Pub Date : 2018-11-01DOI: 10.1109/ICET.2018.8603645
Zunaira Sattar, Shazia Riaz, Shafia, A. U. Mian
With the progressing technology there is a new breed of crimes that is capable of crossing geographical boundaries. Regulatory authorities and legal reforms do not have much capacity to control these crimes. Pakistan as developing country, is determined to follow legal and regulatory frameworks to control cyber terrorism. With emergence of 4G technology, people of Pakistan are venturing into online business and social media entertainment or communication, with rising number of cybercrimes every day. The need to completely eliminate cybercrimes hazard is becoming more important. This study is conducted on the subjects which were either part of victimization by cybercrimes or could identify some of the steps to stop cyberterrorism. The reasons include lack of awareness about cybercrimes, unemployment, lack of education and less implementation of cyber laws. The effects of cybercrimes on the society include reducing the personal growth of people both moral and economical, wastage of time and misrepresentation to the country’s image. It also includes financial damages to large business. This research also focuses the awareness regarding offences to control the cybercrimes in Pakistan in context with legal reforms and cyber laws. Cyber act is the law for prevention of electronic crime act 2016. There is strong need of increasing social campaigns and against cybercrimes. People should adopt strong security measures to prevent themselves from cyber thieves.
{"title":"Challenges of Cybercrimes to Implementation of Legal Framework","authors":"Zunaira Sattar, Shazia Riaz, Shafia, A. U. Mian","doi":"10.1109/ICET.2018.8603645","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603645","url":null,"abstract":"With the progressing technology there is a new breed of crimes that is capable of crossing geographical boundaries. Regulatory authorities and legal reforms do not have much capacity to control these crimes. Pakistan as developing country, is determined to follow legal and regulatory frameworks to control cyber terrorism. With emergence of 4G technology, people of Pakistan are venturing into online business and social media entertainment or communication, with rising number of cybercrimes every day. The need to completely eliminate cybercrimes hazard is becoming more important. This study is conducted on the subjects which were either part of victimization by cybercrimes or could identify some of the steps to stop cyberterrorism. The reasons include lack of awareness about cybercrimes, unemployment, lack of education and less implementation of cyber laws. The effects of cybercrimes on the society include reducing the personal growth of people both moral and economical, wastage of time and misrepresentation to the country’s image. It also includes financial damages to large business. This research also focuses the awareness regarding offences to control the cybercrimes in Pakistan in context with legal reforms and cyber laws. Cyber act is the law for prevention of electronic crime act 2016. There is strong need of increasing social campaigns and against cybercrimes. People should adopt strong security measures to prevent themselves from cyber thieves.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"55 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":"121999387","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/ICET.2018.8603627
A. Raza, Irfan ul Haq, Usman Shaukat
Although Cloud services support wide range of mobile applications, access to Cloud services suffer from several performance issues such as WAN latency, jitter, and packet loss. Frameworks based on the concept known as Edge Computing, Fog Computing or Cloudlet have been proposed to overcome these performance issues. More specifically, Cloud Edge or Cloudlet aims to bring the Cloud or a specific part of the Cloud closer to the mobile device by utilizing proximate computing resources to augment mobile devices. In our proposed framework AD-LET, proximate mobile devices come together to share their resources and create a Cloudlet. AD-LET is self-managing, scalable and can share resources among different types of mobile devices. Experimental results have shown that AD-LET can significantly improves the capability of a mobile device. It augments mobile device thus enabling it to perform resource intensive tasks in the absence of a Cloud or near by infrastructure resources. The layered structure of our framework makes it extensible and allows it to support many types of services and application frameworks.
