International Journal of Computer Science and Technology

International Journal of Computer Science and Technology | Vol. 11, No. 8, August 2009 | pp. 57–64

DOI: 10.46882/2009/IJCST/000017

Article Type: Research Article

Title: Real-Time Human Face Recognition Using Local Binary Patterns and Principle Component Analysis

Names of Authors: Fatima Al-Sayed¹, Youssef Mansour²

Authors’ Affiliations: ¹Department of Computer Engineering, Cairo University, Giza, Egypt; ²Faculty of Information Technology, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

Abstract: Computer vision systems deployed in surveillance frameworks require high facial recognition accuracy alongside computational lightness for real-time video processing. This paper introduces an integrated face recognition framework combining Local Binary Patterns (LBP) for robust texture feature extraction with Principal Component Analysis (PCA) for dimensional reduction. By applying LBP prior to projection, our method maintains resilience against variations in ambient illumination and subtle facial expressions. Testing was executed using the extended Yale Face Database B and the ORL database. The hybrid LBP-PCA system achieved a peak recognition accuracy of 97.8% under variable lighting environments, outperforming standard Eigenfaces approaches by 6.4%. Execution latency tests registered an average matching time of 15.1 milliseconds per frame on standard hardware configurations, rendering it suitable for real-time security installations. The results prove that localized spatial descriptor fusion significantly strengthens global projection matrices against environmental noise without elevating computational costs.

Keywords: Face Recognition, Local Binary Patterns, Principal Component Analysis, Feature Extraction, Computer Vision, Surveillance Systems

Manuscript Timeline: Received: January 11, 2009; Revised: February 22, 2009; Accepted: March 15, 2009; Published: August 14, 2009

Citation: Al-Sayed, F., & Mansour, Y. (2009). Real-Time Human Face Recognition Using Local Binary Patterns and Principle Component Analysis. International Journal of Computer Science and Technology, 11(8), 57–64.

International Journal of Computer Science and Technology | Vol. 8, No. 7, June 2006 | pp. 49–56

DOI: 10.46882/2006/IJCST/080722

Research Article

Title: Energy-Efficient Topology Control Protocols for Wireless Sensor Networks via Minimum Spanning Trees

Names of Authors: Budi Santoso¹, Grace Hopper Moore²

Authors’ Affiliations: ¹Department of Electrical Engineering, Universitas Indonesia, Jakarta, Indonesia; ²Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA

Abstract:
Sensors in battery-powered wireless networks must conserve energy to avoid network disconnections caused by early power depletion. This paper develops an energy-efficient topology control protocol that reduces node transmission power while keeping the network fully connected. The protocol uses a localized adaptation of the Minimum Spanning Tree (MST) algorithm, where each node updates its transmission range based on distance vector estimates collected from immediate neighbors. Network simulations with 300 sensor nodes spread across a 600m x 600m field show that the protocol extended the network's operational lifetime by 37.4% compared to un-optimized networks. The average transmission power per node fell from P = 25 mW down to P = 8.4 mW ± 0.6 mW. The system minimized packet loss rates to less than 1.5% during routing phases, confirming that local topology controls can protect wireless network lifespans without creating routing delays.

Keywords: Wireless Sensor Networks, Topology Control, Minimum Spanning Tree, Energy Management, Network Simulation

Manuscript Timeline: Received April 05, 2006; Revised May 18, 2006; Accepted June 05, 2006; Published June 28, 2006

Citation: Santoso, B., & Moore, G. H. (2006). Energy-Efficient Topology Control Protocols for Wireless Sensor Networks via Minimum Spanning Trees. International Journal of Computer Science and Technology, 8(7), 49–56.

