Amelia Ritahani Ismail

An immune-inspired swarm aggregation algorithm for self-healing swarm robotic systems

Swarm robotics is concerned with the decentralised coordination of multiple robots having only limited communication and interaction abilities. Although fault tolerance and robustness to individual robot failures have often been used to justify the use of swarm robotic systems, recent studies have shown that swarm robotic systems are susceptible to certain types of failure. In this paper we propose an approach to self-healing swarm robotic systems and take inspiration from the process of granuloma formation, a process of containment and repair found in the immune system. We use a case study of a swarm performing team work where previous works have demonstrated that partially failed robots have the most detrimental effect on overall swarm behaviour. We have developed an immune inspired approach that permits the recovery from certain failure modes during operation of the swarm, overcoming issues that effect swarm behaviour associated with partially failed robots.

Towards Self-Healing Swarm Robotic Systems Inspired by Granuloma Formation

Granuloma is a medical term for a ball-like collection of immune cells that attempts to remove foreign substances from a host organism. This response is a special type of inflammatory reaction common to a wide variety of diseases. Granulomas are an organised collection of macrophages, whose formation involves the stimulation of macrophages as well as T-Cells. Fault tolerance in swarm robotic systems is essential to the continued operation of swarm robotic systems. Under certain conditions, a failing robot can have a detrimental effect on the overall swarm behaviour, causing stagnation in the swarm and affecting its ability to undertake its task. Our study is concerned specifically with modelling the trafficking of macrophages and T-cells in the development of granuloma formation, and using that as a basis to create a self-healing swarm robotic system, in the context of power system failure.

Development of effluent removal prediction model efficiency in septic sludge treatment plant through clonal selection algorithm

This study aims at developing a novel effluent removal management tool for septic sludge treatment plants (SSTP) using a clonal selection algorithm (CSA). The proposed CSA articulates the idea of utilizing an artificial immune system (AIS) to identify the behaviour of the SSTP, that is, using a sequence batch reactor (SBR) technology for treatment processes. The novelty of this study is the development of a predictive SSTP model for effluent discharge adopting the human immune system. Septic sludge from the individual septic tanks and package plants will be desuldged and treated in SSTP before discharging the wastewater into a waterway. The Borneo Island of Sarawak is selected as the case study. Currently, there are only two SSTPs in Sarawak, namely the Matang SSTP and the Sibu SSTP, and they are both using SBR technology. Monthly effluent discharges from 2007 to 2011 in the Matang SSTP are used in this study. Cross-validation is performed using data from the Sibu SSTP from April 2011 to July 2012. Both chemical oxygen demand (COD) and total suspended solids (TSS) in the effluent were analysed in this study. The model was validated and tested before forecasting the future effluent performance. The CSA-based SSTP model was simulated using MATLAB 7.10. The root mean square error (RMSE), mean absolute percentage error (MAPE), and correction coefficient (R) were used as performance indexes. In this study, it was found that the proposed prediction model was successful up to 84 months for the COD and 109 months for the TSS. In conclusion, the proposed CSA-based SSTP prediction model is indeed beneficial as an engineering tool to forecast the long-run performance of the SSTP and in turn, prevents infringement of future environmental balance in other towns in Sarawak.

Clustering Natural Language Morphemes from EEG Signals Using the Artificial Bee Colony Algorithm

We present a preliminary study on the use of a Brain Computer Interface (BCI) device to investigate the feasibility of recognizing patterns of natural language morphemes from EEG signals. This study aims at analyzing EEG signals for the purpose of clustering natural language morphemes using the Artificial Bee Colony (ABC) algorithm. Using as input the features extracted from EEG signals during morphological priming tasks, our experimental results indicate that applying the ABC algorithm on EEG datasets to cluster Malay morphemes produces promising results.

Modelling immune systems responses for the development of energy sharing strategies for swarm robotic systems

This paper presents an initial investigation on studying an immune systems response, the granuloma formation, for inspirations on the development of energy sharing strategies for swarm robotic systems. Granuloma formation is a process in which unwanted substances are removed by immune systems. To better understand the components and the processes in granuloma formation, we modeled them using Unified Modelling Language (UML). Based on this model, analogous properties of the granuloma formation and swarm robotic systems are mapped accordingly. Based on these work, energy sharing strategies which are inspired by the process in granuloma formation are proposed for fault tolerance in swarm robotic systems.

A comparative study of clonal selection algorithm for effluent removal forecasting in septic sludge treatment plant

The development of effluent removal prediction is crucial in providing a planning tool necessary for the future development and the construction of a septic sludge treatment plant (SSTP), especially in the developing countries. In order to investigate the expected functionality of the required standard, the prediction of the effluent quality, namely biological oxygen demand, chemical oxygen demand and total suspended solid of an SSTP was modelled using an artificial intelligence approach. In this paper, we adopt the clonal selection algorithm (CSA) to set up a prediction model, with a well-established method - namely the least-square support vector machine (LS-SVM) as a baseline model. The test results of the case study showed that the prediction of the CSA-based SSTP model worked well and provided model performance as satisfactory as the LS-SVM model. The CSA approach shows that fewer control and training parameters are required for model simulation as compared with the LS-SVM approach. The ability of a CSA approach in resolving limited data samples, non-linear sample function and multidimensional pattern recognition makes it a powerful tool in modelling the prediction of effluent removals in an SSTP.

