Pub Date : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279736
A. Sorokin, E. Zhvansky, K. Bocharov, I. Popov, Dmitry Zubtsov, A. Vorobiev, E. Nikolaev, V. Shurkhay, A. Potapov
The mass-spectrometry is the promising tool for the fast characterization of brain biopsy samples as a part of the intraoperative identification of tumor boundary. The spray-from-tissue ambient ionization method is a new instrument for mass-spectrometry analysis of soft tissues without sample preparation. In this contribution, we analyze the performance of multi-label classification techniques in detection of the tumor and necrosis fragments within the sample.
{"title":"Multi-label classification of brain tumor mass spectrometry data In pursuit of tumor boundary detection method","authors":"A. Sorokin, E. Zhvansky, K. Bocharov, I. Popov, Dmitry Zubtsov, A. Vorobiev, E. Nikolaev, V. Shurkhay, A. Potapov","doi":"10.1109/ICIIBMS.2017.8279736","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279736","url":null,"abstract":"The mass-spectrometry is the promising tool for the fast characterization of brain biopsy samples as a part of the intraoperative identification of tumor boundary. The spray-from-tissue ambient ionization method is a new instrument for mass-spectrometry analysis of soft tissues without sample preparation. In this contribution, we analyze the performance of multi-label classification techniques in detection of the tumor and necrosis fragments within the sample.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129816242","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279739
W. Kimpan, Pongpicha Sirivimonsattaya
This article proposes a novel of mobile application to help ophthalmologists diagnose the Ptosis disease. This application applied digital image processing techniques to identify eye parameters: Marginal Reflex Distance-1, Marginal Reflex Distance-2, and L/M Ratio which doctors can use to diagnose patients besides using naked eyes. The application was built for iOS platform in the first version. The inputs of the application are the images of patient's eyes from a mobile device camera or from a mobile device memory. After using digital image processing techniques, at the end of the process, the eye parameters will be displayed on the mobile device screen for the doctors to be used. The experimental results indicated that the proposed mobile application can perform with 86.36% of accuracy in measuring Marginal Reflex Distance-1 value while it can measure Marginal Reflex Distance-2 value with 63.64% of accuracy.
{"title":"Using mobile application as an instrument for ptosis diagnosis","authors":"W. Kimpan, Pongpicha Sirivimonsattaya","doi":"10.1109/ICIIBMS.2017.8279739","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279739","url":null,"abstract":"This article proposes a novel of mobile application to help ophthalmologists diagnose the Ptosis disease. This application applied digital image processing techniques to identify eye parameters: Marginal Reflex Distance-1, Marginal Reflex Distance-2, and L/M Ratio which doctors can use to diagnose patients besides using naked eyes. The application was built for iOS platform in the first version. The inputs of the application are the images of patient's eyes from a mobile device camera or from a mobile device memory. After using digital image processing techniques, at the end of the process, the eye parameters will be displayed on the mobile device screen for the doctors to be used. The experimental results indicated that the proposed mobile application can perform with 86.36% of accuracy in measuring Marginal Reflex Distance-1 value while it can measure Marginal Reflex Distance-2 value with 63.64% of accuracy.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"55 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128953646","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279762
Suriyon Tansuriyong, Motoki Kyan, Kaito Numata, Shuuya Taira, T. Anezaki
In recent years, Drone's research has become popular, and there is a need to automate the cycle of takeoff, flight, landing, and charging of Drone. Mainly, the problem remains in automatic battery charging. Therefore, in this research, we will realize Drone's charging station using RTK-GPS with high accuracy. We verified the landing accuracy by experiment. From the results of the verification, it was found that relative positional error between drone and the charging station can be eliminated by referring to the same reference position. Thus, the possibility of navigating Drone to the charging station can be easily implemented.
