Pub Date : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623207
Sayeda Islam Nahid, Navid Anjum, N. Chowdhury, Laila Tamanna Anni, M. Mahmud, Mohammad Monirujjaman Khan, R. H. Ashique
In comparison to firewood and charcoal, LPG is widely used as a source of fuel, mainly in urban regions. Due to the extremely combustible nature of the gas, there is always the risk of gas leakage as a consequence of carelessness or failure of the regulating valve on the gas cylinder, which poses a significant risk. Gas-related fires are on the rise, which may be prevented by utilizing a gas leakage detection system, necessitating the creation of a microcontroller-based cooking gas detector. The use of a microcontroller allows for the creation of a highly precise and quick reaction time detecting system. The detector includes a MQ-6 LPG gas sensor, a PIC16F690 microcontroller, an LCD, a buzzer, and a number of LEDs to learn about the gas leak's condition. When a voltage signal is present from the MQ-6 sensor exceeds a specific threshold, the microcontroller detects the presence of a gas and sends an audiovisual alert. All peripherals are linked to the microcontroller through its pins, which are coded in the PIC assembly language. When the system was turned on, the microcontroller turned on a green LED to indicate that there was no gas leakage. A digital multimeter is used to monitor the sensor voltage signal when LPG gas is discharged. Whenever the voltage is less than 2.0V, the green light remains illuminated; when the voltage is more than 2.0V, the microcontroller blinks a red LED and sounds an alarm to indicate the presence of a gas. The alert can be recognized by pressing a button on the sensor. When the system was turned on, the microcontroller turned on a green LED to indicate that there was no gas leakage. A digital multimeter is used to monitor the sensor voltage signal when LPG gas is discharged. Whenever the voltage is less than 2.0V, the green light remains illuminated; when the voltage is more than 2.0V, the microcontroller blinks a red LED and sounds an alarm to indicate the presence of a gas. The alert can be recognized by pressing a button on the sensor.
{"title":"Development of a Smart Automatic Gas Leakage Detector and Alarming System","authors":"Sayeda Islam Nahid, Navid Anjum, N. Chowdhury, Laila Tamanna Anni, M. Mahmud, Mohammad Monirujjaman Khan, R. H. Ashique","doi":"10.1109/iemcon53756.2021.9623207","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623207","url":null,"abstract":"In comparison to firewood and charcoal, LPG is widely used as a source of fuel, mainly in urban regions. Due to the extremely combustible nature of the gas, there is always the risk of gas leakage as a consequence of carelessness or failure of the regulating valve on the gas cylinder, which poses a significant risk. Gas-related fires are on the rise, which may be prevented by utilizing a gas leakage detection system, necessitating the creation of a microcontroller-based cooking gas detector. The use of a microcontroller allows for the creation of a highly precise and quick reaction time detecting system. The detector includes a MQ-6 LPG gas sensor, a PIC16F690 microcontroller, an LCD, a buzzer, and a number of LEDs to learn about the gas leak's condition. When a voltage signal is present from the MQ-6 sensor exceeds a specific threshold, the microcontroller detects the presence of a gas and sends an audiovisual alert. All peripherals are linked to the microcontroller through its pins, which are coded in the PIC assembly language. When the system was turned on, the microcontroller turned on a green LED to indicate that there was no gas leakage. A digital multimeter is used to monitor the sensor voltage signal when LPG gas is discharged. Whenever the voltage is less than 2.0V, the green light remains illuminated; when the voltage is more than 2.0V, the microcontroller blinks a red LED and sounds an alarm to indicate the presence of a gas. The alert can be recognized by pressing a button on the sensor. When the system was turned on, the microcontroller turned on a green LED to indicate that there was no gas leakage. A digital multimeter is used to monitor the sensor voltage signal when LPG gas is discharged. Whenever the voltage is less than 2.0V, the green light remains illuminated; when the voltage is more than 2.0V, the microcontroller blinks a red LED and sounds an alarm to indicate the presence of a gas. The alert can be recognized by pressing a button on the sensor.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132643645","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623124
Samaneh Madanian, David Airehrour, Nabilah Ahmad Samsuri, M. Cherrington
We have yet to realise the full capability of social media as an innovative information platform during emergencies and crisis response and management. Sentiment analysis can systematically identify, extract, and scrutinise emotional states and subjective information in social media data. Exploring reactions and perceptions to response messaging is invaluable and proved especially useful for a pandemic response as it can demonstrate general population reaction to the pandemic and governments response actions. This can be further analysed to identify the gap between government response actions and communications and citizens' perceptions. In this paper, an analysis of Twitter data explores population reaction towards COVID-19 health messaging. A Natural Language Processing Python tool is known as TextBlob was used to discover general data sentiment. Data were divided into three sentiments and text extraction of health messages was conducted to explore subsequent tweets in predefined categories. Our findings show the outcome of Tweets analysis could help us to identify the general population concerns and their reactions to COVID-19 to give a better understanding of the situation to governments and support them in implementing appropriate policies.
