Social activities have great impact for human beings in psychological health and social relationship. the recognition of social activities can unobtrusively recognize and record users' daily social activities, ena...
详细信息
ISBN:
(纸本)9781467345750;9781467345736
Social activities have great impact for human beings in psychological health and social relationship. the recognition of social activities can unobtrusively recognize and record users' daily social activities, enabling users to better manage their life. Existing work of social activity recognition focus on recognizing a limited set of social activities and are mainly based on the patterns of individual user such as location pattern, vocal pattern, or others. However, social activities inherently exhibit the patterns with respect to multiple users rather individual user. In this paper, we introduce the concept of social circle, to extract social patterns associated with multiple users in a generic set of social activities. A social circle refers to a set of users frequently gathering to conduct certain social activities. Based on social circle, we design a system called CircleSense that supports accurate recognition of a generic set of social activities. We validate the effectiveness of CircleSense through the real trace collected by 10 volunteers. the result shows that CircleSense outperforms existing methods in terms of accuracy of social activity recognition.
the intelligent home security control, and has gradually become an indispensable basic equipment in our daily lives. In this study, using the handwriting recognition technology to confirm user identity and manage secu...
详细信息
It is essential to monitor sleeping patterns and position in order to learn about one's health state in order to enhance it and minimize sleep apnea. the use of a bed-mounted seismometer device to track the heart ...
详细信息
the use of speech for system identification is an important and relevant topic. there are several ways of doing it, but most are dependent on the language the user speaks. However, if the idea is to create an all-incl...
详细信息
the diversity of available cloud service models yields multiple hosting variants for application components. Moreover, the overall trend of reducing control over the infrastructure and scaling configuration makes it n...
详细信息
ISBN:
(纸本)9789897585104
the diversity of available cloud service models yields multiple hosting variants for application components. Moreover, the overall trend of reducing control over the infrastructure and scaling configuration makes it nontrivial to decide which hosting variant suits more a certain software component. In this work, we introduce a spectrum of component hosting patterns that covers various combinations of management responsibilities related to (i) the deployment stack required by a given component as well as (ii) required infrastructure resources and component's scaling rules. We validate the presented patterns by identifying and showing at least three real world occurrences of each pattern following the well-known Rule of three.
Facial expressions are part of human non-verbal communication. Automatically discriminating between genuine and acted emotion can help psychologists, judges, human-machine interface, and so on. the problems for resear...
详细信息
Intelligent sensor system design demands the efficient patternrecognition method that uses raw time-series sensor data to identify the target gas with fast and accurate results. the presented work uses gas sensor arr...
详细信息
ISBN:
(纸本)9781665426053
Intelligent sensor system design demands the efficient patternrecognition method that uses raw time-series sensor data to identify the target gas with fast and accurate results. the presented work uses gas sensor array response (open sampling setting) for 10 bio-marker gases. the responses are obtained at different concentrations. We propose a 2D convolution neural network (2D-CNN) based adaptive ensemble network for gas identification. the Spatio-temporal correlation of sensor array responses inspired us to design deep-learning-based gas identification networks. the network uses raw time-series gas sensor array data and identifies the target gas mixtures with improved accuracy despite sensor drift. Experimental results show that the proposed methods are an effective technique with identification accuracy approximately 91% for identifying gas mixture for smart sensor system application. the proposed method outperforms and provides higher identification accuracy than comparable various machine learning and deep learning methods.
this paper proposes an approach for finding the maximum power point (MPP) location of the photovoltaic (PV) array in the case of partial shading based on the shading patternrecognition. Shading patternrecognition is...
详细信息
Coverage is a kind of method to cover points of same class samples in feature space, which is based on Biomimetic patternrecognition. the mathematical description of coverage is given and the discriminant boundary of...
详细信息
ISBN:
(纸本)9783540725299
Coverage is a kind of method to cover points of same class samples in feature space, which is based on Biomimetic patternrecognition. the mathematical description of coverage is given and the discriminant boundary of coverage is shown. Coverage is tested in face recognition on ORL database. Boththe COVERAGE and SVM networks are used for covering. the results show that COVERAGE act better than SVM in generalization, especially for small sample set, which are consonant withthe result of the applications of BPR.
A Context-aware Prediction Framework (CAPF) can be provided through a Self-adaptive System (SAS) resource manager to support the autoscaling decision in Edge computing (EC) environments. However, EC dynamicity and wor...
详细信息
ISBN:
(纸本)9789897585104
A Context-aware Prediction Framework (CAPF) can be provided through a Self-adaptive System (SAS) resource manager to support the autoscaling decision in Edge computing (EC) environments. However, EC dynamicity and workload fluctuation represent the main challenges to design a robust prediction framework. Machine Learning (ML) algorithms show a promising accuracy in workload forecasting problems which may vary according to the workload pattern. therefore, the accuracy of such algorithms needs to be evaluated and compared in order to select the most suitable algorithm for EC workload prediction. In this paper, a thorough comparison is conducted focusing on the most popular ML algorithms which are Linear Regression (LR), Support Vector Regression (SVR), and Neural Networks (NN) using real EC dataset. the experimental results show that a robust prediction framework can be supported by more than one algorithm considering the EC contextual behavior. the results also reveal that the NN outperforms LR and SVR in most cases.
暂无评论