In recent years in Taiwan, advances in interactive technology, the evolution of interdisciplinary creation trends, digital technology and performances that transcend traditional boundaries have combined to form a new type of technology performances arts field. This study explores connections between visual technology and performance praxis in the technology performance arts of interdisciplinary collaborations, aesthetic characteristics, and possible future trends.
{"title":"Interdisciplinary praxis in Interactive Visual and Dance: A Case Study of Nu Shu GPS","authors":"Yun-Ju Chen, Ping-Yeh Li, Ruey-Sen Chiu, Ya-Kuan Chou","doi":"10.1109/ICKII.2018.8569086","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569086","url":null,"abstract":"In recent years in Taiwan, advances in interactive technology, the evolution of interdisciplinary creation trends, digital technology and performances that transcend traditional boundaries have combined to form a new type of technology performances arts field. This study explores connections between visual technology and performance praxis in the technology performance arts of interdisciplinary collaborations, aesthetic characteristics, and possible future trends.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125255319","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569065
Kwangsuk Lee, Jae-Kyeong Kim, Jaehyong Kim, K. Hur, Hagbae Kim
This paper proposes a multi-layered anomaly detection scheme to train feature extraction and to test anomaly prediction by using Convolutional Neural Networks (CNNs) layer, Bidirectional and Unidirectional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs), which is one of a novel deep architecture named stacked convolutional bidirectional LSTM network (SCB-LSTM). In the proposed model, the stacked CNNs perform feature extraction of vibration sensor signal patterns, and the result is used to feature learning with the stacked bidirectional LSTMs (SB-LSTMs). After this procedure, the stacked unidirectional LSTMs (SU-LSTMs) enhance the feature learning, and a regression layer finally predicts anomaly detections. The experimental results of bearing data not only show the accuracy of the proposed model in anomaly detection for rotating machinery diagnostics, but also suggest the better performance than other state-of-the-art algorithms such as a plain uni-LSTM or Bi-LSTM.
本文提出了一种多层异常检测方案，利用卷积神经网络(cnn)层双向和单向长短期记忆(LSTM)递归神经网络(RNNs)进行特征提取训练和异常预测测试，这是一种新型的深度体系结构，称为堆叠卷积双向LSTM网络(SCB-LSTM)。在该模型中，堆叠cnn对振动传感器信号模式进行特征提取，并将结果用于堆叠双向lstm (sb - lstm)的特征学习。在此过程之后，堆叠的单向lstm (su - lstm)增强了特征学习，并最终通过回归层预测异常检测。轴承数据的实验结果不仅表明了该模型在旋转机械诊断异常检测中的准确性，而且表明该模型的性能优于其他最先进的算法，如普通的uni-LSTM或Bi-LSTM。
{"title":"Stacked Convolutional Bidirectional LSTM Recurrent Neural Network for Bearing Anomaly Detection in Rotating Machinery Diagnostics","authors":"Kwangsuk Lee, Jae-Kyeong Kim, Jaehyong Kim, K. Hur, Hagbae Kim","doi":"10.1109/ICKII.2018.8569065","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569065","url":null,"abstract":"This paper proposes a multi-layered anomaly detection scheme to train feature extraction and to test anomaly prediction by using Convolutional Neural Networks (CNNs) layer, Bidirectional and Unidirectional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs), which is one of a novel deep architecture named stacked convolutional bidirectional LSTM network (SCB-LSTM). In the proposed model, the stacked CNNs perform feature extraction of vibration sensor signal patterns, and the result is used to feature learning with the stacked bidirectional LSTMs (SB-LSTMs). After this procedure, the stacked unidirectional LSTMs (SU-LSTMs) enhance the feature learning, and a regression layer finally predicts anomaly detections. The experimental results of bearing data not only show the accuracy of the proposed model in anomaly detection for rotating machinery diagnostics, but also suggest the better performance than other state-of-the-art algorithms such as a plain uni-LSTM or Bi-LSTM.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124024364","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569207
Jing Su, Yi-Chi Huang, Jia-Li Yin, Bo-Hao Chen, Shenming Qu
With the growing concern for power-hungry on mobile devices, many power constrained contrast enhancement algorithms have been developed in the mobile devices embedded with emissive displays, such as organic light-emitting diodes. However, conventional power constrained contrast enhancement algorithms inevitably degrade the visual aesthetics of images as a trade-off to gain the power-saving for mobile devices. This paper proposes a trainable power-constrained contrast enhancement algorithm based on a saliency-guided deep framework for suppressing the power consumption of an image while preserving its perceptual quality. Our algorithm relies on the fact that imaging features of a displayed image is salient to human visual perception. Hence, we decompose the input image into the imaging features and textual features with a deep convolutional neural networks, and degrade those textual features to achieve the suppression of power consumption. Experimental results demonstrate that our algorithm is able to maintain visual aesthetics of images while reducing the power consumption effectively, outperforming conventional power-constrained contrast enhancement algorithms.
