Pub Date : 2023-01-09DOI: 10.1109/DeSE58274.2023.10099509
Ahmed Waleed K. Al-Nasir, F. S. Mubarek
Congestion on major highways can be alleviated by moving in platoons. By exchanging information about their vehicles over VANETs, platoon members may keep the distance between their vehicles and inside the platoon consistent. To be sure, the strength of a VANET's connections can be gauged in part by its connection quality. This research investigates the probabilities of access, reachability and the connectivity between nodes (vehicles) and roadside-units (RSUs) in a two-way platoon-based VANETs that make use of such infrastructure. We call this the connectivity probability, and it is the likelihood that, during a given number of hops, moving vehicles on the express-way will be able to reach at least (1) RSU other than the road. In addition to looking at the connection on the same route, we also look at the link via vehicles on nearby surrounding roads and how they connect to the RSU. The analytical results (mathematical equations and calculations) have been validated by simulations, which show that a network's existence of platoons can boost the likelihood of connectivity. There is a greater chance of connectivity in a vehicle-to-infrastructure (V2I) network with multiple communication channels than in a network with only one. The results of this study can help eliminate the traffic jams and promote safer, more considerate motorists. Then everyone who is using the roads can travel in greater ease and security. These findings also provide substantial theoretical support for the design of a relish intelligent transportation system (ITS).
{"title":"The Probability of Connectivity in the 2 Way / 2 Lane Platoon-Based V2I Communication Network","authors":"Ahmed Waleed K. Al-Nasir, F. S. Mubarek","doi":"10.1109/DeSE58274.2023.10099509","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099509","url":null,"abstract":"Congestion on major highways can be alleviated by moving in platoons. By exchanging information about their vehicles over VANETs, platoon members may keep the distance between their vehicles and inside the platoon consistent. To be sure, the strength of a VANET's connections can be gauged in part by its connection quality. This research investigates the probabilities of access, reachability and the connectivity between nodes (vehicles) and roadside-units (RSUs) in a two-way platoon-based VANETs that make use of such infrastructure. We call this the connectivity probability, and it is the likelihood that, during a given number of hops, moving vehicles on the express-way will be able to reach at least (1) RSU other than the road. In addition to looking at the connection on the same route, we also look at the link via vehicles on nearby surrounding roads and how they connect to the RSU. The analytical results (mathematical equations and calculations) have been validated by simulations, which show that a network's existence of platoons can boost the likelihood of connectivity. There is a greater chance of connectivity in a vehicle-to-infrastructure (V2I) network with multiple communication channels than in a network with only one. The results of this study can help eliminate the traffic jams and promote safer, more considerate motorists. Then everyone who is using the roads can travel in greater ease and security. These findings also provide substantial theoretical support for the design of a relish intelligent transportation system (ITS).","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126755606","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10100123
Mahmoud Madi, Y. Basha, Yazan Albadersawi, Fayadh S. Alenezi, S. Mahmoud, D. Abd, D. Al-Jumeily, Wasiq Khan, Abir Jaafar Hussien
Animal-Vehicle Accidents have shown deep increase in the middle east regions over the last decades. These collisions resulting from camels fleeing the wildlife and crossing the roads and hence endangering drivers and camel's lives and leading to habitat degradation. Additionality, the size, strength, and the unpredictable behavior of camels play a key role in high mortality rates in the camel-vehicle collisions. Various solutions and countermeasures such as warning signs and fences have been adopted in the past. However, several drawbacks are associated to them, and their effectiveness are reducing with time. Therefore, this study proposes a framework for the use of machine learning approaches and computer vision for the detection and recognition of camels. This can help to provide warning to drivers about potential animal crossings in an effort to mitigate camel-vehicle accidents.
{"title":"Camel Detection and Monitoring Using Image Processing and IoT","authors":"Mahmoud Madi, Y. Basha, Yazan Albadersawi, Fayadh S. Alenezi, S. Mahmoud, D. Abd, D. Al-Jumeily, Wasiq Khan, Abir Jaafar Hussien","doi":"10.1109/DeSE58274.2023.10100123","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100123","url":null,"abstract":"Animal-Vehicle Accidents have shown deep increase in the middle east regions over the last decades. These collisions resulting from camels fleeing the wildlife and crossing the roads and hence endangering drivers and camel's lives and leading to habitat degradation. Additionality, the size, strength, and the unpredictable behavior of camels play a key role in high mortality rates in the camel-vehicle collisions. Various solutions and countermeasures such as warning signs and fences have been adopted in the past. However, several drawbacks are associated to them, and their effectiveness are reducing with time. Therefore, this study proposes a framework for the use of machine learning approaches and computer vision for the detection and recognition of camels. This can help to provide warning to drivers about potential animal crossings in an effort to mitigate camel-vehicle accidents.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123201515","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10100167
Hayder S. Radeaf, M. Z. Al-Faiz
Calculating the Inverse Kinematic (IK) equations is a complex problem due to the nonlinearity of these equations. Choosing the end effector orientation affects the reach of the target location. The Forward Kinematics (FK) of Humanoid Robotic Legs (HRL) is determined by using Denavit-Hartenberg (DH) method. The HRL has two legs with five Degrees of Freedom (DoF) each. The paper proposes using a Particle Swarm Optimization (PSO) algorithm to optimize the best orientation angle of the end effector of HRL. The selected orientation angle is used to solve the IK equations to reach the target location with minimum error. The performance of the proposed method is measured by six scenarios with different simulated positions of the legs. The proposed method is compared with procedures that used different optimization algorithms such as Genetic Algorithm (GA), Differential Evolution (DE), and Invasive Weed Optimization (IWO). The Root Mean Square Error (RMSE) and computation time are used as comparison measures. The proposed method gives the best results among others, and it reaches the target location with an average RMSE of 10−12 with 2.5 seconds average computation time.