{"title":"Twitter Sentiment Analysis in Covid-19 Pandemic","authors":"Samaneh Madanian, David Airehrour, Nabilah Ahmad Samsuri, M. Cherrington","doi":"10.1109/iemcon53756.2021.9623124","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623124","url":null,"abstract":"We have yet to realise the full capability of social media as an innovative information platform during emergencies and crisis response and management. Sentiment analysis can systematically identify, extract, and scrutinise emotional states and subjective information in social media data. Exploring reactions and perceptions to response messaging is invaluable and proved especially useful for a pandemic response as it can demonstrate general population reaction to the pandemic and governments response actions. This can be further analysed to identify the gap between government response actions and communications and citizens' perceptions. In this paper, an analysis of Twitter data explores population reaction towards COVID-19 health messaging. A Natural Language Processing Python tool is known as TextBlob was used to discover general data sentiment. Data were divided into three sentiments and text extraction of health messages was conducted to explore subsequent tweets in predefined categories. Our findings show the outcome of Tweets analysis could help us to identify the general population concerns and their reactions to COVID-19 to give a better understanding of the situation to governments and support them in implementing appropriate policies.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131643593","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623159
A. A. AlQahtani, Zakaria El-Awadi, Manki Min
Today, digital information decisively permeates all aspects of modern society. In such a connected world, one of the critical factors in maintaining the security of transmitted data is user authentication, which establishes confidence in the user identities presented to an information system. Over time, the definition of user authentication has not changed; however, a simple password is no longer the only factor used for authenticating a user. Two-factor Authentication (2FA) and Multi-factor Authentication (MFA) were proposed to provide a high level of security by adding more than one layer of authentication. For the most part, these layers of Authentication are based on knowledge, ownership, biometrics, and/or users' behaviors. This paper presents and analyzes authentication factors that are utilized to authenticate a user and prove his/her identity to a resource.
{"title":"A Survey on User Authentication Factors","authors":"A. A. AlQahtani, Zakaria El-Awadi, Manki Min","doi":"10.1109/iemcon53756.2021.9623159","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623159","url":null,"abstract":"Today, digital information decisively permeates all aspects of modern society. In such a connected world, one of the critical factors in maintaining the security of transmitted data is user authentication, which establishes confidence in the user identities presented to an information system. Over time, the definition of user authentication has not changed; however, a simple password is no longer the only factor used for authenticating a user. Two-factor Authentication (2FA) and Multi-factor Authentication (MFA) were proposed to provide a high level of security by adding more than one layer of authentication. For the most part, these layers of Authentication are based on knowledge, ownership, biometrics, and/or users' behaviors. This paper presents and analyzes authentication factors that are utilized to authenticate a user and prove his/her identity to a resource.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131649388","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623221
Robert Morris, Shahnam Mirzaei
This paper presents an efficient color based tracking method applied on a sequence of live video frames for use in real time applications such as surveillance, video conferencing, and robot navigation. The proposed integrated system architecture consists of an attached camera that communicates with the FPGA through HDMI interface. The deployed computer vision algorithm in the FPGA can capture video frames at the rate of 60 fps with the large image sizes of up to 1280×1024 pixels. It then identifies the object based on the specified color, removes noise via spatial filtering and calculates the centroid allowing the object to be tracked during motion. The proposed algorithm leverages a reduction method to minimize the FPGA area as well as power consumption by averaging values over a range of several pixels; thus logarithmically reduces the design size. Our implementation is parameterized to be made as accurate or small as an application requires, with minimal error. The proposed tracking system is implemented on a Xilinx ZYNQ-7000 series XC7Z010 FPGA housed on Xilinx Zybo development board. The utilization reports show for a selected reduction rate of 16, 86.5% reduction in Slice LUTs and 81.3% in Slice registers with the maximum error of 1.5% in centroid calculation.