International Journal of Computer Science and Technology | Vol. 5, No. 4, April 2024 | pp. 1–8

DOI: 10.46882/2024/IJCST/000232

Article Type: Original Research Paper

Title: Graph-Based Anomaly Detection in Decentralized Identity Management Systems Using Temporal Tracking

Names of Authors: Elena Rostova¹, Yuki Tanaka²

Authors’ Affiliations: ¹Data Engineering Laboratory, NordTech University, Oslo, Norway; ²Advanced VLSI Systems Laboratory, Tokyo Institute of Technology, Tokyo, Japan

Abstract: Abstract: Decentralized identity frameworks allow web users to control their personal credentials without relying on centralized single sign-on systems. However, malicious users can exploit these networks by creating multiple fake accounts to skew voting metrics or bypass security limits. This paper presents an automated anomaly isolation framework that maps decentralized identity validation logs using a Temporal Graph Neural Network (TGNN). The model builds real-time structural graphs tracking interaction speeds, link patterns, and credential verification histories. A dynamic edge-weighting algorithm identifies abnormal account groups and separates suspicious nodes based on localized graph changes. We validated this network defense layer using a verification dataset of 12,000 decentralized verification logs under active stress. The system isolated suspicious identity patterns with a 96.4% classification rate. The detection pipeline executed its analysis within a strict timeframe of 32 ms per verification request, proving its viability for live application tracking.

Keywords: Decentralized Identity, Graph Neural Networks, Anomaly Detection, Sybil Attacks, Network Security, Token Verification

Manuscript Timeline: Received: September 12, 2023; Revised: November 20, 2023; Accepted: January 18, 2024; Published: April 12, 2024

Citation: Rostova, E., & Tanaka, Y. (2024). Graph-Based Anomaly Detection in Decentralized Identity Management Systems Using Temporal Tracking. International Journal of Computer Science and Technology, 5(5), 1–8. DOI: 10.46882/2024/IJCST/000232

International Journal of Computer Science and Technology | Vol. 5, No. 3, March 2024 | pp. 1–8

DOI: 10.46882/2024/IJCST/000230

Article Type: Original Research Paper

Title: Quantifying Carbon Emission Footprints in Distributed Cloud Architectures via Runtime Telemetry Tracking

Names of Authors: Elena R. Rostova¹, Jean-Pierre Dubois²

Authors’ Affiliations: ¹Cloud Metrics Division, Global Tech Systems, Stockholm, Sweden; ²Department of Computer Science, Swiss Federal Institute of Technology, Lausanne, Switzerland

Abstract: Large-scale cloud data centers consume significant electrical energy, contributing to global carbon emissions. However, existing sustainability metrics estimate carbon impacts using static server configurations, failing to capture dynamic load variations or localized grid energy mixes. This paper presents an automated runtime monitoring framework named Eco-Track that quantifies carbon emission footprints at the individual container level. Eco-Track tracks server hardware activities, including CPU instruction counts, memory cycles, and thermal profiles. It cross-references this real-time consumption data with regional grid carbon intensity tracking feeds. The framework automatically moves low-priority processing tasks to data center zones operating on green energy sources. We tested the tracking tool across a multi-region distributed cloud infrastructure. The tracking results show that Eco-Track accurately measures individual software task carbon footprints with a margin of error under ±2.5%. Implementing our automated task migration loop reduced total operational carbon impacts by 18.6% without degrading application performance metrics.

Keywords: Green Computing, Cloud Data Centers, Carbon Footprint Tracking, Runtime Telemetry, Container Metrics, Sustainable Software

Manuscript Timeline: Received: August 25, 2023; Revised: October 30, 2023; Accepted: December 12, 2023; Published: March 06, 2024

Citation: Rostova, E. R., & Dubois, J. -P. (2024). Quantifying Carbon Emission Footprints in Distributed Cloud Architectures via Runtime Telemetry Tracking. International Journal of Computer Science and Technology, 5(3), 1–8. DOI: 10.46882/2024/IJCST/000230

International Journal of Computer Science and Technology | Vol. 5, No. 2, February 2024 | pp. 1–8

DOI: 10.46882/2024/IJCST/000229

Article Type: Original Research Paper

Title: Decentralized Cross-Chain Liquidity Routing Pools via Cryptographic Time-Lock Commitments