{"title":"Saliency-Guided Deep Framework for Power Consumption Suppressing on Mobile Devices","authors":"Jing Su, Yi-Chi Huang, Jia-Li Yin, Bo-Hao Chen, Shenming Qu","doi":"10.1109/ICKII.2018.8569207","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569207","url":null,"abstract":"With the growing concern for power-hungry on mobile devices, many power constrained contrast enhancement algorithms have been developed in the mobile devices embedded with emissive displays, such as organic light-emitting diodes. However, conventional power constrained contrast enhancement algorithms inevitably degrade the visual aesthetics of images as a trade-off to gain the power-saving for mobile devices. This paper proposes a trainable power-constrained contrast enhancement algorithm based on a saliency-guided deep framework for suppressing the power consumption of an image while preserving its perceptual quality. Our algorithm relies on the fact that imaging features of a displayed image is salient to human visual perception. Hence, we decompose the input image into the imaging features and textual features with a deep convolutional neural networks, and degrade those textual features to achieve the suppression of power consumption. Experimental results demonstrate that our algorithm is able to maintain visual aesthetics of images while reducing the power consumption effectively, outperforming conventional power-constrained contrast enhancement algorithms.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124360032","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569046
Chiu Kuo-Chun
”Contemporary art” refers to art belonging in this era and is a product of western art ideology transformation. Although “Taiwanese contemporary art” does not directly derive from western art, its development has long been under its influence; thus could be interpreted as “Taiwanese Art under the influence of western contemporary art”. The concept of western contemporary art is to transcend past the history and core value that the West has previously been built upon and instead focus on bordering and diverse self-expression [1]. For this reason, when we examine Taiwan’s contemporary art, we should start with the discovery of our inner selves. The past of Taiwan’s photography has seen the correspondence of different stages to that of western photography but under the influence of foreign photographic trends, photographers from different eras are experimenting with different images or to express their individuality; or using photography as foreign methods to incorporate and transfer unique images. This has allowed us to acknowledge the existence of “Taiwan’s contemporary photography”. Through the analysis of content and form as well as in-depth interview of the artists, this study examines how representative works of different eras are affected by foreign or local aesthetics in protruding the existing limits of photography. Finally, the study seeks to unveil the traits of Taiwan’s contemporary photography development. Many photographers choose to continue creating works even under the influences of the new era and despite having experienced different phases. In turn, these photographers use their new creations or ideas to influence the new era. This study does not use historic time as benchmark and instead uses the correspondence and connection of a work of art. As contemporary art critic Arthur C. Danto suggested, rather than historical conclusions and narrations, developing a new form of historic interpretation might be more suitable for contemporary art.
