Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200038
Md. Atiqur Rahman, Pankaj Sarkar
In this paper, a dual-mode bandpass filter based on substrate integrated waveguide (SIW) is presented. Initially, a SIW cavity is designed at higher frequency range. The stepped impedance resonator (SIR) slots are embedded as a slot on the top of the cavity structure. Four SIR slots are etched on the top surface of the cavity which helps to eliminate the higher resonating modes of the cavity. The pass band is centered at 4.7 GHz to pass the WLAN band. The resonating slots generated dual mode characteristics with excellent selectivity. The stop band characteristic of the proposed filter is also satisfactory for mitigation of higher order modes. The proposed structure is EM-simulated to verify the theoretical analysis.
{"title":"A Novel Compact Dual-Mode Substrate Integrated Waveguide Cavity based Bandpass Filter for WLAN Applications","authors":"Md. Atiqur Rahman, Pankaj Sarkar","doi":"10.1109/ComPE49325.2020.9200038","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200038","url":null,"abstract":"In this paper, a dual-mode bandpass filter based on substrate integrated waveguide (SIW) is presented. Initially, a SIW cavity is designed at higher frequency range. The stepped impedance resonator (SIR) slots are embedded as a slot on the top of the cavity structure. Four SIR slots are etched on the top surface of the cavity which helps to eliminate the higher resonating modes of the cavity. The pass band is centered at 4.7 GHz to pass the WLAN band. The resonating slots generated dual mode characteristics with excellent selectivity. The stop band characteristic of the proposed filter is also satisfactory for mitigation of higher order modes. The proposed structure is EM-simulated to verify the theoretical analysis.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"46 1","pages":"059-061"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82128254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200062
B. Saha, Apurbalal Senapati, Anmol Mahajan
This work presents the sentiment analysis of the political news articles in Bengali. This domain is quite complicated, because the political news is subjective and depends on several socio economic factors and largely over the geographical areas, communities, etc. The work is conducted in two steps the pre-processing and the classifications. In the pre-processing phase, the data is prepared. It is an automated process, which collects data from the web and identifies the relevant news article. A special type of Recurrent Neural Network (RNN) based deep learning approach called Long Short Term Memory (LSTM) is used for election sentiment classification and the result is compared with other supervised classifiers like Naive Bayes, SVM, and Decision Tree. Different types of word embedding models are compared for election sentiment analysis. Results demonstrate that LSTM based deep RNN architecture with context encoder provides 85% of accuracy which dominates others. The result shows that it is close to the existing state-of-the-art and it also gives very attractive insights.
{"title":"LSTM based Deep RNN Architecture for Election Sentiment Analysis from Bengali Newspaper","authors":"B. Saha, Apurbalal Senapati, Anmol Mahajan","doi":"10.1109/ComPE49325.2020.9200062","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200062","url":null,"abstract":"This work presents the sentiment analysis of the political news articles in Bengali. This domain is quite complicated, because the political news is subjective and depends on several socio economic factors and largely over the geographical areas, communities, etc. The work is conducted in two steps the pre-processing and the classifications. In the pre-processing phase, the data is prepared. It is an automated process, which collects data from the web and identifies the relevant news article. A special type of Recurrent Neural Network (RNN) based deep learning approach called Long Short Term Memory (LSTM) is used for election sentiment classification and the result is compared with other supervised classifiers like Naive Bayes, SVM, and Decision Tree. Different types of word embedding models are compared for election sentiment analysis. Results demonstrate that LSTM based deep RNN architecture with context encoder provides 85% of accuracy which dominates others. The result shows that it is close to the existing state-of-the-art and it also gives very attractive insights.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"22 1","pages":"564-569"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83198816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200131
Jay P. Singh, Kishorjit Nongmeikapam
It is a known fact that on the daily basis significant amount of information is produced due to large number of people being connected to social networking sites. Online interaction is now included in our lifestyle whether it is through a tweet, a message or through commenting on each other posts on different platforms. Online interaction contributes a significant part to our society but also contains several dangerous results. This paper mainly focuses on the cons of social interaction and a way through which it can be decreased. Aggression and related activities such as trolling peoples, harassing online involves hate comments in various forms. There are numerous such cases coming in present time and sites respond by closing down their remark areas. After the introduction of Machine Learning and having data in massive amount now its quite logical to build a tool which can tackle this situation. While there are algorithmic solution for these probelm but they are slow and expensive which make us curious about new approaches and frameworks. Four models are used for the purpose of classifying the comments, however the model which performed better than other three is Bi-LSTM + Bi-GRU model with accuracy of 97.89.
