Keshav Dahal - Academia.edu (original) (raw)

Papers by Keshav Dahal

Hybrid Artificial Intelligence Systems, 2009

The hybridization of heuristics methods aims at exploring the synergies among stand alone heurist... more The hybridization of heuristics methods aims at exploring the synergies among stand alone heuristics in order to achieve better results for the optimization problem under study. In this paper we present a hybridization of Genetic Algorithms (GAs) and Tabu Search (TS) for scheduling in computational grids. The purpose in this hybridization is to benefit the exploration of the solution space by a population of individuals with the exploitation of solutions through a smart search of the TS. Our GA (TS) hybrid algorithm runs the GA as ...

Sustainability

In modern network infrastructure, Distributed Denial of Service (DDoS) attacks are considered as ... more In modern network infrastructure, Distributed Denial of Service (DDoS) attacks are considered as severe network security threats. For conventional network security tools it is extremely difficult to distinguish between the higher traffic volume of a DDoS attack and large number of legitimate users accessing a targeted network service or a resource. Although these attacks have been widely studied, there are few works which collect and analyse truly representative characteristics of DDoS traffic. The current research mostly focuses on DDoS detection and mitigation with predefined DDoS data-sets which are often hard to generalise for various network services and legitimate users’ traffic patterns. In order to deal with considerably large DDoS traffic flow in a Software Defined Networking (SDN), in this work we proposed a fast and an effective entropy-based DDoS detection. We deployed generalised entropy calculation by combining Shannon and Renyi entropy to identify distributed features...

Applied Acoustics

Cough detection has recently been identified as of paramount importance to fully exploit the pote... more Cough detection has recently been identified as of paramount importance to fully exploit the potential of telemedicine in respiratory conditions and release some of the economic burden of respiratory care in national health systems. Current audio-based cough detection systems are either uncomfortable or not suitable for continuous patient monitoring, since the audio processing methods implemented therein fail to cope with noisy environments such as those where the acquiring device is carried in the pocket (e.g. smartphone). Moment theory has been widely applied in a number of complex problems involving image processing, computer vision, and pattern recognition. Their invariance properties and noise robustness make them especially suitable as "signature" features enabling character recognition or texture analysis. A natural extension of moment theory to one-dimensional signals is the identification of meaningful patterns in audio signals. However, to the best of our knowledge only marginal attempts have been made in this direction. This paper applies moment theory to perform cough detection in noisy audio signals. Our proposal adopts the first steps used to extract Mel frequency cepstral coefficients (time-frequency decomposition and application of a filter bank defined in the Mel scale) while the innovation is introduced in the second step, where energy patterns defined for specific temporal frames and frequency bands are characterised using moment theory. Our results show the feasibility of using moment theory to solve such a problem in a variety of noise conditions, with sensitivity and specificity values around 90%, significantly outperforming popular state-of-the-art feature sets.

Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753), 2004

The classical generation scheduling problem defines on/off decisions (commitment) and dispatch le... more The classical generation scheduling problem defines on/off decisions (commitment) and dispatch level of all available generators in a power system for each scheduling period. In recent years researchers have focused on developing new approaches to solve non-classical generation scheduling problems in the newly deregulated and decentralized electricity market place. In this paper a GA based approach has been developed for a system operator to schedule generation in a market akin to that operating in England and Wales. A generation scheduling problem has been formulated and solved using available trading information at the time of dispatch. The solution is updated after new information is obtained in a rolling fashion. The approach is tested for two IEEE network based problems, and achieves comparable results with a Branch and Bound technique in reasonable CPU time.

2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, 2008

Phishing websites are forged web pages that are created by malicious people to mimic web pages of... more Phishing websites are forged web pages that are created by malicious people to mimic web pages of real websites and it attempts to defraud people of their personal information. Detecting and identifying Phishing websites is really a complex and dynamic problem involving many factors and criteria, and because of the subjective considerations and the ambiguities involved in the detection, Fuzzy Logic model can be an effective tool in assessing and identifying phishing websites than any other traditional tool since it offers a more natural way of dealing with quality factors rather than exact values. In this paper, we present novel approach to overcome the 'fuzziness' in traditional website phishing risk assessment and propose an intelligent resilient and effective model for detecting phishing websites. The proposed model is based on FL operators which is used to characterize the website phishing factors and indicators as fuzzy variables and produces six measures and criteria's of website phishing attack dimensions with a layer structure. Our experimental results showed the significance and importance of the phishing website criteria (URL & Domain Identity) represented by layer one, and the variety influence of the phishing characteristic layers on the final phishing website rate.

