International Journal of Computer Science and Technology

International Journal of Computer Science and Technology | Vol. 1, No. 4, April 2020 | pp. 25–32

Research Article

Title: An Optimized Fog Computing Architecture for Real-Time Traffic Management in Intelligent Transportation Systems

Names of Authors: Marco Rossi¹, Elena Bianchi², and Giovanni Moretti³

Authors’ Affiliations:
¹Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy
²Department of Information Engineering, University of Pisa, Pisa, Italy
³Department of Electronic Systems, Polytechnic University of Milan, Milan, Italy

Abstract: Intelligent transportation systems (ITS) generate massive volumes of real-time vehicular telemetry and video surveillance data that overwhelm centralized cloud infrastructures due to excessive network bandwidth consumption and propagation latency. Offloading time-critical traffic control operations to decentralized fog computing nodes deployed along roadways provides a viable solution for ultra-low latency processing. However, dynamic vehicular mobility and heterogeneous resource allocations create significant challenges in task scheduling and load balancing across distributed fog layers. This paper presents an optimized, context-aware fog computing architecture designed for real-time traffic signal optimization and congestion prediction. The architecture utilizes a dynamic multi-tier task offloading algorithm based on priority-queue scheduling and reinforcement learning to distribute computational workloads between local roadside units (RSUs) and central cloud servers. Analytical models incorporate parameters such as queue length, packet arrival rates measured in packets/sec, and processing capacity measured in gigahertz (GHz). Real-world trace-driven simulations demonstrate that the proposed fog framework reduces end-to-end latency by 41.6% and decreases wide-area network bandwidth utilization by 53.2% compared to pure cloud-centric paradigms. Furthermore, dynamic traffic light phase adjustments improve average vehicle intersection throughput by 18.9% during peak commuting hours. The results illustrate that distributed fog orchestration enhances responsiveness and scalability in modern smart city transportation networks.

Keywords: Fog computing, Intelligent transportation systems, Task offloading, Real-time processing, Reinforcement learning, Smart cities

Manuscript Timeline: Received: January 12, 2020; Revised: February 20, 2020; Accepted: March 18, 2020; Published: April 1, 2020

Citation: Rossi, M., Bianchi, E., & Moretti, G. (2020). An optimized fog computing architecture for real-time traffic management in intelligent transportation systems. International Journal of Computer Science and Technology, 1(4), 25–32. DOI: 10.46882/2020/IJCST/000004

International Journal of Computer Science and Technology | Vol. 1, No. 3, March 2020 | pp. 17–24

Research Article

Title: Enhancing Cloud Datacenter Security Through Lightweight Attribute-Based Encryption and Blockchain Integration

Names of Authors: Kavita Sharma¹, Rohan Mehta², and Siddharth Rao³

Authors’ Affiliations:
¹Department of Information Technology, Indian Institute of Technology Delhi, New Delhi, India
²Department of Computer Science and Engineering, BITS Pilani, Goa, India
³Department of Cyber Security, National University of Singapore, Singapore

Abstract: Cloud computing paradigms facilitate scalable data outsourcing and collaborative processing, yet data privacy and unauthorized access remain formidable security challenges. Traditional centralized access control mechanisms are vulnerable to single points of failure, malicious cloud service provider tampering, and credential leakage. Attribute-based encryption (ABE) enables fine-grained access control over encrypted cloud data based on user attributes, but standard cipher-text policy ABE schemes suffer from high computational overhead during decryption and lack verifiable auditability. This research introduces a hybrid security framework combining ciphertext-policy attribute-based encryption (CP-ABE) with permissioned blockchain architecture to secure decentralized cloud datacenters. The proposed system offloads access policy management and revocation audit logs to an Ethereum-based private blockchain, ensuring tamper-proof immutability and transparent verification of user permissions without exposing raw secret keys. To minimize computation costs on resource-limited user devices, lightweight pairing-friendly elliptic curve cryptography (ECC) primitives are integrated into the encryption and key generation phases. Experimental evaluations indicate that the proposed scheme reduces client-side encryption latency by 19.4% and decryption processing time by 22.1% compared to conventional bilinear pairing schemes. Security analysis proves that the protocol achieves selective ciphertext indistinguishability under chosen-plaintext attack (IND-CPA) models while successfully resisting collusion attacks, replay threats, and unauthorized modifications by compromised cloud administrators.

