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.
This paper is focused on comparing corpus-based methods for estimating word sentiment. Evaluated algorithms represent varying degrees of supervision and range from regression alike approaches to more heavily supervised classifications. The main idea is to explore the opportunities arising from mining medium sized, balanced corpora -- as opposed to web as a corpus paradigm. The comparisons have been...
The contribution describes the application of the Team 'Computational Intelligence Group' from the University of Applied Sciences Mittweida (Germany) to the ICMLA Face Recognition Challenge 2012. In particular we explain the data preprocessing and feature extraction, which was applied before classification learning. Further we give details about the used classification algorithm - the enhanced generalized...
Context-aware information retrieval received a significant attention last years. This paper addresses some of the challenges in context acquisition. It is focused on a method for inference of unavailable contextual information using machine learning. The method for context inference is based on observed behaviour of individual user and virtual communities of similar users. We work with contextual...
Captchas are frequently used on the modern world wide web to differentiate human users from automated bots by giving tests that are easy for humans to answer but difficult or impossible for algorithms. As artificial intelligence algorithms have improved, new types of Captchas have had to be developed. Recent work has proposed a new system called Avatar Captcha, in which a user is asked to distinguish...
Human activity recognition finds many applications in areas such as surveillance, and sports. Such a system classifies a spatio-temporal feature descriptor of a human figure in a video, based on training examples. However many classifiers face the constraints of the long training time, and the large size of the feature vector. Our method, due to the use of an Support Vector Machine (SVM) classifier,...
Pedagogically, feedback in CAPT systems can be improved by focusing on the most critical errors rather than presenting all errors to the users at the same time. This paper presents our work on the use of crowdsourcing for collection of gradations of word-level mispronunciations in non-native English speech. Quality control procedures based on the proposed WorkerRank algorithm (adapted from well-known...
In this paper a new method of eye blink detection and analysis is proposed. The described technique is based on a combination of spatial and temporal derivatives calculated in video sequences acquired with a high speed camera. The pixels of each frame are divided into two groups according to the direction and magnitude of the hybrid gradient vectors and the distance between their centers of gravity...
The segmentation of MR images is of great interests in automatic medical diagnosis. However, such images are corrupted by Rician noise and with fuzzy edges. The non-additive and intensity dependant features of Rician noise make image processing very challenging. In this paper, a combination of techniques are carefully selected, tailored, and organized to improve the image quality for automatic segmentation...
Potential functions can be used to design efficient path planning schemes. However, it is often difficult to design appropriate potential functions to mimic desired behavior of the agent. Instead of using a pre-designed potential function for path planning, this paper presents an algorithm that learns the underlying potential function from a given sample trajectory generated by a “expert” (say, a...
Emotions play a key role in human-computer interaction. They are generally expressed through several ways (e.g. facial expressions, speech, body postures and gestures, etc). In this paper, we present a multimodal approach for the emotion recognition that integrates information coming from different cues and modalities. It is based on a formal multidimensional model using an algebraic representation...
We address the problem of predicting the miRNA: miRNA∗ duplex stemming from a microRNA (miRNA) hairpin precursor and we present a SVM-based methodology to address it. Predicting the miRNA: miRNA∗ duplex is a first step towards identifying the mature miRNA, suggesting possible miRNA targets and ultimately, reducing experimentation effort, time, and cost. We measure the error in terms of the absolute...
We propose a new scheme that exploits characteristics of motion vectors combined with luminance contrast to automatically detect human attention regions of interest (HAROIs) in every I-frame or intra-coded blocks in a group of pictures (GOP). These HAROIs can then be used for adaptive quantization. Motion vectors information is collected before the encoding phase. Our ultimate goal is to obtain a...
Numerous studies have focused on measuring tourism competitiveness. However, few studies have attempted to identify strategies for improving tourism competitiveness, preventing decision makers from obtaining valuable cues for making accurate decisions to improve competitiveness. This study thus explores strategies for improving tourism competitiveness using a new hybrid fuzzy MCDM model combined with...
Online chats are recently shown to result in long term associations among users, represented by a directed weighted network, similar to dialogs in online social networks. We consider the persistent network which emerges from user-to-user communications found in the empirical dataset from IRC Ubuntu channel. The structure of these networks is determined by computing topological centrality measures,...
We present preliminary results on the passive velocity field control (PVFC) of the quadrotor-type UAVs, which allows the quadrotor to follow the direction of a given velocity field while enforcing passivity of the closed-loop system. Some theoretical results are presented along with a simulation result.
The Internet of Things (IoT) extends and expands the range of the internet by interconnecting Internet and end device networks. As the raising of awareness about IoT, more and more application may applied for various areas. Especially, the development of intelligent energy saving becomes a new trend in all circles. This research integrated appliance and activity recognition mechanism for IoT energy...
An important method used to speed up forensic file-system analysis is white-listing of files: Well-known files are detected using signatures (message digests) or similar methods, and omitted from further analysis initially, in order to better focus the initial analysis on files likely to be more important. Typical examples of such well-known files include files used by operating systems, popular applications,...
In order to have a rich representation for human action, we propose to combine two complementary features so that a human posture can be characterized in more details. In particular, the distance signal feature and the width feature are combined in an effective way to enhance each other's discriminating capability. The resulting feature vector is quantized into mid-level features using k-means clustering...
Task allocation strategy has a great impact on the performance of the workflow management system in workflow scheduling. Most task allocation algorithms focus on the resource status only. Few algorithms consider the change of efficiency while performer working with different people. To achieve this, this paper presents a concept of Social Context Impact Factor (SCIF) and implements several task allocation...
This paper proposes a system to recognize quasi-periodic human actions from monocular video sequences. First, each input video frame is analyzed and estimated to generate the best 3D human model pose which consists of a set of 3D coordinates of specific human joints. Next, these 3D coordinates for each frame are converted into corresponding 3D geometric relational features (GRFs), which describe the...
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.