The Initial Investigation of the Design and Energy Sharing Algorithm Using Two-Ways Communication Mechanism for Swarm Robotic Systems

Swarm Robotics (SR) is a new field of study that is mainly concerned with con-trolling and coordinating a multiple small robots. SR has several key characteristics that make it a preferable choice for a variety of tasks. The characteristics include lower cost, easiness to program, scalability of tasks and fault tolerance. The robustness from fault tolerance in SR comes from having a group of small robots working on the same task and thus enabling them to tolerate the loss of a few members of the swarm as the other members can still continue with the mission. However it has shown that continuous failure of members of a swarm such as those due to low energy have a significant impact on the overall performance of the swarm. In addition, the possibility of completion of the task is also dependent on the percentage of the swarm falling out of the group due insufficient energy. Some of the work that has been proposed by the researchers is by adding a charging station or a removable charger. However, these techniques have their own limitations. Therefore a work on having the robot(s) to charger themselves without the help of the charging station or a removable charger is proposed. But the work is only proven successful in simulation without a proper design and testing in a real robots scenario. This paper is therefore will describe our initial investigation on the design and the implementation of energy sharing algorithm using two-ways robotic swarm communication mechanism with NRF2401.

An Analysis of Ambiguity Detection Techniques for Software Requirements Specification (SRS)

Ambiguity is the major problem in Software Requirements Specification (SRS) documents because most of the SRS documents are writ-ten in natural language and natural language is generally ambiguous. There are various types of techniques that have been used to detect ambiguity in SRS documents. Based on an analysis of the existing work, the ambiguity detection techniques can be categorized into three approaches: (1) manual approach, (2) semi-automatic approach using natural language processing, (3) semi-automatic approach using machine learning. Among them, one of the semi-automatic approaches that uses the Naive Bayes (NB) text classification technique obtained high accuracy and performed effectively in detecting ambiguities in SRS.

Comparative Performance of Deep Learning and Machine Learning Algorithms on Imbalanced Handwritten Data

Imbalanced data is one of the challenges in a classification task in machine learning. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms, such as deep belief networks showed promising results in many domains, especially in image processing. Therefore, in this paper, we will review the effect of imbalanced data disparity in classes using deep belief networks as the benchmark model and compare it with conventional machine learning algorithms, such as backpropagation neural networks, decision trees, naive Bayes and support vector machine with MNIST handwritten dataset. The experiment shows that although the algorithm is stable and suitable for multiple domains, the imbalanced data distribution still manages to affect the outcome of the conventional machine learning algorithms.

Comparative Performance of Machine Learning Algorithms for Cryptocurrency Forecasting

