Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765524
Koki Kimura, K. Gunawardena, M. Hirakawa
Owing to the development of graphical user interfaces, computers have become a common tool for use by all age groups both at home and at work. Furthermore, touchscreen-based user interfaces are now commonly used in mobile computers such as smartphones and tablets. When we anticipate that future computers will become invisible, that is, computing functionality will be completely embedded into household appliances, furniture, and houses, our interactions will not be limited to things on a display or a tabletop. In such situations, pleasantness may become important as well as accuracy and efficiency in interface design. This study presents a new scheme for detecting 3D positions of objects in water, based on our experiences with the development of aquatic interactive systems. For the detection of objects on a certain 2D layer in water, a line laser is used with a camera. Stacking multiple line lasers enables the detection of object positions in a 3D space.
{"title":"A framework for detecting positions of objects in water","authors":"Koki Kimura, K. Gunawardena, M. Hirakawa","doi":"10.1109/ICAWST.2013.6765524","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765524","url":null,"abstract":"Owing to the development of graphical user interfaces, computers have become a common tool for use by all age groups both at home and at work. Furthermore, touchscreen-based user interfaces are now commonly used in mobile computers such as smartphones and tablets. When we anticipate that future computers will become invisible, that is, computing functionality will be completely embedded into household appliances, furniture, and houses, our interactions will not be limited to things on a display or a tabletop. In such situations, pleasantness may become important as well as accuracy and efficiency in interface design. This study presents a new scheme for detecting 3D positions of objects in water, based on our experiences with the development of aquatic interactive systems. For the detection of objects on a certain 2D layer in water, a line laser is used with a camera. Stacking multiple line lasers enables the detection of object positions in a 3D space.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80620172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765414
T. Dendou, G. Chakraborty
Data collected from pressure sensors attached to shoe insole is a rich source of information about the dynamics of the varying pressure exerted at different points while a person is in motion. Depending on the accuracy and the density of the points of data collection, this could be applied for different uses. Analyzing the time series data of the pressure, it is possible (1) to detect faults in walking and balancing problems for old people, (2) to design personalized foot orthoses, (3) to calculate the calorie burnt, even when walking and jogging are mixed, and the road slope changes, (4) to find subtle faults in sprinters or tennis players, (5) for person identification, (6) even for initiating alarm arising from mishandling of machines (like accelerator pedal of a car). In this work, we look for an efficient, real-time, yet cheap solution. We use a few thin, cheap, resistive pressure sensors, placed at critical points on the insole of the shoe to collect dynamic pressure data, preprocess it and extract features to identify the mobility speed. Nearly 100% classification accuracy was achieved. Thus, the target to classify whether the person is walking or jogging or climbing up or down the stairs was found to be possible, even with very simple gadget. From the time duration and the speed, the distance travel could be calculated. If, in addition, this signal could tell us the body-weight, we could accurately calculate the calorie burnt at the end of the day. The analysis method, and results from real experiments are discussed.
{"title":"Real-time mobility aware shoe — Analyzing dynamics of pressure variations at important foot points","authors":"T. Dendou, G. Chakraborty","doi":"10.1109/ICAWST.2013.6765414","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765414","url":null,"abstract":"Data collected from pressure sensors attached to shoe insole is a rich source of information about the dynamics of the varying pressure exerted at different points while a person is in motion. Depending on the accuracy and the density of the points of data collection, this could be applied for different uses. Analyzing the time series data of the pressure, it is possible (1) to detect faults in walking and balancing problems for old people, (2) to design personalized foot orthoses, (3) to calculate the calorie burnt, even when walking and jogging are mixed, and the road slope changes, (4) to find subtle faults in sprinters or tennis players, (5) for person identification, (6) even for initiating alarm arising from mishandling of machines (like accelerator pedal of a car). In this work, we look for an efficient, real-time, yet cheap solution. We use a few thin, cheap, resistive pressure sensors, placed at critical points on the insole of the shoe to collect dynamic pressure data, preprocess it and extract features to identify the mobility speed. Nearly 100% classification accuracy was achieved. Thus, the target to classify whether the person is walking or jogging or climbing up or down the stairs was found to be possible, even with very simple gadget. From the time duration and the speed, the distance travel could be calculated. If, in addition, this signal could tell us the body-weight, we could accurately calculate the calorie burnt at the end of the day. The analysis method, and results from real experiments are discussed.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82672081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765512
Yinghui Zhou, Daisuke Saito, Lei Jing
Wearable device based gesture recognition has become a hot topic in healthcare research fields. Effective gesture recognition is helpful to not only provide services for health monitoring, but also develop various applications like appliance control and emergency call. However, significantly individual difference of gesture performance brings challenge for accurate gesture recognition. In this paper, a personalized method of gesture recognition is proposed, which can analyze personal gesture features and automatically adjust gesture templates to improve recognition accuracy. The method was evaluated on a finger-worn device named Magic Ring that collected eight gestures from three subjects for one week testing. Results show the effectiveness of the method that average improvement of 16% in recognition accuracy has been achieved.