Fifth International Conference on Information Technology: New Generations (itng 2008), 2008

Security has been widely recognized as one of the main obstacles to the adoption of Internet bank... more Security has been widely recognized as one of the main obstacles to the adoption of Internet banking and it is considered an important aspect in the debate over challenges facing internet banking. The performance evaluation of e-banking websites requires a model that enables us to analyze the various imperative factors and criteria related to the quality and performance of e-banking websites. Ebanking site evaluation is a complex and dynamic problem involving many factors, and because of the subjective considerations and the ambiguities involved in the assessment, Fuzzy Logic (FL) model can be an effective tool in assessing and evaluating of e-banking security performance and quality. In this paper, we propose an intelligent performance assessment model for evaluating e-banking security websites. The proposed model is based on FL operators and produces four measures of security risk attack dimensions: direct internal attack, communication tampering attack, code programming attack and denial of service attack with a hierarchical ring layer structure. Our experimental results show that direct internal attack risk has a large impact on e-banking security performance. The results also confirm that the risk of direct internal attack for e-banking dynamic websites is doubled that of all other attacks.

Lecture Notes in Computer Science, 2008

In this paper we introduce the variable fitness function which can be used to control the search ... more In this paper we introduce the variable fitness function which can be used to control the search direction of any search based optimisation heuristic where more than one objective can be defined, to improve heuristic performance. The method is applied to a multi-objective travelling salesman problem and the performance of heuristics enhanced with the variable fitness function is compared to the original heuristics, yielding significant improvements. The structure of the variable fitness functions is analysed and the search is visualised to better understand the process.

Enhancing University Research Activities with Knowledge Management

ABSTRACT

Lecture Notes in Computer Science, 2007

2007 IEEE Congress on Evolutionary Computation, 2007

Adjustment of a given age distribution to a desired age distribution within a required time frame... more Adjustment of a given age distribution to a desired age distribution within a required time frame is dynamically performed for the purpose of Human Resource (HR) planning in Human Resource Management (HRM). The adjustment process is carried out by adding the adjustment magnitudes to the existing number of employees at the selected age groups on the yearly basis. A model of a discrete dynamical system is employed to emulate the evolution of the age distribution used under the adjustment process. Genetic Algorithms (GA) is applied for determining the adjustment magnitudes that influence the dynamics of the system. An interesting aspect of the problem lies in the high number of constraints; though the constraints are fundamental, they are considerably higher in number than in many other optimization problems. An adaptive penalty scheme is proposed for handling the constraints. Numerical examples show that GA with the utilized adaptive penalty scheme provides potential means for HR planning in HRM.

2009 International Conference on CyberWorlds, 2009

Detecting and identifying any phishing websites in real-time, particularly for e-banking is reall... more Detecting and identifying any phishing websites in real-time, particularly for e-banking is really a complex and dynamic problem involving many factors and criteria. Because of the subjective considerations and the ambiguities involved in the detection, Fuzzy Data Mining (DM) Techniques can be an effective tool in assessing and identifying phishing websites for e-banking since it offers a more natural way of dealing with quality factors rather than exact values. In this paper, we present novel approach to overcome the 'fuzziness' in the e-banking phishing website assessment and propose an intelligent resilient and effective model for detecting e-banking phishing websites. The proposed model is based on Fuzzy logic (FL) combined with Data Mining algorithms to characterize the e-banking phishing website factors and to investigate its techniques by classifying there phishing types and defining six e-banking phishing website attack criteria's with a layer structure. The proposed e-banking phishing website model showed the significance importance of the phishing website two criteria's (URL & Domain Identity) and (Security & Encryption) in the final phishing detection rate result, taking into consideration its characteristic association and relationship with each others as showed from the fuzzy data mining classification and association rule algorithms. Our phishing model also showed the insignificant trivial influence of the (Page Style & Content) criteria along with (Social Human Factor) criteria in the phishing detection final rate result.

Expert Systems with Applications, 2010

Agent Oriented Peer-to-Peer Supply Chain for Collaborative Planning, Forecasting and Replenishment

eastwest.inf.brad.ac.uk

Abstract In today's complex and competitive market, the competition for better performance ... more Abstract In today's complex and competitive market, the competition for better performance is not only limited to be between the manufacturing companies rather it expands to cover the whole supply chain and hence create a competition between the supply chains. In such a ...

Real-Time System Identification Using Intelligent Algorithms

Proc. IEEE Conf. Intell …, 2004

This research presents an investigation into the development of real time system identification u... more This research presents an investigation into the development of real time system identification using intelligent algorithms. A simulation platform of a flexible beam vibration using finite difference (FD) method is used to demonstrate the real time capabilities of the identification ...