{"title":"Negative Comments Multi-Label Classification","authors":"Jay P. Singh, Kishorjit Nongmeikapam","doi":"10.1109/ComPE49325.2020.9200131","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200131","url":null,"abstract":"It is a known fact that on the daily basis significant amount of information is produced due to large number of people being connected to social networking sites. Online interaction is now included in our lifestyle whether it is through a tweet, a message or through commenting on each other posts on different platforms. Online interaction contributes a significant part to our society but also contains several dangerous results. This paper mainly focuses on the cons of social interaction and a way through which it can be decreased. Aggression and related activities such as trolling peoples, harassing online involves hate comments in various forms. There are numerous such cases coming in present time and sites respond by closing down their remark areas. After the introduction of Machine Learning and having data in massive amount now its quite logical to build a tool which can tackle this situation. While there are algorithmic solution for these probelm but they are slow and expensive which make us curious about new approaches and frameworks. Four models are used for the purpose of classifying the comments, however the model which performed better than other three is Bi-LSTM + Bi-GRU model with accuracy of 97.89.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"54 1","pages":"379-385"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90840987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200149
Pooja Batra, A. Jatain
Software Development has gone through a long journey from waterfall to DevOps. This journey includes Agile methodologies, Continuous Integration, Continuous Delivery and Continuous Deployment approach. With time IT organizations realized that recent approaches are better than traditional approaches in every manner. Recent trends like DevOps are very popular among software industry, still facing many challenges. Performance Evaluation is one of the biggest challenges in this approach. In this paper we shall deal with this challenge by not only introducing measurement-based quality attributes but also evaluating the same. To achieve this objective DevOps implementation will be done and a comparative analysis with traditional method will be executed to show desired targets.
{"title":"Measurement Based Performance Evaluation of DevOps","authors":"Pooja Batra, A. Jatain","doi":"10.1109/ComPE49325.2020.9200149","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200149","url":null,"abstract":"Software Development has gone through a long journey from waterfall to DevOps. This journey includes Agile methodologies, Continuous Integration, Continuous Delivery and Continuous Deployment approach. With time IT organizations realized that recent approaches are better than traditional approaches in every manner. Recent trends like DevOps are very popular among software industry, still facing many challenges. Performance Evaluation is one of the biggest challenges in this approach. In this paper we shall deal with this challenge by not only introducing measurement-based quality attributes but also evaluating the same. To achieve this objective DevOps implementation will be done and a comparative analysis with traditional method will be executed to show desired targets.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"40 1","pages":"757-760"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90212273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200013
C. Kalita, Maushumi Barooah
An adhoc network comprising of an assembly of vehicles irrespective of it being stationary or mobile constitutes Vehicular ad hoc networks (VANET). Traditionally VANET has been exploited for safety of drivers and pedestrians on the road, but now is been also utilized as an infrastructure for intelligent transport systems(ITS).Communication in VANET has always led to frequent handoffs as it is dependent on the vehicular speed along with the number of road side units(RSU)present and the available bandwidth range. These frequent handoffs may affect the throughput, packet delivery and quality of services (QoS). This paper presents detailed taxonomy of different handover processes in VANET and has laid down a comparative study based on their characteristics and features. A scheme has been presented in this paper on Light Fidelity (Li-Fi) based handover scheme involving decision making qualities. The simulation results for the proposed scheme has also been put forward and compared with a state of art hybrid works.
