Adaptive class association rule mining for human activity recognition
07 Sep 2015-pp 19-34
TL;DR: This paper presents an adaptive framework for mining class association rules using subgroup discovery, and analyzes different techniques for obtaining the final classifier in the context of human activity recognition.
Abstract: The analysis of human activity data is an important research area in the context of ubiquitous and social environments. Using sensor data obtained by mobile devices, e. g., utilizing accelerometer sensors contained in mobile phones, behavioral patterns and models can then be obtained. However, the utilized models are often not simple to interpret by humans in order to facilitate assessment, evaluation and validation, e. g., in computational social science or in medical contexts. In this paper, we propose a novel approach for generating interpretable rule sets for classification: We present an adaptive framework for mining class association rules using subgroup discovery, and analyze different techniques for obtaining the final classifier. The approach is investigated in the context of human activity recognition. For our evaluation, we apply real-world activity data collected using mobile phone sensors.
Citations
More filters
TL;DR: This is it, the handbook of data mining and knowledge discovery that will be your best choice for better reading book that you will not spend wasted by reading this website.
Abstract: Give us 5 minutes and we will show you the best book to read today. This is it, the handbook of data mining and knowledge discovery that will be your best choice for better reading book. Your five times will not spend wasted by reading this website. You can take the book as a source to make better concept. Referring the books that can be situated with your needs is sometime difficult. But here, this is so easy. You can find the best thing of book that you can read.
252 citations
01 Jan 2018
TL;DR: This paper embeds a framework for building rule-based classifiers using class association rules and shows that the proposed approach outperforms the baselines clearly, concerning both accuracy and complexity of the resulting predictive models.
Abstract: Computational social sensing is enabled by the Internet of Things at large scale. Using sensors, e. g., implemented in mobile and wearable devices, human behavior and activities can then be investigated, e.g., using according models and patterns. However, the obtained models are often not explicative, i. e., interpretable, transparent, and explanation-aware, which makes assessment and validation difficult for humans. This paper proposes a novel explicative classification approach featuring interpretable and explainable models. For this purpose, we embed a framework for building rule-based classifiers using class association rules. For evaluation, we apply two real-world datasets: One collected in the domain of personalized health using wearable sensors (accelerometers), the second one utilizing smartphone sensors for activity recognition. Our results indicate, that the proposed approach outperforms the baselines clearly, concerning both accuracy and complexity of the resulting predictive models.
19 citations
Cites background or methods from "Adaptive class association rule min..."
...• Rule combination strategy: Based on our experiments in [7] we investigated different strategies, cf....
[...]
...Confirming our initial results presented in [7] for the CARMA framework, we observe that the proposed approach outperforms both baselines in accuracy as well as in complex-...
[...]
...For a detailed discussion, we refer to [7]....
[...]
...As described in [7], confidence is estimated by the respective relative frequency of the class contained in the data records covered by the respective rule, while the Laplace value lval(r) of a rule r is determined by lvar(r) = pri+1 ∑ cj∈C p j +|C| , where p r j (and pi ) are the numbers of covered examples by rule r that belong to the respective classes cj considering all possible classes C, and class ci of the rule, respectively....
[...]
...In this paper, an adapted and substantially extended revision of [7], we propose a novel explicative machine learning approach utilizing class association rules (CARs): These are similar to standard association rules [8], however the righthand-side of the rule is assigned a specific class, while the lefthand-side of the rule is made up of a conjunction of attributevalue pairs making up a pattern....
[...]
01 Jan 2016
TL;DR: This chapter presents the novel SD-MapR algorithmic framework for large-scale local exceptionality detection implemented using subgroup discovery on the Map/Reduce framework and describes the basic algorithm in detail and provides an experimental evaluation using several real-world datasets.
Abstract: Large-scale data processing is one of the key challenges concerning many application domains, especially considering ubiquitous and big data. In these contexts, subgroup discovery provides both a flexible data analysis and knowledge discovery method. Subgroup discovery and pattern mining are important descriptive data mining tasks. They can be applied, for example, in order to obtain an overview on the relations in the data, for automatic hypotheses generation, and for a number of knowledge discovery applications. This chapter presents the novel SD-MapR algorithmic framework for large-scale local exceptionality detection implemented using subgroup discovery on the Map/Reduce framework. We describe the basic algorithm in detail and provide an experimental evaluation using several real-world datasets. We tackle two algorithmic variants focusing on simple and more complex target concepts, i.e., presenting an implementation of exceptional model mining on large attributed graphs. The results of our evaluation show the scalability of the presented approach for large data sets.
10 citations
Book•
25 Dec 2014
TL;DR: The 4th International Workshop on Mining Ubiquitous and Social Environments (MUSE 2013) as mentioned in this paper was held in Prague, Czech Republic, in September 2013, and the 4th Workshop on Modeling Social Media, MSM 2013, held in Paris, France, in May 2013.
Abstract: This book constitutes the thoroughly refereed joint post-workshop proceedings of the 4th International Workshop on Mining Ubiquitous and Social Environments, MUSE 2013, held in Prague, Czech Republic, in September 2013, and the 4th International Workshop on Modeling Social Media, MSM 2013, held in Paris, France, in May 2013. The 8 full papers included in the book are revised and significantly extended versions of papers submitted to the workshops. The focus is on collective intelligence in ubiquitous and social environments. Issues tackled include personalization in social streams, recommendations exploiting social and ubiquitous data, and efficient information processing in social systems. Furthermore, this book presents work dealing with the problem of mining patterns from ubiquitous social data, including mobility mining and exploratory methods for ubiquitous data analysis.
