Pub Date : 2013-12-01DOI: 10.1109/ICICS.2013.6782845
M. Siyal, Jameel Ahmed, U. Khokhar, Taufeeq
Smart antenna is among the fastest emerging technologies employed in wireless communication. An antenna array and a digital signal processor using an Adaptive Algorithm, make a smart antenna, which can precisely locate user position in diverse environments. In this paper, a modified uniform linear array (ULA) setup for spectral estimation of narrow band sources at grazing incident angles has been presented. Unlike common ULA setup where all the array elements are aligned along one axis, modified ULA setup has been proposed with two additional antenna elements along z-axis, which will improve array resolution and efficiency under grazing incident conditions. Simulated results show the significance of the proposed algorithm over the existing spectral estimation technique.
{"title":"Spectral estimation algorithm for smart antenna system with modified ULA","authors":"M. Siyal, Jameel Ahmed, U. Khokhar, Taufeeq","doi":"10.1109/ICICS.2013.6782845","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782845","url":null,"abstract":"Smart antenna is among the fastest emerging technologies employed in wireless communication. An antenna array and a digital signal processor using an Adaptive Algorithm, make a smart antenna, which can precisely locate user position in diverse environments. In this paper, a modified uniform linear array (ULA) setup for spectral estimation of narrow band sources at grazing incident angles has been presented. Unlike common ULA setup where all the array elements are aligned along one axis, modified ULA setup has been proposed with two additional antenna elements along z-axis, which will improve array resolution and efficiency under grazing incident conditions. Simulated results show the significance of the proposed algorithm over the existing spectral estimation technique.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117002129","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782963
T. Yamasaki, Andrew C. Gallagher, Tsuhan Chen
In this paper, a geotag-based travel route recommendation algorithm that considers the seasonal and temporal popularity is presented. Travel routes are extracted from geotags attached to Flickr images. Then, landmarks/routes that become particularly popular at a specific time range in a typical season are extracted. By using the Bayes' theory, the transition probability matrix is efficiently calculated. Experiments were conducted using 21 famous sightseeing cities/places in the world. The results have shown that the recommendation accuracy can be improved by 0.9% - 10.3% on average. The proposed algorithm can also be incoorporated into the state-of-the-art algorithms, having a potential for further recommendation accuracy improvement.
{"title":"Geotag-based travel route recommendation featuring seasonal and temporal popularity","authors":"T. Yamasaki, Andrew C. Gallagher, Tsuhan Chen","doi":"10.1109/ICICS.2013.6782963","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782963","url":null,"abstract":"In this paper, a geotag-based travel route recommendation algorithm that considers the seasonal and temporal popularity is presented. Travel routes are extracted from geotags attached to Flickr images. Then, landmarks/routes that become particularly popular at a specific time range in a typical season are extracted. By using the Bayes' theory, the transition probability matrix is efficiently calculated. Experiments were conducted using 21 famous sightseeing cities/places in the world. The results have shown that the recommendation accuracy can be improved by 0.9% - 10.3% on average. The proposed algorithm can also be incoorporated into the state-of-the-art algorithms, having a potential for further recommendation accuracy improvement.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121208812","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782824
Y. Yang, K. Chow
We demonstrate ultra-short pulse generation using multi-layered graphene as saturable absorbers. The laser operation regimes switched between mode-locking and Q-switching are investigated. The multi-layered graphene saturable absorber is prepared by mechanical exfoliation from graphite flakes located between two fiber connectors. The performance of the laser is investigated under various laser pumping conditions, where the laser is able to operate in both mode-locked and Q-switch regimes for pulse generation.
