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 paper by Kim et al. (2003), the authors propose a new image scaling method called winscale. The presented method can be used for scaling up and down. However, scaling down utilizing the winscale concept gives exactly the same results as the well-known bilinear interpolation. Furthermore, compared to bilinear, scaling up with the proposed winscale "overlap stamping" method has very similar calculations. The basic winscale upscaling differs from the bilinear method.

Comments on "Winscale: an image-scaling algorithm using an area pixel Model"

In Wireless Sensor Networks (WSNs), a robust and energy-efficient Medium Access Control (MAC) protocol is required for high energy efficiency in harsh operating conditions, where node and link failures are common This paper presents the design of a novel MAC protocol for low-power WSNs The developed MAC protocol minimizes the energy overhead of idle time and collisions by strict frame synchronization and slot reservation It combines a dynamic bandwidth adjustment mechanism, multicluster-tree network topology, and a network channel allowing rapid and low-energy neighbor discoveries The protocol achieves high scalability by employing frequency and time division between clusters Performance analysis shows that the MAC protocol outperforms current state-of-the-art protocols in energy efficiency, and the energy overhead compared to an ideal MAC protocol is only 285% to 271% The high energy efficiency is achieved in both leaf and router nodes The models and the feasibility of the protocol were verified by simulations and with a full-scale prototype implementation

/pdf/energy-efficient-reservation-based-medium-access-control-43wjp7yjkf.pdf

Energy-efficient reservation-based medium access control protocol for wireless sensor networks

This paper presents a modular way to synthesize on-chip interconnection architectures for very large scale integrated (VLSI) systems using generic components. The components use a standard interface and, therefore, the functionality of the system can be designed separately from the architecture. Examples from different ends of the performance and cost spectrum are presented. A bus is a simple interconnection that is still powerful enough for many applications. When larger transmission bandwidths are needed, also a crossbar can be considered. The choice of the utilized network should be based on the requirements of the application. The most important metrics helping the decision process are interconnection area and throughput. A bus network is found to be considerably smaller in area than a crossbar but the throughput of a crossbar is over two times higher in large data transfers. The throughput of the examined complex crossbar is mainly bounded by arbitration latencies.

Comparison of synthesized bus and crossbar interconnection architectures

The design and implementation of an application programming interface (API) is a trade-off between abstraction it provides and overheads it causes. This paper presents an implementation of Multicore Communications API (MCAPI) on a heterogeneous platform consisting of FPGA-based multiprocessor system-on-chip (MPSoC) connected via PCIe to an external CPU board. The purpose is to provide a unified programming API to different processor and OS types as well as hardware IP-blocks. MCAPI is shown to meet these requirements. We show the MCAPI transport implementation on three processors and two buses, measure the overhead cost, and analyze the effort required to port an application from a PC to the MPSoC. The measured library memory footprint is less than 25KB and the roundtrip communication latency is diminishing low — only few dozen clock cycles — compared to non-MCAPI implementation.

Multicore Communications API (MCAPI) implementation on an FPGA multiprocessor

This paper presents a set of 9 application traffic models for benchmarking Networks-on-Chip designs. Common benchmarks allow fair comparison, reproduction of research results, and accelerate NoC development. The set is based on real applications found in literature and executable on freely available benchmarking tool called Transaction Generator (TG). It was found that traffic target distribution is far from uniform and bandwidth requirements vary very much between tasks and between applications. TG and the model source codes are freely available. Models are stored in XML format and are based on task graphs with on average 15 processing tasks. The average communication load is about 2 GByte/s.

Timo Hämäläinen

Papers

Comments on "Winscale: an image-scaling algorithm using an area pixel Model"

Energy-efficient reservation-based medium access control protocol for wireless sensor networks

Comparison of synthesized bus and crossbar interconnection architectures

Multicore Communications API (MCAPI) implementation on an FPGA multiprocessor

A set of traffic models for Network-on-Chip benchmarking