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 presents a multi-feature approach for detection of key postures by using a MESA SR4000 time-offlight 3D sensor managed by a low-power embedded PC. Acquired data were pre-processed by using a well-established framework including self-calibration, segmentation and tracking functionalities. To accommodate different application scenarios, hierarchical coarse-to-fine features were extracted...
With the advance of natural user interface technology, studies on detecting human movement and gestures have been conducted. Among these studies, sleep recognition is significant for energy saving as human's special behavior. This paper proposes a novel approach using a depth sensor and camera for increasing sleep recognition accuracy. Several potential errors of sensing gestures when sleeping are...
Human posture classification is one of the most challenging issues in smart homecare system. To achieve high classification accuracy, we propose a new algorithm, called range-based algorithm. In this paper, a range means the distance between body parts. The ranges between body parts are investigated to classify the human posture and to detect a possible fall-down accident. Furthermore, we also proposed...
In this work, we consider a classification problem of 14 physical activities using a body sensor network (BSN) consisting of 14 tri-axial accelerometers. We use a tree-based classifier, and develop a feature selection algorithm based on mutual information to find the relevant features at every internal node of the tree. We evaluate our algorithm on 31 features per accelerometer (total of 434), and...
In this paper, we propose an area-based communication detection system. We aim to detect conversations with their attributes, such as communication length, communication members, relationship among members, and subjects. We think extracting correlations between conversations' attributes and office worker productivity is important for office worker productivity improvement. To evaluate our proposed...
This paper presents a multi-modal affect recognition system that is capable of effectively estimating human affective states through analyzing and fusing a number of non-invasive external cues. The proposed system consists of a probabilistic information fusion model based on the influence diagram and a set of data analysis, feature extraction and affect recognition modules for processing heterogeneous...
In this work, we develop a system to automatically monitoring actions of elderly people at home for safety enhancement and health monitoring. We use an Infrared camera embedded in a living environment to capture images. We study the characteristics of different clothing in Infrared images and develop an efficient silhouette extraction method for Infrared (IR) images using spatio-temporal filtering...
Due to the human activities such as artificial beach and reclaiming land from seawaters along Yancheng's coastal area in Jiangsu province in recent years, the problems of coastline straightening and the mudflat prograding have become highlighted. Therefore, it is great significant to master coastline change for shore and mudflats exploitation and utilization, environmental protection and Marine disaster...
Human computer interface (HCI) is often regarded as the intersection of computer science, behavioral sciences, design and several other fields of study. In order to improve the usability of HCI, investigation of the interaction between human and computers is an important issue. In present study, we use a pointing movement experimental device with visual feedback control function which developed in...
With the increasing of public safety demand, monitoring system has been used widely. However, there are not many mature passenger flow counting systems in the market, because the system's key problem has not been satisfactory resolved. In this paper, the key algorithms in this system are discussed. The main algorithms have been improved, such as: the extraction of human, the segmentation of crowd...
This paper explores a sensor fusion method within Smart Homes to be used to monitor human activities in addition to managing uncertainty in sensor based readings. A case study has shown that the Dempster-Shafer theory of evidence can incorporate the uncertainty derived from the sensor errors and the sensor context and infer the activity. The results from this work show that this method can detect...
Monitoring multimodal data generated by sensor networks for extracting information is a challenging task for the human observer. To manage the barrage of data, one needs to create mechanisms for identifying only those time intervals which are informative and worthy of further highlevel analysis either by machine or the human observer. We regard a time interval to be informative and contain an event...
We describe a cost-effective method which enables location-aware applications in PLMN environments. The proposed approach is assuming no terminal support and it is based on signaling traffic analysis in respect to selected invariant patterns of human behavior, IHAP, and network topology. The experiments carried out in real-life network environment are revealing robust performance, in terms of accuracy...
Networked hosts' vulnerabilities pose some serious threats to the operation of computer networks. Modern at tacks are increasingly complex, and exploit many strategies in order to perform their intended malicious tasks. Attackers have developed the ability of controlling large sets of infected hosts, characterized by complex executable command sets, each taking part in cooperative and coordinated...
The increasing use of virtual reality in the treatment of phobias translates in a just as expanding need for realism in its scenes and characters. Virtual characters need to seem gifted with intelligence. A first step in achieving this is by giving them the possibility to interact with real people. In this paper we present an eye-tracking based method to obtain interactive virtual characters. We use...
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.