{"title":"Optical pulse generation using multi-layered graphene saturable absorber","authors":"Y. Yang, K. Chow","doi":"10.1109/ICICS.2013.6782824","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782824","url":null,"abstract":"We demonstrate ultra-short pulse generation using multi-layered graphene as saturable absorbers. The laser operation regimes switched between mode-locking and Q-switching are investigated. The multi-layered graphene saturable absorber is prepared by mechanical exfoliation from graphite flakes located between two fiber connectors. The performance of the laser is investigated under various laser pumping conditions, where the laser is able to operate in both mode-locked and Q-switch regimes for pulse generation.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121533305","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782809
Wei-Xiang Tang, Shui-An Wen, S. Tung, Keng-Yu Lin, Chun-Chih Chen, Ching-Lung Su
Ultra-low voltage circuit design has become the trend of IC design. In this paper, we develop a low power consumption 32-bit microcontroller, SPARK, operating at 0.5V(20MHz) ~ 0.8V(95MHz) with an ultra-low voltage digital standard cell library. The goal of SPARK is making a small and low-power 32-bit RISC microcontroller. According to the experimental results, the best power consumption performance ratio of SPARK is 42.5μW/MHz.
{"title":"A 42.5µW/MHz ultra-low power 32-bit microcontroller — SPARK","authors":"Wei-Xiang Tang, Shui-An Wen, S. Tung, Keng-Yu Lin, Chun-Chih Chen, Ching-Lung Su","doi":"10.1109/ICICS.2013.6782809","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782809","url":null,"abstract":"Ultra-low voltage circuit design has become the trend of IC design. In this paper, we develop a low power consumption 32-bit microcontroller, SPARK, operating at 0.5V(20MHz) ~ 0.8V(95MHz) with an ultra-low voltage digital standard cell library. The goal of SPARK is making a small and low-power 32-bit RISC microcontroller. According to the experimental results, the best power consumption performance ratio of SPARK is 42.5μW/MHz.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"7 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132664029","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782777
Venice Erin Liong, Jiwen Lu, G. Wang
In this paper, we propose a new deep learning method called Deep PCA (DPCA) for face recognition. Our method performs deep learning through hierarchically projecting face image vectors to different feature subspaces and obtaining the representations from different projections. Specifically, we perform a two-layer ZCA whitening plus PCA structure for learning hierarchical features. The whole feature representation of each face image can be extracted by concatenating the representations from the first and second layers. Our approach learns deep representations from the data, by utilizing information from the first layer to produce a new and different representation, making it more discriminative. Experimental results on the widely used FERET and AR databases are presented to show the efficiency of the proposed approach.
{"title":"Face recognition using Deep PCA","authors":"Venice Erin Liong, Jiwen Lu, G. Wang","doi":"10.1109/ICICS.2013.6782777","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782777","url":null,"abstract":"In this paper, we propose a new deep learning method called Deep PCA (DPCA) for face recognition. Our method performs deep learning through hierarchically projecting face image vectors to different feature subspaces and obtaining the representations from different projections. Specifically, we perform a two-layer ZCA whitening plus PCA structure for learning hierarchical features. The whole feature representation of each face image can be extracted by concatenating the representations from the first and second layers. Our approach learns deep representations from the data, by utilizing information from the first layer to produce a new and different representation, making it more discriminative. Experimental results on the widely used FERET and AR databases are presented to show the efficiency of the proposed approach.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123468139","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782940
B. C. Loh, P. Then
This paper focuses on a healthcare solution capable of converting echocardiography videos into text, and vice versa, for transmission between urban and rural areas. People living in rural areas often encounter restrictions on essential healthcare services because of large distances. Telemedicine provides a possible answer to this problem. Several wireless technologies have been used in telemedicine systems and have widen the availability of medical services. However, wireless connectivity for mobile devices remains low in rural areas, especially Malaysia. The transmission of digital media requires high bandwidth wireless connections due to large file sizes. Without it, transmission delays may prevent effective patient care. Furthermore, in areas lacking internet connectivity, these services may cease to function. Preliminary experiments show that the proposed solution can achieve a file size reduction ranging from 66% to 96% when converting video to text.
