Pub Date : 2019-10-01DOI: 10.1109/ISC246665.2019.9071753
Ali Tekeoglu, Noor O. Ahmed
Internet of Things (IoT) is an emerging technology that have been attracting significant attention from diverse application domains ranging from smart homes, smart cities to smart healthcare and manufacturing. Especially in smart city context, IoT devices play a significant role since the city of the future is an interconnected one, where distributed devices communicate with one another, constantly exchanging streams of real time data. However, the fundamental challenge on deploying such technology is the inherent limitations on IoT device’s computational power, network connectivity, energy consumption, which in turn hinders secure deployment. The introduction of Blockchain technology for digital cash offers a promising data security scheme for IoT applications in trust-less environments. Blockchain promises an elegant approach for secure information dissemination, machine-to-machine micro-transactions, and access control in a smart city context for IoT devices. However, the computational and storage requirements for original Blockchain model presents difficulties for IoT deployment. In this paper, we propose an experimental lightweight distributed ledger for IoT devices, TangoChain, utilizing a directed acyclic graph as underlying ledger data structure. We discuss the rationale behind our design approach, then present our in-progress proof-ofconcept prototype implementation details, and highlight the potentials for secure IoT device deployments in a smart city context.
{"title":"TangoChain: A Lightweight Distributed Ledger for Internet of Things Devices in Smart Cities","authors":"Ali Tekeoglu, Noor O. Ahmed","doi":"10.1109/ISC246665.2019.9071753","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071753","url":null,"abstract":"Internet of Things (IoT) is an emerging technology that have been attracting significant attention from diverse application domains ranging from smart homes, smart cities to smart healthcare and manufacturing. Especially in smart city context, IoT devices play a significant role since the city of the future is an interconnected one, where distributed devices communicate with one another, constantly exchanging streams of real time data. However, the fundamental challenge on deploying such technology is the inherent limitations on IoT device’s computational power, network connectivity, energy consumption, which in turn hinders secure deployment. The introduction of Blockchain technology for digital cash offers a promising data security scheme for IoT applications in trust-less environments. Blockchain promises an elegant approach for secure information dissemination, machine-to-machine micro-transactions, and access control in a smart city context for IoT devices. However, the computational and storage requirements for original Blockchain model presents difficulties for IoT deployment. In this paper, we propose an experimental lightweight distributed ledger for IoT devices, TangoChain, utilizing a directed acyclic graph as underlying ledger data structure. We discuss the rationale behind our design approach, then present our in-progress proof-ofconcept prototype implementation details, and highlight the potentials for secure IoT device deployments in a smart city context.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"51 Pt 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126238112","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071732
Raul Alejandro Vargas-Acosta, D. Becerra, Okan Gurbuz, N. Villanueva-Rosales, G. Nunez-Mchiri, R. Cheu
Older adults are a population underserved by technology that faces unique challenges when commuting in urban areas due to a decrease in their physical and cognitive skills associated with aging (e.g., a decline in their sight, slower reflexes, loss of hearing, fear of getting lost or disoriented, fear of falling). Smart Cities aim to provide a high quality of life to residents regardless of the special needs they may have. This paper describes our recent efforts in increasing our understanding of seniors’ mobility needs and how to address them through technology, and in particular the development of the Urban Connector. Urban Connector is a product of our interdisciplinary research efforts aiming to address mobility challenges of seniors in El Paso, a city in the U.S. Southwest and validated in New York, a city in the U.S. Northeast. The Urban Connector is a mobile application which design follows recommendations for the development of technology catered to seniors. To evaluate the effectiveness of the Urban connector to address mobility needs of seniors through technology, an evaluation with 38 beta-testers was performed. The results of this evaluation are presented in this paper along with our future efforts based on these results. The Urban Connector contributes to efforts to foster the use of technology aiming to bridge the generational digital divide and support the creation of more inclusive, sustainable, smart cities.