{"title":"Cloudlet-based Augmentation of Mobile Devices","authors":"A. Raza, Irfan ul Haq, Usman Shaukat","doi":"10.1109/ICET.2018.8603627","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603627","url":null,"abstract":"Although Cloud services support wide range of mobile applications, access to Cloud services suffer from several performance issues such as WAN latency, jitter, and packet loss. Frameworks based on the concept known as Edge Computing, Fog Computing or Cloudlet have been proposed to overcome these performance issues. More specifically, Cloud Edge or Cloudlet aims to bring the Cloud or a specific part of the Cloud closer to the mobile device by utilizing proximate computing resources to augment mobile devices. In our proposed framework AD-LET, proximate mobile devices come together to share their resources and create a Cloudlet. AD-LET is self-managing, scalable and can share resources among different types of mobile devices. Experimental results have shown that AD-LET can significantly improves the capability of a mobile device. It augments mobile device thus enabling it to perform resource intensive tasks in the absence of a Cloud or near by infrastructure resources. The layered structure of our framework makes it extensible and allows it to support many types of services and application frameworks.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"52 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":"122283947","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/ICET.2018.8603550
Hussain S. Khawaja, M. O. Beg, Saira Qamar
Emotion Classification using lexicons has vast number of applications ranging from social media analysis to pervasive computing. Lexicons are usually hand-crafted and cost a lot of time and effort to generate. The major research challenge in this area is the creation of a generalized lexicon which serves well for every domain. This work focuses on automatic expansion of emotion lexicons to ease the process of domain adaption. Our proposed approach — CB-Lex — relies on a seed lexicon and an unlabeled corpus from the target domain. In experimental results, our expanded lexicons show an improvement of over 6% in F-Measure.
{"title":"Domain Specific Emotion Lexicon Expansion","authors":"Hussain S. Khawaja, M. O. Beg, Saira Qamar","doi":"10.1109/ICET.2018.8603550","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603550","url":null,"abstract":"Emotion Classification using lexicons has vast number of applications ranging from social media analysis to pervasive computing. Lexicons are usually hand-crafted and cost a lot of time and effort to generate. The major research challenge in this area is the creation of a generalized lexicon which serves well for every domain. This work focuses on automatic expansion of emotion lexicons to ease the process of domain adaption. Our proposed approach — CB-Lex — relies on a seed lexicon and an unlabeled corpus from the target domain. In experimental results, our expanded lexicons show an improvement of over 6% in F-Measure.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"380 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":"116566840","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/ICET.2018.8603637
M. Basit, R. Badar
Hybrid power systems are now extensively being used due to their low fuel consumption and greater efficiency. In this context, fuel cell integration with conventional power sources is becoming an interesting solution. Choice of fuel cell as power source also serves to address many environmental concerns. Energy Management Schemes (EMSs) have great influence on dynamic performance and fuel consumption of these sources. EMS controls the power split between different energy sources to fulfill the power demand at load. In this paper, comparative analysis of different NeuroFuzzy based EMSs for emergency landing scenario of More Electric Air-Craft is presented. The performance validity of online adaptive NeuroFuzzy Wavelet Control has been checked against conventional NeuroFuzzy Takagi Sugeno Kang (TSK) control and classical PI control. State of the charge of battery and supercapacitor, fuel consumption and overall system efficiency have been chosen as performance metrics.
{"title":"Online Adaptive NeuroFuzzy Based Energy Management Schemes for Fuel-Cell Based Hybrid Power System","authors":"M. Basit, R. Badar","doi":"10.1109/ICET.2018.8603637","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603637","url":null,"abstract":"Hybrid power systems are now extensively being used due to their low fuel consumption and greater efficiency. In this context, fuel cell integration with conventional power sources is becoming an interesting solution. Choice of fuel cell as power source also serves to address many environmental concerns. Energy Management Schemes (EMSs) have great influence on dynamic performance and fuel consumption of these sources. EMS controls the power split between different energy sources to fulfill the power demand at load. In this paper, comparative analysis of different NeuroFuzzy based EMSs for emergency landing scenario of More Electric Air-Craft is presented. The performance validity of online adaptive NeuroFuzzy Wavelet Control has been checked against conventional NeuroFuzzy Takagi Sugeno Kang (TSK) control and classical PI control. State of the charge of battery and supercapacitor, fuel consumption and overall system efficiency have been chosen as performance metrics.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"1 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":"131292378","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/ICET.2018.8603585
Marium Nafees, H. Dar, I. Lali, Salman Tiwana
Sentiment analysis is the study area in Natural language processing (NLP) that is concerned to identify the mood or opinion with in the text. This paper emphasizes on the different methods utilized for classifying the natural language text reviews in accordance with opinions expressed in text to analyze whether the extensive behavior is negative, positive or neutral. The abundance of discussion platforms, Weblogs, product reviews sites, e-commerce and social networking sites have encouraged stream of thoughts and articulation of opinions. Social media is considered to be a big platform of sentiments, reviews and opinion evaluation. Data used in this study are online product reviews collected from twitter and used to rank the best classifier for sentiments. The method of analysis on polarity classification was discussed in experimental work by using well known classifiers including Naïve byes, Support vector machine and Logistic regression for predicting the user reviews.
