Pub Date : 2018-11-01DOI: 10.1109/IEMCON.2018.8614894
Shiney Jeyaraj, Raghuveera Tripuraribhatla
In many organizations, enquiry emails from customers remain unanswered due to lack of patience and availability of a respondent. Generating FAQs from email repositories with lot of enquiry emails will be beneficial. However, manual generation of FAQs by experts is a time consuming and strenous job. Hence automatic generation of FAQs is a necessity. Automatic generation of FAQs require effective categorization of emails which is challenging since the emails are written by different people with heterogenous cognition levels. In this paper, we propose a framework using Non-negative Matrix Factorization (NMF) and k-means that groups emails into clusters which can be used for FAQ generation. The proposed framework determines not only the broad topic under which the emails have to be tagged but also categorizes the emails into clusters with similar sub contents. The number of clusters was determined by the elbow method whereas the number of topics was fixed by calculating the percentage of relevant topics. The average Silhouette coefficient score of the resulting clusters was found to be 0.52 indicating reasonably good clusters. Also, the Silhouette coefficient score of the proposed method increased by 36.82 % compared to k-means.
{"title":"A Framework for Automatic Generation of FAQs from Email Repositories","authors":"Shiney Jeyaraj, Raghuveera Tripuraribhatla","doi":"10.1109/IEMCON.2018.8614894","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614894","url":null,"abstract":"In many organizations, enquiry emails from customers remain unanswered due to lack of patience and availability of a respondent. Generating FAQs from email repositories with lot of enquiry emails will be beneficial. However, manual generation of FAQs by experts is a time consuming and strenous job. Hence automatic generation of FAQs is a necessity. Automatic generation of FAQs require effective categorization of emails which is challenging since the emails are written by different people with heterogenous cognition levels. In this paper, we propose a framework using Non-negative Matrix Factorization (NMF) and k-means that groups emails into clusters which can be used for FAQ generation. The proposed framework determines not only the broad topic under which the emails have to be tagged but also categorizes the emails into clusters with similar sub contents. The number of clusters was determined by the elbow method whereas the number of topics was fixed by calculating the percentage of relevant topics. The average Silhouette coefficient score of the resulting clusters was found to be 0.52 indicating reasonably good clusters. Also, the Silhouette coefficient score of the proposed method increased by 36.82 % compared to k-means.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125747231","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8615089
Mi Swe Zar Thu, Ei Chaw Htoon
The integration of cloud computing and mobile devices, known as Mobile Cloud Computing (MCC), allows the adoption of offloading techniques for improving compute intensive applications' performance and minimize the energy consumption. Deciding to offload some computing tasks or not is a way to solve the limitations of battery life and computing capability of mobile devices. In this paper, to alleviate the computational burden of mobile devices, we present a cost estimation weight factor for computation offloading in mobile devices. To make the right decisions as to whether or not to perform task offloading, based on the energy cost of the methods. The experimental results will demonstrate that the proposed cost estimator can significantly reduce energy consumption of mobile device as well as execution time of application.
{"title":"Cost Solving Model in Computation Offloading Decision Algorithm","authors":"Mi Swe Zar Thu, Ei Chaw Htoon","doi":"10.1109/IEMCON.2018.8615089","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8615089","url":null,"abstract":"The integration of cloud computing and mobile devices, known as Mobile Cloud Computing (MCC), allows the adoption of offloading techniques for improving compute intensive applications' performance and minimize the energy consumption. Deciding to offload some computing tasks or not is a way to solve the limitations of battery life and computing capability of mobile devices. In this paper, to alleviate the computational burden of mobile devices, we present a cost estimation weight factor for computation offloading in mobile devices. To make the right decisions as to whether or not to perform task offloading, based on the energy cost of the methods. The experimental results will demonstrate that the proposed cost estimator can significantly reduce energy consumption of mobile device as well as execution time of application.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128159041","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614936
Prince Chawla, Supinderiit Singh Kang
Super alloys are advanced engineering materials having high potential for aerospace and defence industries. Inconel 625, a nickel-chromium heat resistant alloy used in various applications such as in the manufacturing of aerospace fasteners, gas turbine engineering and heat treatment equipment. In this research, electric discharge machining is used for making holes on Inconel 625 and three control factors namely pulse current, pulse on time and flushing pressure are considered. These three factors having three levels each be taken into consideration and tool wear rate (TWR) is attained as a response measure. The experiment results are based on (L18 21*33) orthogonal array of Taguchi's methodology. The Anova technique is used for S/N ratio for TWR and showing that pulse current, pulse on time and flushing pressure are significant. The experiment results prove that the TWR is decreased by the use of cryogenically treated electrode.