“当代艺术”是指属于这个时代的艺术，是西方艺术意识形态转型的产物。“台湾当代艺术”虽不直接源自西方艺术，但其发展却长期受到西方艺术的影响;可以理解为“受西方当代艺术影响的台湾艺术”。西方当代艺术的概念是超越过去西方所赖以建立的历史和核心价值，而是关注边缘和多样化的自我表达[1]。因此，审视台湾当代艺术，应该从发现内在的自我开始。台湾摄影的历史经历了不同阶段与西方摄影的对应，但在国外摄影潮流的影响下，不同时代的摄影师都在尝试不同的影像或表达自己的个性;或采用摄影作为外来的方法，将独特的图像融合和传递。这让我们承认了“台湾当代摄影”的存在。本研究通过对内容和形式的分析，以及对艺术家的深度访谈，探讨不同时代的代表性作品如何受到外来或本土美学的影响，从而突破摄影的现有局限。最后，本研究试图揭示台湾当代摄影发展的特质。许多摄影师即使在新时代的影响下，即使经历了不同的阶段，也会选择继续创作。反过来，这些摄影师用他们的新创作或想法来影响新时代。本研究不以历史时间为基准，而是以艺术作品的对应和联系为基准。正如当代艺术评论家Arthur C. Danto所说，比起历史的结论和叙述，发展一种新的历史解释形式可能更适合当代艺术。
{"title":"An Examination of Taiwan’s Contemporary Photography Development Traits","authors":"Chiu Kuo-Chun","doi":"10.1109/ICKII.2018.8569046","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569046","url":null,"abstract":"”Contemporary art” refers to art belonging in this era and is a product of western art ideology transformation. Although “Taiwanese contemporary art” does not directly derive from western art, its development has long been under its influence; thus could be interpreted as “Taiwanese Art under the influence of western contemporary art”. The concept of western contemporary art is to transcend past the history and core value that the West has previously been built upon and instead focus on bordering and diverse self-expression [1]. For this reason, when we examine Taiwan’s contemporary art, we should start with the discovery of our inner selves. The past of Taiwan’s photography has seen the correspondence of different stages to that of western photography but under the influence of foreign photographic trends, photographers from different eras are experimenting with different images or to express their individuality; or using photography as foreign methods to incorporate and transfer unique images. This has allowed us to acknowledge the existence of “Taiwan’s contemporary photography”. Through the analysis of content and form as well as in-depth interview of the artists, this study examines how representative works of different eras are affected by foreign or local aesthetics in protruding the existing limits of photography. Finally, the study seeks to unveil the traits of Taiwan’s contemporary photography development. Many photographers choose to continue creating works even under the influences of the new era and despite having experienced different phases. In turn, these photographers use their new creations or ideas to influence the new era. This study does not use historic time as benchmark and instead uses the correspondence and connection of a work of art. As contemporary art critic Arthur C. Danto suggested, rather than historical conclusions and narrations, developing a new form of historic interpretation might be more suitable for contemporary art.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128825738","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569202
Syu-Hong Huang, T. Chang
Nowadays, ontologies become more and more important as a tool to organize and structure information, and they are considered powerful strategies for designing more easy and precise to use information searching. Ontology visualizations can help in this regard by supporting in the exploration and verification of ontologies.[1] In this research, we decide to build the ontology of WOCAD publications-authors relational database, and further visualize it with VOWL. We build a web system that users can choose which classes of the WOCAD ontology they want to focus on. Graph visualizations are useful only up to a specific graph size, at which point the overview is lost and the graph is difficult to use.[2] With this system, members of CAADRIA who is less familiar with ontologies can understand the WOCAD ontology context quickly. It helps WOCAD ontology user takes less time to learn the knowledge about ontology theory.