{"title":"Efficient FPGA Implementation of Parameterized Real Time Color Based Object Tracking","authors":"Robert Morris, Shahnam Mirzaei","doi":"10.1109/iemcon53756.2021.9623221","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623221","url":null,"abstract":"This paper presents an efficient color based tracking method applied on a sequence of live video frames for use in real time applications such as surveillance, video conferencing, and robot navigation. The proposed integrated system architecture consists of an attached camera that communicates with the FPGA through HDMI interface. The deployed computer vision algorithm in the FPGA can capture video frames at the rate of 60 fps with the large image sizes of up to 1280×1024 pixels. It then identifies the object based on the specified color, removes noise via spatial filtering and calculates the centroid allowing the object to be tracked during motion. The proposed algorithm leverages a reduction method to minimize the FPGA area as well as power consumption by averaging values over a range of several pixels; thus logarithmically reduces the design size. Our implementation is parameterized to be made as accurate or small as an application requires, with minimal error. The proposed tracking system is implemented on a Xilinx ZYNQ-7000 series XC7Z010 FPGA housed on Xilinx Zybo development board. The utilization reports show for a selected reduction rate of 16, 86.5% reduction in Slice LUTs and 81.3% in Slice registers with the maximum error of 1.5% in centroid calculation.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133497640","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623231
Fu-Shiung Hsieh
The lack of trust is one of the barriers that hinders the acceptance of ridesharing. In the past years, one of the hot research issue in the context of ridesharing is to enhance trust. Such trust based ridesharing problem can be described as an optimization problem in which a large number of constraints must be satisfied. Due to complexity of this optimization problem, exact methods are limited and cannot be applied. Therefore, approximate methods are usually applied to find the solutions. This problem can be solved by evolutionary algorithms. The purpose of this study is to develop an algorithm for trust based ridesharing problems by applying neighborhood search in Differential Evolution approach. We compare the proposed algorithm with other competitive algorithms. The numerical results indicate that applying neighborhood search in Differential Evolution approach leads to a more efficient solution algorithm.
{"title":"Neighborhood Search in Differential Evolution for Solving Trusted Ridesharing Problems","authors":"Fu-Shiung Hsieh","doi":"10.1109/iemcon53756.2021.9623231","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623231","url":null,"abstract":"The lack of trust is one of the barriers that hinders the acceptance of ridesharing. In the past years, one of the hot research issue in the context of ridesharing is to enhance trust. Such trust based ridesharing problem can be described as an optimization problem in which a large number of constraints must be satisfied. Due to complexity of this optimization problem, exact methods are limited and cannot be applied. Therefore, approximate methods are usually applied to find the solutions. This problem can be solved by evolutionary algorithms. The purpose of this study is to develop an algorithm for trust based ridesharing problems by applying neighborhood search in Differential Evolution approach. We compare the proposed algorithm with other competitive algorithms. The numerical results indicate that applying neighborhood search in Differential Evolution approach leads to a more efficient solution algorithm.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114476839","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623166
Naheem Olakunle Adesina, Md Azmot Ullah Khan, Jian Xu
In this paper, two different structures of phase locked loop (PLL) are examined and designed in 0.13 µm n-well CMOS process technology. The two PLLs only differ in voltage-controlled oscillator (VCO): current starved and LC VCOs. Using device degradation models and equations, their performances are investigated under the combined effects of soft breakdown, hot carrier injections, and negative bias temperature instability. It is observed in the current starved VCO that the gain reduces by 33.5%, the maximum frequency decreases from 1180 MHz to 1100 MHz, and the phase noise increases from −107.6 dBc/Hz to −103.5 dBc/Hz at 1 MHz offset frequency after 6 hours of stress. The varactor degradation in LC voltage-controlled oscillator causes a decrease in the mean capacitance, resulting in increased oscillation frequency. In addition, the phase noise increases from −120 dBc/Hz to −117.2 dBc/Hz at 1 MHz frequency.
