Pub Date : 2018-09-01DOI: 10.1109/ICFSP.2018.8552048
K. Abe, Kota Shirakawa, Masahide Minami, Daiki Miura
This paper presents image features for evaluating progression of gastric atrophy from gastric X-ray images. In the proposed method, after the target area for the diagnosis is determined and the gastric folds are extracted, the features are extracted from the area based on the diagnostic index for reading the atrophy from the X-ray images. Concretely, the features measure quantity of the folds and parallelism of the folds. In experiments for examining performance of the proposed features, classifications of normal, moderate, and severe cases were conducted to 117 gastric X-ray images by regarding the features as variables of discriminant machines, and experimental results have shown that the proposed features are effective well to measure the progression.
{"title":"Features for Evaluating Gastric Atrophy Using X-ray Images","authors":"K. Abe, Kota Shirakawa, Masahide Minami, Daiki Miura","doi":"10.1109/ICFSP.2018.8552048","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552048","url":null,"abstract":"This paper presents image features for evaluating progression of gastric atrophy from gastric X-ray images. In the proposed method, after the target area for the diagnosis is determined and the gastric folds are extracted, the features are extracted from the area based on the diagnostic index for reading the atrophy from the X-ray images. Concretely, the features measure quantity of the folds and parallelism of the folds. In experiments for examining performance of the proposed features, classifications of normal, moderate, and severe cases were conducted to 117 gastric X-ray images by regarding the features as variables of discriminant machines, and experimental results have shown that the proposed features are effective well to measure the progression.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127934317","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552045
Yu-Shan Deng, An-Chun Luo, M. Dai
In the PCB industry, automatic optical inspection (AOI) system takes an important role to increase yield rate. However, the false alarm rate of AOI equipment is high. Therefore, the high cost of human visual inspection at verify and repair system (VRS) station is becoming a problem. Therefore, we propose an automatic defect verification system, called Auto-VRS, to decrease the false alarm rate and reduce operator's workload. The proposed system is composed of two subsystems, referred to fast circuit comparison and deep neural network based defect classification. The fast circuit comparison is to find the accurate defect region of interest (ROI). The deep neural network based defect classification is to verify which is real defect or pseudo defect. The experiment results showed that the Auto-VRS can recognition defects well and has the significant reduction in both false alarm rate and escape rate. With the advantage of the Auto-VRS, it can further improve the VRS operator's efficiency and accuracy in the future.
{"title":"Building an Automatic Defect Verification System Using Deep Neural Network for PCB Defect Classification","authors":"Yu-Shan Deng, An-Chun Luo, M. Dai","doi":"10.1109/ICFSP.2018.8552045","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552045","url":null,"abstract":"In the PCB industry, automatic optical inspection (AOI) system takes an important role to increase yield rate. However, the false alarm rate of AOI equipment is high. Therefore, the high cost of human visual inspection at verify and repair system (VRS) station is becoming a problem. Therefore, we propose an automatic defect verification system, called Auto-VRS, to decrease the false alarm rate and reduce operator's workload. The proposed system is composed of two subsystems, referred to fast circuit comparison and deep neural network based defect classification. The fast circuit comparison is to find the accurate defect region of interest (ROI). The deep neural network based defect classification is to verify which is real defect or pseudo defect. The experiment results showed that the Auto-VRS can recognition defects well and has the significant reduction in both false alarm rate and escape rate. With the advantage of the Auto-VRS, it can further improve the VRS operator's efficiency and accuracy in the future.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133318697","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552075
Mengying Wang, Lele Xu, Lili Guo
System logs record the execution trajectory of the system and exist in all components of the system. Nowadays, the systems are deployed in a distributed environment and they generate logs which contain complex format and rich semantic information. Simple statistical analysis methods cannot fully capture log information for effective abnormal detection of software systems. In this paper, we propose to analyze the logs by combining feature extraction methods from natural language processing and anomaly detection methods from deep learning. Two feature extraction algorithms, Word2vec and Term Frequency-Inverse Document Frequency (TF-IDF), are respectively adopted and compared here to obtain the log information, and then one deep learning method named Long Short-Term Memory (LSTM) is applied for the anomaly detection. To validate the effectiveness of the proposed method, we compare LSTM with other machine learning algorithms, including Gradient Boosting Decision Tree (GBDT) and Naïve Bayes, the results show that LSTM can perform the best for anomaly detection of system logs with both of the two feature extraction methods, indicating that LSTM can capture contextual semantic information effectively in log anomaly detection and will be a promising tool for log analysis.