{"title":"Li-Fi Based Handoff Technique in VANET","authors":"C. Kalita, Maushumi Barooah","doi":"10.1109/ComPE49325.2020.9200013","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200013","url":null,"abstract":"An adhoc network comprising of an assembly of vehicles irrespective of it being stationary or mobile constitutes Vehicular ad hoc networks (VANET). Traditionally VANET has been exploited for safety of drivers and pedestrians on the road, but now is been also utilized as an infrastructure for intelligent transport systems(ITS).Communication in VANET has always led to frequent handoffs as it is dependent on the vehicular speed along with the number of road side units(RSU)present and the available bandwidth range. These frequent handoffs may affect the throughput, packet delivery and quality of services (QoS). This paper presents detailed taxonomy of different handover processes in VANET and has laid down a comparative study based on their characteristics and features. A scheme has been presented in this paper on Light Fidelity (Li-Fi) based handover scheme involving decision making qualities. The simulation results for the proposed scheme has also been put forward and compared with a state of art hybrid works.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"29 1 1","pages":"654-658"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90442975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200046
G. Amruta, R. Kumar
A patch antenna preferred for the utilization of ultra wide-band operations is designed to enhance its characteristics and it is based on the compound right-left handed transmission process. This antenna model will be designed using the concept of metamaterials and practically simulated using HFSS (High-Frequency Structural Simulator) software. Here three left-handed metamaterial split-rings are aligned in one axis to bring a single convention patch to a different version. This split-ring resonator is refashioned a little bit from the original pattern and used along with capacitively loaded strips. Besides a coplanar waveguide is introduced along the sides of the feed line to decrease the trace width that can lead to some distortions in the transmission line. The main objective involved in this work is to represent a simple patch antenna by shaping its patch in such a manner to improve gain and bandwidth that will produce a better quality factor.
{"title":"Enhancing the Performance Characteristic of Patch Antenna using Split-Ring Resonator Metamaterial","authors":"G. Amruta, R. Kumar","doi":"10.1109/ComPE49325.2020.9200046","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200046","url":null,"abstract":"A patch antenna preferred for the utilization of ultra wide-band operations is designed to enhance its characteristics and it is based on the compound right-left handed transmission process. This antenna model will be designed using the concept of metamaterials and practically simulated using HFSS (High-Frequency Structural Simulator) software. Here three left-handed metamaterial split-rings are aligned in one axis to bring a single convention patch to a different version. This split-ring resonator is refashioned a little bit from the original pattern and used along with capacitively loaded strips. Besides a coplanar waveguide is introduced along the sides of the feed line to decrease the trace width that can lead to some distortions in the transmission line. The main objective involved in this work is to represent a simple patch antenna by shaping its patch in such a manner to improve gain and bandwidth that will produce a better quality factor.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"04 1","pages":"367-370"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75916935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200042
Preity, N. Jayanthi
Retinal blood vessels are one of the most significant features in the fundus image of the eye, which plays a crucial role in the early screening of different ocular diseases like glaucoma, diabetic retinopathy, cataract and hypertensive retinopathy. Also in the area of biometric systems, blood vessel structure plays a vital role as retina scan is one of the finest and reliable methods. This paper proposed a segmentation technique which accurately extracts retinal blood vessels. The proposed algorithm conducted in three phases (i) pre -processing of image using AHE, CLAHE and average filtering, (ii) Multi-threshold based novel segmentation technique is used and (iii) post processing is done to remove the imperfections and for this morphological operation is employed. This method efficiently segments the vessels and improves the performance parameters. The accuracy of 95.3% is achieved. Implementation part was done in MATLAB 2015a using a DRIVE database openly available online.