{"title":"Modeling the Effects of SBD, HCI, and NBTI in CMOS Voltage Controlled Oscillator Design for PLL Applications","authors":"Naheem Olakunle Adesina, Md Azmot Ullah Khan, Jian Xu","doi":"10.1109/iemcon53756.2021.9623166","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623166","url":null,"abstract":"In this paper, two different structures of phase locked loop (PLL) are examined and designed in 0.13 µm n-well CMOS process technology. The two PLLs only differ in voltage-controlled oscillator (VCO): current starved and LC VCOs. Using device degradation models and equations, their performances are investigated under the combined effects of soft breakdown, hot carrier injections, and negative bias temperature instability. It is observed in the current starved VCO that the gain reduces by 33.5%, the maximum frequency decreases from 1180 MHz to 1100 MHz, and the phase noise increases from −107.6 dBc/Hz to −103.5 dBc/Hz at 1 MHz offset frequency after 6 hours of stress. The varactor degradation in LC voltage-controlled oscillator causes a decrease in the mean capacitance, resulting in increased oscillation frequency. In addition, the phase noise increases from −120 dBc/Hz to −117.2 dBc/Hz at 1 MHz frequency.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114650076","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623214
Andrew J. Park, Ryan Ficocelli, Lee D. Patterson, Valerie Spicer, Frank Dodich, Herbert H. Tsang
A crowd is a large number of people who gather at a specific location at the same time with or without shared agendas and/or emotions. A crowd is formed at sporting, holiday, religious, or political events. Proper management of a crowd is one of the major duties for the civic agencies such as police and fire departments to maintain public order and safety. When such management is ill-prepared and poorly executed, it can result in chaotic situations with human injuries and fatalities as well as damage to public properties. Good crowd management requires a good modelling of crowd dynamics and devising strategies accordingly. This paper presents the modelling and simulations of crowd dynamics that resembles the actual crowd behaviours using the social force model. With the realistic crowd dynamics, different scenarios and crowd management strategies were tested for optimal crowd flows. Our framework can be used to test various scenarios of an event that attracts a large crowd and devise suitable strategies for the crowd management.
{"title":"Modelling Crowd Dynamics and Crowd Management Strategies","authors":"Andrew J. Park, Ryan Ficocelli, Lee D. Patterson, Valerie Spicer, Frank Dodich, Herbert H. Tsang","doi":"10.1109/iemcon53756.2021.9623214","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623214","url":null,"abstract":"A crowd is a large number of people who gather at a specific location at the same time with or without shared agendas and/or emotions. A crowd is formed at sporting, holiday, religious, or political events. Proper management of a crowd is one of the major duties for the civic agencies such as police and fire departments to maintain public order and safety. When such management is ill-prepared and poorly executed, it can result in chaotic situations with human injuries and fatalities as well as damage to public properties. Good crowd management requires a good modelling of crowd dynamics and devising strategies accordingly. This paper presents the modelling and simulations of crowd dynamics that resembles the actual crowd behaviours using the social force model. With the realistic crowd dynamics, different scenarios and crowd management strategies were tested for optimal crowd flows. Our framework can be used to test various scenarios of an event that attracts a large crowd and devise suitable strategies for the crowd management.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125123917","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623073
Connor McGee, Jing Guo, Zhaohong Wang
Understanding the behavior of a virus spreading inside a computer network is crucial. In recent years, devices have become increasingly interconnected via communication protocols. Since computer networks are more ubiquitous than ever before, one infected device threatens several others. In order to better defend against network infections, the current methods need more novel means to combat network infections. Spectral graph theory may assist the study of network forensics by better understanding how a virus spreads throughout a networked system. This paper analyzes the spread of a virus throughout a computer network using actual data. The novelty is the calculation of various Laplacian matrices to observe the changes to the network, modeled as a graph resulting from the virus spread. Our discoveries may provide implications to gain early awareness and insights into the infectious situation.