Received May 20, 2018 Revised Jun 21, 2018 Accepted Jun 25, 2018 RFID technology is a Radio frequency identification system that provides a reader reading the data item from its tag. Nowadays, RFID system has rapidly become more common in our life because of its autonomous advantages compared to the traditional barcode. It can detect hundreds of tagged items automatically at a time. However, in RFID, missing tag detection can occur due to signal collisions and interferences. It will cause the system to report incorrect tag’s count due to an incorrect number of tags being detected. The consequences of this problem can be enormous to business, as it will cause incorrect business decisions to be made. Thus, a Missing Tag Detection Algorithm (MTDA) is proposed to solve the missing tag detection problem. There are many other existing approaches has been proposed including Window Sub-range Transition Detection (WSTD), Efficient Missing-Tag Detection Protocol (EMD) and Multi-hashing based Missing Tag Identification (MMTI) protocol. The result from experiments shows that our proposed approach performs better than the other in terms of execution time and reliability.Received May 1, 2018 Revised Jun 21, 2018 Accepted Jun 28, 2018 The diagnosing features for Diabetic Retinopathy (DR) comprises of features occurring in and around the regions of blood vessel zone which will result into exudes, hemorrhages, microaneurysms and generation of textures on the albumen region of eye balls. In this study we presenta probabilistic convolution neural network based algorithms, utilized for the extraction of such features from the retinal images of patient’s eyeballs. The classificat ions proficiency of various DR systems is tabulated and examined. The majority of the reported systems are profoundly advanced regarding the analyzed fundus images is catching up to the human ophthalmologist’s characterization capacities.Received Nov 25, 2017 Revised Jan 9, 2018 Accepted May 27, 2018 The usage of multilevel inverter has increased in a drastic manner for the past years. These novel inverters are useful in various mega power applications. As they are having the ability to change the output waveforms, they are having good harmonic distortions and better output results. This work proposes a novel five level asymmetrical inverter which is incorporated with the zeta converter. Comparison is made with the existing multilevel inverter with the proposed system. The simulation results give the proposed system has less THD [1] when compared to the existing multilevel inverters. The main objective is that the number of switches and capacitors are reduced which in turn reduces the loss and the cost. From the output results is has been proved that the proposed topology gives reduced loss and high quality output when compared with the conventional methods.Received Dec 26, 2017 Revised Jan 09, 2018 Accepted May 26, 2018 Evolutionary Algorithms (EAs) are the potential tools for solving optimization problems. The EAs are the population based algorithms and they search for the optimal solution(s) from a initial set of candidates solutions known as population. This population is to be initialized at first before the evolution of the algorithm starts. There exists different ways to initialize this population. Understanding and choosing the right population initialization technique for the given problem is a difficult task for the researchers and problem solvers. To alleviate this issue, this paper is framed with two objectives. The first objective is to present the details of various Population Initialization (PI) techniques of EAs, for the readers to give brief description of all the PI techniques. The second objective is to present the steps and empirical comparison of the results of two different PI techniques implemented for Differential Evolution (DE) algorithm. Theoretical insights and empirical results of the PI techniques are presented in this paper.Received May 23, 2018 Revised Jun 21, 2018 Accepted Jul 2, 2018 Smoothing filters are essential for noise removal and image restoration. Gaussian filters are used in many digital image and video processing systems. Hence the hardware implementation of the Gaussian filter becomes a reliable solution for real time image processing applications. This paper discusses the implementation of a novel Gaussian smoothing filter with low power approximate adders in Field Programmable Gate Array (FPGA). The proposed Gaussian filter is applied to restore the noisy images in the proposed system. Original test images with 512x512 pixels were taken and divided in to 4x4 blocks with 256x256 pixels. The proposed technique has been applied and the performance metrics were measured for various simulation criteria. The proposed algorithm is also implemented using approximate adders, since approximate adders had been recognized as a reliable alternate for error tolerant applications in circuit based metrics such as power, area and delay where the accuracy may be considered for trade off.Muhammad Farrel Pramono 1 , Kevin Renalda 2 , Harco Leslie Hendric Spits Warnars 3 , Dedy Prasetya Kristiadi 4 , Worapan kusakunniran 1,2 Information Systems Department, School of Information Systems, Bina Nusantara University, Jakarta, Indonesia 11480 3 Computer Science Department, BINUS Graduate Program-Doctor of Computer Science, Bina Nusantara University , Jakarta, Indonesia 11480 4 Computer Systems, STMIK Raharja, Tangerang Banten, Indonesia 15119 Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, ThailandSoft Computing and Data Mining Centre, Faculty of Computer Sciences and Information Technology, Universiti Tun Hussein Onn Malaysia Faculty of Creative Technology and Heritage, Universiti Malaysia Kelantan, Karung Berkunci 01, 16300, Bachok, Kelantan, Malaysia School of Industrial Engineering, Telkom University, 40257 Bandung, West Java, Indonesia Laboratory of Biodiversity and Bioinformatics, Universiti Teknologi Malaysia, 81300 Skudai, Johor, Malaysia Faculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, Pahang, Malaysia Department of Software Engineering & Information System, Faculty of Computer Science and Information Technology, University Putra Malaysia (UPM), 43400 Selangor, Serdang, MalaysiaReceived Mar 19, 2018 Revised May 20, 2018 Accepted Jun 3, 2018 Kinect-based physical rehabilitation grows significantly as a mechanism for clinical assessment and rehabilitation due to its flexibility, low-cost and markerless system for human action capture. It is also an approach to provide convenience for for patients’ exercises continuation at home. In this paper, we discuss a review of the present Kinect-based physiotherapy and assessment for rehabilitation patients to provide an outline of the state of art, limitation and issues of concern as well as suggestion for future work in this approach. The paper is constructed into three main parts. The introduction was discussed on physiotherapy exercises and the limitation of current Kinect-based applications. Next, we also discuss on Kinect Skeleton Joint and Kinect Depth Map features that being used widely nowadays. A concise summary with significant findings of each paper had been tabulate for each feature; Skeleton Joints and Depth Map. Afterwards, we assemble a quite number of classification method that being implemented for activity recognition in past few years.Received May 9, 2018 Revised Jun 2, 2018 Accepted Jun 21, 2018 As the cloud computing is gaining more user base the problem of simultaneously catering computational resources to multitude of users or their application is on rise. It remains a critical problem and pose hindrance in scalability of cloud computing. Thus, in order to layout the proper solution for the mentioned problem; it is necessary to sum up a proper knowledge based of the existing solution, there drawbacks and a detail analysis of its performances. In this study we present a review of multi-tenant frameworks and approaches used in the industry which reaps advantages to facilitate multi-tenancy.