Pattern Recognition and Machine Learning
TL;DR: This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
Abstract: (2007). Pattern Recognition and Machine Learning. Technometrics: Vol. 49, No. 3, pp. 366-366.
Citations
More filters
01 Aug 2009-International Journal of Human-computer Studies \/ International Journal of Man-machine Studies
TL;DR: Comparison of results obtained using either peripheral or EEG signals confirms the interest of using EEGs to assess valence and arousal in emotion recall conditions.
Abstract: The work presented in this paper aims at assessing human emotions using peripheral as well as electroencephalographic (EEG) physiological signals on short-time periods Three specific areas of the valence-arousal emotional space are defined, corresponding to negatively excited, positively excited, and calm-neutral states An acquisition protocol based on the recall of past emotional life episodes has been designed to acquire data from both peripheral and EEG signals Pattern classification is used to distinguish between the three areas of the valence-arousal space The performance of several classifiers has been evaluated on 10 participants and different feature sets: peripheral features, EEG time-frequency features, EEG pairwise mutual information (MI) features Comparison of results obtained using either peripheral or EEG signals confirms the interest of using EEGs to assess valence and arousal in emotion recall conditions The obtained accuracy for the three emotional classes is 63% using EEG time-frequency features, which is better than the results obtained from previous studies using EEG and similar classes Fusion of the different feature sets at the decision level using a summation rule also showed to improve accuracy to 70% Furthermore, the rejection of non-confident samples finally led to a classification accuracy of 80% for the three classes
349 citations
Cites background from "Pattern Recognition and Machine Lea..."
...Classifiers like k-nearest neighbors (KNN), functional discriminant analysis (FDA), neural networks, support vector machines (SVMs), relevance vector machines (RVMs) and others (Bishop, 2006) are useful to detect emotional classes of interest (Table 1)....
[...]
...Classifiers like kNearest Neighbors (KNN), Functional Discriminant Analysis (FDA), neural networks, Support Vector Machines (SVM’s), Relevance Vector Machines (RVM's) and others (Bishop, 2006) are useful to detect emotional classes of interest (Table 1)....
[...]
TL;DR: The BIT model provides a step towards formalizing the translation of developer aims into intervention components, larger treatments, and methods of delivery in a manner that supports research and communication between investigators on how to design, develop, and deploy BITs.
Abstract: A growing number of investigators have commented on the lack of models to inform the design of behavioral intervention technologies (BITs). BITs, which include a subset of mHealth and eHealth interventions, employ a broad range of technologies, such as mobile phones, the Web, and sensors, to support users in changing behaviors and cognitions related to health, mental health, and wellness. We propose a model that conceptually defines BITs, from the clinical aim to the technological delivery framework. The BIT model defines both the conceptual and technological architecture of a BIT. Conceptually, a BIT model should answer the questions why, what, how (conceptual and technical), and when. While BITs generally have a larger treatment goal, such goals generally consist of smaller intervention aims (the "why") such as promotion or reduction of specific behaviors, and behavior change strategies (the conceptual "how"), such as education, goal setting, and monitoring. Behavior change strategies are instantiated with specific intervention components or “elements” (the "what"). The characteristics of intervention elements may be further defined or modified (the technical "how") to meet the needs, capabilities, and preferences of a user. Finally, many BITs require specification of a workflow that defines when an intervention component will be delivered. The BIT model includes a technological framework (BIT-Tech) that can integrate and implement the intervention elements, characteristics, and workflow to deliver the entire BIT to users over time. This implementation may be either predefined or include adaptive systems that can tailor the intervention based on data from the user and the user’s environment. The BIT model provides a step towards formalizing the translation of developer aims into intervention components, larger treatments, and methods of delivery in a manner that supports research and communication between investigators on how to design, develop, and deploy BITs.
346 citations
Additional excerpts
...Finally, if the system is using artificial intelligence and machine learning techniques, related metrics such as accuracy and precision of predictions and recommendations can be used [41,42]....
[...]
TL;DR: This survey article introduces argumentation models and methods, reviews existing systems and applications, and discusses challenges and perspectives of this exciting new research area.
Abstract: Argumentation mining aims at automatically extracting structured arguments from unstructured textual documents. It has recently become a hot topic also due to its potential in processing information originating from the Web, and in particular from social media, in innovative ways. Recent advances in machine learning methods promise to enable breakthrough applications to social and economic sciences, policy making, and information technology: something that only a few years ago was unthinkable. In this survey article, we introduce argumentation models and methods, review existing systems and applications, and discuss challenges and perspectives of this exciting new research area.
344 citations
TL;DR: This paper uses deep convolutional recurrent neural networks for hyperspectral image classification by treating each hyperspectrals pixel as a spectral sequence and proposes a constrained Dirichlet process mixture model (C-DPMM) for semi-supervised clustering which includes pairwise must-link and cannot-link constraints, resulting in improved initialization of the deep neural network.
Abstract: Deep learning has gained popularity in a variety of computer vision tasks. Recently, it has also been successfully applied for hyperspectral image classification tasks. Training deep neural networks, such as a convolutional neural network for classification requires a large number of labeled samples. However, in remote sensing applications, we usually only have a small amount of labeled data for training because they are expensive to collect, although we still have abundant unlabeled data. In this paper, we propose semi-supervised deep learning for hyperspectral image classification—our approach uses limited labeled data and abundant unlabeled data to train a deep neural network. More specifically, we use deep convolutional recurrent neural networks (CRNN) for hyperspectral image classification by treating each hyperspectral pixel as a spectral sequence. In the proposed semi-supervised learning framework, the abundant unlabeled data are utilized with their pseudo labels (cluster labels). We propose to use all the training data together with their pseudo labels to pre-train a deep CRNN, and then fine-tune using the limited available labeled data. Further, to utilize spatial information in the hyperspectral images, we propose a constrained Dirichlet process mixture model (C-DPMM), a non-parametric Bayesian clustering algorithm, for semi-supervised clustering which includes pairwise must-link and cannot-link constraints—this produces high-quality pseudo-labels, resulting in improved initialization of the deep neural network. We also derived a variational inference model for the C-DPMM for efficient inference. Experimental results with real hyperspectral image data sets demonstrate that the proposed semi-supervised method outperforms state-of-the-art supervised and semi-supervised learning methods for hyperspectral classification.
342 citations
Cites background or methods from "Pattern Recognition and Machine Lea..."
..., the KL divergence between the desired posterior and the variational distribution, can be expressed as [48]:...
[...]
...The minimization of the free energy with respect to the variational distribution can be solved using the coordinate ascent variational inference (CAVI) algorithm [47], [48], which iteratively optimizes each factor in Eq....
[...]
01 Jan 2012
TL;DR: The paper addresses large scale image retrieval with short vector representations by studying dimensionality reduction by Principal Component Analysis (PCA) and proposing improvements to its different phases.
341 citations
Cites methods from "Pattern Recognition and Machine Lea..."
...We show that the PCA removes the correlation, while preserving the additional information from the different quantizations....
[...]
...This issue is addressed by using a robust PCA/whitening method....
[...]
...An efficient way to obtain a shorter image vector representation consists of applying principal component analysis (PCA) dimensionality reduction directly on the BOW (or VLAD) vector [8]....
[...]
...This phenomenon can be observed when reconstructing the BOW vector from its PCA projection: The component of the other visual word is “hallucinated”....
[...]
...Different techniques to improve dimensionality reduction by PCA for large scale image retrieval were proposed....
[...]