{"title":"Adaptive template adjustment for personalized gesture recognition based on a finger-worn device","authors":"Yinghui Zhou, Daisuke Saito, Lei Jing","doi":"10.1109/ICAWST.2013.6765512","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765512","url":null,"abstract":"Wearable device based gesture recognition has become a hot topic in healthcare research fields. Effective gesture recognition is helpful to not only provide services for health monitoring, but also develop various applications like appliance control and emergency call. However, significantly individual difference of gesture performance brings challenge for accurate gesture recognition. In this paper, a personalized method of gesture recognition is proposed, which can analyze personal gesture features and automatically adjust gesture templates to improve recognition accuracy. The method was evaluated on a finger-worn device named Magic Ring that collected eight gestures from three subjects for one week testing. Results show the effectiveness of the method that average improvement of 16% in recognition accuracy has been achieved.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82940191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765490
Zunyi Tang, Toshiyo Tamura, Shuxue Ding, Zhenni Li
Recently, sparse representations via an overcomplete dictionary has become a major field of research in signal processing. Much efforts have been focused on the development of dictionary learning algorithms so that the sparse representation of signals can be efficiently performed. In this paper, we propose a method for learning a signal dependent overcomplete dictionary. This is accomplished by posing the sparse representation of signals as a problem of matrix factorization with a sparsity constraint. By generalizing the conventional coordinate descent method, we develop a so-called sparse alternating parallel coordinate descent (SAPCD) algorithm, which is structured by iteratively solving the two optimal problems, the learning process of the dictionary and the estimating process of the coefficients for constructing the signals. Numerical experiments demonstrate that the proposed algorithm performs better than the famous K-SVD algorithm and several other algorithms for comparison.
{"title":"Sparse representation and dictionary learning based on alternating parallel coordinate descent","authors":"Zunyi Tang, Toshiyo Tamura, Shuxue Ding, Zhenni Li","doi":"10.1109/ICAWST.2013.6765490","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765490","url":null,"abstract":"Recently, sparse representations via an overcomplete dictionary has become a major field of research in signal processing. Much efforts have been focused on the development of dictionary learning algorithms so that the sparse representation of signals can be efficiently performed. In this paper, we propose a method for learning a signal dependent overcomplete dictionary. This is accomplished by posing the sparse representation of signals as a problem of matrix factorization with a sparsity constraint. By generalizing the conventional coordinate descent method, we develop a so-called sparse alternating parallel coordinate descent (SAPCD) algorithm, which is structured by iteratively solving the two optimal problems, the learning process of the dictionary and the estimating process of the coefficients for constructing the signals. Numerical experiments demonstrate that the proposed algorithm performs better than the famous K-SVD algorithm and several other algorithms for comparison.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89232766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765542
Anzu Nakada, Michael Cohen, Rasika Ranaweera
We have built interfaces featuring smartphones and tablets that use magnetometer-derived orientation sensing to control spatial sound, motion platforms, panoramic and turnoramic image-based renderings, virtual displays, and other programs. To leverage our Collaborative Virtual Environment (CVE), which is implemented in pure Java, against the power of Mathematica, we use J/Link middleware. As a result, we can exploit Mathematica features of graphics and calculation and control the Mathematica Kernel by data from, among other clients, mobile devices.
{"title":"Integrating the Collaborative Virtual Environment protocol with Mathematica","authors":"Anzu Nakada, Michael Cohen, Rasika Ranaweera","doi":"10.1109/ICAWST.2013.6765542","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765542","url":null,"abstract":"We have built interfaces featuring smartphones and tablets that use magnetometer-derived orientation sensing to control spatial sound, motion platforms, panoramic and turnoramic image-based renderings, virtual displays, and other programs. To leverage our Collaborative Virtual Environment (CVE), which is implemented in pure Java, against the power of Mathematica, we use J/Link middleware. As a result, we can exploit Mathematica features of graphics and calculation and control the Mathematica Kernel by data from, among other clients, mobile devices.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82301407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765544
J. Daemen, Peter Haufs-Brusberg, J. Herder
Virtual (tv) studios gain much more acceptance through improvements in computer graphics and camera tracking. Still commercial studios cannot have full interaction between actors and virtual scene because actors data are not completely digital available as well as the feedback for actors is still not sufficient. Markerless full body tracking might revolutionize virtual studio technology as it allows better interaction between real and virtual world. This article reports about using a markerless actor tracking in a virtual studio with a tracking volume of nearly 40 cubic meter enabling up to three actors within the green box. The tracking is used for resolving the occlusion between virtual objects and actors so that the Tenderer can output automatically a mask for virtual objects in the foreground in case the actor is behind. It is also used for triggering functions scripted within the Tenderer engine, which are attached to virtual objects, starting any kind of action (e.g., animation). Last but not least the system is used for controlling avatars within the virtual set. All tracking and rendering is done within a studio frame rate of 50 Hz with about 3 frames delay. The markerless actor tracking within virtual studios is evaluated by experts using an interview approach. The statistical evaluation is based on a questionnaire.
