zaily Mohamed Noor

A Novel Method to Water Level Prediction using RBF and FFA

Water level prediction of rivers, especially in flood prone countries, can be helpful to reduce losses from flooding. A precise prediction method can issue a forewarning of the impending flood, to implement early evacuation measures, for residents near the river, when is required. To this end, we design a new method to predict water level of river. This approach relies on a novel method for prediction of water level named as RBF-FFA that is designed by utilizing firefly algorithm (FFA) to train the radial basis function (RBF) and (FFA) is used to interpolation RBF to predict the best solution. The predictions accuracy of the proposed RBF–FFA model is validated compared to those of support vector machine (SVM) and multilayer perceptron (MLP) models. In order to assess the models’ performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results show that the developed RBF–FFA model provides more precise predictions compared to different ANNs, namely support vector machine (SVM) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real time water stage measurements. The results specify that the developed RBF–FFA model can be used as an efficient technique for accurate prediction of water stage of river.

BRAIN-F: Beacon Rate Adaption Based on Fuzzy Logic in Vehicular Ad Hoc Network

Beacon rate adaption is a way to cope with congestion of the wireless link and it consequently decreases the beacon drop rate and the inaccuracy of information of each vehicle in the network. In a vehicular environment, the beacon rate adjustment is strongly dependent on the traffic condition. Due to this, we firstly propose a new model to detect traffic density based on the vehicle’s own status and the surrounding vehicle’s status. We also develop a model based on fuzzy logic namely the BRAIN-F, to adjust the frequency of beaconing. This model depends on three parameters including traffic density, vehicle status and location status. Channel congestion and information accuracy are considered the main criteria to evaluate the performance of BRAIN-F under both LOS and NLOS. Simulation results demonstrate that the BRAIN-F not only reduces the congestion of the wireless link but it also increases the information accuracy.

High-Speed Shortest Path Co-processor Design

Shortest path algorithms are significant in graph theory and have been applied in many applications such as transportation and networking. Most of the shortest path calculation is performed on general purpose processor where instructions must be run to read the input, compute the result, and set the output which later on will slow down the overall performance. Therefore, the authors proposed a hardware approach which implements FPGA technology to find the shortest path between two nodes. The FPGA approach will demonstrate how parallelism can be used to significantly reduce calculation steps compared to sequential effort. In this paper, A-Star algorithm has been chosen for the shortest path calculation since it can achieve superior time running based on its heuristic behavior.

A Review on Feature Extraction & Classification Techniques for Biosignal Processing (Part V: Gait Signal)

This paper concentrates on Gait signal processing with the emphasis on Parkinsons’s Disease diagnosis. Gait is a novel biometric intended to recognize human from their walking pattern. This paper discussed in general about feature extraction and classification for Gait application. Among the factor discussed and analysed include the techniques advantages, performance and drawbacks.

Intersection and Complement Set (IACS) Method to Reduce Redundant Node in Mobile WSN Localization

The majority of the Wireless Sensor Network (WSN) localization methods utilize a large number of nodes to achieve high localization accuracy. However, there are many unnecessary data redundancies that contributes to high computation, communication, and energy cost between these nodes. Therefore, we propose the Intersection and Complement Set (IACS) method to reduce these redundant data by selecting the most significant neighbor nodes for the localization process. Through duplication cleaning and average filtering steps, the proposed IACS selects the normal nodes with unique intersection and complement sets in the first and second hop neighbors to localize the unknown node. If the intersection or complement sets of the normal nodes are duplicated, IACS only selects the node with the shortest distance to the blind node and nodes that have total elements larger than the average of the intersection or complement sets. The proposed IACS is tested in various simulation settings and compared with MSL* and LCC. The performance of all methods is investigated using the default settings and a different number of degree of irregularity, normal node density, maximum velocity of sensor node and number of samples. From the simulation, IACS successfully reduced 25% of computation cost, 25% of communication cost and 6% of energy consumption compared to MSL*, while 15% of computation cost, 13% of communication cost and 3% of energy consumption compared to LCC.The majority of the Wireless Sensor Network (WSN) localization methods utilize a large number of nodes to achieve high localization accuracy. However, there are many unnecessary data redundancies that contributes to high computation, communication, and energy cost between these nodes. Therefore, we propose the Intersection and Complement Set (IACS) method to reduce these redundant data by selecting the most significant neighbor nodes for the localization process. Through duplication cleaning and average filtering steps, the proposed IACS selects the normal nodes with unique intersection and complement sets in the first and second hop neighbors to localize the unknown node. If the intersection or complement sets of the normal nodes are duplicated, IACS only selects the node with the shortest distance to the blind node and nodes that have total elements larger than the average of the intersection or complement sets. The proposed IACS is tested in various simulation settings and compared with MSL* and LCC. The performance of all methods is investigated using the default settings and a different number of degree of irregularity, normal node density, maximum velocity of sensor node and number of samples. From the simulation, IACS successfully reduced 25% of computation cost, 25% of communication cost and 6% of energy consumption compared to MSL*, while 15% of computation cost, 13% of communication cost and 3% of energy consumption compared to LCC.

Parallel Matrix Multiplication Design for Monocular SLAM

As software profiling is conducted to determine which section of program demand high processing computation in monocular SLAM inverse depth estimation, matrix multiplication is identified to be one of the most time consuming process. The processing is more demanding when the number of features inserted to the image is increased. For that reason, this paper proposes a parallel matrix multiplier design which could accelerate the execution time. In this design, Field Programmable Gate Array (FPGA) technology which allows parallel design to be implemented is presented. The design manipulates existing classical matrix multiplication algorithm into an architecture that would enable data to be processed concurrently.