Rajneesh Sharma

Bio: Rajneesh Sharma is an academic researcher from Netaji Subhas Institute of Technology. The author has contributed to research in topics: Fuzzy logic & Control theory. The author has an hindex of 13, co-authored 50 publications receiving 523 citations. Previous affiliations of Rajneesh Sharma include Insight Enterprises & Indian Institute of Technology Delhi.

Special issue on intelligent tools and techniques for signals, machines and automation

Abstract: This special issue is a selected collection of papers submitted to the First International Conference on Signals, Machines and Automation (SIGMA-2018), February 23–25, 2018, New Delhi, India. These papers have been reviewed and accepted for presentation at the conference and for publication in the Journal of Intelligent & Fuzzy Systems (JIFS). In this special issue there are 49 papers covering a wide range of topics in the area of intelligent systems and their application in various domains. The International Conference SIGMA-2018 aims to provide a common platform to the researchers in related fields to explore and discuss various aspects of artificial intelligence applications and advances in soft computing techniques. The Conference will provide excellent opportunities for the presentation of interesting new research results and discussion about them, leading to knowledge transfer and the generation of new ideas. Among the 49 papers in this special issue, there are twelve papers addressing the applications of intelligent tools and techniques in the operation and control of power systems. In [1], the Ant Colony Optimization (ACO) algorithm is used for mitigating contingencies by means of reconfiguration in an electrical distribution network. The results are validated on the IEEE 30-bus system and show that the algorithm is able to better reduce real power losses

EMD and ANN based intelligent fault diagnosis model for transmission line

Abstract: In the presented work, an intelligent model for fault classification of a transmission line is proposed. Ten different types of faults (LAG, LBG, LCG, LABG, LBCG, LCAG, LAB, LBC, LCA and LABC) have been considered along with one healthy condition on a simulated transmission line system. Post fault current signatures have been used for feature extraction for further study. Empirical Mode Decomposition (EMD) method is used to decompose post fault current signals into Intrinsic Mode Functions (IMFs). These IMFs are used as input variables to an artificial neural network (ANN) based intelligent fault classification model. Relief Attribute Evaluator with Ranker search method is used to select the most relevant input variables for fault classification of a three-phase transmission line. Proposed approach is able to select most relevant input variables and gives better result than other combinations. Ours is a first attempt at using EMD for feature selection in fault classification of transmission lines.

Review article: Synergizing reinforcement learning and game theory-A new direction for control

Abstract: Reinforcement learning (RL) has now evolved as a major technique for adaptive optimal control of nonlinear systems. However, majority of the RL algorithms proposed so far impose a strong constraint on the structure of environment dynamics by assuming that it operates as a Markov decision process (MDP). An MDP framework envisages a single agent operating in a stationary environment thereby limiting the scope of application of RL to control problems. Recently, a new direction of research has focused on proposing Markov games as an alternative system model to enhance the generality and robustness of the RL based approaches. This paper aims to present this new direction that seeks to synergize broad areas of RL and Game theory, as an interesting and challenging avenue for designing intelligent and reliable controllers. First, we briefly review some representative RL algorithms for the sake of completeness and then describe the recent direction that seeks to integrate RL and game theory. Finally, open issues are identified and future research directions outlined.