{"title":"To Compare and Optimization of Tool Wear Rate Using Electric Discharge Machining for Industrial Control","authors":"Prince Chawla, Supinderiit Singh Kang","doi":"10.1109/IEMCON.2018.8614936","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614936","url":null,"abstract":"Super alloys are advanced engineering materials having high potential for aerospace and defence industries. Inconel 625, a nickel-chromium heat resistant alloy used in various applications such as in the manufacturing of aerospace fasteners, gas turbine engineering and heat treatment equipment. In this research, electric discharge machining is used for making holes on Inconel 625 and three control factors namely pulse current, pulse on time and flushing pressure are considered. These three factors having three levels each be taken into consideration and tool wear rate (TWR) is attained as a response measure. The experiment results are based on (L18 21*33) orthogonal array of Taguchi's methodology. The Anova technique is used for S/N ratio for TWR and showing that pulse current, pulse on time and flushing pressure are significant. The experiment results prove that the TWR is decreased by the use of cryogenically treated electrode.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125126525","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614802
Md Inzamam Ul Haque, Damian Valles
In this paper, an initial work of a research is discussed which is to teach young autistic children recognizing human facial expression with the help of computer vision and image processing. This paper mostly discusses the initial work of facial expression recognition using a deep convolutional neural network. The Kaggle's FER2013 dataset has been used to train and experiment with a deep convolutional neural network model. Once a satisfactory result is achieved, the dataset is modified with pictures of four different lighting conditions and each of these datasets is again trained with the same model. This is necessary for the end goal of the research which is to recognize facial expression in any possible environment. Finally, the comparison between results with different datasets is discussed and future work of the project is outlined.
{"title":"A Facial Expression Recognition Approach Using DCNN for Autistic Children to Identify Emotions","authors":"Md Inzamam Ul Haque, Damian Valles","doi":"10.1109/IEMCON.2018.8614802","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614802","url":null,"abstract":"In this paper, an initial work of a research is discussed which is to teach young autistic children recognizing human facial expression with the help of computer vision and image processing. This paper mostly discusses the initial work of facial expression recognition using a deep convolutional neural network. The Kaggle's FER2013 dataset has been used to train and experiment with a deep convolutional neural network model. Once a satisfactory result is achieved, the dataset is modified with pictures of four different lighting conditions and each of these datasets is again trained with the same model. This is necessary for the end goal of the research which is to recognize facial expression in any possible environment. Finally, the comparison between results with different datasets is discussed and future work of the project is outlined.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123479769","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614849
Jordan Lui, Alex Naylor, M. Zhou, Mahta Khoshnam, Neha Chhatre, A. Mahanfar, C. Menon
Unobtrusive human motion tracking has been facilitated by realizing various sensing technologies in the form of a network of wearable sensors. These sensors are well-suited for applications that call for continuous or tele-motion tracking, nevertheless, the research for characterizing their performance in different applications is ongoing. The study presented in this paper explores the potential of constructing a wearable sensor system based on radio frequency time-of-flight distance measurement for monitoring activities of upper limbs. In this regard, a prototype sensor is developed and experimentally characterized. The performance of the system is then evaluated in an elbow flexion-extension scenario and it is shown that the system can be easily calibrated for use in different environments and is able to estimate the hand distance from body with an accuracy of 4.66 cm. This preliminary study is presented as a proof-of-concept that designing a wearable sensor system based on radio frequency time-of-flight distance measurement is feasible and can be a potential solution for telemonitoring of upper limb activity in a free-living environment.