10 citations
12 Sep 2016
TL;DR: This paper proposes an anticipatory ubiquitous perspective on the Ubicon platform, considering data capture, localization, context inference and activity recognition, enabled by an integration of different technologies and tools.
Abstract: Anticipatory systems require different steps like sensing, data processing, context inference, and context prediction. Then, suitable platforms can support the implementation of the respective steps. This paper proposes an anticipatory ubiquitous perspective on the Ubicon platform, considering data capture (sensing), localization (context inference) and activity recognition (context prediction), enabled by an integration of different technologies and tools. In an integrated approach, we propose different components for augmenting the Ubicon platform. For these, we present results of respective case studies in ubiquitous and social environments. Our results demonstrate the applicability of the Ubicon platform for these tasks, towards an extended platform for anticipatory ubiquitous computing.
8 citations
Cites methods from "Adaptive class association rule min..."
...Then, subgroup discovery can be adapted as a rule generator for class association rule mining, using our CARMA framework presented in [6]....
[...]
References
More filters
Book•
15 Oct 1992TL;DR: A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Abstract: From the Publisher:
Classifier systems play a major role in machine learning and knowledge-based systems, and Ross Quinlan's work on ID3 and C4.5 is widely acknowledged to have made some of the most significant contributions to their development. This book is a complete guide to the C4.5 system as implemented in C for the UNIX environment. It contains a comprehensive guide to the system's use , the source code (about 8,800 lines), and implementation notes. The source code and sample datasets are also available on a 3.5-inch floppy diskette for a Sun workstation.
C4.5 starts with large sets of cases belonging to known classes. The cases, described by any mixture of nominal and numeric properties, are scrutinized for patterns that allow the classes to be reliably discriminated. These patterns are then expressed as models, in the form of decision trees or sets of if-then rules, that can be used to classify new cases, with emphasis on making the models understandable as well as accurate. The system has been applied successfully to tasks involving tens of thousands of cases described by hundreds of properties. The book starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting. Advantages and disadvantages of the C4.5 approach are discussed and illustrated with several case studies.
This book and software should be of interest to developers of classification-based intelligent systems and to students in machine learning and expert systems courses.
21,674 citations
01 Jan 1994
TL;DR: In his new book, C4.5: Programs for Machine Learning, Quinlan has put together a definitive, much needed description of his complete system, including the latest developments, which will be a welcome addition to the library of many researchers and students.
Abstract: Algorithms for constructing decision trees are among the most well known and widely used of all machine learning methods. Among decision tree algorithms, J. Ross Quinlan's ID3 and its successor, C4.5, are probably the most popular in the machine learning community. These algorithms and variations on them have been the subject of numerous research papers since Quinlan introduced ID3. Until recently, most researchers looking for an introduction to decision trees turned to Quinlan's seminal 1986 Machine Learning journal article [Quinlan, 1986]. In his new book, C4.5: Programs for Machine Learning, Quinlan has put together a definitive, much needed description of his complete system, including the latest developments. As such, this book will be a welcome addition to the library of many researchers and students.
8,046 citations
Book•
01 Jan 1990
TL;DR: In this paper, the authors present a tour of categorical data analysis for Contingency Tables and Logit and Loglinear models for contingency tables, as well as generalized linear models for Matched Pairs.
Abstract: Two--Way Contingency Tables. Three--Way Contingency Tables. Generalized Linear Models. Logistic Regression. Loglinear Models for Contingency Tables. Building and Applying Logit and Loglinear Models. Multicategory Logit Models. Models for Matched Pairs. A Twentieth--Century Tour of Categorical Data Analysis. Appendix. Table of Chi--Squared Distribution Values for Various Right--Tail Probabilities. Bibliography. Indexes.
7,062 citations
Additional excerpts
...[1]:...
[...]
09 Jul 1995
TL;DR: This paper evaluates the recently-proposed rule learning algorithm IREP on a large and diverse collection of benchmark problems, and proposes a number of modifications resulting in an algorithm RIPPERk that is very competitive with C4.5 and C 4.5rules with respect to error rates, but much more efficient on large samples.
Abstract: Many existing rule learning systems are computationally expensive on large noisy datasets. In this paper we evaluate the recently-proposed rule learning algorithm IREP on a large and diverse collection of benchmark problems. We show that while IREP is extremely efficient, it frequently gives error rates higher than those of C4.5 and C4.5rules. We then propose a number of modifications resulting in an algorithm RIPPERk that is very competitive with C4.5rules with respect to error rates, but much more efficient on large samples. RIPPERk obtains error rates lower than or equivalent to C4.5rules on 22 of 37 benchmark problems, scales nearly linearly with the number of training examples, and can efficiently process noisy datasets containing hundreds of thousands of examples.
4,081 citations
21 Apr 2004
TL;DR: This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves, and suggests that multiple accelerometers aid in recognition.
Abstract: In this work, algorithms are developed and evaluated to de- tect physical activities from data acquired using five small biaxial ac- celerometers worn simultaneously on different parts of the body. Ac- celeration data was collected from 20 subjects without researcher su- pervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told specifically where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classifiers using these features were tested. De- cision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subject-specific training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can effectively discriminate many activities. With just two biaxial accelerometers - thigh and wrist - the recognition performance dropped only slightly. This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves.
3,223 citations
"Adaptive class association rule min..." refers background in this paper
...Also, Bao and Intille [16] asked 20 subjects to perform some everyday activities while wearing ve biaxial accelerometers on di erent parts of the body....
[...]