A Markov Game-Adaptive Fuzzy Controller for Robot Manipulators

Abstract: This paper develops an adaptive fuzzy controller for robot manipulators using a Markov game formulation. The Markov game framework offers a promising platform for robust control of robot manipulators in the presence of bounded external disturbances and unknown parameter variations. We propose fuzzy Markov games as an adaptation of fuzzy Q-learning (FQL) to a continuous-action variation of Markov games, wherein the reinforcement signal is used to tune online the conclusion part of a fuzzy Markov game controller. The proposed Markov game-adaptive fuzzy controller uses a simple fuzzy inference system (FIS), is computationally efficient, generates a swift control, and requires no exact dynamics of the robot system. To illustrate the superiority of Markov game-adaptive fuzzy control, we compare the performance of the controller against a) the Markov game-based robust neural controller, b) the reinforcement learning (RL)-adaptive fuzzy controller, c) the FQL controller, d) the Hinfin theory-based robust neural game controller, and e) a standard RL-based robust neural controller, on two highly nonlinear robot arm control problems of i) a standard two-link rigid robot arm and ii) a 2-DOF SCARA robot manipulator. The proposed Markov game-adaptive fuzzy controller outperformed other controllers in terms of tracking errors and control torque requirements, over different desired trajectories. The results also demonstrate the viability of FISs for accelerating learning in Markov games and extending Markov game-based control to continuous state-action space problems.

Transmission line fault classification using modified fuzzy Q learning

Abstract: The authors propose an adaptive, self-learning fault classifier based on modified fuzzy Q learning (MFQL) for transmission lines. Proposed MFQL fault classifier is able to achieve very high classification accuracy with relatively small number of samples. The authors' is a first attempt at designing a fault identifier using reinforcement learning for fault segregation in transmission lines. The authors' identifier does not assume prior knowledge of transmission line model or target fault information. Raw voltage and current data (supply and load side) is processed using empirical mode decomposition to generate 13 intrinsic mode functions (IMFs'). Classifier employs the J48 algorithm to further prune these 13 IMF's to eight most relevant input variables, which serve as inputs to the MFQL fault classifier. The authors compare performance of the proposed MFQL classifier to other contemporary AI-based classifiers, e.g. neural networks and support vector machines. Simulation results and performance comparison against other AI-based classifiers elucidates that the proposed MFQL-based identifier achieves a significantly higher performance level and could serve as an important tool for transmission line fault diagnosis.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Optimum design of hybrid renewable energy systems: Overview of different approaches

Abstract: Public awareness of the need to reduce global warming and the significant increase in the prices of conventional energy sources have encouraged many countries to provide new energy policies that promote the renewable energy applications. Such renewable energy sources like wind, solar, hydro based energies, etc. are environment friendly and have potential to be more widely used. Combining these renewable energy sources with back-up units to form a hybrid system can provide a more economic, environment friendly and reliable supply of electricity in all load demand conditions compared to single-use of such systems. One of the most important issues in this type of hybrid system is to optimally size the hybrid system components as sufficient enough to meet all load requirements with possible minimum investment and operating costs. There are many studies about the optimization and sizing of hybrid renewable energy systems since the recent popular utilization of renewable energy sources. In this concept, this paper provides a detailed analysis of such optimum sizing approaches in the literature that can make significant contributions to wider renewable energy penetration by enhancing the system applicability in terms of economy.

Arsenic contamination in groundwater: a global perspective with emphasis on the Asian scenario.

Abstract: The incidence of high concentrations of arsenic in drinking-water has emerged as a major publichealth problem. With newer-affected sites discovered during the last decade, a significant change has been observed in the global scenario of arsenic contamination, especially in Asian countries. This communication presents an overview of the current scenario of arsenic contamination in countries across the globe with an emphasis on Asia. Along with the present situation in severely-affected countries in Asia, such as Bangladesh, India, and China, recent instances from Pakistan, Myanmar, Afghanistan, Cambodia, etc. are presented.

Robust Adversarial Reinforcement Learning

Abstract: Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based approaches fail to generalize since: (a) the gap between simulation and real world is so large that policy-learning approaches fail to transfer; (b) even if policy learning is done in real world, the data scarcity leads to failed generalization from training to test scenarios (e.g., due to different friction or object masses). Inspired from H-infinity control methods, we note that both modeling errors and differences in training and test scenarios can be viewed as extra forces/disturbances in the system. This paper proposes the idea of robust adversarial reinforcement learning (RARL), where we train an agent to operate in the presence of a destabilizing adversary that applies disturbance forces to the system. The jointly trained adversary is reinforced -- that is, it learns an optimal destabilization policy. We formulate the policy learning as a zero-sum, minimax objective function. Extensive experiments in multiple environments (InvertedPendulum, HalfCheetah, Swimmer, Hopper and Walker2d) conclusively demonstrate that our method (a) improves training stability; (b) is robust to differences in training/test conditions; and c) outperform the baseline even in the absence of the adversary.

