Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061415
L. Dung, Hoa T. K. Tran, S. Choi
In this paper, we investigate the probability of existing a secure wireless multi-hop connection between two legitimate users in stochastic wireless networks under the existence of colluding eavesdroppers. Specifically, we introduce a simulation-based analysis that returns the path connectivity by averaging the connection status of a vast number of topology trails with a security-aware routing algorithm is taken into account. The behaviors of the multi-hop connectivity are examined for different network sizes and the numbers of legitimate users and eavesdroppers. The obtained results in this paper show that increasing the number of legitimate users leads to maximum path connectivity of less than one; meanwhile, path connectivity is continuously reduced as the number of eavesdroppers gets higher. Moreover, scaling down the network size does not always help to increase path connectivity.
{"title":"Connectivity of Wireless Multi-hop Stochastic Networks under the Security Constraints in Rayleigh Fading Environment","authors":"L. Dung, Hoa T. K. Tran, S. Choi","doi":"10.23919/ICACT48636.2020.9061415","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061415","url":null,"abstract":"In this paper, we investigate the probability of existing a secure wireless multi-hop connection between two legitimate users in stochastic wireless networks under the existence of colluding eavesdroppers. Specifically, we introduce a simulation-based analysis that returns the path connectivity by averaging the connection status of a vast number of topology trails with a security-aware routing algorithm is taken into account. The behaviors of the multi-hop connectivity are examined for different network sizes and the numbers of legitimate users and eavesdroppers. The obtained results in this paper show that increasing the number of legitimate users leads to maximum path connectivity of less than one; meanwhile, path connectivity is continuously reduced as the number of eavesdroppers gets higher. Moreover, scaling down the network size does not always help to increase path connectivity.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121787588","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061419
Chin-Wei Chen, Ching-Hung Su, Kun-Wei Lee, Ping-Hao Bair
In the past few years, the malware industry has been thriving. Malware variants among the same malware family shared similar behavioural patterns or signatures reflecting their purpose. We propose an approach that combines support vector machine (SVM) classifiers and active learning by learning (ALBL) techniques to deal with insufficient labeled data in terms of the malware classification tasks. The proposed approach is evaluated with the malware family dataset from Microsoft Malware Classification Challenge (BIG 2015) on Kaggle. The results show that ALBL techniques can effectively boost the performance of our machine learning models and improve the quality of labeled samples.
{"title":"Malware Family Classification using Active Learning by Learning","authors":"Chin-Wei Chen, Ching-Hung Su, Kun-Wei Lee, Ping-Hao Bair","doi":"10.23919/ICACT48636.2020.9061419","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061419","url":null,"abstract":"In the past few years, the malware industry has been thriving. Malware variants among the same malware family shared similar behavioural patterns or signatures reflecting their purpose. We propose an approach that combines support vector machine (SVM) classifiers and active learning by learning (ALBL) techniques to deal with insufficient labeled data in terms of the malware classification tasks. The proposed approach is evaluated with the malware family dataset from Microsoft Malware Classification Challenge (BIG 2015) on Kaggle. The results show that ALBL techniques can effectively boost the performance of our machine learning models and improve the quality of labeled samples.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115998967","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061354
Da-Yu Kao
Cybercriminals increasingly use sophisticated tools and advanced methods to attack bank systems. Cyber black markets for hacking tools or services are gaining widespread attention as more advanced persistent threat attacks are relevant to such markets. The recent cyber-attacks on banks or financial institutions have increased the technical expertise of cybercriminals. This study reviews ATM threats and highlights the cybercrime investigation of ATM heist. An incident investigation strategy from ISO/IEC 27043:2015 is proposed to embed cyber-attack phases and detect ATM heist. It demonstrates how this strategy can provide investigators with exceptional abilities to interpret evidence. By integrating an effective cybercrime investigation strategy, investigators can minimize the cost of collecting evidence in a forensically sound manner.
