A5068631993- Distributed and Parallel Computing Systems
- Parallel Computing and Optimization Techniques
- Optimization and Search Problems
- Transportation and Mobility Innovations
- Indoor and Outdoor Localization Technologies
- Vehicular Ad Hoc Networks (VANETs)
- Mobile Ad Hoc Networks
- Distributed systems and fault tolerance
- IoT Networks and Protocols
- ECG Monitoring and Analysis
- IoT and Edge/Fog Computing
- Traffic control and management
- Rings, Modules, and Algebras
- Energy Efficient Wireless Sensor Networks
- Imbalanced Data Classification Techniques
- Scheduling and Optimization Algorithms
- Advanced Wireless Communication Technologies
- EEG and Brain-Computer Interfaces
Islamic Azad University, Tehran
2011-2023
Polytechnic Institute of Porto
2023
Instituto Superior de Engenharia do Porto
2023
Islamic Azad University, Science and Research Branch
2018-2019
This paper proposes a hybrid model to classify cardiac arrhythmias and select their features in an optimal way. In the proposed model, Genetic Algorithm was used optimally features, Decision Tree with C4.5 algorithm applied extracted train model. The approach data into normal abnormal classes as well 16-class collection of arrhythmias. To evaluate performance compared similar methods, we UCI arrhythmia dataset along accuracy, sensitivity, specificity, average Sen-Spec metrics. efficiency...
In this paper intelligent search technique of variable structure learning automata (VSLA) has been used to solve single machine total weighted tardiness job scheduling problem.The goal is investigating reduction in delays result late execution the jobs after specified deadline as well reducing time required find best order jobs.For reason, fixed and genetic algorithm approaches studied then a new approach called VSLA-Scheduler proposed by employing technique.In identify strengths weaknesses...
Purpose Grid computing is an effective environment for the execution of parallel applications that requires great power. This paper aims to present, based on hierarchical architecture, improved weighted resource discovery (WRD) algorithm manage allocation resources and minimize cost communications between grid nodes. Design/methodology/approach A behavioral modeling method addressed prove proposed correctness. The model implemented by StarUML tool with two different model-checking...
In recent years, wireless sensor networks are in great use applications like disaster management, combat field reconnaissance, border protection and safe care.Although, much research has been done on networks, but the quality of service (QoS) there not enough researches.Since these widely used many areas, different QoS parameters contrast with traditional such as network coverage, optimal number active nodes, lifetime energy consumption.We have proposed an automata-based scheduling method to...
As penetration of autonomous technology grows, vehicular platooning also becomes a reality with clear benefits on efficiency and traffic management. One can consider that platoons may grow to arbitrary lengths, limited solely by the ability achieving reliable end-to-end communication. We introduce Long Heterogeneous Platoon (LHP) protocol, meant handle very long composed vehicles different characteristics facilities. It creates sub-units, sub-platoons, facilitate platoon maneuvers internal...
In the mid-term future, vehicles will generate large amounts of data for both standalone usage (e.g., to recognize road features and external elements such as lanes, signs, pedestrians) cooperative lane merging). However, processing captured video image results comes with significant computational requirements GPUs). Computer vision tasks, feature extraction, are unfeasible from a business perspective if performed directly in User Equipment (UE), automotive manufacturers unwilling increase...
In this paper an improved approach based on CBR-LA model is proposed for static task assignment in heterogeneous computing systems. The composed of case reasoning (CBR) and learning automata (LA) techniques. LA used as adaptation mechanism that adapts previously experienced cases to the problem which must be solved (new case). goal expressing some weak points proposing new algorithm called ICBR-LA has performance terms Makespan metric. results experiments have shown performs better than previous one.