{"title":"Smart Mobility for Seniors through the Urban Connector","authors":"Raul Alejandro Vargas-Acosta, D. Becerra, Okan Gurbuz, N. Villanueva-Rosales, G. Nunez-Mchiri, R. Cheu","doi":"10.1109/ISC246665.2019.9071732","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071732","url":null,"abstract":"Older adults are a population underserved by technology that faces unique challenges when commuting in urban areas due to a decrease in their physical and cognitive skills associated with aging (e.g., a decline in their sight, slower reflexes, loss of hearing, fear of getting lost or disoriented, fear of falling). Smart Cities aim to provide a high quality of life to residents regardless of the special needs they may have. This paper describes our recent efforts in increasing our understanding of seniors’ mobility needs and how to address them through technology, and in particular the development of the Urban Connector. Urban Connector is a product of our interdisciplinary research efforts aiming to address mobility challenges of seniors in El Paso, a city in the U.S. Southwest and validated in New York, a city in the U.S. Northeast. The Urban Connector is a mobile application which design follows recommendations for the development of technology catered to seniors. To evaluate the effectiveness of the Urban connector to address mobility needs of seniors through technology, an evaluation with 38 beta-testers was performed. The results of this evaluation are presented in this paper along with our future efforts based on these results. The Urban Connector contributes to efforts to foster the use of technology aiming to bridge the generational digital divide and support the creation of more inclusive, sustainable, smart cities.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"268 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114107643","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071700
Irini Spyridakis, Madison Holbrook, Brent Gruenke, S. Latha
Food waste is a prevalent issue worldwide. Close to 15 percent of households in the U.S. are food insecure. The U.S. wastes up to 40 percent of food, disposing not only food, but also wasting precious resources ranging from land, water, labor, and energy in the production and transportation of food from farm to consumers. At the University of Washington (UW), a research group in the department of Human Centered Design &Engineering (HCDE) designed a solution to food waste by creating an interactive, responsive open source website (Meal Matchup) to facilitate food donation and connect dining hall managers, local shelters, and student deliverers. This paper focuses on the consequences of food waste as well as how Meal Matchup manages resources and helps deliver leftover food to those in need through the use of technology, volunteerism, and civic engagement.
{"title":"Smart Resource Management: Civic Engagement and Food Recovery","authors":"Irini Spyridakis, Madison Holbrook, Brent Gruenke, S. Latha","doi":"10.1109/ISC246665.2019.9071700","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071700","url":null,"abstract":"Food waste is a prevalent issue worldwide. Close to 15 percent of households in the U.S. are food insecure. The U.S. wastes up to 40 percent of food, disposing not only food, but also wasting precious resources ranging from land, water, labor, and energy in the production and transportation of food from farm to consumers. At the University of Washington (UW), a research group in the department of Human Centered Design &Engineering (HCDE) designed a solution to food waste by creating an interactive, responsive open source website (Meal Matchup) to facilitate food donation and connect dining hall managers, local shelters, and student deliverers. This paper focuses on the consequences of food waste as well as how Meal Matchup manages resources and helps deliver leftover food to those in need through the use of technology, volunteerism, and civic engagement.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125541157","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071768
C. Boccaletti, C. Moscatiello, M. Jubran, Haifa Takruri, M. Abdelati, J. Munilla
The paper presents the mid-term progress report of a project granted by the Erasmus+ Programme, focused in particular on three fields that are considered enablers for Smart Cities (SCs): Telecommunications and Computer Networks, IT Security, and Smart Grids (SGs). Policy makers and stakeholders in Palestine (PS) have made the decision to move towards a knowledge-based economy with the aim of providing a rapid but sustainable economic growth. Moreover, the implementation of the SC concept in urban areas is recognized as the mean to promote the development of infrastructures and services, and improve the quality of life of citizens. The project main contributions are: (i) the transfer of know-how from European experts to PS; (ii) the enhancement of capacity building and skills of professors, students, and industry employees. Since Academia-Industry partnerships play a pivotal role in this process, the aim of the project is also to provoke Academia-Industry cooperation, which is not only a national priority, but is also necessary to increase the employability of new graduates.
