An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

The wavelet transform has emerged over recent years as a powerful time-frequency analysis and signal coding tool favoured for the interrogation of complex nonstationary signals. Its application to biosignal processing has been at the forefront of these developments where it has been found particularly useful in the study of these, often problematic, signals: none more so than the ECG. In this review, the emerging role of the wavelet transform in the interrogation of the ECG is discussed in detail, where both the continuous and the discrete transform are considered in turn.

/pdf/wavelet-transforms-and-the-ecg-a-review-36a6zg0xg1.pdf

Wavelet transforms and the ECG: a review.

Pattern recognition

Machine learning algorithms for wireless sensor networks: A survey

Increasing cost and demand of energy has led many organizations to find smart ways for monitoring, controlling and saving energy. A smart Energy Management System (EMS) can contribute towards cutting the costs while still meeting energy demand. The emerging technologies of Internet of Things (IoT) and Big Data can be utilized to better manage energy consumption in residential, commercial, and industrial sectors. This paper presents an Energy Management System (EMS) for smart homes. In this system, each home device is interfaced with a data acquisition module that is an IoT object with a unique IP address resulting in a large mesh wireless network of devices. The data acquisition System on Chip (SoC) module collects energy consumption data from each device of each smart home and transmits the data to a centralized server for further processing and analysis. This information from all residential areas accumulates in the utility’s server as Big Data. The proposed EMS utilizes off-the-shelf Business Intelligence (BI) and Big Data analytics software packages to better manage energy consumption and to meet consumer demand. Since air conditioning contributes to 60% of electricity consumption in Arab Gulf countries, HVAC (Heating, Ventilation and Air Conditioning) Units have been taken as a case study to validate the proposed system. A prototype was built and tested in the lab to mimic small residential area HVAC systems1.

A smart home energy management system using IoT and big data analytics approach

There is no doubt that prevention is better than cure, preventing insect infestation on farm will save more than 40% of agricultural farm destruction [1]. Therefore, this paper presents the design and simulation of an agricultural robot. It is based on the execution of a harmful insect detection algorithm and equipped with non-chemical based killing mechanism. Previous agricultural insect/pest killing robots aim at reducing bulk chemical application on farm by dosing chemical (pesticide) on the agricultural farm after it has been affected. However, this work took a natural approach by adopting killing method of a bird scientifically refer to as BUBULCUS ibis. The objective of the proposed system is to detect the insect at early stage (larvae) and then kill it. This approach shows that we could handle several insects with simple robot and ecofriendly killing mechanism. The designed mobile manipulator robot has a 4-DOF manipulator mounted on a 2-DOF skid driven mobile platform Seekur Jr. The manipulator link lengths have been optimized to cover the workspace with maximum manipulability, and the cross sections have been designed for minimum deflection. The robot has been equipped with an eco-friendly laser light of 480 nm wavelength, 7W power as a killing mechanism and 2 RGB cameras feeds into our detection algorithm. Results from the co-simulation of ADAMS MSC and MATLAB/SIMULINK with computer vision toolbox shows a good detection capability and controller response with minimal tracking error. Significant correction of the approximate initial position was achieved with image-based visual servoing. The simulation results indicates the success of our proposed system.

Insect Killing Robot for Agricultural Purposes

This paper presents a new adaptive mutation approach for fastening the convergence of immune algorithms (IAs). This method is adopted to realize the twin goals of maintaining diversity in the population and sustaining the convergence capacity of the IA. In this method, the mutation rate (pm) is adaptively varied depending on the fitness values of the solutions. Solutions of high fitness are protected, while solutions with sub-average fitness are totally disrupted. A solution to the problem of deciding the optimal value of pm is obtained. Experiments are carried out to compare the proposed approach to traditional one on a set of optimization problems. These are namely: 1) an exponential multi-variable function; 2) a rapidly varying multimodal function and 3) design of a second order 2-D narrow band recursive LPF. Simulation results show that the proposed method efficiently improves IA’s performance and prevents it from getting stuck at a local optimum.

