R. Jagadeesh Kannan

Quasi Opportunistic Supercomputing for Geospatial Socially Networked Mobile Devices

due to several reasons such as attentions given to design features and to modification from littler to medium sized system that results in trivial enhancement in performance.In spite of the tremendous achievement of grids which run parallel jobs, there still exists demand of requesting applications to avail opportunistic computing for considering the right selection of prerogative supercomputers. The objective of this research is to build a framework for on the fly computational commencing on socially convolved terrestrial grids to facilitate the sharing of computing workload over wireless networks as virtual supercomputers of unprecedented power. This will assist computing in heterogeneously interconnected mobile assets, Internet of Things, in crowdedscenarios for variable ranges like: stadiums, shopping centers, and so forth.

An Adaptive Approach of Tamil Character Recognition Using Deep Learning with Big Data-A Survey

Deep learning is currently an extremely active research area in machine learning and pattern recognition society. It has gained huge successes in a broad area of applications such as speech recognition, computer vision, and natural language processing. With the sheer size of data available today, big data brings big opportunities and transformative potential for various sectors; on the other hand, it also presents unprecedented challenges to harnessing data and information. As the data keeps getting bigger, deep learning is coming to play a key role in providing big data predictive analytics solutions. This paper presents a brief overview of deep learning and highlight how it can be effectively applied for optical character recognition in Tamil language.

Membrane Computing Based Scalable Distributed Learning and Collaborative Decision Making for Cyber Physical Systems

Machine to Machine based communication and coordination in cyber physical systems for manufacturing application is a daunting problem. Here, the difficulty is in developing a multi task learning algorithm for finding collaborative key points within high dimensional decision space. In order to overcome such a problem a gradient based method is required to enable distributed control and collaborative decision making. This paper presents membrane computing based gradient method for online multitask learning and controlling the distributed coordination to achieve stochastic planning to formulate optimize semantic network to derive a local optimal policy. Experimental verification is achieved through implementation of several concurrent functioning of mobile robotic platforms.

Multi-user networked framework for virtual reality platform

Networked Virtual Environments (NEV) are sets of disjointed virtual worlds which are topographically set apart from the users yet connected through the communication network to give them the illusion of being in the same virtual location. NVEs are increasingly receiving consideration from business and research point of view. Contrasted with various sorts of possible applications, NVEs require a high responsiveness to ensure continuous streaming of live data for full immersion. It is as yet difficult to develop such applications since it require to create virtual reality framework over distributed databases; as every user needs locally adequate data flow to concurrently construct a scene as with other users and able to accommodate multi-user interactions in the virtual environment. Such information requires simultaneous computation and communication of streaming data. In this study we built up a prototype of a NVE in view of the blend of Minority Game (MG) and Online Induction Algorithm (OIA) with lossless transfer functions.

Cascaded Neural Network Based Data Mining Strategy for Cloud Intrusion Detection

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.

Cooperative Sensors for Identifying an Impulsive Events of Asynchronous Environment

Reducing the risk of person in vehicular network is essential, has premier priority to be achieved with prominent specifics such as collision detection and avoidance. Advances in image processing, falling cost on hardware and others allowed decreasing number of accidents are involved and step out from it. Today, new vehicles list safety as one of the highest priorities and use it as their main selling points. Existing series can detect obstacles in the path, and apply the brakes faster than the car user can. Introducing sensor backed scheme using light control for detecting proximity entity at emergency and decision is made in advance to avoid risk due to fatigue while driving. Falling cost of camera technology, manufacturers are started to equip their vehicles with cameras positioned at various places around the body of the vehicle. To remove any blind spots while driving, where as unpredictable traveling object found. Aim of this scheme is for detecting when a vehicle meets risk zone, drifts out of lane, or when it is within the safe stopping distance of an object ahead of it. This system is vision based, Instead of using the camera again to calculate the distance of the object to determine whether it is within the safe stopping distance, a short wave sensor used. This is done to ensure if such a system is possible, based on minimal cost and hardware usage implementation would be built.

An Efficient System Model for Multicasting Measured Noise Value of Polluting Industries

In highly densely populated country like India, environmental pollution is a major problem. Specifically, the hot mix plant used for laying roadways is posing a threat to the environment by emitting heavy noise and smoke. This paper proposes an air pollution monitoring system that measures the noise generated from polluting hot mix plant and multicast the acquired noise data to the Central Pollution Control Board (CPCB) and other communication media. Initially, the pressure is acquired from sound source by microphone and then converted to electrical signals in time domain. Applying Fast Fourier Transform converts time function into the spectrum of frequency component to which A-weighting filtering technique is applied. The resulting magnitude is given as the input to the microcontroller to calculate the noise in terms of decibels. The calculated value is compared with the ambient air quality standards in respect of noise and then the appropriate outputs are displayed in LCD. The abnormalities are indicated by red, orange and green LED based on the intensity of the sound levels as heavy, medium and normal respectively. To achieve the centralized monitoring process, the results are multicast using GSM module to facilitate the authorities to take the necessary decision.