{"title":"Discovering Co-Author Relationship In Wocad Data Using Ontology Visualization","authors":"Syu-Hong Huang, T. Chang","doi":"10.1109/ICKII.2018.8569202","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569202","url":null,"abstract":"Nowadays, ontologies become more and more important as a tool to organize and structure information, and they are considered powerful strategies for designing more easy and precise to use information searching. Ontology visualizations can help in this regard by supporting in the exploration and verification of ontologies.[1] In this research, we decide to build the ontology of WOCAD publications-authors relational database, and further visualize it with VOWL. We build a web system that users can choose which classes of the WOCAD ontology they want to focus on. Graph visualizations are useful only up to a specific graph size, at which point the overview is lost and the graph is difficult to use.[2] With this system, members of CAADRIA who is less familiar with ontologies can understand the WOCAD ontology context quickly. It helps WOCAD ontology user takes less time to learn the knowledge about ontology theory.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129047767","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569098
Yi-Chieh Chen, Chao-Ming Wang
Herbal tea is treated as a health tea in the West and professional tea farmers make up many types of herbal tea. ‘Tastee’ interactive device is a function that provides people with understanding their health. This new system is constructed by a Arduino chip with RFID chip to form the interactive design experience. Through this new design apply to a different herbal tea, and a different curative effect for experiencing the fun of mixing teas.
{"title":"The Research of Applying Interactive Design to A New Experience of Tea Culture","authors":"Yi-Chieh Chen, Chao-Ming Wang","doi":"10.1109/ICKII.2018.8569098","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569098","url":null,"abstract":"Herbal tea is treated as a health tea in the West and professional tea farmers make up many types of herbal tea. ‘Tastee’ interactive device is a function that provides people with understanding their health. This new system is constructed by a Arduino chip with RFID chip to form the interactive design experience. Through this new design apply to a different herbal tea, and a different curative effect for experiencing the fun of mixing teas.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"210 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117104693","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}
From the observation in 2014, cancer was the number one cause of deaths in Thailand and has been continuously increased until present. Cholangiocarcinoma is the subset of liver cancer, which is one of the top five cancers founded in Thailand. To reduce the risk of cholangiocarcinoma in patients, we need to find the factors of causing cancer and predict the probability of cancer earlier. However, the probability of cholangiocarcinoma is less than 1%. This causes imbalance classification problem in machine learning. In this paper, we propose an adaptive cancer prognosis framework for cholangiocarcinoma based on machine learning techniques, namely “CanWiser”. CanWiser is used to automatically learn the patient dataset (e.g., demographics and laboratory test results), pre-process data, oversample data to solve the imbalance problem using SMOTE, generate the prediction models using classification of machine learning techniques (i.e., support vector machine, decision tree, naïve Bayes, and random forest), and predict the probability of cholangiocarcinoma. The proposed framework can generate the prediction model providing the sensitivity 75%, specificity 83.41%, and accuracy 83.34%. CanWiser also provides the personalized recommendation for patients to reduce the risk of cholangiocarcinoma. Moreover, our proposed framework can adaptively learn and generate the models, which can fit for the new dataset.
{"title":"An Adaptive Cancer Prognosis Framework for Cholangiocarcinoma based on Machine Learning Techniques","authors":"Supanuth Ongsuk, Sakan Komolvatin, Intouch Kunakorntum, P. Phunchongharn, Sumet Amonyingchareon, Woranich Hinthong","doi":"10.1109/ICKII.2018.8569049","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569049","url":null,"abstract":"From the observation in 2014, cancer was the number one cause of deaths in Thailand and has been continuously increased until present. Cholangiocarcinoma is the subset of liver cancer, which is one of the top five cancers founded in Thailand. To reduce the risk of cholangiocarcinoma in patients, we need to find the factors of causing cancer and predict the probability of cancer earlier. However, the probability of cholangiocarcinoma is less than 1%. This causes imbalance classification problem in machine learning. In this paper, we propose an adaptive cancer prognosis framework for cholangiocarcinoma based on machine learning techniques, namely “CanWiser”. CanWiser is used to automatically learn the patient dataset (e.g., demographics and laboratory test results), pre-process data, oversample data to solve the imbalance problem using SMOTE, generate the prediction models using classification of machine learning techniques (i.e., support vector machine, decision tree, naïve Bayes, and random forest), and predict the probability of cholangiocarcinoma. The proposed framework can generate the prediction model providing the sensitivity 75%, specificity 83.41%, and accuracy 83.34%. CanWiser also provides the personalized recommendation for patients to reduce the risk of cholangiocarcinoma. Moreover, our proposed framework can adaptively learn and generate the models, which can fit for the new dataset.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115456275","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569082
Yueting Xiang, H. Hsieh
In recent years, the aging population has become a serious global concern in various fields. For the elderly, the television media is still a mainstream media presence in their vision and shoulders the irreplaceable function and responsibility. For TV industry, the new media has caused a massive loss of young and middle-aged audience, but elderly audiences continue to grow. At this point, it would be a good choice if the TV station were able to attract elderly audiences, whether from a service or a business perspective.This study takes the Uses and Gratifications theory as the theoretical framework, uses content analysis method to summarize the present situation of the elderly TV programs in mainland China, and uses questionnaire method to conduct the viewing behavior, viewing demand and satisfaction degree of elderly audiences.