{"title":"Comprehending Taiwan ATM Heist: From Cyber-attack Phases to Investigation Processes","authors":"Da-Yu Kao","doi":"10.23919/ICACT48636.2020.9061354","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061354","url":null,"abstract":"Cybercriminals increasingly use sophisticated tools and advanced methods to attack bank systems. Cyber black markets for hacking tools or services are gaining widespread attention as more advanced persistent threat attacks are relevant to such markets. The recent cyber-attacks on banks or financial institutions have increased the technical expertise of cybercriminals. This study reviews ATM threats and highlights the cybercrime investigation of ATM heist. An incident investigation strategy from ISO/IEC 27043:2015 is proposed to embed cyber-attack phases and detect ATM heist. It demonstrates how this strategy can provide investigators with exceptional abilities to interpret evidence. By integrating an effective cybercrime investigation strategy, investigators can minimize the cost of collecting evidence in a forensically sound manner.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"36 45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125701936","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061305
S. Muneer, Muhammad Nadeem, B. Kasi, Mir Hamayoun Yousaf
Existing software design approaches used to design security aspects lack notations that can be used to design the security requirements of a system which may result in more complex and dense designs. However, literature review has shown that there are some proposed notations to represent security aspects within a system. Other researchers have proposed evidence-based principles that provide basis for constructing Visual Notations in Software Engineering. The principles include: Graphic Economy, Perceptual Discriminability, Semiotic Clarity, Cognitive Integration, Visual Expressiveness etc. In this research, we have evaluated a set of proposed notations in accordance with principles for designing cognitively accepted graphics by conducting a human subject study. A questionnaire was distributed among a group of graduate and post-graduate students. The goal was to validate the notations based on theory of “How Visual Notations Communicate?”. This study will help researchers in developing cognitively accepted notations and set a course for designing new notations for UMLsec that are perceptually, semantically and visually expressive.
{"title":"Evaluating the Effectiveness of Notations for Designing Security Aspects","authors":"S. Muneer, Muhammad Nadeem, B. Kasi, Mir Hamayoun Yousaf","doi":"10.23919/ICACT48636.2020.9061305","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061305","url":null,"abstract":"Existing software design approaches used to design security aspects lack notations that can be used to design the security requirements of a system which may result in more complex and dense designs. However, literature review has shown that there are some proposed notations to represent security aspects within a system. Other researchers have proposed evidence-based principles that provide basis for constructing Visual Notations in Software Engineering. The principles include: Graphic Economy, Perceptual Discriminability, Semiotic Clarity, Cognitive Integration, Visual Expressiveness etc. In this research, we have evaluated a set of proposed notations in accordance with principles for designing cognitively accepted graphics by conducting a human subject study. A questionnaire was distributed among a group of graduate and post-graduate students. The goal was to validate the notations based on theory of “How Visual Notations Communicate?”. This study will help researchers in developing cognitively accepted notations and set a course for designing new notations for UMLsec that are perceptually, semantically and visually expressive.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127018370","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061449
Seong-Hun Ham, Dihn-Lam Pham, Kyoungsook Kim, Kwanghoon Pio Kim
The issue of workflow process mining and analytics is beginning to make its appearance in the workflow-supported enterprise intelligence and systems literature. In order to improve the quality of workflow process intelligence, it is essential for an efficient and effective data center storing workflow enactment event logs to be provisioned in carrying out the workflow process mining and analytics. In this paper, we propose a three-dimensional datacube, which is named as a process-aware dat-acube, for organizing workflow-supported enterprise data centers to efficiently as well as effectively store the workflow process enactment event logs in the IEEE XES format, and also we carry out an experimental process mining and analytics to show how much perfectly the process-aware datacubes are suitable for discovering workflow process patterns and its analytical knowledge, like enacted proportions and enacted work transferences, from the workflow process enactment event histories. From the process-aware datacubes, the workflow process mining must be able to properly discover all the workflow process patterns based upon the four types of control-flow primitives such as linear (sequential) routing, disjunctive (selective) routing, conjunctive (parallel) routing, and iterative (loop) routing patterns, whereas the workflow process analytics is to discover the enacted pro-protions of each of the process pattherns and the enacted work transferences of each of the workflow performers.
{"title":"Process-aware Event Log Datacubes for Workflow Process and Knowledge Mining, Predicting and Analyzing Frameworks","authors":"Seong-Hun Ham, Dihn-Lam Pham, Kyoungsook Kim, Kwanghoon Pio Kim","doi":"10.23919/ICACT48636.2020.9061449","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061449","url":null,"abstract":"The issue of workflow process mining and analytics is beginning to make its appearance in the workflow-supported enterprise intelligence and systems literature. In order to improve the quality of workflow process intelligence, it is essential for an efficient and effective data center storing workflow enactment event logs to be provisioned in carrying out the workflow process mining and analytics. In this paper, we propose a three-dimensional datacube, which is named as a process-aware dat-acube, for organizing workflow-supported enterprise data centers to efficiently as well as effectively store the workflow process enactment event logs in the IEEE XES format, and also we carry out an experimental process mining and analytics to show how much perfectly the process-aware datacubes are suitable for discovering workflow process patterns and its analytical knowledge, like enacted proportions and enacted work transferences, from the workflow process enactment event histories. From the process-aware datacubes, the workflow process mining must be able to properly discover all the workflow process patterns based upon the four types of control-flow primitives such as linear (sequential) routing, disjunctive (selective) routing, conjunctive (parallel) routing, and iterative (loop) routing patterns, whereas the workflow process analytics is to discover the enacted pro-protions of each of the process pattherns and the enacted work transferences of each of the workflow performers.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127043323","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061478
Yoonkwan Byun, Hyunji Lee, Sek-Jin Jang, S. Choi, Seung-hee Oh, Yong-Tae Lee
Emergency alert message is effective way to send text information for public alert service in disaster situation. But the textual information has limitations to make people understand. In this paper, we suggest a method to expression image on cell phone device.
