scispace - formally typeset
Search or ask a question
Author

Arunkumar Thangavelu

Other affiliations: Central University of Kerala
Bio: Arunkumar Thangavelu is an academic researcher from VIT University. The author has contributed to research in topics: Vehicular ad hoc network & Service (systems architecture). The author has an hindex of 13, co-authored 23 publications receiving 461 citations. Previous affiliations of Arunkumar Thangavelu include Central University of Kerala.

Papers
More filters
Journal ArticleDOI
TL;DR: A new singular value decomposition (SVD) and discrete wavelet transformation (DWT) based technique is proposed for hiding watermark in full frequency band of color images (DSFW) and it is observed that the quality of the watermark is maintained with the value of 36dB.
Abstract: Due to the advancement in Computer technology and readily available tools, it is very easy for the unknown users to produce illegal copies of multimedia data which are floating across the Internet. In order to protect those multimedia data on the Internet many techniques are available including various encryption techniques, steganography techniques, watermarking techniques and information hiding techniques. Digital watermarking is a technique in which a piece of digital information is embedded into an image and extracted later for ownership verification. Secret digital data can be embedded either in spatial domain or in frequency domain of the cover data. In this paper, a new singular value decomposition (SVD) and discrete wavelet transformation (DWT) based technique is proposed for hiding watermark in full frequency band of color images (DSFW). The quality of the watermarked image and extracted watermark is measured using peak signal to noise ratio (PSNR) and normalized correlation (NC) respectively. It is observed that the quality of the watermarked image is maintained with the value of 36dB. Robustness of proposed algorithm is tested for various attacks including salt and pepper noise and Gaussian noise, cropping and JPEG compression.

67 citations

Journal ArticleDOI
TL;DR: An ontology modelling approach for assisting vehicle drivers through safety warning messages during time critical situation is proposed and the presented approach shows the simulation that can be implemented to all vehicles in real time scenario with promising results.
Abstract: This paper proposes an ontology modelling approach for assisting vehicle drivers through safety warning messages during time critical situation. Intelligent Driver Assistance System (I-DAS) is a major component of InVANET[12], which focuses on generating the alert messages based on the context aware parameters such as driving situations, vehicle dynamics, driver activity and environment. I-DAS manages the parameter representation, consistent update /maintenance in XML format while the interpretation of a critical situation is done using ontology modeling. Related safety technologies such as Adaptive Cruise Control, Collision Avoidance System, Lane Departure Warning System, Driver Drowsiness detection system, Parking Assistance System, which generate warnings and alerts to driver continuously, for assistance according to context which is integrated in Vehicle and Vehicle 2 Driver (V2D) communications by DVI(Driver Vehicle Interface) had been applied. The simulation test bed developed using Java framework[21] to generate safety alerts in various driving situations shows the usefulness of this approach. The response time graph for the simulation of context IDAS is depicted and analysed. The effective performance of the driving scenarios in various modes like day and night for single, 2-way and 4-way road scenario for the best, worst and average cases of simulation had been studied. The system works in VANET scenario, which needs to be adaptive for environment changes and to vary according to the context. The presented approach shows the simulation that can be implemented to all vehicles in real time scenario with promising results.

63 citations

Journal ArticleDOI
01 May 2015
TL;DR: This study evaluates the GSD team-level service climate and GSD project outcome relationship based on adaptive neuro-fuzzy inference system (ANFIS) with the genetic learning algorithm and results show that the optimal prediction error is obtained by the HTGLA-based ANFIS approach.
Abstract: ANFIS architecture for a multi-inputs and single output Sugeno model with fuzzy n rules. The GSD team-level service climate is one of the key determinants to achieve the outcome of global software development (GSD) projects.To evaluate the GSD team-level service climate and GSD project outcome relationship based on Adaptive Neuro-Fuzzy Inference System (ANFIS) with the Hybrid Taguchi-Genetic Learning Algorithm (HTGLA).The applicability and capability of HTGLA-based ANFIS approach is investigated through the real data sets obtained from Indian software industries. The GSD team-level service climate is one of the key determinants to achieve the outcome of global software development (GSD) projects from the software service outsourcing perspective. The main aim of this study is to evaluate the GSD team-level service climate and GSD project outcome relationship based on adaptive neuro-fuzzy inference system (ANFIS) with the genetic learning algorithm. For measuring the team-level service climate, the Hybrid Taguchi-Genetic Learning Algorithm (HTGLA) is adopted in the ANFIS, which is more appropriate to determine the optimal premise and consequent constructs by reducing the root-mean-square-error (RMSE) of service climate criteria. For measuring the GSD team-level service climate, synthesizing the literature reviews and consistent with the earlier studies on IT service climate which is classified into three main criterion: managerial practices (deliver quality of service), global service climate (measure overall perceptions), service leadership (goal setting, work planning, and coordination) which comprises 25 GSD team-level service climate attributes. The experimental results show that the optimal prediction error is obtained by the HTGLA-based ANFIS approach is 3.26%, which outperforms the earlier result that is the optimal prediction errors 4.41% and 5.75% determined, respectively, by ANFIS and statistical methods.