{"title":"Verification experiment for drone charging station using RTK-GPS","authors":"Suriyon Tansuriyong, Motoki Kyan, Kaito Numata, Shuuya Taira, T. Anezaki","doi":"10.1109/ICIIBMS.2017.8279762","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279762","url":null,"abstract":"In recent years, Drone's research has become popular, and there is a need to automate the cycle of takeoff, flight, landing, and charging of Drone. Mainly, the problem remains in automatic battery charging. Therefore, in this research, we will realize Drone's charging station using RTK-GPS with high accuracy. We verified the landing accuracy by experiment. From the results of the verification, it was found that relative positional error between drone and the charging station can be eliminated by referring to the same reference position. Thus, the possibility of navigating Drone to the charging station can be easily implemented.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"1993 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130995127","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279758
Chun-Yu Lin, Yan-Lian Chiu
A high-voltage / high-power driving circuit for the applicatrions such as a motor controller in robot is presented in this work. The driving circuit is further equipped with a novel electrostatic discharge (ESD) protection design to enhance its reliability. A 3×VDD-tolerant driving circuit with on-chip ESD protection is demonstrated using a 0.18 μm CMOS process with Vdd of 3.3V. The ESD robustness can be improved without the use of any additional ESD protection device or layout area. Furthermore, this design technique can be used for an n∗Vdd-tolerant driving circuit with improved ESD robustness.
{"title":"High-voltage driving circuit with on-chip ESD protection in CMOS technology","authors":"Chun-Yu Lin, Yan-Lian Chiu","doi":"10.1109/ICIIBMS.2017.8279758","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279758","url":null,"abstract":"A high-voltage / high-power driving circuit for the applicatrions such as a motor controller in robot is presented in this work. The driving circuit is further equipped with a novel electrostatic discharge (ESD) protection design to enhance its reliability. A 3×VDD-tolerant driving circuit with on-chip ESD protection is demonstrated using a 0.18 μm CMOS process with Vdd of 3.3V. The ESD robustness can be improved without the use of any additional ESD protection device or layout area. Furthermore, this design technique can be used for an n∗Vdd-tolerant driving circuit with improved ESD robustness.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115179667","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279743
N. T. T. Suzuki, A. Suda, H. Onishi, T. Muromaki, T. Watanabe
Assist chairs with simple mechanism to flip up a seat at the front edge to assist sit-to-stand (STS) is well known as commercial products developed from around 1980. The speed of flipping up the seat on the assist chairs would play a key role how to adjust assisting STS in individual cases, but there is almost no discussion how the speed of flipping up the seat affects the benefit of assisting STS. The aim of study is to investigate the optimised speed of flipping up the seat of the assist chairs. As a first step, a motorised assist chair with controllable speed of flipping up the seat was developed and tested with four healthy participants in three seat height conditions; High:520mm, Middle:420mm, and Low:320mm without and with flipping up the seat at maximum speed 30degree/second. Significant main effect of assisting was found on peak vGRF at Low seat height (p<0.005) by Wilcoxon rank test. There was no significant effect at Middle (p=0.126) and High seat height (p=0.507). With assisting at the Low seat height, the reduction of peak vGRF means that the flipping up the seat successfully supports trunk movement and knee function to lift up the hip from the seat. All participants felt the assisting was effective to reduce the hardness of STS at the Low seat height. With further studies to optimise the speed of flipping the seat, the motorised assist chair in this study would provide a proper assist for individual STS movement, with leaving certain part of physical load for keeping muscle functioning.