{"title":"Markerless actor tracking for virtual (TV) studio applications","authors":"J. Daemen, Peter Haufs-Brusberg, J. Herder","doi":"10.1109/ICAWST.2013.6765544","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765544","url":null,"abstract":"Virtual (tv) studios gain much more acceptance through improvements in computer graphics and camera tracking. Still commercial studios cannot have full interaction between actors and virtual scene because actors data are not completely digital available as well as the feedback for actors is still not sufficient. Markerless full body tracking might revolutionize virtual studio technology as it allows better interaction between real and virtual world. This article reports about using a markerless actor tracking in a virtual studio with a tracking volume of nearly 40 cubic meter enabling up to three actors within the green box. The tracking is used for resolving the occlusion between virtual objects and actors so that the Tenderer can output automatically a mask for virtual objects in the foreground in case the actor is behind. It is also used for triggering functions scripted within the Tenderer engine, which are attached to virtual objects, starting any kind of action (e.g., animation). Last but not least the system is used for controlling avatars within the virtual set. All tracking and rendering is done within a studio frame rate of 50 Hz with about 3 frames delay. The markerless actor tracking within virtual studios is evaluated by experts using an interview approach. The statistical evaluation is based on a questionnaire.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78904247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765444
R. D. A. Ludena, A. Ahrary
The advent of Big Data analytics is changing some of the current knowledge paradigms in Science as well in Industry. Although, the term and some of the core methodologies have been around for many years, the continuous price reduction of hardware and some services (e.g. cloud computing) are making more affordable the application of these methodologies to almost any Research Area being developed in Academic Institutions or Company Research Centers. This growing popularity is also raising some concerns regarding some of its core concepts and the way Data is treated through the analysis process. It is the aim of this paper to address these concerns because big Data Methodologies will be extensively use in the new ICT Agriculture project granted by NEDO, in order to improve the efficiency and accuracy of the proposed system, therefore it is necessary to establish a common background for all the project members in which Sojo University plays a fundamental role in the improvement of the general performance of the proposed system.
{"title":"Big Data approach in an ICT Agriculture project","authors":"R. D. A. Ludena, A. Ahrary","doi":"10.1109/ICAWST.2013.6765444","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765444","url":null,"abstract":"The advent of Big Data analytics is changing some of the current knowledge paradigms in Science as well in Industry. Although, the term and some of the core methodologies have been around for many years, the continuous price reduction of hardware and some services (e.g. cloud computing) are making more affordable the application of these methodologies to almost any Research Area being developed in Academic Institutions or Company Research Centers. This growing popularity is also raising some concerns regarding some of its core concepts and the way Data is treated through the analysis process. It is the aim of this paper to address these concerns because big Data Methodologies will be extensively use in the new ICT Agriculture project granted by NEDO, in order to improve the efficiency and accuracy of the proposed system, therefore it is necessary to establish a common background for all the project members in which Sojo University plays a fundamental role in the improvement of the general performance of the proposed system.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76215620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765427
W. Budiharto, R. N. Rachmawati, M. Ricky, B. R. P. Chyntia
The mobile games industry and its development goals were not just for entertainment, but also used for educational of students interactively. Unfortunately the development of adaptive educational games that consider the psychological aspects for student on mobile platforms in Indonesian language that interesting and entertaining for learning process is very limited. This paper shows the research of development of novel adaptive games for students who can adjust the difficulty level of games based on the ability of the user, so that it can motivate students to continue to play these games. We propose a method where these games can adjust the level of difficulty, based on the assessment of the results of previous problems using neural networks with three inputs in the form of percentage correct, the speed of answer and interest mode of games (animation / lessons) to producel output. The experimental results are presented and show the adaptive games are running well on mobile devices based on BlackBerry platform.
