Please login to be able to save your searches and receive alerts for new content matching your search criteria.
This paper explores the use of a reservoir computing (RC) method, Echo State Networks (ESN) to classify inertial sensor motion data collected from sensors worn by horse riders into punctual activities of interest within a scripted movement environment. ...
The Internet is home to an ever increasing array of products and services available to the general consumer. This trend has given rise to a unique category of internet search where bargain seekers have conjugated towards deal collection databases. This ...
Clickthrough data has been proposed for numerous uses, and this paper describes how a special form of clickthough data, coselection data, can form non-ambiguous clusters that can then be used to detect semantic similarity between query terms. This ...
Clustering methods partition datasets into subgroups with some homogeneous properties, with information about the number and particular characteristics of each subgroup unknown a priori. The problem of predicting the number of clusters and quality of ...
This paper explores the practical aspects associated with visual-geometric reconstruction of a complex 3D scene from a sequence of unconstrained and uncalibrated 2D images. These image sequences can be acquired by a video camera or a handheld digital ...
In this study, we present the investigations being pursued in our research laboratory on magnetic resonance images (MRI) of various states of brain by extracting the most significant features, and to classify them into normal and abnormal brain images. ...
Affect detection where users' mental states are automatically recognized from facial expressions, speech, physiology and other modalities, requires accurate machine learning and classification techniques. This paper investigates how combined classifiers,...
This paper is devoted to empirical investigation of novel multi-level ensemble meta classifiers for the detection and monitoring of progression of cardiac autonomic neuropathy, CAN, in diabetes patients. Our experiments relied on an extensive database ...
This paper shows that some time series problems can be better served as non-time series problems. We used two unsupervised learning anomaly detectors to analyse a vehicle related time series problem and showed that non-time series treatment produced a ...
We present a novel fuzzy clustering technique called CRUDAW that allows a data miner to assign weights on the attributes of a data set based on their importance (to the data miner) for clustering. The technique uses a novel approach to select initial ...
The value of a single dataset is increased when it is linked to combinations of datasets to provide users with more information. Linked Data is a style of publishing data on the Web by using a structured machine-readable format, RDF, and semantically ...
Unlike news stories and product reviews which usually have a strong focus on a single topic, blog posts are often unstructured, and opinions expressed in blog posts do not necessarily correspond to a specific topic. This can lead to unsatisfactory ...
Despite games often being used as a testbed for new computational intelligence techniques, the majority of artificial intelligence in commercial games is scripted. This means that the computer agents are non-adaptive and often inherently exploitable ...
It can be desirable to specify policies that require a system to achieve some outcome even if a certain number of failures occur. The temporal logic of robustness RoCTL* extends CTL* with operators from Deontic logic, and a novel operator referred to as ...
On-line Machine Learning using Stochastic Gradient Descent is an inherently sequential computation. This makes it difficult to improve performance by simply employing parallel architectures. Langford et al. made a modification to the standard stochastic ...
Understanding the dynamics of disease spread is essential in contexts such as estimating load on medical services, as well as risk assessment and intervention policies against large-scale epidemic outbreaks. However, most of the information is available ...
It can be desirable to specify policies that require a system to achieve some outcome even if a certain number of failures occur. The temporal logic of robustness RoCTL* extends CTL* with operators from Deontic logic, and a novel operator referred to as ...
No consistent conclusions have been drawn from existing studies regarding the effectiveness of different approaches to learning from imbalanced data. In this paper we apply bias-variance analysis to study the utility of different strategies for ...
Term frequency and document frequency are currently used to measure term significance in text classification. However, these measures cannot provide sufficient information to differentiate important terms. Thus, in this research, a new term ranking (...
Research on embodied conversational agents' reasoning and actions has mostly ignored the external environment. This papers argues that believability of such agents is tightly connected with their ability to relate to the environment during a ...