An efficient feature selection based Bayesian and rough set approach for intrusion detection

Applied Soft Computing

IEEE Systems Journal

Life time of battery is one of the major concerns in Wireless Sensor Networks (WSNs). Traditional... more Life time of battery is one of the major concerns in Wireless Sensor Networks (WSNs). Traditional network algorithm chooses the data transmission path based on the distance between sender and receiver. For example, in Directed Diffusion (DD), the nodes closer to the sink node are more active so that the continuous data flow of the network is maintained. However, in such scenario, there is an energy hole problem because the nodes closer to the sink reduce their energy since they are more active. But if the residual energy and shortest hop counts can be taken together, then the problem can be overcome. We have analyzed different transmission cost functions with respect to Approximated Uniform Energy Dissipation Directed Diffusion Algorithm (AUEDDD). The final goal of the paper is to find out the suitable cost function to resist the early death of the first node of a network. We introduce dynamic priority variable, which is a tradeoff between total energy consumption and uniform energy dissipation.

Structural and Multidisciplinary Optimization

Free-form surfaces are defined with NURBS (non-uniform rational basis spline) for most computer-a... more Free-form surfaces are defined with NURBS (non-uniform rational basis spline) for most computer-aided engineering (CAE) applications. The NURBS method requires the definition of parameters such as weights, knot vectors and degree of the curves which make the configuration of the surface computationally expensive and complex. When the control points are randomly spaced in the point cloud and the topology of the desired surface is unknown, surface configuration with NURBS method becomes a challenging task. Optimization attempts for such surfaces create enormous amounts of computing data when coupled with physics solvers such as finite element analysis (FEA) tools and computational fluid dynamics (CFD) tools. In this paper, an adapted Delaunay triangulation (ADT) method for surface generation from the random points cloud is proposed and compared with widely used implicit functions based NURBS fitting method. The surface generated from ADT method can be simultaneously used with stochastic optimization algorithms (SOA) and CFD applications to search for the optimal results with minimum computational costs. It was observed while comparing ADT with NURBS-based geometry configuration that the computation time can be reduced by 3 folds. The corresponding deviation between both geometry configuration methods has been observed as low as 5% for all optimisation scenarios during the comparison. In addition, ADT method can provide light weight CFD approach as any instance of design iteration has at least half storage footprint as compared to corresponding NURBS surface. The proposed approach provides novel methodology towards establishing light weight CFD geometry, absence of which currently isolates methodologies for optimization and CFD analysis.

IET Image Processing

Salient object detection (SOD) has been attracting a lot of interest, and recently many computati... more Salient object detection (SOD) has been attracting a lot of interest, and recently many computational models have been developed. In this paper, we formulate a SOD model, in which saliency map is computed as a combination of the colour, its distribution-based saliency and orientation saliency. Similar to traditional SODs, the proposed method is based on super-pixel segmentation and super-pixelutilizes both colour and its distribution-based saliency to generate a coarse saliency map. However, distinct from traditional SODs, we further use orientation contrast to optimize the coarse saliency map to obtain an improved saliency map. Our contributions are twofold. First, we combine colour uniqueness and its distribution with local orientation information (LOI) used in Itti's model to effectively improve profiles of salient regions. Second, a reciprocal function is defined to substitute the Gabor function used in LOI and we have proved that the substitution could detect relatively homogeneous and uniform regions at the boundary of salient object, whereas it is what the traditional models lack. Our approach significantly outperforms state-of-the-art methods on four benchmark datasets while, we demonstrate that the proposed method runs as fast as most existing algorithms.

IET Networks

Life in modern society becomes easier due to rapid growth of different technologies like real-tim... more Life in modern society becomes easier due to rapid growth of different technologies like real-time analytic, ubiquitous wireless communication, commodity sensors, machine learning, and embedded systems. Nowadays, there seems to be a need to merge these technologies in the form of Internet of Things (IoT) so that smart systems can be achieved. On the other hand, cloud computing is a pillar in IoT by which end users get connected through the cloud servers for getting different services. However, to recognize the legitimacy of communicators during communication sessions through insecure channels like the Internet, serious issues in cloud based IoT applications need to be addressed. Thus authentication procedure is highly desirable to remove the unapproved access in IoT applications. This paper presents an ElGamal cryptosystem and biometric information along with a user's password-based authentication scheme for cloud based IoT applications refereed as SAS-Cloud. Security of the proposed scheme has been analyzed by well popular random oracle model and it is found that SAS-Cloud has ability to defend all the possible attacks. Furthermore, performance of SAS-Cloud has been evaluated and it was found that SAS-Cloud has better efficiency than other existing competing ElGamal cryptosystem-based authentication schemes.