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

Recent development of wireless communication systems and standards is characterized by constant increase of allocated spectrum resources. Since lower frequency ranges cannot provide sufficient amount of bandwidth, new bands are allocated at higher frequencies, for which operators might resort to deploy more base stations to ensure the same coverage. Connecting increased number of base stations to the backhaul network with wired connections becomes a non-trivial task and requires more capital investments. To overcome this challenge, it is possible to consider relaying technologies. However, as the operating frequency range increases, so the relay communication range shrinks, which in turn calls for multi-hop relays.

Multi-hop relays for high frequency next generation wireless systems

The low cost and variety of future clients (e.g., PDAs, laptops, pagers, printers, and specialized appliances) will result in a larger number of client devices per user. Thin clients will have fast processors, but little or no disk storage so that they will download most of their data and executables. The existence of cheap client hardware with high-resolution graphics and high-quality audio together with high-bandwidth networks will probably lead to applications with increasing demands on network and server performance. We focus on the development of a high-performance, cache-based architecture that is general enough to support most type of server applications. Such an architecture should enable the server to achieve very close to the maximum performance that the architecture can achieve. In addition, customizability and handling heterogeneous objects are also relevant to the architecture because it must be general enough to support a wide variety of applications with different QoS needs.

Method for improving cache hit-rates in QoS-aware load balancing algorithm (QoS-LB)

Mobile IPv6 (MIPv6) has been standardized for mobility management in the IPv6 network. When a mobile node changes its point of attachment in the IPv6 network, it experiences a time due MIPv6 procedures when it cannot receive or send any packets. This time called the handover delay might also cause packet loss resulting undesired quality-of-service degradation for various types of applications. The minimization of this delay is especially important for real-time applications. In this chapter we present a fast handover method called the flowbased fast handover for Mobile IPv6 (FFHMIPv6) to speed up the MIPv6 handover processes. FFHMIPv6 employs flow information and IPv6-in-IPv6 tunneling for the fast redirection of the flows during the MIPv6 handover. Also, FFHMIPv6 employs a temporary hand-offaddress to minimize the upstream connectivity. We present the performance results comparing the FFHMIPv6 method to other fundamental handover methods with Network Simulator 2 (ns2) and Mobile IPv6 for Linux (MIPL) network.

A Fast Handover Method for Real-Time Multimedia Services

In this paper, we review the currently proposed, and most potential, host-centric multihoming solutions by the Internet Engineering Task Force. The concerns, related to the scalability and performance of the global routing system in current and in the IPv6 Internet, resulted in the selection of host-centric approaches to multihoming. It strengthens the endto-end nature of the Internet, which proved to be so important and beneficial, by pushing more logic to the edge of the network. At the same time, this approach opens some new challenges for end hosts and also new possibilities. Core challenges include fault tolerance and transport layer survivability in the face of network failures, renumbering or host mobility; while new possibilities arise in host-centric traffic engineering. We describe how current solutions tackle these challenges.

State of Host-Centric Multihoming in IP Networks

FPGAs are traditionally designed with RTL-level IP-block descriptions. Many FPGA designs include several synthesizable processors and SW executables are mapped to them after a separate software development process. The tools help connecting physical blocks together and typically provide a board support package for SW development to access HW from the application code. The designer is still responsible of carefully planning how the applications on multiple cores communicate, which is getting the more difficult the more cores and other IP blocks are introduced. We apply Multicore Association Communications API (MCAPI) to implement hardware independent communication mechanism between the applications. The benefit is a unified programming API to different processor and operating system types, but also for hardware IP-blocks that the cores can access. We introduce MCAPI and show a case study of a simple video encoder with and without MCAPI abstraction. Porting an application function takes 3 hours with MCAPI and 5 without, i.e. 40% reduction. However, the overhead from MCAPI is increase memory footprint by 25 KB and effect on the video encoder performance -22% compared to non-MCAPI case.

Timo Hämäläinen

Papers

Multi-hop relays for high frequency next generation wireless systems

Method for improving cache hit-rates in QoS-aware load balancing algorithm (QoS-LB)

A Fast Handover Method for Real-Time Multimedia Services

State of Host-Centric Multihoming in IP Networks

MCAPI abstraction on FPGA based SoC design