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

The Smart Grid, regarded as the next generation power grid, uses two-way flows of electricity and information to create a widely distributed automated energy delivery network. In this article, we survey the literature till 2011 on the enabling technologies for the Smart Grid. We explore three major systems, namely the smart infrastructure system, the smart management system, and the smart protection system. We also propose possible future directions in each system. colorred{Specifically, for the smart infrastructure system, we explore the smart energy subsystem, the smart information subsystem, and the smart communication subsystem.} For the smart management system, we explore various management objectives, such as improving energy efficiency, profiling demand, maximizing utility, reducing cost, and controlling emission. We also explore various management methods to achieve these objectives. For the smart protection system, we explore various failure protection mechanisms which improve the reliability of the Smart Grid, and explore the security and privacy issues in the Smart Grid.

/pdf/smart-grid-the-new-and-improved-power-grid-a-survey-4jypbbgv3j.pdf

Smart Grid — The New and Improved Power Grid: A Survey

Measuring Health: A Guide to Rating Scales and Questionnaires

Smart Grid - The New and Improved Power Grid:

Digital processing of speech signals

A new-type of three-dimensional (3D) display system based on two different techniques, image floating and integral imaging, is proposed. The image floating is an antiquated 3D display technique, in which a large convex lens or a concave mirror is used to display the image of a real object to observer. The electro-floating system, which does not use a real object, requires a volumetric display part in order to present 3D moving pictures. Integral imaging is an autostereoscopic technique consisting of a lens array and a two-dimensional display device. The integral imaging method can be adapted for use in an electro-floating display system because the integrated image has volumetric characteristics within the viewing angle. The proposed system combines the merits of the two techniques such as an impressive feel of depth and the facility to assemble. In this paper, the viewing characteristics of the two techniques are defined and analyzed for the optimal design of the proposed system. The basic experiments for assembling the proposed system were performed and the results are presented. The proposed system can be successfully applied to many 3D applications such as 3D television.

Three-dimensional electro-floating display system using an integral imaging method

Voice activity detection (VAD) classifies incoming signal segments into speech or background noise; its performance is crucial in various speech-related applications. Although speech-signal context is a relevant VAD asset, its usefulness varies in unpredictable noise environments. Therefore, its usage should be adaptively adjustable to the noise type. This letter improves the use of context information by using an adaptive context attention model (ACAM) with a novel training strategy for effective attention, which weights the most crucial parts of the context for proper classification. Experiments in real-world scenarios demonstrate that the proposed ACAM-based VAD outperforms the other baseline VAD methods.

Voice Activity Detection Using an Adaptive Context Attention Model

An algorithm is presented for automatically classifying speech into four categories: silent and speech produced by three types of excitation, namely, voiced, unvoiced, and mixed (a combination of voiced and unvoiced). The algorithm uses two-channel (speech and electroglottogram) signal analysis and has been tested on data from six speakers (three male and three female), each speaking five sentences. An overall correct classification accuracy of approximately 98.2% was achieved when compared to skilled manual classification. This is superior to previously reported automatic classification schemes. If word boundary errors, including the beginning and ending of sentences, are excluded, then the algorithm's performance improves to 99.5%. >

Silent and voiced/unvoiced/mixed excitation (four-way) classification of speech

Recently, energy management has become one of the emerging services in the area of residential network service. A smart meter is the most essential component of advanced metering infrastructure (AMI) that connects the home energy management system of individual residences and a smart grid that optimizes the production, distribution, and consumption of electric power. Power strip type smart meters can be used to not only monitor but also control the electric power consumption at individual power outlet ports in the power outlet directly. They can be used to control and effectively reduce standby power consumption by the application of the direct power supply control. A smart multi-power tap (SMPT) is an advanced multi-outlet power strip type smart meter that provides important contextual information such as the identity and location of electric home appliances on the basis of the temporal power consumption data and the control of power supply to the appliances. However, the SMPT cannot be used to determine the location of appliances when the connections among SMPTs form a tree structure. In this study, we develop a mathematical model of cascade connections among SMPTs and propose a solution for obtaining the location information of the tree structure. The proposed method helps realize real applications of the SMPT for providing activity-based context-aware home network services and energy management services.

Determining location of appliances from multi-hop tree structures of power strip type smart meters

Providing Feedback of power consumption by using Advanced Metering Infrastructure (AMI) and smart meters is considered the best method to lower consumers' power consumption. Automatic analysis of power consumption data that provides information on user activity is essential in order to provide effective feedback in time, and advanced services such as automatic power load control based on context information. The activity should be matched with user's behavior in order to make it understandable for the user and readable for the machine. In this paper, a new method for extracting activities from power consumption data is proposed. By using the concept of activities in daily living (ADLs), the method extracts the activities as tasks from context information such as identification and location of electric appliances and temporal power consumption from the AMI and the smart meters. Using ontology, the tasks are tagged by semantic meta-information in order to be used for sophisticated user friendly services.

Minsoo Hahn

Papers

Three-dimensional electro-floating display system using an integral imaging method

Voice Activity Detection Using an Adaptive Context Attention Model

Silent and voiced/unvoiced/mixed excitation (four-way) classification of speech

Determining location of appliances from multi-hop tree structures of power strip type smart meters

AERO: extraction of user's activities from electric power consumption data