{"title":"Cardiac echo to text conversion: Closing the urban-rural connectivity gap","authors":"B. C. Loh, P. Then","doi":"10.1109/ICICS.2013.6782940","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782940","url":null,"abstract":"This paper focuses on a healthcare solution capable of converting echocardiography videos into text, and vice versa, for transmission between urban and rural areas. People living in rural areas often encounter restrictions on essential healthcare services because of large distances. Telemedicine provides a possible answer to this problem. Several wireless technologies have been used in telemedicine systems and have widen the availability of medical services. However, wireless connectivity for mobile devices remains low in rural areas, especially Malaysia. The transmission of digital media requires high bandwidth wireless connections due to large file sizes. Without it, transmission delays may prevent effective patient care. Furthermore, in areas lacking internet connectivity, these services may cease to function. Preliminary experiments show that the proposed solution can achieve a file size reduction ranging from 66% to 96% when converting video to text.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124614269","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782864
Yue-Dar Jou, Chao-Ming Sun, Fu-Kun Chen
The optimization of least-squares filter design can be formulated as an eigenproblem by solving an appropriate positive-definite matrix. Based on Rayleigh's principle, eigenfilter design can be achieved by solving a single eigenvector corresponding to the smallest eigenvalue of an associated matrix. In this paper, the minor component analysis based on neural approach is exploited for the design of eigenfilter with effectiveness. As the learning algorithm achieves convergence, the weight vector of the neural system would approximate to the minimum eigenvector which results in the optimal filter coefficients of the eigenfilter design. Simulation results indicate that the proposed neural learning approach achieves good performance.
{"title":"Eigenfilter design of FIR digital filters using minor component analysis","authors":"Yue-Dar Jou, Chao-Ming Sun, Fu-Kun Chen","doi":"10.1109/ICICS.2013.6782864","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782864","url":null,"abstract":"The optimization of least-squares filter design can be formulated as an eigenproblem by solving an appropriate positive-definite matrix. Based on Rayleigh's principle, eigenfilter design can be achieved by solving a single eigenvector corresponding to the smallest eigenvalue of an associated matrix. In this paper, the minor component analysis based on neural approach is exploited for the design of eigenfilter with effectiveness. As the learning algorithm achieves convergence, the weight vector of the neural system would approximate to the minimum eigenvector which results in the optimal filter coefficients of the eigenfilter design. Simulation results indicate that the proposed neural learning approach achieves good performance.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"59 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116760064","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782832
S. Narayanan, A. Makur
In this paper, we exploit the relationship between the translational image motion and the Compressive Sensing (CS) measurements in order to perform the camera motion estimation in the compressed domain. Various CS measurement matrices have been investigated, and most of them are random Gaussian/Bernoulli matrices. Data acquisition using such matrices becomes computationally expensive for real time applications. Data acquisition using circulant CS matrices can be efficiently implemented in hardware using shift registers. We propose to use a circulant CS matrix on image frames to obtain the CS measurements and then to perform motion estimation in the measurement domain. Experimental results show that our method guarantees high motion estimation accuracy with few measurements. Our proposed method finds its application in video shot segmentation and video tracking where fast camera motion estimation is needed.
{"title":"Camera motion estimation using circulant compressive sensing matrices","authors":"S. Narayanan, A. Makur","doi":"10.1109/ICICS.2013.6782832","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782832","url":null,"abstract":"In this paper, we exploit the relationship between the translational image motion and the Compressive Sensing (CS) measurements in order to perform the camera motion estimation in the compressed domain. Various CS measurement matrices have been investigated, and most of them are random Gaussian/Bernoulli matrices. Data acquisition using such matrices becomes computationally expensive for real time applications. Data acquisition using circulant CS matrices can be efficiently implemented in hardware using shift registers. We propose to use a circulant CS matrix on image frames to obtain the CS measurements and then to perform motion estimation in the measurement domain. Experimental results show that our method guarantees high motion estimation accuracy with few measurements. Our proposed method finds its application in video shot segmentation and video tracking where fast camera motion estimation is needed.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115042326","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}
Photo events in personal photo collection management are important because people take photos according to the specific events. Event is one of important cues to retrieve photos which are well remembered by people. However, event classification work needs some useful cues to annotate the photo events well. Our main contribution is to annotate photo events automatically using simple temporal cues such as month, weekday/weekends, day/night, the correlations between scene and events, and the relation between concepts such as people/non-people and indoor/outdoor and events. In this paper, we propose an automatic photo event classification framework to address these problems. The framework is composed of four main components: the temporal detector, the scene detector, the concept detector, and the event detector. Our experimental results show that the methods in the framework are useful to detect the events of personal photos. According to the contents of events, we now can detect four events: beachfun, graduation, urbantour, and yardprk, and are expanding to detect other events.