系统日志记录了系统的执行轨迹，存在于系统的所有组件中。目前，系统部署在分布式环境中，产生的日志格式复杂，语义信息丰富。简单的统计分析方法无法充分捕获日志信息，无法有效地对软件系统进行异常检测。在本文中，我们提出将自然语言处理中的特征提取方法和深度学习中的异常检测方法相结合来分析日志。本文分别采用Word2vec和Term Frequency- inverse Document Frequency (TF-IDF)两种特征提取算法进行对比，获取日志信息，然后采用长短期记忆(LSTM)深度学习方法进行异常检测。为了验证该方法的有效性，我们将LSTM与其他机器学习算法(包括梯度增强决策树(GBDT)和Naïve贝叶斯)进行了比较，结果表明LSTM在两种特征提取方法下都能很好地进行系统日志异常检测，这表明LSTM在日志异常检测中可以有效地捕获上下文语义信息，将是一种很有前途的日志分析工具。
{"title":"Anomaly Detection of System Logs Based on Natural Language Processing and Deep Learning","authors":"Mengying Wang, Lele Xu, Lili Guo","doi":"10.1109/ICFSP.2018.8552075","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552075","url":null,"abstract":"System logs record the execution trajectory of the system and exist in all components of the system. Nowadays, the systems are deployed in a distributed environment and they generate logs which contain complex format and rich semantic information. Simple statistical analysis methods cannot fully capture log information for effective abnormal detection of software systems. In this paper, we propose to analyze the logs by combining feature extraction methods from natural language processing and anomaly detection methods from deep learning. Two feature extraction algorithms, Word2vec and Term Frequency-Inverse Document Frequency (TF-IDF), are respectively adopted and compared here to obtain the log information, and then one deep learning method named Long Short-Term Memory (LSTM) is applied for the anomaly detection. To validate the effectiveness of the proposed method, we compare LSTM with other machine learning algorithms, including Gradient Boosting Decision Tree (GBDT) and Naïve Bayes, the results show that LSTM can perform the best for anomaly detection of system logs with both of the two feature extraction methods, indicating that LSTM can capture contextual semantic information effectively in log anomaly detection and will be a promising tool for log analysis.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"72 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123132915","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 : 2018-09-01DOI: 10.1109/icfsp.2018.8552071
{"title":"ICFSP 2018 Title Page","authors":"","doi":"10.1109/icfsp.2018.8552071","DOIUrl":"https://doi.org/10.1109/icfsp.2018.8552071","url":null,"abstract":"","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130880055","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 : 2018-09-01DOI: 10.1109/icfsp.2018.8552040
{"title":"ICFSP 2018 Cover Page","authors":"","doi":"10.1109/icfsp.2018.8552040","DOIUrl":"https://doi.org/10.1109/icfsp.2018.8552040","url":null,"abstract":"","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133231685","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552072
N. R. Poespawati, A. Bastian, Elang Aji Defrianto, Michael Hariadi, T. Abuzairi, R. W. Purnamaningsih
Nowadays solar cells are mainly produced using silicon as their active layer but silicon solar cells have reached their maximum efficiency potential. Perovskite solar cells (PSC) are a potential candidate to replace silicon solar cells because of their high efficiency prospective and easy to fabricate over silicon solar cells. Therefore, many researchers have examined PSCs to obtain the most optimal PSC performance. Solar cells use solar radiation as their source to produce electricity that we know as photovoltaic effects. In this research we had fabricated the PSC only by using low-cost fabrication methods, namely the spin coating deposition method and under ambient condition. From the fabrication results, the PSC can produce an open circuit voltage of 0.6 V, a short circuit current of 13 mA, and 0.28 Fill Factor.
