avoids the reusing pooling indices. In this research work, a convolutional neural network (CNN) model is proposed for multi-class classification problem with the efficient use of memory consumption. The proposed model has been evaluated on standard benchmark dataset of Eye Net having 32 classes of retinal diseases. From experimental evaluation it has been concluded that the proposed model performs better in terms of memory management and accuracy. The overall comparison has been performed on the bases of precision, recall, accuracy with different number of epochs and time consumption by each step. Proposed technique achieved an accuracy of 95% on Eye-net dataset.