{"title":"A study on the present-situation analysis and feasible path of the elderly TV programs in mainland China","authors":"Yueting Xiang, H. Hsieh","doi":"10.1109/ICKII.2018.8569082","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569082","url":null,"abstract":"In recent years, the aging population has become a serious global concern in various fields. For the elderly, the television media is still a mainstream media presence in their vision and shoulders the irreplaceable function and responsibility. For TV industry, the new media has caused a massive loss of young and middle-aged audience, but elderly audiences continue to grow. At this point, it would be a good choice if the TV station were able to attract elderly audiences, whether from a service or a business perspective.This study takes the Uses and Gratifications theory as the theoretical framework, uses content analysis method to summarize the present situation of the elderly TV programs in mainland China, and uses questionnaire method to conduct the viewing behavior, viewing demand and satisfaction degree of elderly audiences.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114774719","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 : 2018-07-01DOI: 10.1109/ICKII.2018.8569176
Xin Luo, Jia Wang, Huijie Zhang, Xiao Wang
Estimating the intrinsic dimensionality of hyper spectral remote sensing imagery is an essential step in processing this kind of data. A novel estimation algorithm is proposed, which can preserve both abundant and rare features in original data. First of all, the QR decomposition of an original data matrix is carried out in order to decrease computational complexity, and a sliding noise detection window is applied to noise reduction for improving the accuracy of dimensionality estimation. Furthermore, a manifold learning method is used to determine a limit of intrinsic dimensionality and finally, intrinsic dimensionality is estimated through the singular value decomposition and $l_{2,infty }$-norm theory. The experimental results of simulated and real data are presented, which shown our proposed algorithm outperforms some classical algorithms.
{"title":"Estimating the Intrinsic Dimensionality of Hyperspectral Remote Sensing Imagery with Rare Features","authors":"Xin Luo, Jia Wang, Huijie Zhang, Xiao Wang","doi":"10.1109/ICKII.2018.8569176","DOIUrl":"https://doi.org/10.1109/ICKII.2018.8569176","url":null,"abstract":"Estimating the intrinsic dimensionality of hyper spectral remote sensing imagery is an essential step in processing this kind of data. A novel estimation algorithm is proposed, which can preserve both abundant and rare features in original data. First of all, the QR decomposition of an original data matrix is carried out in order to decrease computational complexity, and a sliding noise detection window is applied to noise reduction for improving the accuracy of dimensionality estimation. Furthermore, a manifold learning method is used to determine a limit of intrinsic dimensionality and finally, intrinsic dimensionality is estimated through the singular value decomposition and $l_{2,infty }$-norm theory. The experimental results of simulated and real data are presented, which shown our proposed algorithm outperforms some classical algorithms.","PeriodicalId":170587,"journal":{"name":"2018 1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124741353","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：