International Journal of Computer Science and Technology

International Journal of Computer Science and Technology | Vol. 7, No. 9, September 2005 | pp. 65–72

DOI: 10.46882/2005/IJCST/070912

Research Article

Title: Energy-Aware Task Scheduling in Heterogeneous Mobile Ad-Hoc Networks Using Ant Colony Optimization

Names of Authors: Fatoumata Diallo¹, Diego Silva²

Authors’ Affiliations: ¹Département de Génie Informatique, École Nationale d'Ingénieurs de Bamako, Bamako, Mali; ²Departamento de Engenharia de Computação, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil

Abstract:
Mobile Ad-hoc Networks (MANETs) consist of battery-powered terminal devices that are resource-constrained and highly prone to premature power exhaustion under intense distributed computing workloads. This paper details a novel energy-aware task scheduling architecture that optimizes workload allocation across heterogeneous mobile groups using a modified Ant Colony Optimization (ACO) heuristic. The scheduling algorithm monitors residual battery energy vectors alongside wireless link quality metrics to assign computational sub-tasks dynamically without over-stressing critical routing nodes. Network modeling configurations with node densities varying between 50 and 200 units showed that the energy-aware ACO model extended the overall operational lifespan of the network topology by 26.8% compared to traditional minimum-laxity scheduling methods. The computational throughput rose by 14.3%, and the packet delivery ratio remained resilient above 96.5% even during rapid spatial changes in the network structure, establishing a durable paradigm for ad-hoc grid computations.

Keywords: Mobile Ad-Hoc Networks, Task Scheduling, Ant Colony Optimization, Energy Harvesting, Network Lifetime

Manuscript Timeline: Received June 04, 2005; Revised July 18, 2005; Accepted August 12, 2005; Published September 23, 2005

Citation: Diallo, F., & Silva, D. (2005). Energy-Aware Task Scheduling in Heterogeneous Mobile Ad-Hoc Networks Using Ant Colony Optimization. International Journal of Computer Science and Technology, 7(9), 65–72.

International Journal of Computer Science and Technology | Vol. 7, No. 8, August 2005 | pp. 57–64

DOI: 10.46882/2005/IJCST/070811

Research Article

Title: An Adaptive Edge-Computing Framework for Low-Latency Multimedia Content Delivery Networks

Names of Authors: Kofi Mensah¹, Hiroshi Tanaka²

Authors’ Affiliations: ¹Department of Computer Engineering, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana; ²Department of Information and Communication Engineering, University of Tokyo, Tokyo, Japan

Abstract:
The increasing consumer demand for high-definition streaming media presents substantial bandwidth bottlenecks for legacy centralized content delivery networks (CDNs). This study introduces an adaptive edge-computing framework designed to decentralize caching operations by deploying localized data staging nodes at the network periphery. The distribution engine evaluates real-time client request matrices and uses a proactive prediction model to push popular media blocks during off-peak hours. Simulations were executed using synthetic traffic profiles across a modeled regional network topology with 150 edge cache layers. The experimental data show that the edge framework reduces the core backbone network utilization by 38.4%, while improving the final end-user content delivery latency from t = 142 ms down to an average of t = 34 ms ± 4 ms under highly congested request scenarios. Additionally, the cache hit ratio (CHR) stabilized at a highly efficient index of 92.15%, validating the system's capacity to minimize backhaul congestion and scale smoothly under sudden, high-volume user traffic spikes.

Keywords: Edge Computing, Content Delivery Networks, Cache Optimization, Low Latency, Multimedia Streaming

Manuscript Timeline: Received May 10, 2005; Revised June 22, 2005; Accepted July 14, 2005; Published August 26, 2005

Citation: Mensah, K., & Tanaka, H. (2005). An Adaptive Edge-Computing Framework for Low-Latency Multimedia Content Delivery Networks. International Journal of Computer Science and Technology, 7(8), 57–64.

International Journal of Computer Science and Technology | Vol. 7, No. 7, July 2005 | pp. 49–56

DOI: 10.46882/2005/IJCST/070710

Research Article

Title: Semantic Web Service Discovery Using Description Logics and Ontology Mapping Filters

Names of Authors: Alessandro Rossi¹, Lin Wei²

Authors’ Affiliations: ¹Dipartimento di Informatica, Università di Pisa, Pisa, Italy; ²Department of Computer Science and Technology, Tsinghua University, Beijing, China

Abstract:
Standard registry-based discovery methods for web services often miss highly compatible options because they match text strings rather than evaluating semantic concepts. This paper outlines an advanced semantic web service discovery mechanism that evaluates functional profiles using Description Logics (DL) syntax and structural ontology mapping rules. The system measures degree-of-match variables (Exact, Plug-in, Subsumes, Fail) by traversing taxonomic paths within Web Ontology Language for Services (OWL-S) profiles. Benchmarked against the OWL-S TC2 repository dataset, the proposed semantic selection engine achieved an overall precision rating of P = 91.3% and a recall metric of R = 87.5%, outperforming standard keyword-matching registries by more than 35%. The execution latency required to process semantic matchmaking operations scale linearly at O(N) relative to registry size, validating the framework's capability to power automated service composition workflows in distributed enterprise systems.

Keywords: Semantic Web Services, Ontology Mapping, Description Logics, OWL-S, Service Discovery

Manuscript Timeline: Received April 02, 2005; Revised May 14, 2005; Accepted June 11, 2005; Published July 25, 2005

Citation: Rossi, A., & Wei, L. (2005). Semantic Web Service Discovery Using Description Logics and Ontology Mapping Filters. International Journal of Computer Science and Technology, 7(7), 49–56.

