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

/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

The Grid 2: Blueprint for a New Computing Infrastructure

The Internet of Things (IoT) is defined as a paradigm in which objects equipped with sensors, actuators, and processors communicate with each other to serve a meaningful purpose. In this paper, we survey state-of-the-art methods, protocols, and applications in this new emerging area. This survey paper proposes a novel taxonomy for IoT technologies, highlights some of the most important technologies, and profiles some applications that have the potential to make a striking difference in human life, especially for the differently abled and the elderly. As compared to similar survey papers in the area, this paper is far more comprehensive in its coverage and exhaustively covers most major technologies spanning from sensors to applications.

/pdf/internet-of-things-architectures-protocols-and-applications-46rpfbd58i.pdf

Internet of Things: Architectures, Protocols, and Applications

Cloud computing environments allow customers to dynamically scale their applications. The key problem is how to lease the right amount of resources, on a pay-as-you-go basis. Application re-dimensioning can be implemented effortlessly, adapting the resources assigned to the application to the incoming user demand. However, the identification of the right amount of resources to lease in order to meet the required Service Level Agreement, while keeping the overall cost low, is not an easy task. Many techniques have been proposed for automating application scaling. We propose a classification of these techniques into five main categories: static threshold-based rules, control theory, reinforcement learning, queuing theory and time series analysis. Then we use this classification to carry out a literature review of proposals for auto-scaling in the cloud.

A Review of Auto-scaling Techniques for Elastic Applications in Cloud Environments

Multiple sinks are deployed in large-scale wireless sensor networks (WSNs) to minimize transmission delay and energy consumption and also to extend the network life time. Since the data collected by sensor nodes are forwarded to the sink, therefore proper placement of sinks has a great impact on the performance of the WSNs. This paper introduces two sink placement strategies and discusses their advantages and disadvantages in comparison with an existing strategy. The two strategies are compared with the Geographic Sink Placement (GSP) [3] strategy which is used as a benchmark. Both GSP and proposed two strategies are implemented and evaluated in a simulation environment. Performances of these strategies are analyzed and analysis results are presented in this paper. It has been observed that the proposed strategies exhibit better performances with respect to energy usage and lifetime in comparison with GSP.

Multiple-sink placement strategies in wireless sensor networks

As the population is increasing worldwide, huge need arises to provide proper health-care services. With the advent of modern technologies the need-gap may be augmented. Sensor is one such technology which can be used to enable Internet of Things based health-care monitoring system. In this paper, implementation of such a system is described. In a real time health monitoring system, there are many sensors connected to a local data processing unit through a shared channel having a fixed bandwidth. These sensors have a wide variety of channel access requirements. The access to the channel should be discrete, so that each and every sensor avails the required bandwidth and delay in the shared channel. In this paper, a scheduling technique is proposed for the IoT based system, which nullify interference among different sensors and consequent distortation of precious health data. Implementation of this technique in our prototype health-care monitoring application is discussed in this paper.

Interference Aware Scheduling of Sensors in IoT Enabled Health-Care Monitoring System

There has been a recent attempt by the researchers to leverage the widespread usage of small sensor nodes and integrate them with cloud technology for building an environment for Internet of Things. While some applications have already been developed to transmit the data from physical sensors to cloud environment, we propose to create and include virtual sensors, i.e. abstractions of physical sensors, in cloud that can enable on demand, pervasive, shared access to sensors. The definition and description of virtual sensors have already been presented in our earlier work. This paper presents implementation of virtual sensors at IaaS level. It provides a virtual sensor system architecture for both health and environment sensors and describes virtual sensor operations in four different stages. It provides description of APIs for sensing, processing, communication and storage at IaaS end. The virtual sensors can be used by any user application at PaaS or SaaS levels. Performance of a preliminary implementation of such virtual sensor system is also analyzed in this paper.

Implementation of virtual sensors for building a sensor-cloud environment

Recent advancements in cloud and sensor technologies have created opportunities for introducing Sensor-Cloud as a convenient framework for developing applications in various fields. It has already been possible to integrate sensor technology with cloud environment and services have been developed to access the sensors via Internet. Here, the sensors can communicate with remote resources and transmit the sensed data. This paper presents a scheme to create Sensor-Cloud infrastructure with virtualization of sensors. We introduce an architectural overview along with new concepts about resource abstraction at the sensor level. We also discuss about providing uninterrupted services by a collection of sensors that can be used as shared resources for online provisioning to the consumers.

Towards a Sensor-Cloud Infrastructure with Sensor Virtualization

FINESSE is a prototype environment designed to support rapid development of parallel programs for single-address space computers by both expert and non-expert programmers. The environment provides semi-automatic support for systematic, feedback-based reduction of the various classes of overhead associated with parallel execution. The characterisation of parallel performance by overhead analysis is first reviewed, and then the functionality provided by FINESSE is described. The utility of this environment is demonstrated by using it to develop parallel implementations for an SGI Origin 2000 platform of Tred2, a well-known benchmark for automatic parallelising compilers.

Nandini Mukherjee

Papers

Multiple-sink placement strategies in wireless sensor networks

Interference Aware Scheduling of Sensors in IoT Enabled Health-Care Monitoring System

Implementation of virtual sensors for building a sensor-cloud environment

Towards a Sensor-Cloud Infrastructure with Sensor Virtualization

FINESSE: a prototype feedback-guided performance enhancement system