The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Point patterns are sets or multi-sets of unordered elements that can be found in numerous data sources. However, in data analysis tasks such as classification and novelty detection, appropriate statistical models for point pattern data have not received much attention. This paper proposes the modelling of point pattern data via random finite sets (RFS). In particular, we propose appropriate likelihood...
This paper addresses the problem of modeling long-range motion patterns of a 3D human skeleton performing an activity. This problem is important, as such a model can be used in many applications, including person tracking via 3D pose estimation, and probabilistic sampling of realistic 3D skeleton sequences conducting different activities with different motion styles. To this end, we formulate a new...
Regularization plays an important role in machine learning systems. We propose a novel methodology for model regularization using random projection. We demonstrate the technique on neural networks, since such models usually comprise a very large number of parameters, calling for strong regularizers. It has been shown recently that neural networks are sensitive to two kinds of samples: (i) adversarial...
In this article wearable sensors based human activity recognition is approached with a case where personal data collected has a high inner activity variety. With this kind of approach, the model adaptivity as well as update becomes more important issues for the activity recognition models. In authors' previous article it was shown that with this kind of data the personal models do not always outperform...
This paper describes a new technique to automatically obtain large high-quality training speech corpora for acoustic modeling. Traditional approaches select utterances based on confidence thresholds and other heuristics. We propose instead to use an ensemble approach: we transcribe each utterance using several recognizers, and only keep those on which they agree. The recognizers we use are trained...
Due to limited resource, noise and unreliable link, data loss and sensor faults are common in medical body sensor networks (BSN). Most available works used data reconstruction to improve data quality in traditional wireless sensor networks (WSN). However, existing data reconstruction schemes using redundant information of WSN can not provide a satisfactory accuracy for BSN. In light of this, a Bayesian...
Induction of descriptive models is one of the most important technologies in data mining. The expressiveness of descriptive models are of paramount importance in applications that examine the causality of relationships between variables. Most of the work on descriptive models has concentrated on less expressive approaches such as clustering algorithms or rule-based approaches that are limited to a...
We tackle the problem of learning a rotation invariant latent factor model when the training data is comprised of lower-dimensional projections of the original feature space. The main goal is the discovery of a set of 3-D bases poses that can characterize the manifold of primitive human motions, or movemes, from a training set of 2-D projected poses obtained from still images taken at various camera...
In this paper, we propose a Reliable Semi-Supervised Learning framework, called ReSSL, for both static and streaming data. Instead of relaxing different assumptions, we do model the reliability of cluster assumption, quantify the distinct importance of clusters (or evolving micro-clusters on data streams), and integrate the cluster-level information and labeled data for prediction with a lazy learning...
We introduce a powerful technique to make classifiers more reliable and versatile. Background Check equips classifiers with the ability to assess the difference of unlabelled test data from the training data. In particular, Background Check gives classifiers the capability to (i) perform cautious classification with a reject option, (ii) identify outliers, and (iii) better assess the confidence in...
In this paper, a noise injection method to improve personal recognition models is presented. The idea of the method is to build more general recognition models for eHealth using a small original data set and by expanding the area covered by training data using noise injection. This way, it is possible to train models that are less vulnerable to changing conditions, and thus more accurate, but still...
In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the network—thus generalising the already well-established...
Acoustic model performance typically decreases when evaluated on a dialectal variation of the same language that was not used during training. Similarly, models simultaneously trained on a group of dialects tend to underperform dialect-specific models. In this paper, we report on our efforts towards building a unified acoustic model that can serve a multi-dialectal language. Two techniques are presented:...
Manufacturers collect large amounts of information during production. This data can be hard to interpret because of the presence of many unknown interactions. The goal of this study is to demonstrate how machine learning methods can uncover important relationships between these parameters. This paper describes several techniques to predict rare failure events. Single parameter methods are used to...
Microsoft Office users submit hundreds of thousands of pieces of verbatim feedback per month. How can an engineer or manager in Office find the signal in this data to make business decisions? This paper presents an overview of the Office Customer Voice (OCV) system. OCV combines classification, on-demand clustering and other machine learning techniques with a rich web UI to solve this problem. In...
We present a city-scale crowd simulation model based on a large data set (25 million GPS data points from 28'000 volunteers recorded during a 3-day city-wide festival held in Zurich in 2013). The model is based on a spatio-temporal abstraction of the festival, focusing on event sites and event times. Thus, we assume a certain number of events (concerts, shows, etc. as it's typical at such festivals)...
We propose two simple methods to improve the performance of a keyword spotting system. In our application, the users are allowed to change the keywords anytime if they want. Thus we focused on phone-based GMM-HMM models since they do not require keyword-specific training data. However, the GMM-HMM based models usually have very high false alarm rate, i.e., a keyword is not present but the system gives...
Training very deep neural networks is very difficult because of gradient degradation. However, the incomparable expressiveness of the many deep layers is highly desirable at testing time and usually leads to better performance. Recently, training techniques such as residual networks that enable us to train very deep networks have proved to be a great success. In this paper, we studied the application...
Fully automated detection and localisation of fruit in orchards are key components in creating automated robotic harvesting systems. During recent years a lot of research on this topic has been performed, either using basic computer vision techniques, like colour based segmentation, or by resorting to other sensors, like LWIR, hyperspectral or 3D. Recent advances in computer vision present a broad...
The integration of neural networks into agent based models can provide a better understanding of dynamic agent responses when modelling complex systems. Additionally, due to the nature of agent based models and the networks that exist in them, individual neural networks can be trained in a supervised learning environment and assigned to individual agents. The advantage of using this approach is that...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.