{"title":"A Segmentation Technique of Retinal Blood Vessels using Multi-Threshold and Morphological Operations","authors":"Preity, N. Jayanthi","doi":"10.1109/ComPE49325.2020.9200042","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200042","url":null,"abstract":"Retinal blood vessels are one of the most significant features in the fundus image of the eye, which plays a crucial role in the early screening of different ocular diseases like glaucoma, diabetic retinopathy, cataract and hypertensive retinopathy. Also in the area of biometric systems, blood vessel structure plays a vital role as retina scan is one of the finest and reliable methods. This paper proposed a segmentation technique which accurately extracts retinal blood vessels. The proposed algorithm conducted in three phases (i) pre -processing of image using AHE, CLAHE and average filtering, (ii) Multi-threshold based novel segmentation technique is used and (iii) post processing is done to remove the imperfections and for this morphological operation is employed. This method efficiently segments the vessels and improves the performance parameters. The accuracy of 95.3% is achieved. Implementation part was done in MATLAB 2015a using a DRIVE database openly available online.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"26 1","pages":"447-452"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79061734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200089
Prachi Agrawal, T. Ganesh, A. W. Mohamed
This paper presents the application of gaining sharing knowledge (GSK) based optimization algorithm to an uncertain solid transportation (UST) problem. The UST problem consists of supply, demand, and conveyance constraints under uncertain environment. To solve the said problem, the expected criterion model is considered so that the expected value of the objective function is minimized. 99-method generates the expected value of the assumed uncertain variables, and the transformed problem is solved. Due to the consideration of integer decision variables, GSK is modified to integer gaining sharing knowledge based optimization algorithm (IGSK). IGSK, along with 99-method i.e., hybrid algorithm solves the considered problem. A numerical example illustrates the methodology, and the obtained results are compared with other metaheuristic algorithms and the global optimal solution. It indicates that the IGSK performs same as other metaheuristic algorithms in terms of convergence, ability of finding optimal solution, and robustness.
{"title":"Solution of Uncertain Solid Transportation Problem by Integer Gaining Sharing Knowledge Based Optimization Algorithm","authors":"Prachi Agrawal, T. Ganesh, A. W. Mohamed","doi":"10.1109/ComPE49325.2020.9200089","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200089","url":null,"abstract":"This paper presents the application of gaining sharing knowledge (GSK) based optimization algorithm to an uncertain solid transportation (UST) problem. The UST problem consists of supply, demand, and conveyance constraints under uncertain environment. To solve the said problem, the expected criterion model is considered so that the expected value of the objective function is minimized. 99-method generates the expected value of the assumed uncertain variables, and the transformed problem is solved. Due to the consideration of integer decision variables, GSK is modified to integer gaining sharing knowledge based optimization algorithm (IGSK). IGSK, along with 99-method i.e., hybrid algorithm solves the considered problem. A numerical example illustrates the methodology, and the obtained results are compared with other metaheuristic algorithms and the global optimal solution. It indicates that the IGSK performs same as other metaheuristic algorithms in terms of convergence, ability of finding optimal solution, and robustness.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"36 1","pages":"158-162"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83887552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200028
Sudhanshu Raj, Navpreet Kaur Walia
In today’s world, the usage of internet is everywhere. It plays an important part in the life of humans. As we all know that the Internet has made the life of humans much easier not only in personal but also in professional aspect. This ease in life has given birth to so many threats and flaws that are further giving access to the intruders known as ‘Hackers’ to enter in a user’s private space and perform some activities which can be very harmful for that particular user. In this paper, we will discuss about the Metasploit Framework tool which is always used by the Hackers & Pen-testers to perform activities i.e. from Scanning to exploiting the systems.