{"title":"Sentiment Analysis of Polarity in Product Reviews In Social Media","authors":"Marium Nafees, H. Dar, I. Lali, Salman Tiwana","doi":"10.1109/ICET.2018.8603585","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603585","url":null,"abstract":"Sentiment analysis is the study area in Natural language processing (NLP) that is concerned to identify the mood or opinion with in the text. This paper emphasizes on the different methods utilized for classifying the natural language text reviews in accordance with opinions expressed in text to analyze whether the extensive behavior is negative, positive or neutral. The abundance of discussion platforms, Weblogs, product reviews sites, e-commerce and social networking sites have encouraged stream of thoughts and articulation of opinions. Social media is considered to be a big platform of sentiments, reviews and opinion evaluation. Data used in this study are online product reviews collected from twitter and used to rank the best classifier for sentiments. The method of analysis on polarity classification was discussed in experimental work by using well known classifiers including Naïve byes, Support vector machine and Logistic regression for predicting the user reviews.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"2 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":"123042673","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/ICET.2018.8603612
Anam Rasool, Muqudas Rafiq, Aisha Nasir, Faisal M. Kashif
Continuous and noninvasive monitoring of blood pressure is of vital importance in critical care. Its role in management of patients with or at risk of cardiovascular disease is ever increasing. Pulse-transit-time based approaches for estimation of blood pressure hold potential to provide a convenient solution, however there is a need to improve their accuracy. We employ a novel two-sensor technique using photoplethysmogram and piezo sensors for a more accurate measurement of pulse transit time (PTT). PTT is then mapped to arterial blood pressure via calibration process. We implement two different techniques for the PTT measurement. The first technique uses two pulse sensors, while the second technique makes use of one pulse sensor and one piezo element. Clinical data is collected from 46 subjects in the form of systolic, diastolic and mean blood pressure to provide a reference for the calibration step in two techniques. The results show decrease in error of systolic arterial pressure (SAP) and mean arterial pressure (MAP) for the second technique. The root mean square (RMS) error, measured for the calibration equations, reduced from 7.72 mm Hg to 5.26 mm Hg for SAP and from 7.07 mm Hg to 6.30 mm Hg for MAP. RMS error, measured by leave-one-out method, reduced from 8.45 mm Hg to 5.77 mm Hg for SAP and from 7.67 mm Hg to 6.90 mm Hg for MAP.
在重症监护中,持续无创监测血压是至关重要的。它在管理心血管疾病患者或有心血管疾病风险的患者中的作用越来越大。基于脉冲传递时间的血压估计方法有可能提供一种方便的解决方案,但是需要提高其准确性。我们采用了一种新的双传感器技术,使用光电容积图和压电传感器来更准确地测量脉冲传递时间(PTT)。然后通过校准过程将PTT映射到动脉血压。我们实现了两种不同的PTT测量技术。第一种技术使用两个脉冲传感器,而第二种技术使用一个脉冲传感器和一个压电元件。收集46名受试者的收缩压、舒张压和平均血压的临床数据,为两种技术的校准步骤提供参考。结果表明,第二种方法的收缩压(SAP)和平均动脉压(MAP)误差减小。校准方程测量的均方根误差(RMS)从SAP的7.72毫米汞柱降至5.26毫米汞柱,MAP的7.07毫米汞柱降至6.30毫米汞柱。采用留一法测量的均方根误差,SAP从8.45 mm Hg降至5.77 mm Hg, MAP从7.67 mm Hg降至6.90 mm Hg。
{"title":"Continuous and Noninvasive Blood Pressure Estimation by Two-Sensor Measurement of Pulse Transit Time","authors":"Anam Rasool, Muqudas Rafiq, Aisha Nasir, Faisal M. Kashif","doi":"10.1109/ICET.2018.8603612","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603612","url":null,"abstract":"Continuous and noninvasive monitoring of blood pressure is of vital importance in critical care. Its role in management of patients with or at risk of cardiovascular disease is ever increasing. Pulse-transit-time based approaches for estimation of blood pressure hold potential to provide a convenient solution, however there is a need to improve their accuracy. We employ a novel two-sensor technique using photoplethysmogram and piezo sensors for a more accurate measurement of pulse transit time (PTT). PTT is then mapped to arterial blood pressure via calibration process. We implement two different techniques for the PTT measurement. The first technique uses two pulse sensors, while the second technique makes use of one pulse sensor and one piezo element. Clinical data is collected from 46 subjects in the form of systolic, diastolic and mean blood pressure to provide a reference for the calibration step in two techniques. The results show decrease in error of systolic arterial pressure (SAP) and mean arterial pressure (MAP) for the second technique. The root mean square (RMS) error, measured for the calibration equations, reduced from 7.72 mm Hg to 5.26 mm Hg for SAP and from 7.07 mm Hg to 6.30 mm Hg for MAP. RMS error, measured by leave-one-out method, reduced from 8.45 mm Hg to 5.77 mm Hg for SAP and from 7.67 mm Hg to 6.90 mm Hg for MAP.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"134 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":"127927464","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/ICET.2018.8603652