{"title":"A Study for Image Expression of Emergency Alert","authors":"Yoonkwan Byun, Hyunji Lee, Sek-Jin Jang, S. Choi, Seung-hee Oh, Yong-Tae Lee","doi":"10.23919/ICACT48636.2020.9061478","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061478","url":null,"abstract":"Emergency alert message is effective way to send text information for public alert service in disaster situation. But the textual information has limitations to make people understand. In this paper, we suggest a method to expression image on cell phone device.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132090162","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061262
M. Barry, J. K. Tamgno, C. Lishou, Ismaël Habou Dere
This thesis work concerns the modelling and simulation of IPTV and VoD streams in an IP/MPLS network. Video traffic and their protocols are studied. We started from the M/G/∞ model which allowed us to have images (I, B and P). These are the images that were used during the modeling process. Indeed, this model allows to characterize a video sequence by the following parameters: Slot or time to generate a packet; image level or GOP. Image size or GOP distribution: Mixing distribution. Type of correlation: Markov, short-term dependence or long-term dependence. The protocols involved are: MPEG-TS; UDP; RTP; RTSP; IP; IGMPv2; MPLS. In order to find a packet output model, we created a “modeler” in a python environment to estimate multicast and VoD traffic. We have created four (4) functions to materialize this modeling: “Packer”, TS, Sequencer and Transport. The results collected allowed us to determine the law and mathematical model of packet output. And it is the M/M/∞ model that models a video source. We used the RStudio software for this purpose. All these theoretical results could be compared during the simulation of the IPTV and VoD servers.
{"title":"Modeling and Simulation of Multicast IPTV and VoD Streams for a Multiservice IP Network","authors":"M. Barry, J. K. Tamgno, C. Lishou, Ismaël Habou Dere","doi":"10.23919/ICACT48636.2020.9061262","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061262","url":null,"abstract":"This thesis work concerns the modelling and simulation of IPTV and VoD streams in an IP/MPLS network. Video traffic and their protocols are studied. We started from the M/G/∞ model which allowed us to have images (I, B and P). These are the images that were used during the modeling process. Indeed, this model allows to characterize a video sequence by the following parameters: Slot or time to generate a packet; image level or GOP. Image size or GOP distribution: Mixing distribution. Type of correlation: Markov, short-term dependence or long-term dependence. The protocols involved are: MPEG-TS; UDP; RTP; RTSP; IP; IGMPv2; MPLS. In order to find a packet output model, we created a “modeler” in a python environment to estimate multicast and VoD traffic. We have created four (4) functions to materialize this modeling: “Packer”, TS, Sequencer and Transport. The results collected allowed us to determine the law and mathematical model of packet output. And it is the M/M/∞ model that models a video source. We used the RStudio software for this purpose. All these theoretical results could be compared during the simulation of the IPTV and VoD servers.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131472680","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061395
Ji Won Lee, Do-Won Nam, Jungsoo Lee, S. Moon, Arum Oh, Wonyoung Yoo
Ships, coastal posts, and control centers need to verify the information, location, and speed of nearby vessels for various purposes, such as traffic control or maritime warfare. In the field of defense where accurate information on nearby ships is important, radar is used to acquire location information on nearby ships. However, the selection of the opponent's position as well as the high-value units must be more important and prioritized, and image-based warship type/class identification techniques are required in naval warfare. This paper presents a detailed method for system construction that supports detailed identification of warship type/class through structural analysis. Through the development of the proposed system, reliable warship identification can be used for tactical applications in the defense field, thereby contributing to the enhancement of defense capabilities.