{"title":"The psychological aspects and implementation of adaptive games for mobile application","authors":"W. Budiharto, R. N. Rachmawati, M. Ricky, B. R. P. Chyntia","doi":"10.1109/ICAWST.2013.6765427","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765427","url":null,"abstract":"The mobile games industry and its development goals were not just for entertainment, but also used for educational of students interactively. Unfortunately the development of adaptive educational games that consider the psychological aspects for student on mobile platforms in Indonesian language that interesting and entertaining for learning process is very limited. This paper shows the research of development of novel adaptive games for students who can adjust the difficulty level of games based on the ability of the user, so that it can motivate students to continue to play these games. We propose a method where these games can adjust the level of difficulty, based on the assessment of the results of previous problems using neural networks with three inputs in the form of percentage correct, the speed of answer and interest mode of games (animation / lessons) to producel output. The experimental results are presented and show the adaptive games are running well on mobile devices based on BlackBerry platform.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76370589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765447
Chen-Shen Huang, K. Huang, G. Jong
This paper describes an expert system of bio-information, which is combined with the smart devices using wireless sensor network (WSN). The physiological signals can be acquired by some wireless bio-sensor module, such as electrocardiogram (ECG), heart rate (HR), heart rate variability (HRV) and autonomic nervous system (ANS) activity, etc. The smart device transmits the bio-information by wireless network, which provides the real-time expert consultation function requirements for the purpose of bio-information analysis, storage and decision. The smart device is also connected the expert system server by the wireless network The HRV detection parameter value is adopted the criteria and basis for the features of diabetes by using artificial neural network (ANN) algorithm. The remote client can be inquired the bio-information at any time on internet information service (IIS) platform. In addition, the system platform is adequate for comparing the data files. The bio-information and diabetes information can be provided for the alert message timely and actively. The system of this paper is achieved a ubiquitous mobile physiological monitor purpose.
{"title":"Artificial neural network integrated heart rate variability with detection system","authors":"Chen-Shen Huang, K. Huang, G. Jong","doi":"10.1109/ICAWST.2013.6765447","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765447","url":null,"abstract":"This paper describes an expert system of bio-information, which is combined with the smart devices using wireless sensor network (WSN). The physiological signals can be acquired by some wireless bio-sensor module, such as electrocardiogram (ECG), heart rate (HR), heart rate variability (HRV) and autonomic nervous system (ANS) activity, etc. The smart device transmits the bio-information by wireless network, which provides the real-time expert consultation function requirements for the purpose of bio-information analysis, storage and decision. The smart device is also connected the expert system server by the wireless network The HRV detection parameter value is adopted the criteria and basis for the features of diabetes by using artificial neural network (ANN) algorithm. The remote client can be inquired the bio-information at any time on internet information service (IIS) platform. In addition, the system platform is adequate for comparing the data files. The bio-information and diabetes information can be provided for the alert message timely and actively. The system of this paper is achieved a ubiquitous mobile physiological monitor purpose.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76624149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765433
Jingyu Wang, Ke Zhang, K. Madani, C. Sabourin
Human beings are more intelligent in dealing with sound which occurred in everyday life than robots or other kind of unmanned ground vehicles because of the instinct of "sense" or "awareness", which is an ability to distinguish the most salient sound, object or events in the surrounding environment. Inspired by the biological acoustic awareness of human hearing system and the visual saliency talent of human vision, a heterogeneous information saliency feature fusion (HISFF) approach which simulates human awareness of environment sound for machine's awareness is proposed in this paper. The sound signal is visualized by using the Short-Time Fourier Transform (STFT) algorithm in order to convert the acoustic saliency into visual saliency, and the Mel-Frequency Cepstrum Coefficient (MFCC) is used to represent the human acoustic awareness. The proposed HISFF approach is tested by using the environment sound data which collected from the real world of both indoor and outdoor environment. The results show that this approach is able to extract the saliency signal from both long-term and short-term sound signal successfully and clearly, and conducts to very distinguishable features for machine's environment sounds based awareness.
{"title":"Heterogeneous information saliency features' fusion approach for machine's environment sounds based awareness","authors":"Jingyu Wang, Ke Zhang, K. Madani, C. Sabourin","doi":"10.1109/ICAWST.2013.6765433","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765433","url":null,"abstract":"Human beings are more intelligent in dealing with sound which occurred in everyday life than robots or other kind of unmanned ground vehicles because of the instinct of \"sense\" or \"awareness\", which is an ability to distinguish the most salient sound, object or events in the surrounding environment. Inspired by the biological acoustic awareness of human hearing system and the visual saliency talent of human vision, a heterogeneous information saliency feature fusion (HISFF) approach which simulates human awareness of environment sound for machine's awareness is proposed in this paper. The sound signal is visualized by using the Short-Time Fourier Transform (STFT) algorithm in order to convert the acoustic saliency into visual saliency, and the Mel-Frequency Cepstrum Coefficient (MFCC) is used to represent the human acoustic awareness. The proposed HISFF approach is tested by using the environment sound data which collected from the real world of both indoor and outdoor environment. The results show that this approach is able to extract the saliency signal from both long-term and short-term sound signal successfully and clearly, and conducts to very distinguishable features for machine's environment sounds based awareness.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79231962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：