International Journal of Computer Science and Technology | Vol. 7, No. 6, June 2005 | pp. 41–48

DOI: 10.46882/2005/IJCST/070609

Research Article

Title: An Intrusion Detection System for Cloud Environments Based on Hypervisor-Level Introspection

Names of Authors: David Miller¹, Siti Aminah²

Authors’ Affiliations: ¹Department of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA; ²School of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia

Abstract:
Traditional network-based intrusion detection frameworks are often unable to detect sophisticated attacks running inside virtualized cloud server nodes. This study details a host-level intrusion detection system (IDS) that operates via virtual machine introspection (VMI) at the hypervisor layer, completely isolated from the monitored guest operating systems. The software captures kernel data structures and memory allocations in real-time, matching changes against known malicious control-flow patterns. Testing within a Xen-hypervisor environment exposed to rootkit injection scripts demonstrated a true positive detection accuracy rate of 99.1%, while maintaining a low false alarm rate of 0.04%. Because the monitoring processes are decoupled from the target virtual machine, attackers cannot tamper with or disable the logging system. The hypervisor monitoring execution loop adds a minor performance penalty of just 2.3% on guest CPU workloads, ensuring the security model remains practical for enterprise cloud service provider deployment.

Keywords: Cloud Computing, Virtual Machine Introspection, Intrusion Detection, Hypervisor Security, Virtualization

Manuscript Timeline: Received March 14, 2005; Revised April 28, 2005; Accepted May 19, 2005; Published June 23, 2005

Citation: Miller, D., & Aminah, S. (2005). An Intrusion Detection System for Cloud Environments Based on Hypervisor-Level Introspection. International Journal of Computer Science and Technology, 7(6), 41–48.

International Journal of Computer Science and Technology | Vol. 7, No. 5, May 2005 | pp. 33–40

DOI: 10.46882/2005/IJCST/070508

Research Article

Title: High-Performance Parallel Simulation of Fluid Dynamics on Cluster Architectures Using MPI

Names of Authors: Guillaume Mercier¹, Aparna Rao²

Authors’ Affiliations: ¹Département d'Informatique, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland; ²Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India

Abstract:
Simulating complex fluid dynamics variables requires significant computational resources, often necessitating high-performance parallel computing solutions. This paper implements a parallelized Navier-Stokes equation solver across distributed-memory cluster setups using the Message Passing Interface (MPI) framework. The computational space is divided using a 3D block-decomposition algorithm designed to minimize border communication overhead between processing ranks. Evaluation on a 64-node Linux cluster system achieved a parallel execution speedup efficiency metric of E = 87.5% when scaling up to maximum core allocations. The processing latency added by inter-node network communication was kept exceptionally low at less than 6.2% of total operational runtimes. This was achieved by using non-blocking MPI communication primitives (MPI_Isend and MPI_Irecv) to overlap computational steps with network data transfers. The framework can compute complex mesh structures exceeding 10⁸ elements, providing a scalable backbone for industrial aerodynamic design testing.

Keywords: Parallel Computing, Fluid Dynamics, MPI, Domain Decomposition, Scalability, Computational Grids

Manuscript Timeline: Received February 10, 2005; Revised March 24, 2005; Accepted April 15, 2005; Published May 26, 2005

Citation: Mercier, G., & Rao, A. (2005). High-Performance Parallel Simulation of Fluid Dynamics on Cluster Architectures Using MPI. International Journal of Computer Science and Technology, 7(5), 33–40.

International Journal of Computer Science and Technology | Vol. 7, No. 4, April 2005 | pp. 25–32

DOI: 10.46882/2005/IJCST/070407

Research Article

Title: Content-Based Image Retrieval Using Color Co-occurrence Matrices and Wavelet Transform Subbands

Names of Authors: Min-Seok Kim¹, Fatma Al-Jahani²

Authors’ Affiliations: ¹Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea; ²Department of Computer Science, Qatar University, Doha, Qatar

Abstract:
As large digital image repositories become increasingly common, standard textual indexing approaches are no longer sufficient for precise image search and retrieval. This paper presents an integrated Content-Based Image Retrieval (CBIR) method that captures spatial color structures and high-frequency textural properties simultaneously. Spatial color distributions are computed using customized Color Co-occurrence Matrices (CCCM), while micro-texture feature extractions are derived from Discrete Wavelet Transform (DWT) subband coefficient variances. The system was validated against the Corel 1,000-image benchmark dataset. Experimental results demonstrate a mean precision rate of P = 89.4% and a recall index of R = 82.1% across ten distinct semantic image categories. This configuration outperformed standard color histogram indexing frameworks by 16.3% in precision. The average indexing query response execution time was recorded at t = 68 ms per retrieval iteration, establishing a reliable baseline for large-scale multimedia search tasks.

Keywords: Content-Based Image Retrieval, Color Co-occurrence Matrix, Discrete Wavelet Transform, Texture Features, Multimedia Databases

Manuscript Timeline: Received January 05, 2005; Revised February 18, 2005; Accepted March 12, 2005; Published April 21, 2005

Citation: Kim, M. S., & Al-Jahani, F. (2005). Content-Based Image Retrieval Using Color Co-occurrence Matrices and Wavelet Transform Subbands. International Journal of Computer Science and Technology, 7(4), 25–32.