{"title":"e-Academy to support Smart Cities Operations in Palestine (eSCO) project: progress report","authors":"C. Boccaletti, C. Moscatiello, M. Jubran, Haifa Takruri, M. Abdelati, J. Munilla","doi":"10.1109/ISC246665.2019.9071768","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071768","url":null,"abstract":"The paper presents the mid-term progress report of a project granted by the Erasmus+ Programme, focused in particular on three fields that are considered enablers for Smart Cities (SCs): Telecommunications and Computer Networks, IT Security, and Smart Grids (SGs). Policy makers and stakeholders in Palestine (PS) have made the decision to move towards a knowledge-based economy with the aim of providing a rapid but sustainable economic growth. Moreover, the implementation of the SC concept in urban areas is recognized as the mean to promote the development of infrastructures and services, and improve the quality of life of citizens. The project main contributions are: (i) the transfer of know-how from European experts to PS; (ii) the enhancement of capacity building and skills of professors, students, and industry employees. Since Academia-Industry partnerships play a pivotal role in this process, the aim of the project is also to provoke Academia-Industry cooperation, which is not only a national priority, but is also necessary to increase the employability of new graduates.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130612940","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071727
Miguel B. Costa, Paulo Cambra, Filipe Moura, Manuel Marques
Walking is an increasingly important issue in city planning. Sidewalk conditions are important to promote walking in cities and to ensure equitable accessibility for all. However, current methods of evaluating sidewalks are rather complex, subjective and resource-intensive, requiring expensive equipment or experts in the field. These factors make collecting sidewalk data at city level a challenge.In this paper, we propose WalkBot, an innovative, cost effective system to scan sidewalks. WalkBot is a portable data acquisition system capable of scanning and mapping sidewalk information. WalkBot collects 3D information about the environment and its geolocation, which is processed offline to provide key accessibility metrics, such as effective width and the presence of ground irregularities, thus evaluating the pedestrian network for compliance with accessibility standards more efficiently than current methods of manual and visual auditing.The device was tested in a sample of Lisbon’s sidewalks, measuring sidewalk width, smoothness and free passing distance. The obtained results show that we can provide good measurements for the evaluation of the sidewalk conditions. These findings encourage the application of the WalkBot system to city-level, ultimately contributing to a people and environment-friendly city.
{"title":"WalkBot: A Portable System to Scan Sidewalks","authors":"Miguel B. Costa, Paulo Cambra, Filipe Moura, Manuel Marques","doi":"10.1109/ISC246665.2019.9071727","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071727","url":null,"abstract":"Walking is an increasingly important issue in city planning. Sidewalk conditions are important to promote walking in cities and to ensure equitable accessibility for all. However, current methods of evaluating sidewalks are rather complex, subjective and resource-intensive, requiring expensive equipment or experts in the field. These factors make collecting sidewalk data at city level a challenge.In this paper, we propose WalkBot, an innovative, cost effective system to scan sidewalks. WalkBot is a portable data acquisition system capable of scanning and mapping sidewalk information. WalkBot collects 3D information about the environment and its geolocation, which is processed offline to provide key accessibility metrics, such as effective width and the presence of ground irregularities, thus evaluating the pedestrian network for compliance with accessibility standards more efficiently than current methods of manual and visual auditing.The device was tested in a sample of Lisbon’s sidewalks, measuring sidewalk width, smoothness and free passing distance. The obtained results show that we can provide good measurements for the evaluation of the sidewalk conditions. These findings encourage the application of the WalkBot system to city-level, ultimately contributing to a people and environment-friendly city.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130570039","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071684
Mirzodaler Muhsinzoda, Carlos Cruz Corona, D. Pelta, J. Verdegay
We describe the problem of partially sighted pedestrians who identify crossing the street as a difficult task. Pedestrian call buttons remain difficult to activate for partially sighted pedestrians. We believe that human-technology interfaces such as speech-related technologies can help to make this task easier. We propose a deep learning model for keyword spotting system where pedestrians can activate the pedestrian call button using their voice and thus enable them to cross the streets safely.
{"title":"Activating accessible pedestrian signals by voice using keyword spotting systems","authors":"Mirzodaler Muhsinzoda, Carlos Cruz Corona, D. Pelta, J. Verdegay","doi":"10.1109/ISC246665.2019.9071684","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071684","url":null,"abstract":"We describe the problem of partially sighted pedestrians who identify crossing the street as a difficult task. Pedestrian call buttons remain difficult to activate for partially sighted pedestrians. We believe that human-technology interfaces such as speech-related technologies can help to make this task easier. We propose a deep learning model for keyword spotting system where pedestrians can activate the pedestrian call button using their voice and thus enable them to cross the streets safely.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131109187","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071781
Ubaldo Castro, Jonathan Avila, Cynthia V. Sustaita, M. Hernandez, Víctor M. Larios-Rosillo, N. Villanueva-Rosales, O. Mondragon, R. Cheu, Ma. Roció Maciel Arellano
Flooding hinders the ability of residents to move through-out urban areas. Current weather information systems provide weather forecasts with a granularity too coarse to inform city residents of floods at a street level. Reliable real-time data is also limited in some cities and only a few systems enable users to report flooding events. This research project aims to inform residents about flooding events through the Flooding Alert System (FAS), which seamlessly integrates real-time data, crowdsourced data, historical data and provides timely and precise information to users so that they can make informed decisions during these events. The proposed Smart Cities solution, uses Internet of Things sensors equipped with an image processing algorithm for approximating the water level at at-risk areas. In adittion, a mobile application allows users to report and receive alerts of nearby flooding events as they occur. The expected products will be piloted in Guadalajara, JAL, MX. Transferability of our solution is planned to be evaluated through the application of these products in El Paso, TX, USA.
