Papers by Mohammad Hamdan
Parallel bio-inspired algorithms have been successful in solving multi-objective optimisation pro... more Parallel bio-inspired algorithms have been successful in solving multi-objective optimisation problems. In this work, we discuss a parallel particle swarm algorithm with added clustering for solving multi-objective optimisation problems. The aim of this work is to perform sensitivity analysis of the parallel particle swarm algorithm. We need to see how the added parallelism improves the overall execution time. Also, looked at the effect of different strategies for population initialisation (such as mutating current set of leaders, random population and lookup in archive for nearest points using geometric calculation). The results show that using different migration frequencies for scattering reduced the overall overlap between processors. Results regarding how clustering and gathering affect performance metrics are also reported.
Information Innovation Technology in Smart Cities, 2017
Health monitoring system is an important application since the last decade. A Health monitoring s... more Health monitoring system is an important application since the last decade. A Health monitoring system comprises of different health sensors such as wearable sensor, ECG sensor, pillow sensor and bed sensor. All of these sensors operate on the license-free 2.4-GHz industrial, scientific, and medical band (ISM). Thus probably the issue of interference by other devices is high especially the ones that use this band like microwave oven and Wi-Fi. Here, we try to provide a mathematical multiobjective model to help understand the issues and impacts of 2.4-GHz ISM band interference on IEEE 802.15.4 health sensors. Our composite model maximizes network throughput and energy efficiency. We used three evolutionary algorithms: SPEA-II, NSGA-II and OMOPSO for the experimental evaluation of our study. The findings are interesting as interference varies according to topology and distance.
International Journal of Technology Diffusion, 2018
In this article, we have proposed a novel tool that helps to objectively quantify eye blink rate.... more In this article, we have proposed a novel tool that helps to objectively quantify eye blink rate. Using the proposed algorithm, a threshold for normal blink rate can be set to test those who have to reduce eye blink rate and are prone to ocular surface dryness. The statistical results show excellent agreement between software-detected number of blinks and visually measured with 90% accuracy for the participants. In addition, the comparison between our tool and other approaches of eye blink monitoring shows that our tool is competitive with only 5% wasted blinks.
2015 11th International Conference on Innovations in Information Technology (IIT), 2015
Health monitoring system has been an important application in the last decade. There are many typ... more Health monitoring system has been an important application in the last decade. There are many types of health sensors that make this system worth and real like wearable sensor, bed sensor and ECG sensor. Primarily, these sensors operate on the license-free 2.4-GHz industrial, scientific, and medical band (ISM). This feature makes this system not only easily applicable, but also probably vulnerable to intrusion and interference by other appliances that works on this band like Wi-Fi and microwave oven. In this paper we introduce and discuss the modeling of a multi objective problem with consideration on the aspects that affect these models. We try to maximize energy efficiency and packet throughput. The work has been tested using three evolutionary algorithms: SPEA-II, NSGA-II and OMOPSO.
International Journal of Open Problems in Computer Science and Mathematics, 2015
The most challenges of Wireless Body Area Network (WBAN) are energy consumption because its works... more The most challenges of Wireless Body Area Network (WBAN) are energy consumption because its works using limited resource like battery and end-to-end delay because it is used to transmit real time parameters of patients' health status like Electrocardiogram (ECG). In this paper we present and discuss the modeling of a multi objective problem. The first objective is the minimization of the end to end delay; the second objective is maximization of the energy efficiency of the network depending on packets payload size. We use jMetal to test the problem using three genetic algorithms (NSGA-II, SPEA-II and OMOPSO) and we compare between them.
The International Journal on Communications Antenna and Propagation, 2017
Health care is very expensive for countries with large population. Recently, wireless sensor netw... more Health care is very expensive for countries with large population. Recently, wireless sensor networks are used to structure health care in many applications. Wireless Body Area Network (WBAN) and remote health monitoring has minimized the cost and improved the health care monitoring of patients' vital signs at hospital or outside hospital environment. Many types of wireless sensors are used for monitoring patient's health status, including those that are attached to the patient's body such as heart rate sensor, blood pressure sensor, temperature sensor, and those used on bed (bed sensor). Sensors use a modern communication technology, such as Zigbee, to transmit patients’ health status parameters to the central monitor. We propose a novel approach for health monitoring system. The new approach depends on a smart health network, where patients are classified into a set of clusters, based on their health status. This approach helps manage communications between patients...
