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.).

Machine learning

In this survey paper, we characterize the learning problem in cognitive radios (CRs) and state the importance of artificial intelligence in achieving real cognitive communications systems. We review various learning problems that have been studied in the context of CRs classifying them under two main categories: Decision-making and feature classification. Decision-making is responsible for determining policies and decision rules for CRs while feature classification permits identifying and classifying different observation models. The learning algorithms encountered are categorized as either supervised or unsupervised algorithms. We describe in detail several challenging learning issues that arise in cognitive radio networks (CRNs), in particular in non-Markovian environments and decentralized networks, and present possible solution methods to address them. We discuss similarities and differences among the presented algorithms and identify the conditions under which each of the techniques may be applied.

A Survey on Machine-Learning Techniques in Cognitive Radios

Summary form only given. The layered architecture is one of the key reasons behind the explosive and continuing growth of the Internet. There are, however, special networks in which cross-layer design is appropriate and may even be necessary. Two such cases are small wireless LAN and large-scale sensor networks. We consider first the design of medium access control (MAC) for a small wireless LAN based on a multiuser physical layer. We present a complete characterization of the throughput region and present conditions under which ALOHA is optimal. Next we consider the estimation of signal field using data collected from a large scale sensor network. The impact of medium access control on estimation is examined. We show that there exists a threshold on sensor outage probability above which a distributed random access protocol (such as ALOHA) outperforms the centralized deterministic schedulers.

On cross-layer design of wireless networks

The emerging Internet-of-Things (IoT) are vulnerable to Sybil attacks where attackers can manipulate fake identities or abuse pseudoidentities to compromise the effectiveness of the IoT and even disseminate spam. In this paper, we survey Sybil attacks and defense schemes in IoT. Specifically, we first define three types Sybil attacks: SA-1, SA-2, and SA-3 according to the Sybil attacker’s capabilities. We then present some Sybil defense schemes, including social graph-based Sybil detection (SGSD), behavior classification-based Sybil detection (BCSD), and mobile Sybil detection with the comprehensive comparisons. Finally, we discuss the challenging research issues and future directions for Sybil defense in IoT.

Sybil Attacks and Their Defenses in the Internet of Things

The Internet of Medical Things (IoMT) designates the interconnection of communication-enabled medical-grade devices and their integration to wider-scale health networks in order to improve patients’ health. However, because of the critical nature of health-related systems, the IoMT still faces numerous challenges, more particularly in terms of reliability, safety, and security. In this paper, we present a comprehensive literature review of recent contributions focused on improving the IoMT through the use of formal methodologies provided by the cyber-physical systems community. We describe the practical application of the democratization of medical devices for both patients and health-care providers. We also identify unexplored research directions and potential trends to solve uncharted research problems.

/pdf/internet-of-medical-things-a-review-of-recent-contributions-2ft727ty1v.pdf

Internet of Medical Things: A Review of Recent Contributions Dealing With Cyber-Physical Systems in Medicine

Wireless sensor networks has grown a lot in recent years and offers excellent opportunities in defense related applications such as monitoring environment and collecting data related to antisocial activities. Currently, the needs of wireless sensors have become inevitable in daily life. With the continuous growth of Wireless sensor networks in daily life, business, and defense applications, the security of transferring data from sensors to their destination has become an important research area. Due to the limitations of power, storage, and processing capabilities, current security mechanisms of wireless networks or wired networks can not apply directly to wireless sensor networks. So there is a need to develop new techniques or modify the current security mechanisms to transfer data from source (from the field) to base station (destination). In this paper, we discuss currently available intrusion detection techniques, attack models using game theory, and then propose a new framework to detect malicious nodes using zero sum game approach for nodes in the forward data path. The first part of research provides the game model with probability of energy required for transferring the data packets. The second part derives the model to detect the malicious nodes using probability of acknowledgement at source.

A Game Theory Approach to Detect Malicious Nodes in Wireless Sensor Networks

The problem of detecting malicious nodes in wireless sensor networks is considered. Since current security mechanisms are inadequate for wireless sensor networks, we must develop a new framework to detect malicious nodes using Zero-Sum game approach and selective node acknowledgements in the forward data path. The first few sections of the paper provide a game model with probability of cost required to defend the nodes and the subsequent sections derives the model to detect malicious nodes using the probability of acknowledgment at source.

http://bit.csc.lsu.edu/~ssrini1/papers/GameTheory_MED_2009.pdf

Game theory model for selective forward attacks in wireless sensor networks

The cyber-physical systems are the combination of computational elements and physical entities that can interact with humans through many modalities. The security includes the malicious attempts by adversary that disrupts or destructs the functions of physical systems that affects infrastructure, businesses, and routine human life. The research in cyber-physical systems is in its infantry. The work requires the development of security models at cloud interacting with physical systems. The current research discusses four parts. The security requirements in the future engineering systems includes the state of security in cloud cyberphysical systems, security requirements in Hadoop distributed file systems and trust-based security model in sensor networks. Further, the proposed research develops the agent-based approach as an example of trust-based packet transfer. The approach keeps the each node’s current status. The results show that maintaining the ratings of each node, the trust can be calculated and eliminate the malicious node.

Cyber-Physical Systems: Survey

Dr. Natarajan Meghanathan is a tenured Associate Professor of Computer Science at Jackson State University, Jackson, MS. He graduated with a Ph.D. in Computer Science from The University of Texas at Dallas in May 2005. Dr. Meghanathan has published more than 140 peer-reviewed articles (more than half of them being journal publications). He has also received federal education and research grants from the U. S. National Science Foundation, Army Research Lab and Air Force Research Lab. Dr. Meghanathan has been serving in the editorial board of several international journals and in the Technical Program Committees and Organization Committees of several international conferences. His research interests are Wireless Ad hoc Networks and Sensor Networks, Graph Theory, Network and Software Security, Bioinformatics and Computational Biology. For more information, visit http://www.jsums.edu/cms/nmeghanathan. Released: June 2013 An Excellent Addition to Your Library!

Cognitive Radio Technology Applications for Wireless and Mobile Ad Hoc Networks

The efficient utilization of underutilized spectrum is the main theme of current research. The cognitive radio with the help of Q-learning algorithm is used to detect the presence of primary signals and utilize the spectrum in the absence of primary signals. The proposed Q-learning algorithm model identifies previously known signals and learns to detect the signals which otherwise could not be detected, and helps for efficient utilization of spectrum. The simulations are further confirmed with results obtained through MATLAB gatool.

Yenumula B. Reddy

Papers

A Game Theory Approach to Detect Malicious Nodes in Wireless Sensor Networks

Game theory model for selective forward attacks in wireless sensor networks

Cyber-Physical Systems: Survey

Cognitive Radio Technology Applications for Wireless and Mobile Ad Hoc Networks

Detecting Primary Signals for Efficient Utilization of Spectrum Using Q-Learning