{"title":"Low Cost Perovskite Solar Cell Performance under Ambient Condition","authors":"N. R. Poespawati, A. Bastian, Elang Aji Defrianto, Michael Hariadi, T. Abuzairi, R. W. Purnamaningsih","doi":"10.1109/ICFSP.2018.8552072","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552072","url":null,"abstract":"Nowadays solar cells are mainly produced using silicon as their active layer but silicon solar cells have reached their maximum efficiency potential. Perovskite solar cells (PSC) are a potential candidate to replace silicon solar cells because of their high efficiency prospective and easy to fabricate over silicon solar cells. Therefore, many researchers have examined PSCs to obtain the most optimal PSC performance. Solar cells use solar radiation as their source to produce electricity that we know as photovoltaic effects. In this research we had fabricated the PSC only by using low-cost fabrication methods, namely the spin coating deposition method and under ambient condition. From the fabrication results, the PSC can produce an open circuit voltage of 0.6 V, a short circuit current of 13 mA, and 0.28 Fill Factor.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124735065","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552064
Thanet Markchom, R. Lipikorn
In observation of land information using satellite images, clouds are one of the most serious obstacles due to their opacity property which can block the visibility of ground objects and can also be blended with the underlying details. Hence, retrieval the actual information covered by clouds is frequently necessary. In this paper, we propose a novel method to remove clouds by taking an advantage of HSI color space instead of directly removing clouds in RGB color space. The proposed method uses a concept of dark channel prior method to estimate the cloud appearance called the scattering light and perform a subtraction in only the intensity channel to avoid an effect to the original color and also enhance the intensity with gamma correction to recover some information accidentally removed from the previous step and restore obscure details distorted by clouds. Furthermore, since clouds involve in both intensity and saturation channel, we increase the saturation that was reduced as a result from clouds by using logarithm image transformation as well. From the results, the proposed method can remove clouds that are not extremely opaque and preserve the actual information such as color and texture due to the higher contrast gain in the experiments comparing to the results obtained from other single-image methods.
{"title":"Thin Cloud Removal Using Local Minimization and Logarithm Image Transformation in HSI Color Space","authors":"Thanet Markchom, R. Lipikorn","doi":"10.1109/ICFSP.2018.8552064","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552064","url":null,"abstract":"In observation of land information using satellite images, clouds are one of the most serious obstacles due to their opacity property which can block the visibility of ground objects and can also be blended with the underlying details. Hence, retrieval the actual information covered by clouds is frequently necessary. In this paper, we propose a novel method to remove clouds by taking an advantage of HSI color space instead of directly removing clouds in RGB color space. The proposed method uses a concept of dark channel prior method to estimate the cloud appearance called the scattering light and perform a subtraction in only the intensity channel to avoid an effect to the original color and also enhance the intensity with gamma correction to recover some information accidentally removed from the previous step and restore obscure details distorted by clouds. Furthermore, since clouds involve in both intensity and saturation channel, we increase the saturation that was reduced as a result from clouds by using logarithm image transformation as well. From the results, the proposed method can remove clouds that are not extremely opaque and preserve the actual information such as color and texture due to the higher contrast gain in the experiments comparing to the results obtained from other single-image methods.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124176759","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552079
K. Abe, Masaru Tanaka, H. Habe, Y. Taniguchi, N. Iguchi
As a method for supporting aquaculture for bluefin tuna, this paper presents a video scene detection when a burst swimming is provoked by fry of farmed-raised bluefin tuna in land-based tanks due to environmental stimuli. From the fact the fry often die crashing to the tank’s wall and between the fry because of the burst swimming, this automated monitoring could use for analyzing environmental stimuli around the tanks when the burst swimming occurs and result in decrease of the death number of the fry. In the proposed method, the fry which swim in a land-based tank are monitored by a video camera and the video scenes at the burst swimming are detected by discriminant analysis with a feature value which represents fry’s acceleration using sequential frames of the moving image. Preparing the moving images which include scenes of the burst swimming by the fry, performances of the proposed method were examined. From experimental results, recall ratio of the scene detection has shown more than 57% in linear discriminant analysis and more than 98% in discriminant analysis by Mahalanobis distance.