International Journal of Applied Metaheuristic Computing, 2016
This paper presents a detailed optimization analysis of tower height and rotor diameter for a wid... more This paper presents a detailed optimization analysis of tower height and rotor diameter for a wide range of small wind turbines using Genetic Algorithm (GA). In comparison with classical, calculus-based optimization techniques, the GA approach is known by its reasonable flexibilities and capability to solve complex optimization problems. Here, the values of rotor diameter and tower height are considered the main parts of the Wind Energy Conversion System (WECS), which are necessary to maximize the output power. To give the current study a practical sense, a set of manufacturer's data was used for small wind turbines with different design alternatives. The specific cost and geometry of tower and rotor are selected to be the constraints in this optimization process. The results are presented for two classes of small wind turbines, namely 1.5kW and 10kW turbines. The results are analyzed for different roughness classes and for two height-wind speed relationships given by power and ...
In this paper, a new approach was identified and tested to detect abnormal events in producing we... more In this paper, a new approach was identified and tested to detect abnormal events in producing wells when a labeled dataset is unavailable or the number of instances are below 10% and are insufficient for conventional modelling methods. Autoencoders (AE), a type of unsupervised learning, are trained to learn normal behavior by trying to reconstruct the input data that is fed into the model. When run in prediction mode, low reconstruction errors are classified as Normal behavior whilst higher errors are classified as anomalous behavior. Different model structures were tested. An average accuracy of 94% with a precision and recall rate of 70% was achieved using a 6-Layered AE-NN model. The results of the models created show encouraging results and can help detect events and notify engineers when the well is deviates from expected behavior.
This paper looks at two variants of polynomial mutation used in various evolutionary optimisation... more This paper looks at two variants of polynomial mutation used in various evolutionary optimisation algorithms for mutliobjective problems. The first is a non-highly disruptive and the second is a highly disruptive mutation. Both are used for problems with box constraints. A new hybrid polynomial mutation that combines the benefits of both is proposed and implemented. The experiments with three evolutionary multi-objective algorithms on well-known multi-objective optimisation problems show the difference in terms of generational distance, hypervolume, convergence speed and hit rate metrics. The hybrid polynomial mutation in general retains the advantages of both versions in the same algorithm.
Lecture Notes in Computer Science, 2015
Evolutionary algorithms are the most widely used meta-heuristics for solving multi objective opti... more Evolutionary algorithms are the most widely used meta-heuristics for solving multi objective optimization problems, and since all of these algorithms are population based, such as NSGAII, there are a set of factors that affect the final outcomes of these algorithms such as selection criteria, crossover, mutation and fitness evaluation. Unfortunately, little research sheds light at how to generate the initial population. The common method is to generate the initial population randomly. In this work, a set of initialization methods were examined such as, Latin hypercube sampling LHS, Quasi-Random sampling and stratified sampling. Nonetheless. We also propose a modified version of Latin Hypercube sampling method called Quasi_LHS that uses Quasi random numbers as a backbone in its body. Furthermore, we propose a modified version of Stratified sampling method that uses Quasi-Random numbers to represent the intervals. For our research, a set of well known multi objective optimization problems were used in order to evaluate our initial population strategies using NSGAII algorithm. The results show that the proposed initialization methods Quasi_LHS and Quasi-based Stratified improved to some extent the quality of final results of the experiments.
2020 IEEE Congress on Evolutionary Computation (CEC), 2020
Parallel evolutionary algorithms have been used for solving multiobjective optimization problems.... more Parallel evolutionary algorithms have been used for solving multiobjective optimization problems. The aim is to find or approximate the Pareto optimal set in a reasonable time. In this work, we present a new approach that divides the objective search-space into different partitions and assigns each processor its corresponding partition. Each processor will try to find the set of solutions for its partition only. The sub-Pareto fronts will be combined later and the parallelisation approach is based on a mutli-start approach by having independent algorithm on every processor with its own starting points. Experimental results on well known test cases showed that the proposed method outperformed several state-of-the-art evolutionary algorithms regarding convergence to the true Pareto front and gave very competitive results when considering the hypervolume metric. Also, superlinear speedup results were achieved for all test functions.