Names of Authors: Liam O'Donnell¹, Sophia Rossi²

Authors’ Affiliations: ¹School of Computer Science, Trinity College Dublin, Dublin, Ireland; ²FinTech Infrastructure Lab, Bocconi University, Milan, Italy

Abstract: The rapid expansion of decentralized financial architectures has resulted in fragmented liquidity ecosystems isolated across independent, non-compatible blockchain networks. Existing cross-chain bridge mechanisms rely heavily on centralized wrapped tokens, creating single points of failure vulnerable to multi-million dollar exploits. This study introduces a completely decentralized cross-chain liquidity routing protocol utilizing Hash Time-Locked Contracts (HTLCs) combined with threshold signatures. This design allows users to swap digital assets across independent chains without relying on intermediary custody agents. The protocol uses an automated market maker function to balance pool ratios dynamically, minimizing asset slippage across cross-network transactions. We tested the system by processing transactions across independent Ethereum, Avalanche, and Polygon test networks. The tracking evaluations show that cross-chain swaps were finalized within an average duration of 48 seconds. The framework reduced overall transaction cost structures by 28.3% compared to classic bridge implementations while maintaining structural transaction safety.

Keywords: Blockchain, Cross-Chain Bridges, Hash Time-Locked Contracts, Automated Market Makers, Cryptographic Protocols, Liquidity Pools

Manuscript Timeline: Received: August 20, 2023; Revised: October 22, 2023; Accepted: December 05, 2023; Published: February 14, 2024

Citation: O'Donnell, L., & Rossi, S. (2024). Decentralized Cross-Chain Liquidity Routing Pools via Cryptographic Time-Lock Commitments. International Journal of Computer Science and Technology, 5(2), 1–8. DOI: 10.46882/2024/IJCST/000229

International Journal of Computer Science and Technology | Vol. 5, No. 1, January 2024 | pp. 1–8

DOI: 10.46882/2024/IJCST/000228

Article Type: Original Research Paper

Title: Mitigating Epistemic Uncertainty in Autonomous Vehicle Trajectory Planning via Bayesian Neural Networks

Names of Authors: Klaus Meyer¹, Rachel Green²

Authors’ Affiliations: ¹Autonomous Systems Engineering Center, Fraunhofer Institute, Karlsruhe, Germany; ²Robotics Intelligence Group, Apex Auto Labs, Detroit, USA

Abstract: Autonomous vehicle systems operating within highly dynamic urban settings struggle with sensor noise and unpredictable pedestrian activities. Standard deterministic trajectory planning models fail to quantify model uncertainty, occasionally resulting in unsafe maneuvers under novel traffic scenarios. This paper introduces an adaptive trajectory planning framework that uses Bayesian Neural Networks (BNNs) to estimate epistemic uncertainty fields in real time. The model estimates variance boundaries across its structural network paths, outputting a localized confidence metric alongside each path prediction. If tracking confidence falls below a pre-configured target, the navigation layer selects a defensive path option. We verified this framework on an autonomous driving test platform navigating complex urban simulations. The validation results show that our Bayesian model decreased localized near-miss incidents by 41.2% compared to standard deterministic planning networks. The system executed its processing iterations within an average latency window of 22 ms, satisfying real-time safety requirements.

Keywords: Autonomous Vehicles, Trajectory Planning, Bayesian Neural Networks, Epistemic Uncertainty, Safety-Critical Systems, Robotics

Manuscript Timeline: Received: August 12, 2023; Revised: October 15, 2023; Accepted: November 28, 2023; Published: January 08, 2024

Citation: Meyer, K., & Green, R. (2024). Mitigating Epistemic Uncertainty in Autonomous Vehicle Trajectory Planning via Bayesian Neural Networks. International Journal of Computer Science and Technology, 5(1), 1–8. DOI: 10.46882/2024/IJCST/000228