{"title":"Video Scene Detection of Burst Swimming by Fry of Farmed-raised Bluefin Tuna","authors":"K. Abe, Masaru Tanaka, H. Habe, Y. Taniguchi, N. Iguchi","doi":"10.1109/ICFSP.2018.8552079","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552079","url":null,"abstract":"As a method for supporting aquaculture for bluefin tuna, this paper presents a video scene detection when a burst swimming is provoked by fry of farmed-raised bluefin tuna in land-based tanks due to environmental stimuli. From the fact the fry often die crashing to the tank’s wall and between the fry because of the burst swimming, this automated monitoring could use for analyzing environmental stimuli around the tanks when the burst swimming occurs and result in decrease of the death number of the fry. In the proposed method, the fry which swim in a land-based tank are monitored by a video camera and the video scenes at the burst swimming are detected by discriminant analysis with a feature value which represents fry’s acceleration using sequential frames of the moving image. Preparing the moving images which include scenes of the burst swimming by the fry, performances of the proposed method were examined. From experimental results, recall ratio of the scene detection has shown more than 57% in linear discriminant analysis and more than 98% in discriminant analysis by Mahalanobis distance.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130433115","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552056
Y. Matsuo, A. Ichigaya, Kikufumi Kanda
Inter-frame prediction in video coding can be difficult if an object is sharped or blurred between inter frames. We therefore propose a video coding method for inter-frame prediction using super-resolved and blurred decoded pictures. In the joint exploration model (JEM) of random-access mode, inter-frame prediction is performed by using previously decoded pictures. In the proposed method, super-resolved and blurred pictures of the previously decoded pictures are generated before the inter-frame prediction. The inter-frame prediction is performed by using a three-type picture, which consist of a previously decoded picture and its super-resolved and blurred pictures. A previously decoded picture with the lowest rate distortion (RD) cost is selected from these three- type pictures. In the experiment, the proposed method is implemented in the JEM 7.0. The experimental results show that the proposed method produces higher video quality than the conventional JEM 7.0 coder.
{"title":"Super-Resolved and Blurred Decoded Pictures for Improving Coding Efficiency in Inter-Frame Prediction","authors":"Y. Matsuo, A. Ichigaya, Kikufumi Kanda","doi":"10.1109/ICFSP.2018.8552056","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552056","url":null,"abstract":"Inter-frame prediction in video coding can be difficult if an object is sharped or blurred between inter frames. We therefore propose a video coding method for inter-frame prediction using super-resolved and blurred decoded pictures. In the joint exploration model (JEM) of random-access mode, inter-frame prediction is performed by using previously decoded pictures. In the proposed method, super-resolved and blurred pictures of the previously decoded pictures are generated before the inter-frame prediction. The inter-frame prediction is performed by using a three-type picture, which consist of a previously decoded picture and its super-resolved and blurred pictures. A previously decoded picture with the lowest rate distortion (RD) cost is selected from these three- type pictures. In the experiment, the proposed method is implemented in the JEM 7.0. The experimental results show that the proposed method produces higher video quality than the conventional JEM 7.0 coder.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129436851","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 : 2018-09-01DOI: 10.1109/ICFSP.2018.8552061
S. Mantsevich, V. Balakshy
The optoelectronic system combining collinear acousto-optic filter and positive electronic feedback is examined both experimentally and theoretically. The feedback signal is formed at the acousto-optic filter output using the part of optical beam intensity. The feedback introduction may increase the acousto-optic diffraction efficiency and narrow the system passband. It is shown that controlling the feedback electronic parameters it is possible to adjust the collinear filter transmission function shape.
{"title":"The Peculiarities of Collinear Acousto-optic Filtration in the Presence of Optoelectronic Feedback","authors":"S. Mantsevich, V. Balakshy","doi":"10.1109/ICFSP.2018.8552061","DOIUrl":"https://doi.org/10.1109/ICFSP.2018.8552061","url":null,"abstract":"The optoelectronic system combining collinear acousto-optic filter and positive electronic feedback is examined both experimentally and theoretically. The feedback signal is formed at the acousto-optic filter output using the part of optical beam intensity. The feedback introduction may increase the acousto-optic diffraction efficiency and narrow the system passband. It is shown that controlling the feedback electronic parameters it is possible to adjust the collinear filter transmission function shape.","PeriodicalId":355222,"journal":{"name":"2018 4th International Conference on Frontiers of Signal Processing (ICFSP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128720911","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：