{"title":"A Study on Metasploit Framework: A Pen-Testing Tool","authors":"Sudhanshu Raj, Navpreet Kaur Walia","doi":"10.1109/ComPE49325.2020.9200028","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200028","url":null,"abstract":"In today’s world, the usage of internet is everywhere. It plays an important part in the life of humans. As we all know that the Internet has made the life of humans much easier not only in personal but also in professional aspect. This ease in life has given birth to so many threats and flaws that are further giving access to the intruders known as ‘Hackers’ to enter in a user’s private space and perform some activities which can be very harmful for that particular user. In this paper, we will discuss about the Metasploit Framework tool which is always used by the Hackers & Pen-testers to perform activities i.e. from Scanning to exploiting the systems.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"19 1","pages":"296-302"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88404885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9199993
Suma Dawn, Utkarsh Saraogi, Utkarsh Singh Thakur
Virtual reality is a field that can be widely explored for sustainability requirements. In this work, a virtual city environment was developed with intend to help city navigation especially by personnel with special abilities, mainly while traveling. They may need assistance to perform such daily tasks. The goal is to build an agent that can be trained to help guide daily commute from a given source to destination, optimizing for a minimum possible time as well as avoiding multiple obstacles. Real-time traffic and crowd were simulated to train learning agents. Apart from using the shortest path, factors such as following traffic rules and avoiding accidents with obstacles are also considered. The agent must be trained in order to avoid heavy traffic and change its path to reach the goal taking minimum time, not just the shortest distance. By using machine learning gents and simulations, training of the agent using reinforcement learning has been achieved. Identification of certain unsafe paths and behaviors have also been considered for simulation and learning purposes. Custom scenarios to mitigate the risks before actual accidents happen have been created for understanding and further resolution. Agent-based learning for successful space exploration is established on the relationship parameter between actions and the virtual environment. Initially, the agent explores the virtual city on its own and interacts with numerous components of the environment. The main objective of the agent is to reach its goal following the reward system, as used in a game environment. Maximization of the score using these parameters helps in training the agent. Route learning is also considered to facilitate backtracking wherein the obstacles are placed in the route. The virtual environment, so created, then has an agent that depicts that shorted, safe and accident-free path for a person to reach his or her destination from a given source point. The city has numerous parameters of an actual live city of building, paths, and unruly movements, amongst others.
{"title":"Agent-based Learning for Auto-Navigation within the Virtual City","authors":"Suma Dawn, Utkarsh Saraogi, Utkarsh Singh Thakur","doi":"10.1109/ComPE49325.2020.9199993","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9199993","url":null,"abstract":"Virtual reality is a field that can be widely explored for sustainability requirements. In this work, a virtual city environment was developed with intend to help city navigation especially by personnel with special abilities, mainly while traveling. They may need assistance to perform such daily tasks. The goal is to build an agent that can be trained to help guide daily commute from a given source to destination, optimizing for a minimum possible time as well as avoiding multiple obstacles. Real-time traffic and crowd were simulated to train learning agents. Apart from using the shortest path, factors such as following traffic rules and avoiding accidents with obstacles are also considered. The agent must be trained in order to avoid heavy traffic and change its path to reach the goal taking minimum time, not just the shortest distance. By using machine learning gents and simulations, training of the agent using reinforcement learning has been achieved. Identification of certain unsafe paths and behaviors have also been considered for simulation and learning purposes. Custom scenarios to mitigate the risks before actual accidents happen have been created for understanding and further resolution. Agent-based learning for successful space exploration is established on the relationship parameter between actions and the virtual environment. Initially, the agent explores the virtual city on its own and interacts with numerous components of the environment. The main objective of the agent is to reach its goal following the reward system, as used in a game environment. Maximization of the score using these parameters helps in training the agent. Route learning is also considered to facilitate backtracking wherein the obstacles are placed in the route. The virtual environment, so created, then has an agent that depicts that shorted, safe and accident-free path for a person to reach his or her destination from a given source point. The city has numerous parameters of an actual live city of building, paths, and unruly movements, amongst others.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"12 1","pages":"007-012"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90142364","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：