{"title":"Towards Smart Mobility During Flooding Events in Urban Areas using Crowdsourced Information","authors":"Ubaldo Castro, Jonathan Avila, Cynthia V. Sustaita, M. Hernandez, Víctor M. Larios-Rosillo, N. Villanueva-Rosales, O. Mondragon, R. Cheu, Ma. Roció Maciel Arellano","doi":"10.1109/ISC246665.2019.9071781","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071781","url":null,"abstract":"Flooding hinders the ability of residents to move through-out urban areas. Current weather information systems provide weather forecasts with a granularity too coarse to inform city residents of floods at a street level. Reliable real-time data is also limited in some cities and only a few systems enable users to report flooding events. This research project aims to inform residents about flooding events through the Flooding Alert System (FAS), which seamlessly integrates real-time data, crowdsourced data, historical data and provides timely and precise information to users so that they can make informed decisions during these events. The proposed Smart Cities solution, uses Internet of Things sensors equipped with an image processing algorithm for approximating the water level at at-risk areas. In adittion, a mobile application allows users to report and receive alerts of nearby flooding events as they occur. The expected products will be piloted in Guadalajara, JAL, MX. Transferability of our solution is planned to be evaluated through the application of these products in El Paso, TX, USA.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134365890","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071664
Jatuwat Sa-ngiampak, Chutipon Hirankanokkul, Yanisa Sunthornyotin, Jakpat Mingmongkolmitr, Sojirath Thunprateep, Nicha Rojsrikul, Tai Tantipiwatanaskul, Kachamas Techapichetvanich, Anon Pongsawang, Thanakorn Prayoonkittikul, Ukrit Wattanakulchart, N. Prompoon, C. Ratanamahatana, M. Pipattanasomporn
At any college-level institutions, students typically carry heavy belongings to the university every day. While generic lockers are available on campus, these lockers can only be used by one person at a time. In addition, information regarding locker locations and their availability are not available. This project focuses on the use of Internet of Things (IoT) and full stack software development to offer an alternative smart locker solution, called LockerSwarm. Instead of a physical key, each locker can be unlocked by scanning a Quick Response code (QR code), and its access can be shared among selected individuals. Users can search for the closest lockers, see the locations of all lockers, and check locker availability. Overall, this project sheds the new light on integrating IoT technologies to transform traditional lockers to smart lockers, which is a part of a smart campus initiative. With the prototype development and testing experience at Chulalongkorn University, Thailand, the entire LockerSwarm system is deemed to be easily replicable at any other university campuses.
{"title":"LockerSwarm: An IoT-based Smart Locker System with Access Sharing","authors":"Jatuwat Sa-ngiampak, Chutipon Hirankanokkul, Yanisa Sunthornyotin, Jakpat Mingmongkolmitr, Sojirath Thunprateep, Nicha Rojsrikul, Tai Tantipiwatanaskul, Kachamas Techapichetvanich, Anon Pongsawang, Thanakorn Prayoonkittikul, Ukrit Wattanakulchart, N. Prompoon, C. Ratanamahatana, M. Pipattanasomporn","doi":"10.1109/ISC246665.2019.9071664","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071664","url":null,"abstract":"At any college-level institutions, students typically carry heavy belongings to the university every day. While generic lockers are available on campus, these lockers can only be used by one person at a time. In addition, information regarding locker locations and their availability are not available. This project focuses on the use of Internet of Things (IoT) and full stack software development to offer an alternative smart locker solution, called LockerSwarm. Instead of a physical key, each locker can be unlocked by scanning a Quick Response code (QR code), and its access can be shared among selected individuals. Users can search for the closest lockers, see the locations of all lockers, and check locker availability. Overall, this project sheds the new light on integrating IoT technologies to transform traditional lockers to smart lockers, which is a part of a smart campus initiative. With the prototype development and testing experience at Chulalongkorn University, Thailand, the entire LockerSwarm system is deemed to be easily replicable at any other university campuses.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"201 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130284223","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071756
M. Manjutha, P. Subashini, M. Krishnaveni, V. Narmadha
Speech is the most important and indispensable mode of communication between humans. In communication, the continuous flow of speech gets affected due to the interruption of emotional, panic and psychological factors that cause syllable or word repetition, prolongation and interjection. Speech dysfluency is a primary challenge for speech pathologist to isolate the normal speech from the stuttered speech. The primary objective of this paper is to propose a novel approach through optimized cepstral features selection that improves the classifiers accuracy. In this paper, Particle Swarm Optimization (PSO) and Synergistic Fibroblast Optimization (SFO) were introduced to select optimal features from conventional MFCC (Mel-Frequency Cepstrum Coefficients). The optimized cepstral features from PSO and SFO of pre-processed Tamil speech data is used to discriminate among different categories of speech signals like Normal, Moderate and Sever stutter through machine learning classification methods such as Support Vector Machine (SVM) and Naive Bayes (NB). From the experimental results, the optimal selection of cepstral features using SFO algorithm has achieved high accuracy of 96.08% employed with NB which outperforms well to the feature selection of PSO and classical MFCC. The evaluation of the proposed methodology is done by using performance metrics like sensitivity, specificity, precision, f-score and accuracy.
