The increasing volume of data in modern business and science calls for more complex and sophisticated tools. Although advances in data mining technology have made extensive data collection much easier, it's still always evolving and there is a constant need for new techniques and tools that can help us transform this data into useful information and knowledge. Since the previous edition's publication, great advances have been made in the field of data mining. Not only does the third of edition of Data Mining: Concepts and Techniques continue the tradition of equipping you with an understanding and application of the theory and practice of discovering patterns hidden in large data sets, it also focuses on new, important topics in the field: data warehouses and data cube technology, mining stream, mining social networks, and mining spatial, multimedia and other complex data. Each chapter is a stand-alone guide to a critical topic, presenting proven algorithms and sound implementations ready to be used directly or with strategic modification against live data. This is the resource you need if you want to apply today's most powerful data mining techniques to meet real business challenges. * Presents dozens of algorithms and implementation examples, all in pseudo-code and suitable for use in real-world, large-scale data mining projects. * Addresses advanced topics such as mining object-relational databases, spatial databases, multimedia databases, time-series databases, text databases, the World Wide Web, and applications in several fields. *Provides a comprehensive, practical look at the concepts and techniques you need to get the most out of real business data

/pdf/data-mining-concepts-and-techniques-4dtvdfkvmi.pdf

Data Mining: Concepts and Techniques

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

Data Mining - Concepts and Techniques.

We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. 
The dataset is freely available at this https URL

SQuAD: 100,000+ Questions for Machine Comprehension of Text

Mobile devices have become popular to access the information on-the-move. However, the physical restrictions of mobile devices such as display size and input capabilities and the changes of users' contexts may affect the users' information needs and search behaviors. In order to design a new search service which takes mobile users' situation into consideration, it is essential to understand search behaviors of mobile users in detail. In this work, we conducted a diary study using 26 participants in Japan, focusing on how mobile context affects users' information needs and search behaviors. In particular, we focus on detailed behaviors when users failed to find the information they needed. Our main findings include that user's search behaviors were affected not only by the information needs but also the place where the searches were conducted, which might be an important cue to design future mobile search services and applications.

How Does Mobile Context Affect People's Web Search Behavior?: A Diary Study of Mobile Information Needs and Search Behaviors

In mobile ad hoc networks (MANETs), to acquire only necessary data items, it is effective that each mobile node retrieves data items using a top-k query, in which data items are ordered by the score of a particular attribute and the query-issuing mobile node acquires data items with k highest scores. In this paper, we propose a query processing method for top-k query for reducing traffic and also keeping high accuracy of the query result. In this method, each mobile node constructs a histogram from the scores of its holding data items and estimates the distribution of scores of all data items and k-th score in the entire network. This histogram is attached with query messages and replies so that other mobile nodes can estimate the score distribution and k-th score more accurately. When transmitting a reply, each mobile node sends back only data items whose scores that are larger than the estimated k-th score to reduce traffic as much as possible. We also present simulation results to evaluate the performance of our proposed method.

A Top-k Query Method by Estimating Score Distribution in Mobile Ad Hoc Networks

Due to the recent proliferation of digital broadcasting systems, various schemes for broadcasting continuous media data such as music or movies have been studied. In general broadcasting systems, since clients have to wait until their desired data are broadcast, these schemes reduce the waiting time by dividing the data into several segments of equal size. However, continuous media data often have units for playing portions of the data. For example, data encoded by MPEG2 can be played every GOP (group of pictures). In this paper, we propose a scheme to reduce the waiting time considering the units. Our proposed scheme divides a continuous media data at every unit. By scheduling divided data so that clients finish receiving a unit before starting to play the unit, waiting time is effectively reduced.

/pdf/a-broadcasting-scheme-considering-units-to-play-continuous-149mato5vu.pdf

A Broadcasting Scheme Considering Units to Play Continuous Media Data

In this paper, we propose two beacon-less \(k\) NN query processing methods for reducing traffic and maintaining high accuracy of the query result in mobile ad hoc networks (MANETs). In these methods, the query-issuing node first forwards a \(k\) NN query using geo-routing to the nearest node from the point specified by the query (query point). Then, the nearest node from the query point forwards the query to other nodes close to the query point, and each node receiving the query replies with the information on itself. In this process, we adopt two different approaches: the Explosion (EXP) method and the Spiral (SPI) method. In the EXP method, the nearest node from the query point floods the query to nodes within a specific circular region, and each node receiving the query replies with information on itself. In the SPI method, the nearest node from the query point forwards the query to other nodes in a spiral manner, and the node that collects a satisfactory \(k\) NN result transmits the result to the query-issuing node. Experimental results show that our proposed methods reduce traffic and achieve high accuracy of the query result, in comparison with existing methods.

\(K\) NN Query Processing Methods in Mobile Ad Hoc Networks

In ad hoc networks, it is effective that each mobile host creates replicas of data items held by other mobile hosts for improving data accessibility In our previous work, we assumed an environment where data items are updated and proposed two updated data dissemination methods which efficiently update old replicas In these methods, the communication traffic is large since every mobile host necessarily requests updated data items when it knows that its own replicas are old In this paper, we propose an updated data dissemination method exploiting an epidemic model, which is a popular bio-inspired approach, for reducing the communication traffic In our proposed method, mobile hosts disseminate invalidation reports and discard old replicas when a mobile host updates a data item or when two mobile hosts are connected with each other Each mobile host which discards an old replica requests the updated data item with a certain probability We also present simulation results to evaluate the performance of our proposed method

Shojiro Nishio

Papers

How Does Mobile Context Affect People's Web Search Behavior?: A Diary Study of Mobile Information Needs and Search Behaviors

A Top-k Query Method by Estimating Score Distribution in Mobile Ad Hoc Networks

A Broadcasting Scheme Considering Units to Play Continuous Media Data

\(K\) NN Query Processing Methods in Mobile Ad Hoc Networks

On updated data dissemination exploiting an epidemic model in ad hoc networks