{"title":"A Study on the Composition of Image-Based Ship-type/class Identification System","authors":"Ji Won Lee, Do-Won Nam, Jungsoo Lee, S. Moon, Arum Oh, Wonyoung Yoo","doi":"10.23919/ICACT48636.2020.9061395","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061395","url":null,"abstract":"Ships, coastal posts, and control centers need to verify the information, location, and speed of nearby vessels for various purposes, such as traffic control or maritime warfare. In the field of defense where accurate information on nearby ships is important, radar is used to acquire location information on nearby ships. However, the selection of the opponent's position as well as the high-value units must be more important and prioritized, and image-based warship type/class identification techniques are required in naval warfare. This paper presents a detailed method for system construction that supports detailed identification of warship type/class through structural analysis. Through the development of the proposed system, reliable warship identification can be used for tactical applications in the defense field, thereby contributing to the enhancement of defense capabilities.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"4 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131226303","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 : 2020-02-01DOI: 10.23919/icact48636.2020.9061288
Heechang Chung, Dongil Kim, Kyoung-Sook Jung, Byeong-Beom Kang, SokPal Cho, Soonghee Lee
Agricultural data is the key foundation for Smart Farm models, in which a wide range of Information and Communication Technology (ICT) such as IoT and Big Data are converged, to be operated and managed. Given the fact that every single stage in Smart Farm models from crop growing to selling requires appropriate data, it is crucial to have a well-established service model for data collection and its provision. This service model should gather and process data before providing it for users to enhance their convenience in farm business. By converging various data collected from each stage of production, the model should ensure higher quality of service. This paper describes the reference architecture of the service model.
{"title":"Study on Service model of the Agriculture Information based Convergence Service","authors":"Heechang Chung, Dongil Kim, Kyoung-Sook Jung, Byeong-Beom Kang, SokPal Cho, Soonghee Lee","doi":"10.23919/icact48636.2020.9061288","DOIUrl":"https://doi.org/10.23919/icact48636.2020.9061288","url":null,"abstract":"Agricultural data is the key foundation for Smart Farm models, in which a wide range of Information and Communication Technology (ICT) such as IoT and Big Data are converged, to be operated and managed. Given the fact that every single stage in Smart Farm models from crop growing to selling requires appropriate data, it is crucial to have a well-established service model for data collection and its provision. This service model should gather and process data before providing it for users to enhance their convenience in farm business. By converging various data collected from each stage of production, the model should ensure higher quality of service. This paper describes the reference architecture of the service model.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131074170","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061497
Sabyasachi Chakraborty, S. Aich, J. Sim, Eunyoung Han, Jinse Park, Hee-Cheol Kim
Identification of the correct biomarkers with respect to particular health issues and detection of the same is of paramount importance for the development of clinical decision support systems. For the patients suffering from Parkinson's Disease (PD), it has been duly observed that impairment in the handwriting is directly proportional to the severity of the disease. Also, the speed and pressure applied to the pen while sketching or writing something are also much lower in patients suffering from Parkinson's disease. Therefore, correctly identifying such biomarkers accurately and precisely at the onset of the disease will lead to a better clinical diagnosis. Therefore, in this paper, a system design is proposed for analyzing Spiral drawing patterns and wave drawing patterns in patients suffering from Parkinson's disease and healthy subjects. The system developed in the study leverages two different convolutional neural networks (CNN), for analyzing the drawing patters of both spiral and wave sketches respectively. Further, the prediction probabilities are trained on a metal classifier based on ensemble voting to provide a weighted prediction from both the spiral and wave sketch. The complete model was trained on the data of 55 patients and has achieved an overall accuracy of 93.3%, average recall of 94%, average precision of 93.5% and average f1 score of 93.94%
{"title":"Parkinson's Disease Detection from Spiral and Wave Drawings using Convolutional Neural Networks: A Multistage Classifier Approach","authors":"Sabyasachi Chakraborty, S. Aich, J. Sim, Eunyoung Han, Jinse Park, Hee-Cheol Kim","doi":"10.23919/ICACT48636.2020.9061497","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061497","url":null,"abstract":"Identification of the correct biomarkers with respect to particular health issues and detection of the same is of paramount importance for the development of clinical decision support systems. For the patients suffering from Parkinson's Disease (PD), it has been duly observed that impairment in the handwriting is directly proportional to the severity of the disease. Also, the speed and pressure applied to the pen while sketching or writing something are also much lower in patients suffering from Parkinson's disease. Therefore, correctly identifying such biomarkers accurately and precisely at the onset of the disease will lead to a better clinical diagnosis. Therefore, in this paper, a system design is proposed for analyzing Spiral drawing patterns and wave drawing patterns in patients suffering from Parkinson's disease and healthy subjects. The system developed in the study leverages two different convolutional neural networks (CNN), for analyzing the drawing patters of both spiral and wave sketches respectively. Further, the prediction probabilities are trained on a metal classifier based on ensemble voting to provide a weighted prediction from both the spiral and wave sketch. The complete model was trained on the data of 55 patients and has achieved an overall accuracy of 93.3%, average recall of 94%, average precision of 93.5% and average f1 score of 93.94%","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116590595","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：