Keywords: Cloud computing, Attribute-based encryption, Blockchain, Access control, Elliptic curve cryptography, Data security

Manuscript Timeline: Received: December 5, 2019; Revised: January 18, 2020; Accepted: February 14, 2020; Published: March 1, 2020

Citation: Sharma, K., Mehta, R., & Rao, S. (2020). Enhancing cloud datacenter security through lightweight attribute-based encryption and blockchain integration. International Journal of Computer Science and Technology, 1(3), 17–24. DOI: 10.46882/2020/IJCST/000003

International Journal of Computer Science and Technology | Vol. 1, No. 2, February 2020 | pp. 9–16

Review Article

Title: A Comprehensive Survey of Deep Learning Techniques for Automated Skin Lesion Classification in Dermatology

Names of Authors: Fatima Zahra¹, Tariq Al-Mansoor², and David Miller³

Authors’ Affiliations:
¹Department of Biomedical Engineering, Cairo University, Giza, Egypt
²Department of Artificial Intelligence, King Abdulaziz University, Jeddah, Saudi Arabia
³Department of Computer Science, University of Oxford, Oxford, United Kingdom

Abstract: Early detection of malignant melanoma and other pigmented skin lesions remains a critical factor in improving patient survival rates in modern dermatology. Manual visual inspection by clinicians is inherently subjective, time-consuming, and prone to diagnostic variability, necessitating reliable computer-aided diagnostic (CAD) systems. In recent years, deep learning (DL) architectures—particularly convolutional neural networks (CNNs)—have revolutionized medical image analysis by automating feature extraction and classification tasks with high precision. This paper delivers a comprehensive, structured survey of state-of-the-art deep learning methodologies applied to automated skin lesion classification using benchmark datasets such as ISIC and HAM10000. We examine the evolution of deep architectures ranging from traditional AlexNet and VGG models to advanced residual networks (ResNet), dense networks (DenseNet), and vision transformers (ViT). Special attention is dedicated to preprocessing challenges, including hair artifact removal, color normalization, class imbalance handling via data augmentation, and generative adversarial networks (GANs). Furthermore, we analyze quantitative performance metrics across studies, noting that ensemble CNN models achieve diagnostic accuracy exceeding 94.8% and area under the ROC curve (AUC) values up to 0.99. Open research gaps are highlighted, including model interpretability, cross-domain generalization under varying clinical imaging equipment, and the deployment constraints of lightweight models on mobile edge devices. Finally, future directions are outlined to bridge the translational gap between algorithmic development and routine clinical workflows.

Keywords: Deep learning, Convolutional neural networks, Skin lesion classification, Melanoma detection, Medical image analysis, Computer-aided diagnosis

Manuscript Timeline: Received: November 10, 2019; Revised: December 15, 2019; Accepted: January 12, 2020; Published: February 1, 2020

Citation: Zahra, F., Al-Mansoor, T., & Miller, D. (2020). A comprehensive survey of deep learning techniques for automated skin lesion classification in dermatology. International Journal of Computer Science and Technology, 1(2), 9–16. DOI: 10.46882/2020/IJCST/000002

International Journal of Computer Science and Technology | Vol. 1, No. 1, January 2020 | pp. 1–8

Research Article

Title: An Energy-Efficient Clustering Routing Protocol Based on Genetic Algorithm for Wireless Sensor Networks

Names of Authors: Amina Bello¹, Chinedu Okafor², and Oluwaseun Adebayo³

Authors’ Affiliations:
¹Department of Computer Science, University of Lagos, Lagos, Nigeria
²Department of Electrical and Computer Engineering, Federal University of Technology, Minna, Nigeria
³Department of Computer Engineering, Covenant University, Ota, Nigeria

Abstract: Wireless sensor networks (WSNs) face significant performance constraints due to limited battery energy in individual sensor nodes. Uneven energy dissipation rapidly depletes network nodes, leading to premature network partitioning and reduced operational lifespan. Traditional routing approaches often fail to balance energy consumption across dynamic topologies, resulting in inefficient data transmission paths. This paper proposes an optimized, energy-efficient clustering routing protocol leveraging a genetic algorithm (GA) to maximize the overall lifetime of large-scale WSNs. The core methodology formulates a multi-objective fitness function incorporating residual node energy, distance to the base station, and local node density to select optimal cluster heads dynamically. Chromosome encoding and genetic operators, including roulette-wheel selection, single-point crossover, and bit-mutation, are iteratively executed to avoid local optima convergence during cluster head formation. Simulation results conducted in a randomized deployment area of 100m x 100m demonstrate that the proposed GA-based protocol reduces average energy consumption per round by 28.5% compared to standard Low-Energy Adaptive Clustering Hierarchy (LEACH) and Power-Efficient Gathering in Sensor Information Systems (PEGASIS) algorithms. Furthermore, the time to first node death (FND) is extended by 34.2%, and total packet delivery ratio improves significantly under high traffic loads. The findings confirm that genetic algorithm-driven optimization provides a robust framework for prolonging network longevity and maintaining reliable connectivity in resource-constrained industrial and environmental monitoring applications.

Keywords: Wireless sensor networks, Energy efficiency, Clustering routing, Genetic algorithm, Network lifetime, Optimization

Manuscript Timeline: Received: October 14, 2019; Revised: November 22, 2019; Accepted: December 10, 2019; Published: January 5, 2020

Citation: Bello, A., Okafor, C., & Adebayo, O. (2020). An energy-efficient clustering routing protocol based on genetic algorithm for wireless sensor networks. International Journal of Computer Science and Technology, 1(1), 1–8. DOI: 10.46882/2020/IJCST/000001