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

This document provides updates to IEEE Std 802.16's MIB for the MAC, PHY and asso- ciated management procedures in order to accommodate recent extensions to the standard.

IEEE Standard for Local and Metropolitan Area Networks Part 16: Air Interface for Fixed Broadband Wireless Access Systems Draft Amendment: Management Information Base Extensions

Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.

/pdf/a-comprehensive-survey-on-machine-learning-for-networking-3t5h3kbpe8.pdf

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Context: Web Services are emerging technologies that enable application to application communication and reuse of autonomous services over Web. Composition of web services is a concept of integrating individual web services to conduct complex business transactions based on functionality and performance constraints Objective: To satisfy user requirements, technologies of Quality of service (QoS)-based web service composition (QWSC) are widely used to build complex applications by discovering the best-fit web services in term of QoS. Method: In this paper, a QoS-based service selection (RQSS) algorithm is proposed to help composite web application development by discovering feasible web services based on functionalities and QoS criteria of user requirements. The RQSS recommends prospective service candidates to users by relaxing QoS constraints if no suitable or available web service could exactly fulfill user requirements. Results: A generic framework is implemented to demonstrate the feasibility and performance of RQSS by adapting WS-BPEL standards, and can be reused for QoS-based web composition applications. Conclusion: The experimental results show that the RQSS algorithm indeed performs well and increases the system availability and reliability.

https://ir.nctu.edu.tw:443/bitstream/11536/14623/1/000296986900006.pdf

A relaxable service selection algorithm for QoS-based web service composition

Mobile telemedicine for moving vehicle scenarios: Wireless technology options and challenges

In the last few years telecommunications and Internet have spread all over the world, in a pervasive way, connecting millions of devices, people, sensors and services without a planned strategy. In such scenario the discovery of services represent still an open challenging research field. To address that problem this paper proposes a context-aware semantic service discovery architecture designed to perform distributed service discovery in heterogeneous networks. This novel architecture is technology independent and compatible with most of the existent service discovery protocols; it inherits and extends the results of the last research groups in the field of context-aware service discovery based on the use of semantic languages. The present work presents the first results of the service discovery design activity which has been carried out within DAIDALOS II (Designing Advanced network Interfaces for the Delivery and Administration of Location independent, Optimised personal Services), a project granted in the European 6th Framework Research Programme, within the IST (Information Society and Technology) thematic area.

Context-aware Semantic Service Discovery

Peer-to-Peer systems are nowadays a very popular solution for multimedia distribution, as they provide significant cost benefits compared with traditional server-client distribution. Additionally, the distribution of scalable content enables the consumption of the content in a quality suited for the available bandwidth and the capabilities of the end-user devices. Thus, the distribution of scalable content over P2P networks is a very actual research topic. This paper presents an architecture for the distribution of scalable content in a fully distributed Peer-to-Peer network. The architectural description includes how the scalable layers of the content are mapped to the pieces distributed in the Peer-to-Peer system and detailed descriptions of the producer- and consumer-site architecture of the system. The presented system is to our knowledge the first open-source Peer-to-Peer network with full Scalable Video Coding support.

An Architecture for Distributing Scalable Content over Peer-to-Peer Networks

Wireless Metropolitan Area Networks based on IEEE 802.16d/e standards are soon to be deployed in several countries. However, there is lack of published literature with results from actual testbeds. This paper introduces the work done in the EU Sixth Framework Programme Project WEIRD to design and set up WiMAX testbeds in four EU countries. We describe the methodlogy followed, detail our implementation and present results from the testbeds, as deployed in the first phase of WEIRD. The testbeds are used to demonstrate how WiMAX technology can be used to extend the connectivity of the pan-European data communications network (GEANT2) to isolated and impervious areas and, furthermore, to assure end-to-end quality of service to novel applications.

/pdf/weird-testbeds-with-fixed-and-mobile-wimax-technology-for-40uj71upx9.pdf

WEIRD testbeds with fixed and mobile WiMAX technology for user applications, telemedicine and monitoring of impervious areas

In this paper we study the call admission control problem to optimize the network operators revenue guaranteeing quality of service to the end users. We consider a network scenario where each class of service is characterized by a different constant bit rate and an associated revenue. We formulate the problem as a Semi-Markov Decision Process,and we use a model based Reinforcement Learning approach.Other traditional algorithms require an explicit knowledge of the state transition models while our solution learn it on-line.We will show how our policy provides better solution than a classic greedy algorithm.

A Model Based RL Admission Control Algorithm for Next Generation Networks

In this paper we study the call admission control problem to optimize the network operators' revenue guaranteeing the quality of service to the end users. We consider a network scenario where each class of service is characterized by a different constant bit rate and an associated revenue. We formulate the problem as a Semi-Markov Decision Process, and we use a model based Reinforcement Learning approach. Other traditional algorithms require an explicit knowledge of the state transition models while our solution learns it on-line. We will show how our policy provides better solution than a classic greedy algorithm.

Silvano Mignanti

Papers

Context-aware Semantic Service Discovery

An Architecture for Distributing Scalable Content over Peer-to-Peer Networks

WEIRD testbeds with fixed and mobile WiMAX technology for user applications, telemedicine and monitoring of impervious areas

A Model Based RL Admission Control Algorithm for Next Generation Networks

A Model Based RL Admission Control Algorithm for Next Generation Networks