iArc monogrAphs on the evAluAtion oF cArcinogenic risks to humAns

Abstract: pReVIously ClAssIfIed by IARC As “CARCInogenIC to humAns (gRoup 1)” And wAs deVeloped by sIx sepARAte woRkIng gRoups: phARmACeutICAls; bIologICAl Agents; ARsenIC, metAls, fIbRes, And dusts; RAdIAtIon; peRsonAl hAbIts And IndooR CombustIons; ChemICAl Agents And RelAted oCCupAtIons. thIs Volume 100f CoVeRs ChemICAl Agents And RelAted oCCupAtIons, speCIfICAlly 4-AmInobIphenyl, benzIdIne, dyes metAbolIzed to benzIdIne, 4,4’-methylenebIs(2-ChloRoAnIlIne), 2-nAphthylAmIne, oRtho-toluIdIne, AuRAmIne And AuRAmIne pRoduCtIon, mAgentA And mAgentA pRoduCtIon, benzo[A]pyRene, CoAl gAsIfICAtIon, oCCupAtIonAl exposuRes duRIng CoAl-tAR dIstIllAtIon, CoAl-tAR pItCh, Coke pRoduCtIon, untReAted oR mIldly tReAted mIneRAl oIls, shAle oIls, soot, As found In oCCupAtIonAl exposuRe of ChImney-sweeps, oCCupAtIonAl exposuRes duRIng AlumInIum pRoduCtIon, AflAtoxIns, benzene, bIs(ChloRomethyl)etheR And ChloRomethyl methyl etheR, 1,3-butAdIene, 2,3,7,8-tetRAChloRodIbenzo-pARA-dIoxIn, 2,3,4,7,8-pentAChloRodIbenzofuRAn, And 3,3’,4,4’,5-pentAChloRobIphenyl, ethylene oxIde, foRmAldehyde, sulfuR mustARd, VInyl ChloRIde, IsopRopyl AlCohol mAnufACtuRe by the stRong-ACId pRoCess, mIsts fRom stRong InoRgAnIC ACIds, oCCupAtIonAl exposuRes duRIng IRon And steel foundIng, oCCupAtIonAl exposuRe As A pAInteR, oCCupAtIonAl exposuRes In the RubbeR mAnufACtuRIng IndustRy. beCAuse the sCope of Volume 100 Is so bRoAd, Its monogRAphs ARe foCused on key InfoRmAtIon. eACh monogRAph pResents A desCRIptIon of A CARCInogenIC Agent And how people ARe exposed, CRItICAl oVeRVIews of the epIdemIologICAl studIes And AnImAl CAnCeR bIoAssAys, And A ConCIse ReVIew of the Agent’s toxICokInetICs, plAusIble meChAnIsms of CARCInogenesIs, And potentIAlly susCeptIble populAtIons, And lIfe-stAges. detAIls of the desIgn And Results of IndIVIduAl epIdemIologICAl studIes And AnImAl CAnCeR bIoAssAys ARe summARIzed In tAbles. shoRt tAbles thAt hIghlIght key Results ARe pRInted In Volume 100, And moRe extensIVe tAbles thAt InClude All studIes AppeAR on the monogRAphs pRogRAmme websIte (http://monogRAphs.IARC.fR). It Is hoped thAt thIs Volume, by CompIlIng the knowledge ACCumulAted thRough seVeRAl deCAdes of CAnCeR ReseARCh, wIll stImulAte CAnCeR pReVentIon ACtIVItIes woRldwIde, And wIll be A VAlued ResouRCe foR futuRe ReseARCh to IdentIfy otheR Agents suspeCted of CAusIng CAnCeR In humAns. D es ig n by A ude la d es m ot s