{"title":"Experimental evaluation of an assist chair for sit-to-stand on speed of flipping up a seat of chair","authors":"N. T. T. Suzuki, A. Suda, H. Onishi, T. Muromaki, T. Watanabe","doi":"10.1109/ICIIBMS.2017.8279743","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279743","url":null,"abstract":"Assist chairs with simple mechanism to flip up a seat at the front edge to assist sit-to-stand (STS) is well known as commercial products developed from around 1980. The speed of flipping up the seat on the assist chairs would play a key role how to adjust assisting STS in individual cases, but there is almost no discussion how the speed of flipping up the seat affects the benefit of assisting STS. The aim of study is to investigate the optimised speed of flipping up the seat of the assist chairs. As a first step, a motorised assist chair with controllable speed of flipping up the seat was developed and tested with four healthy participants in three seat height conditions; High:520mm, Middle:420mm, and Low:320mm without and with flipping up the seat at maximum speed 30degree/second. Significant main effect of assisting was found on peak vGRF at Low seat height (p<0.005) by Wilcoxon rank test. There was no significant effect at Middle (p=0.126) and High seat height (p=0.507). With assisting at the Low seat height, the reduction of peak vGRF means that the flipping up the seat successfully supports trunk movement and knee function to lift up the hip from the seat. All participants felt the assisting was effective to reduce the hardness of STS at the Low seat height. With further studies to optimise the speed of flipping the seat, the motorised assist chair in this study would provide a proper assist for individual STS movement, with leaving certain part of physical load for keeping muscle functioning.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134332395","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279696
Masaru Yoshioka, N. Suganuma, Keisuke Yoneda, Mohammad Aldibaja
Object classification is an important issue in order to bring autonomous vehicle into reality. In this paper, real-time and robust classification based on Real AdaBoost algorithm is researched and improved. Various effective features of road objects are computed using LIDAR 3D point clouds. The improved classifier provides an accuracy of over 90 (%) in a range of 50 (m) and classifies objects into car, pedestrian, bicyclist and background. Moreover, processing time of classifying an object consumes only 0.07∗10−3 (sec) that enables this method to be used for autonomous driving on urban roads.
{"title":"Real-time object classification for autonomous vehicle using LIDAR","authors":"Masaru Yoshioka, N. Suganuma, Keisuke Yoneda, Mohammad Aldibaja","doi":"10.1109/ICIIBMS.2017.8279696","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279696","url":null,"abstract":"Object classification is an important issue in order to bring autonomous vehicle into reality. In this paper, real-time and robust classification based on Real AdaBoost algorithm is researched and improved. Various effective features of road objects are computed using LIDAR 3D point clouds. The improved classifier provides an accuracy of over 90 (%) in a range of 50 (m) and classifies objects into car, pedestrian, bicyclist and background. Moreover, processing time of classifying an object consumes only 0.07∗10−3 (sec) that enables this method to be used for autonomous driving on urban roads.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134461120","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279689
Ting-Wei Chang, Hung-Chih Chiang, Chir-Weei Chang, Chy-Lin Wang, Yuan-Chin Lee
A full-field optical coherence tomography with a swept source integrating a superluminescent diode and an acousto-optic tunable filter is designed, implemented, and tested. The center wavelength and the bandwidth of the swept source are 840nm and 50nm, respectively. There are estimated about 688 laser lines generated in a sweep cycle. For convenience, a Mirau objective lens is adopted to simplify the system structure. Some preliminary experiments were conducted by using the system, and an onion was adopted as the sample. Two clear restored 3D images of the onion were obtained by using two different algorithms. The differences between the two images were also compared with each other. Further improvement and experiments by using this system are still in progress.
{"title":"FF OCT with a swept source integrating a SLD and an AOTF","authors":"Ting-Wei Chang, Hung-Chih Chiang, Chir-Weei Chang, Chy-Lin Wang, Yuan-Chin Lee","doi":"10.1109/ICIIBMS.2017.8279689","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279689","url":null,"abstract":"A full-field optical coherence tomography with a swept source integrating a superluminescent diode and an acousto-optic tunable filter is designed, implemented, and tested. The center wavelength and the bandwidth of the swept source are 840nm and 50nm, respectively. There are estimated about 688 laser lines generated in a sweep cycle. For convenience, a Mirau objective lens is adopted to simplify the system structure. Some preliminary experiments were conducted by using the system, and an onion was adopted as the sample. Two clear restored 3D images of the onion were obtained by using two different algorithms. The differences between the two images were also compared with each other. Further improvement and experiments by using this system are still in progress.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114790947","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279699
V. Mikos, C. Heng, A. Tay, N. S. Chia, K. Koh, D. Tan, W. Au
Freezing of gait (FoG) is a common gait impairment in Parkinson's disease that puts patients at risk of falls and deteriorates their quality of life. Relief is sought after by evaluating the possibility of wearable systems that detect FoG in real-time and provide gait-reinforcing biofeedback cues. The successful detection relies on the extraction of high quality features, which have to be computed from recent samples of an inertial measurement unit in order to ensure real-time applicability. Unfortunately, the amount of samples considered for a feature's computation, i.e. the data window length, has been subjected to widespread disagreement: With no thorough analysis available, employed window lengths differed by several seconds among implementations. We derive optimal window lengths for a broad number of features used throughout literature by using mutual information as an evaluation metric, and elaborate on a window length's significance in affecting classification performance. With conventional feature selection methods, feature subsets tailored to various machine learning algorithms are established. Relying on these feature subsets for FoG classification, whereby all features are extracted with optimal window lengths, F1-scores increase up to 17.1% for individual classifiers and up to 12.7% on average when compared to previously proposed feature sets that are extracted with sub-optimal window lengths.