{"title":"Monitoring Upper-Limb Activity Based on Radio Frequency Time-of-Flight Distance Measurement","authors":"Jordan Lui, Alex Naylor, M. Zhou, Mahta Khoshnam, Neha Chhatre, A. Mahanfar, C. Menon","doi":"10.1109/IEMCON.2018.8614849","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614849","url":null,"abstract":"Unobtrusive human motion tracking has been facilitated by realizing various sensing technologies in the form of a network of wearable sensors. These sensors are well-suited for applications that call for continuous or tele-motion tracking, nevertheless, the research for characterizing their performance in different applications is ongoing. The study presented in this paper explores the potential of constructing a wearable sensor system based on radio frequency time-of-flight distance measurement for monitoring activities of upper limbs. In this regard, a prototype sensor is developed and experimentally characterized. The performance of the system is then evaluated in an elbow flexion-extension scenario and it is shown that the system can be easily calibrated for use in different environments and is able to estimate the hand distance from body with an accuracy of 4.66 cm. This preliminary study is presented as a proof-of-concept that designing a wearable sensor system based on radio frequency time-of-flight distance measurement is feasible and can be a potential solution for telemonitoring of upper limb activity in a free-living environment.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123501197","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614832
Anirudha Bhaskar
The main objective of this paper is to allow an suspicious aggressor estimate statistics without harming individual's privacy and is resilient to user failure and compromise, and can efficiently support dynamic leaves and joins. This paper will also show the combination of cryptography and computational differential privacy. The world requires applications where an suspicious aggressor can collect information without harming user's privacy and compute aggregate stats periodically.
{"title":"Fault-Tolerant Privacy-Preserving Block Aggregation Scheme With Straw-Man Construction","authors":"Anirudha Bhaskar","doi":"10.1109/IEMCON.2018.8614832","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614832","url":null,"abstract":"The main objective of this paper is to allow an suspicious aggressor estimate statistics without harming individual's privacy and is resilient to user failure and compromise, and can efficiently support dynamic leaves and joins. This paper will also show the combination of cryptography and computational differential privacy. The world requires applications where an suspicious aggressor can collect information without harming user's privacy and compute aggregate stats periodically.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122735416","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614960
P. Helebrandt, Matej Bellus, M. Ries, I. Kotuliak, V. Khilenko
Mass application of blockchain technology is becoming reality. Adopting blockchain to enterprise network is innovative approach. It brings novel solution for increasing network security and improved efficiency of network maintenance. Key feature of blockchain is storing data securely in encrypted chains of blocks. It is a distributed database processing continuously growing list of transactions. This feature makes blockchain extremely resistant to unauthorized modifications of stored data. Application of blockchain for network monitoring and management facilitates secure and distributed medium for configuration of network nodes. Furthermore, all modifications in configuration of devices are traceable in blockchain and configuration recovery after incident is rather simple and transparent. In this paper we introduce architecture for monitoring and managing enterprise networks through private blockchain. Using blockchain, any change is attributable to administrator as in traditional network management with AAA implemented, but in addition rollback to previous configuration is simple. Using blockchain instead of traditional network management approaches built on database, distributed nature of blockchain removes single point of failure and simplify management of distributed networks. Our solution utilizes blockchain for secure dissemination of configuration changes to network nodes. Proof of concept of our solution was validated with Hyperledger Composer in our Cisco Lab.