{"title":"The Application of the Graph Laplacian in Network Forensics","authors":"Connor McGee, Jing Guo, Zhaohong Wang","doi":"10.1109/iemcon53756.2021.9623073","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623073","url":null,"abstract":"Understanding the behavior of a virus spreading inside a computer network is crucial. In recent years, devices have become increasingly interconnected via communication protocols. Since computer networks are more ubiquitous than ever before, one infected device threatens several others. In order to better defend against network infections, the current methods need more novel means to combat network infections. Spectral graph theory may assist the study of network forensics by better understanding how a virus spreads throughout a networked system. This paper analyzes the spread of a virus throughout a computer network using actual data. The novelty is the calculation of various Laplacian matrices to observe the changes to the network, modeled as a graph resulting from the virus spread. Our discoveries may provide implications to gain early awareness and insights into the infectious situation.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121714885","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 : 2021-10-27DOI: 10.1109/iemcon53756.2021.9623078
Samira Zad, Maryam Heidari, P. Hajibabaee, Masoud Malekzadeh
Semantics is a research field that has gained an extensive interest recently. This survey describes recent works in the field of semantics, a part of the broader area of computational linguistics. One of the important aspects of computational linguistics is using proper methods to distribute semantics for obtaining representations of the meaning of words. This survey summarizes the latest state of the art approaches in semantics that use deep learning methods, datasets, and lexical databases, specifying semantics under two categories such as semantic similarity and sentence modeling.
{"title":"A Survey of Deep Learning Methods on Semantic Similarity and Sentence Modeling","authors":"Samira Zad, Maryam Heidari, P. Hajibabaee, Masoud Malekzadeh","doi":"10.1109/iemcon53756.2021.9623078","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623078","url":null,"abstract":"Semantics is a research field that has gained an extensive interest recently. This survey describes recent works in the field of semantics, a part of the broader area of computational linguistics. One of the important aspects of computational linguistics is using proper methods to distribute semantics for obtaining representations of the meaning of words. This survey summarizes the latest state of the art approaches in semantics that use deep learning methods, datasets, and lexical databases, specifying semantics under two categories such as semantic similarity and sentence modeling.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123593674","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}
A pothole is one among the first reasons for road accidents and is becoming increasingly important to detect while driving on roads. Detection and warning can significantly reduce accidents and damages caused to vehicles. Advanced neural networks process the pictures from the camera on a realtime basis to spot if there is a pothole within the image. Detection of potholes using neural networks will be time-consuming. Recently, the advances in artificial neural network have led to varied high-performance single-shot detection algorithms. These algorithms are especially useful in real-time applications. Hence, in this paper, we present a study of various object detection algorithms towards pothole detection with its speed and accuracy. The dataset comprises around 9000 training images with and without potholes. The article analyzes Yolo V3, Yolo V4, Yolo V5, and SSD algorithms to judge the results with the identical dataset for training and evaluation.
{"title":"Pothole Detection Using Advanced Neural Networks","authors":"Narayana Darapaneni, Naresh Suresh Reddy, Anitha Urkude, A. Paduri, Arati Alok Satpute, Aakash Yogi, Dilip Krishna Natesan, Sarang Surve, Utkarsh Srivastava","doi":"10.1109/iemcon53756.2021.9623237","DOIUrl":"https://doi.org/10.1109/iemcon53756.2021.9623237","url":null,"abstract":"A pothole is one among the first reasons for road accidents and is becoming increasingly important to detect while driving on roads. Detection and warning can significantly reduce accidents and damages caused to vehicles. Advanced neural networks process the pictures from the camera on a realtime basis to spot if there is a pothole within the image. Detection of potholes using neural networks will be time-consuming. Recently, the advances in artificial neural network have led to varied high-performance single-shot detection algorithms. These algorithms are especially useful in real-time applications. Hence, in this paper, we present a study of various object detection algorithms towards pothole detection with its speed and accuracy. The dataset comprises around 9000 training images with and without potholes. The article analyzes Yolo V3, Yolo V4, Yolo V5, and SSD algorithms to judge the results with the identical dataset for training and evaluation.","PeriodicalId":272590,"journal":{"name":"2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125309089","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：