{"title":"Optimal window lengths, features and subsets thereof for freezing of gait classification","authors":"V. Mikos, C. Heng, A. Tay, N. S. Chia, K. Koh, D. Tan, W. Au","doi":"10.1109/ICIIBMS.2017.8279699","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279699","url":null,"abstract":"Freezing of gait (FoG) is a common gait impairment in Parkinson's disease that puts patients at risk of falls and deteriorates their quality of life. Relief is sought after by evaluating the possibility of wearable systems that detect FoG in real-time and provide gait-reinforcing biofeedback cues. The successful detection relies on the extraction of high quality features, which have to be computed from recent samples of an inertial measurement unit in order to ensure real-time applicability. Unfortunately, the amount of samples considered for a feature's computation, i.e. the data window length, has been subjected to widespread disagreement: With no thorough analysis available, employed window lengths differed by several seconds among implementations. We derive optimal window lengths for a broad number of features used throughout literature by using mutual information as an evaluation metric, and elaborate on a window length's significance in affecting classification performance. With conventional feature selection methods, feature subsets tailored to various machine learning algorithms are established. Relying on these feature subsets for FoG classification, whereby all features are extracted with optimal window lengths, F1-scores increase up to 17.1% for individual classifiers and up to 12.7% on average when compared to previously proposed feature sets that are extracted with sub-optimal window lengths.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114716633","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279750
Syna Sreng, Noppadol Maneerat, D. Isarakorn, K. Hamamoto, Ronakorn Panjaphongse
Diabetic retinopathy is one of the most frequent causes of blindness due to diabetes. Primary screening is essential due to prerequisite step toward the diagnosis of diabetic retinopathy in order to prevent vision loss or blindness. This paper presents the methods to discriminate between healthy images and diabetic retinopathy images on the retinal images. The proposed method involves three main steps. Initially, the image is preprocessed to remove small noises and enhance the contrast of the image. Secondly, Kirsch edge detection is utilized to detect the bright lesions. Subsequently, the red lesions are detected depending on top-hat morphological filtering methods. Then the bright and dark lesions are combined by using logical AND operator. In order to be left only pathological signs, the noises near the vicinity of the optic disc and blood vessels are further removed using blob analysis. Finally, morphological features are extracted and fed to the SVM classifier. The proposed method was evaluated with three datasets containing 229 images. It achieved the accuracy of 90%, sensitivity of 86.33% and specificity of 98.55% with the average computational time 8 seconds per image. The method is simple and fast, easy to implement and the result is promising.