{"title":"Blockchain Adoption for Monitoring and Management of Enterprise Networks","authors":"P. Helebrandt, Matej Bellus, M. Ries, I. Kotuliak, V. Khilenko","doi":"10.1109/IEMCON.2018.8614960","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614960","url":null,"abstract":"Mass application of blockchain technology is becoming reality. Adopting blockchain to enterprise network is innovative approach. It brings novel solution for increasing network security and improved efficiency of network maintenance. Key feature of blockchain is storing data securely in encrypted chains of blocks. It is a distributed database processing continuously growing list of transactions. This feature makes blockchain extremely resistant to unauthorized modifications of stored data. Application of blockchain for network monitoring and management facilitates secure and distributed medium for configuration of network nodes. Furthermore, all modifications in configuration of devices are traceable in blockchain and configuration recovery after incident is rather simple and transparent. In this paper we introduce architecture for monitoring and managing enterprise networks through private blockchain. Using blockchain, any change is attributable to administrator as in traditional network management with AAA implemented, but in addition rollback to previous configuration is simple. Using blockchain instead of traditional network management approaches built on database, distributed nature of blockchain removes single point of failure and simplify management of distributed networks. Our solution utilizes blockchain for secure dissemination of configuration changes to network nodes. Proof of concept of our solution was validated with Hyperledger Composer in our Cisco Lab.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123747556","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}
The steady increasing requirement for food requires rapid development in food production technology. There is a wide range of crops and plants with different varieties. Various crops and plants have different requirements for water, fertilizers and sunlight. In a country like India, much of the economy is based on agriculture. India thrives on agriculture and farmers work day and night for the best productivity of crops. But they might be having problems in farming during natural hazards and the scheduled watering of the crops can get hampered. The main reason is lack of rain and shortcoming of land reservoir water. The continuous water removal results in the reduction of water from the earth's surface. As a result this leads to the increase of uncultivated land. Water wastage is also a big concern that the world faces. Nowadays water shortage is increasing day by day as a result saving water is also a topic of concern nowadays. Therefore smart irrigation system has been proposed and designed so that the plants or crops can be supplied with water in a proper time interval.
{"title":"Smart Irrigation System Using Arduino and GSM Module","authors":"Himadri Nath Saha, Tanishq Banerjee, S. Saha, Ayush Das, Arjun Dutta, Anirup Roy, Samabrit Kund, Arghyadyuti Patra, Arkodip Neogi, Smita Bandyopadhyay, Sampriti Das, Niloy Chakravorty","doi":"10.1109/IEMCON.2018.8614839","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614839","url":null,"abstract":"The steady increasing requirement for food requires rapid development in food production technology. There is a wide range of crops and plants with different varieties. Various crops and plants have different requirements for water, fertilizers and sunlight. In a country like India, much of the economy is based on agriculture. India thrives on agriculture and farmers work day and night for the best productivity of crops. But they might be having problems in farming during natural hazards and the scheduled watering of the crops can get hampered. The main reason is lack of rain and shortcoming of land reservoir water. The continuous water removal results in the reduction of water from the earth's surface. As a result this leads to the increase of uncultivated land. Water wastage is also a big concern that the world faces. Nowadays water shortage is increasing day by day as a result saving water is also a topic of concern nowadays. Therefore smart irrigation system has been proposed and designed so that the plants or crops can be supplied with water in a proper time interval.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131487883","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614748
Hazza Al-Shamisi, Humaid Al-Shamsi, I. Kostanic, J. Zec
RF engineers use drive test systems and equipment to measure the characteristics of cellular networks as a part of their everyday work. Their tasks include planning, performance monitoring, optimization, etc. A fundamental Long Term Evolution (LTE) performance measurement is the Reference Signal Received Power (RSRP). Measurements of RSRP are taken using either smartphones, receivers or channel scanners. The RSRP is considered as the fundamental coverage metric in an L TE network. This paper describes an Android application (LTENetScan) that enables RSRP measurement and logging. A comparison is made between RSRP measurements taken by LTENetScan on phones from different manufacturers with the same data captured by a professional-grade scanner. This comparison validates the accuracy of the phone-based systems as well as their feasibility as alternative test drive systems.
