Mohamed Ahmed El-Rashidy

The proliferation of Internet of Things (IoT) devices challenges deep learning (DL) deployment due to their limited computational power, while cloud offloading introduces high latency and network strain. Fog computing provides a viable middle ground. We present a resource-aware framework that intelligently partitions DL tasks between fog nodes and the cloud using a novel Binary Search-Inspired Recursive (BSIR) optimization algorithm for rapid, low-overhead decision-making. This is enhanced by a novel module that fine-tunes deployment by analyzing memory at a per-layer level. For true adaptability, a Retrieval-Augmented Generation (RAG) technique consults a knowledge base to dynamically select the best optimization strategy. Our experiments demonstrate dramatic improvements over established metaheuristics. The complete framework boosts memory utilization in fog environments to a remarkable 99%, a substantial leap from the 85.25% achieved by standard algorithms like Genetic Algorithms (GA), Simulated Annealing (SA), and Particle Swarm Optimization (PSO). The enhancement module alone improves these traditional methods by over 13% without added computational cost. Our system consistently operates with a CPU footprint under 3% and makes decisions in fractions of a second, significantly outperforming recent methods in speed and resource efficiency. In contrast, recent DL methods may use 51% CPU and take over 90 s for the same task. This framework effectively reduces cloud dependency, offering a scalable solution for DL in the IoT landscape.

Artificial intelligence (AI) technologies have vastly improved. AI is now being used in a variety of applications to diagnose Breast Cancer (BC). However, most of the recent research has focused on centralized learning, which can pose privacy risks. In this paper, we propose a novel Federated Learning (FL) framework for the BC classification systems. The main objectives of this research are to improve data security and privacy, increase the accuracy of the Deep Learning (DL) model, and minimize energy consumption and related carbon emissions, which provides a way toward achieving green AI and sustainability goals. However, continuously transmitting model updates between the client and the server may cause lag and escalate host energy consumption. To minimize communication cost and simultaneously achieve the best accuracy, the proposed FL framework develops a new DL architecture for mammography classification, taking into account the optimal number of rounds between client hosts and the central server. The proposed DL architecture employs attention mechanisms, convolutional layers, and LSTMs to extract and analyze features and uses techniques to prevent overfitting and manage imbalanced data. The proposed FL framework is evaluated on three benchmark datasets. The results indicate that the proposed framework is more effective in detecting breast cancer compared to the recent approaches, achieving 95.17%, 100%, and 98.82% on the DDSM, INbreast, and Macrocalcification datasets, respectively.

This study proposes an intelligent IoT-based framework for forecasting crop damage in smart agricultural systems. Integrating smart farming with machine learning (ML) to comprehend the complex relationships in agriculture requires access to comprehensive and coherent datasets. However, such datasets are often incomplete due to missing data across various input features, posing a challenge for developing robust predictive models using ML. Addressing the issue of missing data is critical throughout the development, evaluation, and implementation phases of predictive models in smart farming. While ML methods are commonly believed to handle missing data well, their applicability in agriculture research remains unclear. This study aims to assess how ML-based prediction model studies address missing data and to what extent. To systematically explore the performance and applicability of both single ML algorithms and ensemble learning (EL) algorithms, this study adopts appropriate criteria for assessing missing data treatment in decision-making processes. The performance of various missing data processing techniques varies across different scenarios of missing data. Overall, ensemble learning demonstrates superior imputation performance compared to traditional ML methods, particularly in scenarios with high correlations among missing features. Among the ensemble learning algorithms evaluated, XGBoost, CatBoost, and LGBM classifiers with hyperparameter optimization exhibit notable performance, surpassing that of linear regression. Specifically, the XGBoost classifier achieves average sensitivity, accuracy, precision, and F-score values of 88.1, 89.56, 83.4, and 84.8, respectively. Similarly, the CatBoost classifier attains values of 88.1, 90.50, 83.3, and 84.6 for the same metrics. In comparison, the LGBM classifier achieves values of 86.3, 90.23, 81.1, and 83.1 for sensitivity, accuracy, precision, and F-score, respectively. Moreover, the accuracy of predicting missing values is assessed using Mean Squared Error (MSE) and R-squared (R2), with the XGBoost model demonstrating notably low MSE (0.0213) and high R2 (0.99), indicative of its strong performance in this aspect.

Clinical decision support systems (CDSSs) can effectively detect illnesses such as breast cancer (BC) using a variety of medical imaging techniques. BC is a key factor contributing to the rise in the death rate among women worldwide. Early detection will lessen its impact, which may motivate patients to have quick surgical therapy. Computer-aided diagnosis (CAD) systems are designed to provide radiologists recommendations to assist them in diagnosing BC. However, it is still restricted and limited, the interpretability cost, time consumption, and complexity of architecture are not considered. These limitations limit their use in healthcare devices. Therefore, we thought of presenting a revolutionary deep learning (DL) architecture based on recurrent and convolutional neural networks called Bi-xBcNet-96. In order to decrease carbon emissions while developing the DL model for medical image analysis and meet the objectives of sustainable artificial intelligence, this study seeks to attain high accuracy at the lowest computing cost. It takes into consideration the various characteristics of the pathological variation of BC disease in mammography images to obtain high detection accuracy. It consists of six stages: identifying the region of interest, detecting spatial features, discovering the effective features of the BC pathological types that have infected nearby cells in a concentrated area, identifying the relationships between distantly infected cells in some BC pathological types, weighing the extracted features, and classifying the mammography image. According to experimental findings, Bi-xBcNet-96 beat other comparable works on the benchmark datasets, attaining a classification accuracy of 98.88% in DDSM dataset, 100% in INbreast dataset with 5.08% and 0.3% improvements over the state-of-the-art methods, respectively. Furthermore, a 95.79% reduction in computing complexity was achieved.

Learning is an essential requirement for humans, and its means have evolved. Ten years ago, Massive Open Online Courses (MOOCs) were introduced, attracting many interests and learners. MOOCs provide forums for learners to interact with instructors and to express any problems they encounter in the educational process. However, MOOCs have a high dropout rate due to the difficulties of following up on learners' posts and identifying the urgent ones to react quickly. This research aims to assist instructors in automatically identifying urgent posts, making it easier to respond to such posts rapidly, increasing learner engagement, and improving course completion rate. In this paper, we propose a novel classification model for identifying urgent posts. The proposed model consists of four stages. In the first stage, the post-text is code-encoded and vectorized using a pre-trained BERT model. In the second stage, a novel feature aggregation model is proposed to reveal data-based relationships between token features and their representation in a higher-level feature. In the third stage, a novel model based on convolutional neural networks (CNNs) is proposed to reveal the meaning of a text context more accurately. In the last stage, the extracted composite features are used to classify the text of the post. Several experimental studies were conducted to get the best performance of the proposed stages of the system. The experimental results demonstrated the architectural efficiency of the proposed feature aggregation and multiple CNN models, as well as the accuracy of the proposed system compared to the current research.