There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

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

Wireless indoor positioning systems have become very popular in recent years. These systems have been successfully used in many applications such as asset tracking and inventory management. This paper provides an overview of the existing wireless indoor positioning solutions and attempts to classify different techniques and systems. Three typical location estimation schemes of triangulation, scene analysis, and proximity are analyzed. We also discuss location fingerprinting in detail since it is used in most current system or solutions. We then examine a set of properties by which location systems are evaluated, and apply this evaluation method to survey a number of existing systems. Comprehensive performance comparisons including accuracy, precision, complexity, scalability, robustness, and cost are presented.

Survey of Wireless Indoor Positioning Techniques and Systems

The PASCAL Visual Object Classes Challenge

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

In the modern world, a rapid growth of malicious software production has become one of the most significant threats to the network security. Unfortunately, widespread signature-based anti-malware strategies can not help to detect malware unseen previously nor deal with code obfuscation techniques employed by malware designers. In our study, the problem of malware detection and classification is solved by applying a data-mining-based approach that relies on supervised machine-learning. Executable files are presented in the form of byte and opcode sequences and n-gram models are employed to extract essential features from these sequences. Feature vectors obtained are classified with the help of support vector classifiers integrated with a genetic algorithm used to select the most essential features, and a game-theory approach is applied to combine the classifiers together. The proposed algorithm, ZSGSVM, is tested by using a set of byte and opcode sequences obtained from a set containing executable files of benign software and malware. As a result, almost all malicious files are detected while the number of false alarms remains very low.

/pdf/support-vector-machine-integrated-with-game-theoretic-54kfn78f79.pdf

Support vector machine integrated with game-theoretic approach and genetic algorithm for the detection and classification of malware

Wireless Sensor Networks (WSN) consist of autonomous and intelligent nodes that combine sensing, actuation, and distributed computing with small size and low energy One of the major issues is overcoming the non-ideality of unreliable real-world wireless links and avoiding interferences This paper presents a link quality-based lightweight channel selection mechanism that discovers low interference and lightly loaded channels, thus improving latency, reliability, and throughput The mechanism grades a channel from link reliability and changes the channel on interference The proposed selection is suitable for resource and energy constrained WSNs as it does not require any extra communication or channel sensing The channel selection is implemented with a low energy 24GHz multihop mesh WSN using 1mW transmission power In practical measurements in a typical office environment with 100mW WLAN interference, the selection had 96% average link reliability compared to the 84% of randomized channel selection

Link quality-based channel selection for resource constrained WSNs

Resource constrained wireless sensor networks (WSN) require an energy efficient medium access control (MAC) protocol that minimizes the radio active time (duty cycle). Time slotted MAC schemes provide lowest duty cycles by dividing time into consecutive data exchange and sleep periods. Synchronization for data exchange and network maintenance is achieved by exchanging beacons. For detecting changes in network topology, nodes periodically perform scanning during which beacons are received from neighbors. This is energy consuming, and the energy required equals to the transmission of thousands of packets. This paper shows that the energy consumption is mainly depending on the beacon transmission rate, and that an optimal rate is a function of three parameters: a network scanning interval, beacon transmission energy, and radio reception power. The optimal beacon transmission rate is derived for a TUTWSN prototype by power analysis and energy models. According to the analysis, the optimization decreases the average network energy consumption up to an order of magnitude. For the prototype, the optimal beacon transmission rate is 3.7 Hz, when network scanning is performed with 2 minutes intervals

Energy optimized beacon transmission rate in a wireless sensor network

Automatic-dependent surveillance-broadcast (ADS-B) is a cornerstone of the next-generation digital sky and is now mandated in several countries. However, there have been many reports of serious security vulnerabilities in the ADS-B architecture. In this article, we demonstrate and evaluate the impact of multiple cyberattacks on ADS-B via remote radio frequency links that affected various network, processing, and display subsystems used within the ADS-B ecosystem. Overall we implemented and tested 12 cyberattacks on ADS-B in a controlled environment, out of which 5 attacks were presented or implemented for the first time. For all these attacks, we developed a unique testbed that consists of 36 tested configurations. Each of the attacks was successful on various subsets of the tested configurations. In some attacks, we discovered wide qualitative variations and discrepancies in how particular configurations react to and treat ADS-B inputs that contain errors or contradicting flight information, with the main culprit almost always being the software implementation. In some other attacks, we managed to cause denial of service by remotely crashing/impacting more than 50% of the test set that corresponded to those attacks. We also implemented, and report some practical countermeasures to these attacks. We demonstrated that the strong relationship between the received signal strength and the distance-to-emitter might help verify the aircraft.s advertised ADS-B position and distance. For example, our best machine learning models achieved 90% accuracy in detecting attackers' spoofed ADS-B signals.

/pdf/cybersecurity-attacks-on-software-logic-and-error-handling-26wtbfvt.pdf

Cybersecurity Attacks on Software Logic and Error Handling Within ADS-B Implementations: Systematic Testing of Resilience and Countermeasures

Software and embedded system companies today encounter problems related to requirements management tool integration, incorrect tool usage, and lack of traceability. This is due to utilized tools with no clear meta-model and semantics to communicate requirements between different stakeholders. This paper presents a comprehensive meta-model for requirements management. The focus is on software and embedded system domains. The goal is to define generic requirements management domain concepts and abstract interfaces between requirements management and system development. This leads to a portable requirements management meta-model which can be adapted with various system modeling languages. The created meta-model is prototyped by translating it into a UML profile. The profile is imported into a UML tool which is used for rapid evaluation of meta-model concepts in practice. The developed profile is associated with a proof of concept report generator tool that automatically produces up-to-date documentation from the models in form of web pages. The profile is adopted to create an example model of embedded system requirement specification which is built with the profile.

/pdf/meta-model-and-uml-profile-for-requirements-management-of-1m7et2pzdh.pdf

Timo Hämäläinen

Papers

Support vector machine integrated with game-theoretic approach and genetic algorithm for the detection and classification of malware

Link quality-based channel selection for resource constrained WSNs

Energy optimized beacon transmission rate in a wireless sensor network

Cybersecurity Attacks on Software Logic and Error Handling Within ADS-B Implementations: Systematic Testing of Resilience and Countermeasures

Meta-Model and UML Profile for Requirements Management of Software and Embedded Systems