{"title":"Verifying Measurements of Reference Signal Received Power (RSRP) on LTE Network using an App on Android Smartphones","authors":"Hazza Al-Shamisi, Humaid Al-Shamsi, I. Kostanic, J. Zec","doi":"10.1109/IEMCON.2018.8614748","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614748","url":null,"abstract":"RF engineers use drive test systems and equipment to measure the characteristics of cellular networks as a part of their everyday work. Their tasks include planning, performance monitoring, optimization, etc. A fundamental Long Term Evolution (LTE) performance measurement is the Reference Signal Received Power (RSRP). Measurements of RSRP are taken using either smartphones, receivers or channel scanners. The RSRP is considered as the fundamental coverage metric in an L TE network. This paper describes an Android application (LTENetScan) that enables RSRP measurement and logging. A comparison is made between RSRP measurements taken by LTENetScan on phones from different manufacturers with the same data captured by a professional-grade scanner. This comparison validates the accuracy of the phone-based systems as well as their feasibility as alternative test drive systems.","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126325972","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 : 2018-11-01DOI: 10.1109/IEMCON.2018.8614883
Louis B. Rosenberg, M. Lungren, S. Halabi, G. Willcox, David Baltaxe, Mimi Lyons
Swarm Intelligence (SI) is a biological phenomenon in which groups of organisms amplify their combined brainpower by forming real-time systems. It has been studied for decades in fish schools, bird flocks, and bee swarms. Recent advances in networking and AI technologies have enabled distributed human groups to form closed-loop systems modeled after natural swarms. The process is referred to as Artificial Swarm Intelligence (ASI) and has been shown to significantly amplify group performance. The present research applies ASI technology to the field of medicine, exploring if small groups of networked radiologists can improve their diagnostic accuracy when reviewing chest X-rays for the presence of pneumonia. Performance data was collected for individual radiologists generating diagnoses alone, as well as for small groups of radiologists working together to generate diagnoses as a real-time ASI system. Diagnoses were also collected from a state-of-the-art deep learning system (CheXNet) developed at Stanford University. Results showed that small groups of networked radiologists, when working as a real-time ASI system, were significantly more accurate than the individual radiologists on their own, reducing diagnostic errors by 33%. Results also showed that small groups of networked radiologists, when working as an ASI system, were significantly more accurate (22%) than a state-of-the-art deep learning system (CheXNet).
{"title":"Artificial Swarm Intelligence employed to Amplify Diagnostic Accuracy in Radiology","authors":"Louis B. Rosenberg, M. Lungren, S. Halabi, G. Willcox, David Baltaxe, Mimi Lyons","doi":"10.1109/IEMCON.2018.8614883","DOIUrl":"https://doi.org/10.1109/IEMCON.2018.8614883","url":null,"abstract":"Swarm Intelligence (SI) is a biological phenomenon in which groups of organisms amplify their combined brainpower by forming real-time systems. It has been studied for decades in fish schools, bird flocks, and bee swarms. Recent advances in networking and AI technologies have enabled distributed human groups to form closed-loop systems modeled after natural swarms. The process is referred to as Artificial Swarm Intelligence (ASI) and has been shown to significantly amplify group performance. The present research applies ASI technology to the field of medicine, exploring if small groups of networked radiologists can improve their diagnostic accuracy when reviewing chest X-rays for the presence of pneumonia. Performance data was collected for individual radiologists generating diagnoses alone, as well as for small groups of radiologists working together to generate diagnoses as a real-time ASI system. Diagnoses were also collected from a state-of-the-art deep learning system (CheXNet) developed at Stanford University. Results showed that small groups of networked radiologists, when working as a real-time ASI system, were significantly more accurate than the individual radiologists on their own, reducing diagnostic errors by 33%. Results also showed that small groups of networked radiologists, when working as an ASI system, were significantly more accurate (22%) than a state-of-the-art deep learning system (CheXNet).","PeriodicalId":368939,"journal":{"name":"2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116622647","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：