{"title":"Primary screening of diabetic retinopathy based on integrating morphological operation and support vector machine","authors":"Syna Sreng, Noppadol Maneerat, D. Isarakorn, K. Hamamoto, Ronakorn Panjaphongse","doi":"10.1109/ICIIBMS.2017.8279750","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279750","url":null,"abstract":"Diabetic retinopathy is one of the most frequent causes of blindness due to diabetes. Primary screening is essential due to prerequisite step toward the diagnosis of diabetic retinopathy in order to prevent vision loss or blindness. This paper presents the methods to discriminate between healthy images and diabetic retinopathy images on the retinal images. The proposed method involves three main steps. Initially, the image is preprocessed to remove small noises and enhance the contrast of the image. Secondly, Kirsch edge detection is utilized to detect the bright lesions. Subsequently, the red lesions are detected depending on top-hat morphological filtering methods. Then the bright and dark lesions are combined by using logical AND operator. In order to be left only pathological signs, the noises near the vicinity of the optic disc and blood vessels are further removed using blob analysis. Finally, morphological features are extracted and fed to the SVM classifier. The proposed method was evaluated with three datasets containing 229 images. It achieved the accuracy of 90%, sensitivity of 86.33% and specificity of 98.55% with the average computational time 8 seconds per image. The method is simple and fast, easy to implement and the result is promising.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115749277","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 : 2017-11-01DOI: 10.1109/ICIIBMS.2017.8279723
Y. Lu, Chi-Jie Lu, Chi-Chang Chang, Yu-Wen Lin
This study applied advanced machine learning techniques and combined with ensemble learning, widely considered as the most successful method to produce objective to an inferential problem of recurrent ovarian cancer. In this study, five machine learning approaches including SVM(support vector machine), C5.0, ELM(extreme learning machine), MARS(Multivariate Adaptive Regression Splines) and RF(Random Forests) were considered to find important risk factors and to predict the recurrence-proneness for ovarian cancer. We use ensemble learning to improve the defect of classification accuracy used normal machine learning: first, selecting important risk factors by ensemble learning, then, using the five machine learning approaches to analyze again. The medical records and pathology were accessible by the Chung Shan Medical University Hospital Tumor Registry. The existing literature on recurrent ovarian cancer reveals that factors include Age, Histology, Grade, Pathologic T, Pathologic N, Pathologic M, Pathologic Stage, The International Federation of Gynecology and Obstetrics (FIGO), Surgical Margins, Performance status, CA125, Operation Optimal Debulking, Chemotherapy Guideline. There are totally 987 patients in the data set. In our study, C5.0 is the superior approach in predicting recurrence of ovarian cancer. Moreover, the classification accuracy of C5.0, MARS, RF and SVM indeed increases after using ensemble learning. Particularly the classification accuracy of C5.0 obviously improves by using ensemble learning with hybrid scheme.
{"title":"A hybrid of data mining and ensemble learning forecasting for recurrent ovarian cancer","authors":"Y. Lu, Chi-Jie Lu, Chi-Chang Chang, Yu-Wen Lin","doi":"10.1109/ICIIBMS.2017.8279723","DOIUrl":"https://doi.org/10.1109/ICIIBMS.2017.8279723","url":null,"abstract":"This study applied advanced machine learning techniques and combined with ensemble learning, widely considered as the most successful method to produce objective to an inferential problem of recurrent ovarian cancer. In this study, five machine learning approaches including SVM(support vector machine), C5.0, ELM(extreme learning machine), MARS(Multivariate Adaptive Regression Splines) and RF(Random Forests) were considered to find important risk factors and to predict the recurrence-proneness for ovarian cancer. We use ensemble learning to improve the defect of classification accuracy used normal machine learning: first, selecting important risk factors by ensemble learning, then, using the five machine learning approaches to analyze again. The medical records and pathology were accessible by the Chung Shan Medical University Hospital Tumor Registry. The existing literature on recurrent ovarian cancer reveals that factors include Age, Histology, Grade, Pathologic T, Pathologic N, Pathologic M, Pathologic Stage, The International Federation of Gynecology and Obstetrics (FIGO), Surgical Margins, Performance status, CA125, Operation Optimal Debulking, Chemotherapy Guideline. There are totally 987 patients in the data set. In our study, C5.0 is the superior approach in predicting recurrence of ovarian cancer. Moreover, the classification accuracy of C5.0, MARS, RF and SVM indeed increases after using ensemble learning. Particularly the classification accuracy of C5.0 obviously improves by using ensemble learning with hybrid scheme.","PeriodicalId":122969,"journal":{"name":"2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126558523","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：