/pdf/a-new-method-for-fastening-the-convergence-of-immune-3za6uzxakr.pdf

A New Method for Fastening the Convergence of Immune Algorithms Using an Adaptive Mutation Approach

Many wireless applications are deployed and available to customers via their mobile phones. Variety of these applications and services are based on determination of the current or future location of mobile user. Location based services (LBS) are one of the vital applications which are subdivided into two main categories: economical category and public category. Economic applications include mobile marketing, entertainment and tracking applications. Whereas, emergency cases, safety, traffic management, Muslims’ applications and public information applications are sort of public applications. The first part of the paper presents a new proposed system with developed procedure to recreate public and economic applications with high positioning accuracy and good authentication of users’ data. The developed system is created to enhance both location based services and network allocation resources within mobile network platform using either normal or GPS supported mobile equipment. The second part of the paper introduces future location prediction of mobile user dependent applications. New algorithm is developed depending on utilizing both intra-cell Movement Pattern algorithm (ICMP) [1] and hybrid uplink time Difference of Arrival and Assisted GPS technique (UTDOA_AGPS) [2]. It has been noticed that ICMP algorithm outperforms other future location prediction algorithms with high precision and within suitable time (less than 220) msec. However, UTDOA_AGPS guarantees high precession of mobile user independent of the surrounding environment. The proposed technique is used to enhance reliability and efficiency of location based services using cellular network platform.

https://file.scirp.org/pdf/IJCNS_2013041713292519.pdf

Services and Applications Based on Mobile User’s Location Detection and Prediction

An interactive filter design program suitable for both experts and non-experts is described. It can be used for the design and synthesis of 64 filter families. These include: lumped, wave-digital (WD) FIR and IIR filters where each may be lowpass, highpass, band rejection, bandpass or phase corrector. Four amplitude approximation functions are available for all these cases; namely Butterworth, Chebyshev, inverse Chebyshev and elliptic approximation functions. Although it operates in both batch and interactive modes, this paper deals exclusively with the interactive mode which is somewhat more general and very easy to use. The filter designer offers superior accuracy and flexibility in manipulating filters with different specifications and network realizations. The synthesized networks are in the form of an LC ladder for lumped filters; lattice and bireciprocal for wave-digital filters: direct form for FIR filters as well as direct, cascade and parallel realizations for IIR filters. Utilities are given for the analysis of the amplitude, phase and group delay for all possible filter designs. In addition, pole-zero patterns and network realization are available in both numerical and graphical formats. Examples illustrating different design and synthesize capabilities are given.

Filter designer: a complete design and synthesis program for lumped, wave-digital, FIR and IIR filters

In this paper, a new approach for human recognition using heart sounds is proposed. The new approach is based mainly on extracting features from heart sounds using wavelet packet decomposition. Different linear and non-linear filter banks at different decomposition levels are designed using wavelet packet decomposition to select the appropriate bases for extracting discriminant features. Automatic wavelet de-noising and linear discriminant analysis are adopted for pre-processing and classification stages, respectively. The proposed system is tested using an open database for heart sounds known as HSCT-11 which contains data collected from 206 subjects. Based on the achieved results, the proposed system can identify subjects with best accuracy of 91.05% and verify them with an equal error rate of 3.2%. The obtained results in this paper show that wavelet packet based features are appropriate for human recognition task using heart sounds.

Sabah M. Ahmed

Papers

Insect Killing Robot for Agricultural Purposes

A New Method for Fastening the Convergence of Immune Algorithms Using an Adaptive Mutation Approach

Services and Applications Based on Mobile User’s Location Detection and Prediction

Filter designer: a complete design and synthesis program for lumped, wave-digital, FIR and IIR filters

A new biometric authentication system using heart sounds based on wavelet packet features