51 citations

Journal ArticleDOI
TL;DR: In this paper, a fuzzy multi-criteria decision-making (FMCDM) approach for analyzing the influential factors affecting the outcome/success of global software development (GSD) projects is presented.
Abstract: This study presents a fuzzy multi-criteria decision making (FMCDM) approach for analyzing the influential factors affecting the outcome/success of global software development (GSD) projects. The main aim of this study is to demonstrate the potential of proposed methodology based on FMCDM which is used to measure the offshore/onsite teams’ partnership quality dimensions and underlying the influential factors towards the outcome of GSD projects. The uncertainty and subjective vagueness within the decision making process are dealing with fuzzy linguistic terms quantified in an interval scale [0,1]. The proposed FMDCM framework is used to determine the priority weights of partnership quality factors and rating the GSD project outcome/success from the service provider perspective into three dimensions: service quality, schedule and cost improvement. The predicted GSD project outcome values are obtained to facilitate organization and to determine the impact of offshore/on-site teams’ partnership quality towards success of GSD project outcome otherwise initiate actions to improve the GSD project outcome. This study established survey research method that involves thirty-eight critical influential factors evaluated by twenty software professionals for their assessment of GSD projects outcome in India.

34 citations

Proceedings ArticleDOI
01 Jan 2007
TL;DR: An Intelligent Vehicle Navigation System, which identify an optimally minimal path for navigation with minimal traffic intensity using WiFi, which can be used as a city guide to locate and identify landmarks in a new city.
Abstract: Large cities with fleet of vehicles require a system to determine location of movement of passenger vehicles at a given time. Vehicle tracking systems can be used in theft prevention, retrieval of lost vehicles, providing trafricoriented services on lanes. The Vehicle tracking systems VETRAC enables vehicle drivers or any third party to track the location of any moving vehicle. Most modern vehicle tracking systems use GPS[71 modules which is costly in usage and implementation. Many systems also combine a communications component such as cellular or satellite transmitters to communicate the vehicle's location to a remote user. VETRAC uses WiFi IEEE 802.11 b/g for easy and accurate location of the vehicle, which provides effective and simple communication. Vehicle information can be viewed on electronic maps using the Internet or specialized software. We have designed and developed an Intelligent Vehicle Navigation System, which identify an optimally minimal path for navigation with minimal traffic intensity using WiFi. The system can also be used as a city guide to locate and identify landmarks in a new city.

33 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A taxonomy for vehicular cloud is presented in which special attention has been devoted to the extensive applications, cloud formations, key management, inter cloud communication systems, and broad aspects of privacy and security issues, which found that VCC is a technologically feasible and economically viable technological shifting paradigm for converging intelligent vehicular networks towards autonomous traffic, vehicle control and perception systems.

711 citations

Journal ArticleDOI
TL;DR: This paper surveys each of the localization techniques that can be used to localize vehicles and examines how these localization techniques can be combined using Data Fusion techniques to provide the robust localization system required by most critical safety applications in VANets.

639 citations

Journal ArticleDOI
TL;DR: Analysis and comparison of the results show that all five landslide models performed well for landslide susceptibility assessment, but it has been observed that the SVM model has the best performance in comparison to other landslide models.
Abstract: Landslide susceptibility assessment of Uttarakhand area of India has been done by applying five machine learning methods namely Support Vector Machines (SVM), Logistic Regression (LR), Fisher's Linear Discriminant Analysis (FLDA), Bayesian Network (BN), and Naive Bayes (NB). Performance of these methods has been evaluated using the ROC curve and statistical index based methods. Analysis and comparison of the results show that all five landslide models performed well for landslide susceptibility assessment (AUCź=ź0.910-0.950). However, it has been observed that the SVM model (AUCź=ź0.950) has the best performance in comparison to other landslide models, followed by the LR model (AUCź=ź0.922), the FLDA model (AUCź=ź0.921), the BN model (AUCź=ź0.915), and the NB model (AUCź=ź0.910), respectively. Machine learning methods namely SVM, LR, FLDA, BN, and NB have been evaluated and compared for landslide susceptibility assessment.Results indicate that all these five models can be applied efficiently for landslide assessment and prediction.Analysis of comparative results reaffirmed that the SVM model is one of the best methods.

363 citations

Journal ArticleDOI
Yu Huang1, Lu Zhao1
01 Jun 2018-Catena
TL;DR: A review of landslide susceptibility mapping using SVM, a machine learning algorithm that uses a small number of samples for prediction and has been widely used in recent years, and its strengths and weaknesses.
Abstract: Landslides are natural phenomena that can cause great loss of life and damage to property. A landslide susceptibility map is a useful tool to help with land management in landslide-prone areas. A support vector machine (SVM) is a machine learning algorithm that uses a small number of samples for prediction and has been widely used in recent years. This paper presents a review of landslide susceptibility mapping using SVM. It presents the basic concept of SVM and its application in landslide susceptibility assessment and mapping. Then it compares the SVM method with four other methods (analytic hierarchy process, logistic regression, artificial neural networks and random forests) used in landslide susceptibility mapping. The application of SVM in landslide susceptibility assessment and mapping is discussed and suggestions for future research are presented. Compared with some of the methods commonly used in landslide susceptibility assessment and mapping, SVM has its strengths and weaknesses owing to its unique theoretical basis. The combination of SVM and other techniques may yield better performance in landslide susceptibility assessment and mapping. A high-quality informative database is essential and classification of landslide types prior to landslide susceptibility assessment is important to help improve model performance.

328 citations

Patent
18 Nov 2013
TL;DR: In this paper, an adaptive speed control system for controlling the speed of a vehicle is proposed to detect a curve in the road ahead of the vehicle via processing by the image processor of image data captured by the imaging device.
Abstract: A driver assistance system for a vehicle includes an imaging device having a field of view forward of a vehicle and in a direction of travel of the equipped vehicle, an image processor operable to process image data captured by the imaging device, and a global positioning system operable to determine a geographical location of the vehicle. The equipped vehicle includes an adaptive speed control system for controlling the speed of the equipped vehicle. The adaptive speed control system may reduce the speed of the equipped vehicle responsive at least in part to a detection of a curve in the road ahead of the equipped vehicle via processing by the image processor of image data captured by the imaging device.

305 citations