Muhammad Adeel Hafeez, S. Shakil, Sobia Jangsher
Mental stress can be one of the most prominent factors of failure or poor performance in students. The traditional method of examination involves evaluating performance of students in limited time that may increase their stress level and may deteriorate their performance. Electroencephalogram (EEG) is one of the most commonly used methods to measure stress using brain waves. In this study, we investigate the influence of time limitation in exam on the performance of students and use EEG to explore the contribution of stress towards the change in performance. For this purpose, students performed mental arithmetic task (MAT) based on Montreal Imaging Stress Task of same difficulty level twice; once with time limitation accompanied by feedback for every question to induce stress and once without any time limitation and feedback. We observe vast difference in performance of the students for the two MAT tests and significant change in the power spectral density of theta, alpha, and beta frequency bands associated with increase in stress level for three chosen electrodes in EEG results. Our results show that stress may be one of the major factors for bad performance of the students in the exam resulting in failure.
{"title":"Stress Effects on Exam Performance using EEG","authors":"Muhammad Adeel Hafeez, S. Shakil, Sobia Jangsher","doi":"10.1109/ICET.2018.8603652","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603652","url":null,"abstract":"Mental stress can be one of the most prominent factors of failure or poor performance in students. The traditional method of examination involves evaluating performance of students in limited time that may increase their stress level and may deteriorate their performance. Electroencephalogram (EEG) is one of the most commonly used methods to measure stress using brain waves. In this study, we investigate the influence of time limitation in exam on the performance of students and use EEG to explore the contribution of stress towards the change in performance. For this purpose, students performed mental arithmetic task (MAT) based on Montreal Imaging Stress Task of same difficulty level twice; once with time limitation accompanied by feedback for every question to induce stress and once without any time limitation and feedback. We observe vast difference in performance of the students for the two MAT tests and significant change in the power spectral density of theta, alpha, and beta frequency bands associated with increase in stress level for three chosen electrodes in EEG results. Our results show that stress may be one of the major factors for bad performance of the students in the exam resulting in failure.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"9 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":"127407783","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/ICET.2018.8603551
Maryam Iqbal, A. Mahmood
A control paradigm can be created by the coordinated movement of the fingers with the central nervous system. In this paper we added a structured uncertainty to a system to study and investigate a biomechanical model of reflexive movement of human ring finger when the little finger is bent. We then applied a robust feedback H∞ control synthesisd by combining a full order estimator with a full information controller to achieve stable results. Structured uncertainties have been incorporated using µ-synthesis. Analysis with the help of µ-synthesis generates a better modeling and control strategy for a movement coordination of human fingers. We also introduced the reference input tracking problem for the model. We simulated the model for studying stability analysis and for comparison of performance. The simulation results help in understanding the coordination of human fingers with central nervous system which can be utilized in application of active prosthetics.