{"title":"An Optimized Cepstral Feature Selection method for Dysfluencies Classification using Tamil Speech Dataset","authors":"M. Manjutha, P. Subashini, M. Krishnaveni, V. Narmadha","doi":"10.1109/ISC246665.2019.9071756","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071756","url":null,"abstract":"Speech is the most important and indispensable mode of communication between humans. In communication, the continuous flow of speech gets affected due to the interruption of emotional, panic and psychological factors that cause syllable or word repetition, prolongation and interjection. Speech dysfluency is a primary challenge for speech pathologist to isolate the normal speech from the stuttered speech. The primary objective of this paper is to propose a novel approach through optimized cepstral features selection that improves the classifiers accuracy. In this paper, Particle Swarm Optimization (PSO) and Synergistic Fibroblast Optimization (SFO) were introduced to select optimal features from conventional MFCC (Mel-Frequency Cepstrum Coefficients). The optimized cepstral features from PSO and SFO of pre-processed Tamil speech data is used to discriminate among different categories of speech signals like Normal, Moderate and Sever stutter through machine learning classification methods such as Support Vector Machine (SVM) and Naive Bayes (NB). From the experimental results, the optimal selection of cepstral features using SFO algorithm has achieved high accuracy of 96.08% employed with NB which outperforms well to the feature selection of PSO and classical MFCC. The evaluation of the proposed methodology is done by using performance metrics like sensitivity, specificity, precision, f-score and accuracy.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134510748","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 : 2019-10-01DOI: 10.1109/ISC246665.2019.9071659
D. Petrova-Antonova, Olga B. Mora Sánchez, Víctor M. Larios-Rosillo, M. M. Z. Ramirez
Air pollution in urban areas has increased exponentially in recent years, causing cardiovascular, respiratory, endocrine and oncology diseases, reducing the quality of life of citizens. Since the vegetation, fauna, water, and soil together with the services they support are directly affected, the air quality becomes a primary challenge for cities. This work shows the tendencies of the air pollution levels for two cities, namely the city of Sofia, Bulgaria and the city of Guadalajara, México. We performed a first correlation analysis in order to find emission patterns and display similar characteristics in both cities as well as to cooperate in jointly strategies to improve the air quality.
{"title":"Air quality monitoring and correlation: a use case of Sofia and Guadalajara","authors":"D. Petrova-Antonova, Olga B. Mora Sánchez, Víctor M. Larios-Rosillo, M. M. Z. Ramirez","doi":"10.1109/ISC246665.2019.9071659","DOIUrl":"https://doi.org/10.1109/ISC246665.2019.9071659","url":null,"abstract":"Air pollution in urban areas has increased exponentially in recent years, causing cardiovascular, respiratory, endocrine and oncology diseases, reducing the quality of life of citizens. Since the vegetation, fauna, water, and soil together with the services they support are directly affected, the air quality becomes a primary challenge for cities. This work shows the tendencies of the air pollution levels for two cities, namely the city of Sofia, Bulgaria and the city of Guadalajara, México. We performed a first correlation analysis in order to find emission patterns and display similar characteristics in both cities as well as to cooperate in jointly strategies to improve the air quality.","PeriodicalId":306836,"journal":{"name":"2019 IEEE International Smart Cities Conference (ISC2)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132982691","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：