{"title":"Personal photo organization using event annotation","authors":"Jia-Min Gu, Yi-Leh Wu, Wei-Chih Hung, Cheng-Yuan Tang","doi":"10.1109/ICICS.2013.6782958","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782958","url":null,"abstract":"Photo events in personal photo collection management are important because people take photos according to the specific events. Event is one of important cues to retrieve photos which are well remembered by people. However, event classification work needs some useful cues to annotate the photo events well. Our main contribution is to annotate photo events automatically using simple temporal cues such as month, weekday/weekends, day/night, the correlations between scene and events, and the relation between concepts such as people/non-people and indoor/outdoor and events. In this paper, we propose an automatic photo event classification framework to address these problems. The framework is composed of four main components: the temporal detector, the scene detector, the concept detector, and the event detector. Our experimental results show that the methods in the framework are useful to detect the events of personal photos. According to the contents of events, we now can detect four events: beachfun, graduation, urbantour, and yardprk, and are expanding to detect other events.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129682516","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 : 2013-12-01DOI: 10.1109/ICICS.2013.6782908
HongJun Yin, Jing Li, Yue Niu
In this paper, we propose a fast MPI algorithm for Monte Carlo approximation PageRank vector of all the nodes in a graph, named Fast Fibonacci Series-Based Personal PageRank. In the latter paper we will call it FFSB algorithm for short. The basic ideal is very efficiently computing single random walks of a given length starting at each node in a graph. More precisely, we design FFSB, which given a graph G and a length λ, outputs a single random walk of length λ at each node in G. We will exhibit that the number of MPI iterations and machine time is better than the most efficient algorithm at present with machine time log2 λ (λ is the given walk length). The algorithm with the complexity 0.72022 × log2 λ × (g + max {L + 2 × o, 2 × g}) is optimal among a broad family of algorithms for the problem. Also the empirical evaluation on real-life graph data crawled from Sina micro blog demonstrates that our algorithm is significantly more efficient than all the existing candidates in production parallel programing environment MPI.
在本文中，我们提出了一种快速的MPI算法，用于蒙特卡罗逼近图中所有节点的PageRank向量，称为fast Fibonacci seriesbased Personal PageRank。在后一篇文章中，我们将其简称为FFSB算法。基本理想是非常有效地计算从图中的每个节点开始的给定长度的单个随机行走。更准确地说，我们设计了FFSB，给定一个图G和一个长度λ，在G中的每个节点上输出一个长度为λ的随机漫步。我们将证明MPI迭代次数和机器时间优于目前最有效的算法，机器时间为log2 λ (λ为给定的行走长度)。复杂度为0.72022 × log2 λ × (g + max {L + 2 × o, 2 × g})的算法是解决该问题的众多算法中的最优算法。此外，对从新浪微博抓取的真实图形数据的实证评估表明，我们的算法比生产并行编程环境MPI中现有的所有候选算法都要高效得多。
{"title":"FFSB: Fast Fibonacci Series-Based personalized PageRank on MPI","authors":"HongJun Yin, Jing Li, Yue Niu","doi":"10.1109/ICICS.2013.6782908","DOIUrl":"https://doi.org/10.1109/ICICS.2013.6782908","url":null,"abstract":"In this paper, we propose a fast MPI algorithm for Monte Carlo approximation PageRank vector of all the nodes in a graph, named Fast Fibonacci Series-Based Personal PageRank. In the latter paper we will call it FFSB algorithm for short. The basic ideal is very efficiently computing single random walks of a given length starting at each node in a graph. More precisely, we design FFSB, which given a graph G and a length λ, outputs a single random walk of length λ at each node in G. We will exhibit that the number of MPI iterations and machine time is better than the most efficient algorithm at present with machine time log2 λ (λ is the given walk length). The algorithm with the complexity 0.72022 × log2 λ × (g + max {L + 2 × o, 2 × g}) is optimal among a broad family of algorithms for the problem. Also the empirical evaluation on real-life graph data crawled from Sina micro blog demonstrates that our algorithm is significantly more efficient than all the existing candidates in production parallel programing environment MPI.","PeriodicalId":184544,"journal":{"name":"2013 9th International Conference on Information, Communications & Signal Processing","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124631038","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：