Journal of Advanced Transportation
Journal of Intelligent Systems
In agile software processes, the issue of team size is an important one. In this work we look at ... more In agile software processes, the issue of team size is an important one. In this work we look at how to find the optimal, or near optimal, self-organizing team size using a genetic algorithm (GA) which considers team communication efforts. Communication, authority, roles, and learning are the team’s performance characteristics. The GA has been developed according to performance characteristics. A survey was used to evaluate the communication weight factors, which were qualitatively assessed and used in the algorithm’s objective function. The GA experiments were performed in different stages: each stage results were tested and compared with the previous results. The results show that self-organizing teams of sizes ranged from five to nine members scored more. The model can be improved by adding other team characteristics, i.e. software development efforts and costs.
International Journal of Bio Inspired Computation, 2011
Intelligent Water Drops (IWD) algorithm is a new metaheuristic approach belongs to a class of swa... more Intelligent Water Drops (IWD) algorithm is a new metaheuristic approach belongs to a class of swarm intelligence based algorithms. It is inspired from observing processes of natural water swarm that happen in the natural river systems. This paper presents an improved IWD algorithm based on developing an adaptive schema to prevent the IWD algorithm from premature convergence. The performance of the Adaptive-IWD is compared with Original IWD and other metaheuristic algorithms in solving Travelling Salesman Problem (TSP). The results clearly show that the proposed algorithm has better performance than those of Original IWD, and MIWD-TSP algorithm and very competitive results to others metaheuristics.
Govt Inform Quart, 2009
With the latest revolution of technology in information, communications, and media, the need for ... more With the latest revolution of technology in information, communications, and media, the need for computerization has been identified in most countries. Many social and technical advantages and problems come along with it. As a result, the Information Society concept has been created. There exist certain principles for building such a society, but in Arab regions it has unique challenges and obstacles. Jordan, responding to a royal vision, has established the goal of becoming a leader in information and economic developments among other countries in the region. Several plans and initiatives have been developed for this purpose. One of these initiatives is the implementation of e-Government, which offers several benefits for both the government and society. e-Government has five building blocks to achieve the expected results and the process of implementation involves passing through certain stages. Jordan, as an Arab country, faces several obstacles in the area of implementation. A readiness study for Jordan has been accomplished and implementation and achievements have been made in Jordanian e-Government.
Communications libraries like MPI enable architecture independent parallel program development bu... more Communications libraries like MPI enable architecture independent parallel program development but cannot alone guarantee performance consistency across different architectures. Here an algorithmic skeleton for a process farm is discussed and an architecture independent performance model is developed for it. The skeleton has been ported from a Meiko Computing Surface to a Cray T3D and a Fujitsu AP1000, demonstrating consistent behaviour. Preliminary performance prediction accuracy on the Cray T3D is around 90%, on a test application based on arbitrary length arithmetic. (The performance model is currently being instantiated for the other systems. This will be reported in the final paper.) 1 Introduction It is well known that parallelism adds an additional level of difficulty to software development. Following Cole's characterisation[3], algorithmic skeletons have been recognised widely as a valuable basis for parallel software construction. A skeleton abstracts a control structu...
There is a big need for the parallelisation of genetic algorithms. In this paper, a heterogeneous... more There is a big need for the parallelisation of genetic algorithms. In this paper, a heterogeneous framework for the global parallelisation of genetic algorithms is presented. The framework uses a static all-worker parallel programming paradigm based on collective communication. It follows the single program multiple data parallel programming model. It utilises the power of parallel machines by allowing multiple crossover and mutation operators being used within a single genetic algorithm. This mixture of operators can be applied to the strings of a population in parallel without changes to the canonical sequential genetic algorithm. These features help the parallel genetic algorithm in exploiting the search space efficiently and thoroughly when compared to the sequential genetic algorithm. The framework is instantiated with specific parameters to solve an NP-hard problem, the asymmetric travelling salesman problem. The results for the parallel genetic algorithm are very good in term...
A Thorough Analysis Of Various Nesting Structures Of Algorithmic Skeletons Mohammad M. Hamdan Dep... more A Thorough Analysis Of Various Nesting Structures Of Algorithmic Skeletons Mohammad M. Hamdan Dept. of Computer Science Yarmouk University Jordan E-mail: hamdan@ yu. edu. jo ABSTRACT: Nested Higher-order functions can be realised by the corresponding nested algorithmic skeletons. Here we give a thorough analysis of various nesting structures for two examples. The results show that the parallel implementations of the higher-order functions allow nesting of arbitrary skeletons and for an arbitrary depth. KEYWORDS: 1 ...
Uploads
Papers by Mohammad Hamdan