{"title":"Structured Uncertainty Modeling, Control Synthesis & Tracking of Coordinated Fingers Movement","authors":"Maryam Iqbal, A. Mahmood","doi":"10.1109/ICET.2018.8603551","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603551","url":null,"abstract":"A control paradigm can be created by the coordinated movement of the fingers with the central nervous system. In this paper we added a structured uncertainty to a system to study and investigate a biomechanical model of reflexive movement of human ring finger when the little finger is bent. We then applied a robust feedback H∞ control synthesisd by combining a full order estimator with a full information controller to achieve stable results. Structured uncertainties have been incorporated using µ-synthesis. Analysis with the help of µ-synthesis generates a better modeling and control strategy for a movement coordination of human fingers. We also introduced the reference input tracking problem for the model. We simulated the model for studying stability analysis and for comparison of performance. The simulation results help in understanding the coordination of human fingers with central nervous system which can be utilized in application of active prosthetics.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","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":"128777071","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/ICET.2018.8603597
Sofia Yousuf, M. Kadri
Robot Localization (robot pose determination) has become an important aspect for a variety of tasks accomplished by mobile robots. Also accurate localization is required for robot tracking, path planning and control. Today, many sensor technologies are utilized to determine the exact robot location, for instance, in indoor environments, odometers (wheel encoders) and inertial navigation system (INS) are used to ascertain the relative position and pose of the robot. In outdoor environments, Global Positioning System (GPS) can also be integrated in the sensor suite to determine the actual position of the robot in terms of latitude and longitude. This paper presents a robust methodology for robot localization in indoor as well as outdoor environments by a mechanism known as "data fusion" of multiple sensors also called Multi-Sensor Fusion (MSF) or Information Fusion (IF). In, outdoor environments, the sensor information collected from the embedded INS and GPS modules on mobile test robot are fused using a recursive state estimation and fusion algorithm known as Kalman Filter (KF). The estimated position obtained using KF is then combined with odometer based position data using weighting scheme to obtain the final position estimate of the robot. The main contribution of this work is to employ a multi-layer perceptron neural network (MLP-NN) to provide robot position estimates in an indoor environment where GPS signals are blocked. The MLP-NN is trained when the GPS data is available. As soon as the GPS signals are lost the trained MLP-NN provides predictions regarding the current position of robot. The proposed scheme is tested on the GPS-INS data obtained from on board sensors attached to a mobile robot. Simulation results have been presented which establish the efficacy of the proposed scheme.
{"title":"Robot Localization in Indoor and Outdoor Environments by Multi-sensor Fusion","authors":"Sofia Yousuf, M. Kadri","doi":"10.1109/ICET.2018.8603597","DOIUrl":"https://doi.org/10.1109/ICET.2018.8603597","url":null,"abstract":"Robot Localization (robot pose determination) has become an important aspect for a variety of tasks accomplished by mobile robots. Also accurate localization is required for robot tracking, path planning and control. Today, many sensor technologies are utilized to determine the exact robot location, for instance, in indoor environments, odometers (wheel encoders) and inertial navigation system (INS) are used to ascertain the relative position and pose of the robot. In outdoor environments, Global Positioning System (GPS) can also be integrated in the sensor suite to determine the actual position of the robot in terms of latitude and longitude. This paper presents a robust methodology for robot localization in indoor as well as outdoor environments by a mechanism known as \"data fusion\" of multiple sensors also called Multi-Sensor Fusion (MSF) or Information Fusion (IF). In, outdoor environments, the sensor information collected from the embedded INS and GPS modules on mobile test robot are fused using a recursive state estimation and fusion algorithm known as Kalman Filter (KF). The estimated position obtained using KF is then combined with odometer based position data using weighting scheme to obtain the final position estimate of the robot. The main contribution of this work is to employ a multi-layer perceptron neural network (MLP-NN) to provide robot position estimates in an indoor environment where GPS signals are blocked. The MLP-NN is trained when the GPS data is available. As soon as the GPS signals are lost the trained MLP-NN provides predictions regarding the current position of robot. The proposed scheme is tested on the GPS-INS data obtained from on board sensors attached to a mobile robot. Simulation results have been presented which establish the efficacy of the proposed scheme.","PeriodicalId":443353,"journal":{"name":"2018 14th International Conference on Emerging Technologies (ICET)","volume":"7 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":"114937138","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}