{"title":"Inverse Kinematics Optimization for Humanoid Robotic Legs Based on Particle Swarm Optimization","authors":"Hayder S. Radeaf, M. Z. Al-Faiz","doi":"10.1109/DeSE58274.2023.10100167","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100167","url":null,"abstract":"Calculating the Inverse Kinematic (IK) equations is a complex problem due to the nonlinearity of these equations. Choosing the end effector orientation affects the reach of the target location. The Forward Kinematics (FK) of Humanoid Robotic Legs (HRL) is determined by using Denavit-Hartenberg (DH) method. The HRL has two legs with five Degrees of Freedom (DoF) each. The paper proposes using a Particle Swarm Optimization (PSO) algorithm to optimize the best orientation angle of the end effector of HRL. The selected orientation angle is used to solve the IK equations to reach the target location with minimum error. The performance of the proposed method is measured by six scenarios with different simulated positions of the legs. The proposed method is compared with procedures that used different optimization algorithms such as Genetic Algorithm (GA), Differential Evolution (DE), and Invasive Weed Optimization (IWO). The Root Mean Square Error (RMSE) and computation time are used as comparison measures. The proposed method gives the best results among others, and it reaches the target location with an average RMSE of 10−12 with 2.5 seconds average computation time.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"485 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127568978","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10100058
S. Gupta
The emotion is an intricated impression present in the music that is extremely hard to capture even using refined feature engineering techniques. The emotion of a song is an important feature that can be used for various MIR tasks like recommendation systems, music therapy, and automatic playlist generation. In this research, we investigate the application of L3- Net deep audio embeddings with the attention-based deep neural network model using positional encoding for recognizing musical emotions. In addition, we have constructed a master dataset using the 4Q audio emotion dataset and Bi-modal emotion dataset which is used in this research as the main dataset. The L3-Net deep audio embeddings are being used as features for the neural network model that does not require any feature engineering and other audio-based features. We have proposed two attention-based neural network models with and without recurrent layers. The positional encoding mechanism has helped the ACNN model to learn the recurrent information in the audio embeddings without any recurrent layers. Therefore, we conclude that the ACNN model has performed better than other models with the F1-score of 0.79 using the AdamP optimizer.
{"title":"Deep Audio Embeddings and Attention Based Music Emotion Recognition","authors":"S. Gupta","doi":"10.1109/DeSE58274.2023.10100058","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100058","url":null,"abstract":"The emotion is an intricated impression present in the music that is extremely hard to capture even using refined feature engineering techniques. The emotion of a song is an important feature that can be used for various MIR tasks like recommendation systems, music therapy, and automatic playlist generation. In this research, we investigate the application of L3- Net deep audio embeddings with the attention-based deep neural network model using positional encoding for recognizing musical emotions. In addition, we have constructed a master dataset using the 4Q audio emotion dataset and Bi-modal emotion dataset which is used in this research as the main dataset. The L3-Net deep audio embeddings are being used as features for the neural network model that does not require any feature engineering and other audio-based features. We have proposed two attention-based neural network models with and without recurrent layers. The positional encoding mechanism has helped the ACNN model to learn the recurrent information in the audio embeddings without any recurrent layers. Therefore, we conclude that the ACNN model has performed better than other models with the F1-score of 0.79 using the AdamP optimizer.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124480439","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10099757
Sarah Abdulrezzak, Firas A. Sabir
Information systems in businesses, organizations live through continuous evolution, including Centralized data centers, local area networks, and Internet access. Although Internet access offers myriad resources, it also enables the outside world to connect to and engage with local network resources. This generates a vulnerability to organizational information systems, which require security measures. To keep the network secure from unauthorized access and survive an attack without affecting the availability of services to legitimate users; various security measures were forged to provide protected network connection, including intrusion Detection and Prevention System (IDPS). IDPS aims to secure the network from both internal and external Intrusions; acting like a safety net and an additional layer of defense. Network IDPS can identify and mitigate numerous attacks by alerting security administrators, dropping malign packets and blocking offending IPs and potential attacks. Snort is a rule based IDPS. In this paper Snort is used to prevent probing, DoS and brute force attacks by utilizing inline mode and iptable and net filter library. New snort rules are proposed to block the three attacks by dropping their packets. The experimental results of this study show that all the attacks are halted and the prevention rate is about 99 percent for malicious packets.
{"title":"Enhancing Intrusion Prevention in Snort System","authors":"Sarah Abdulrezzak, Firas A. Sabir","doi":"10.1109/DeSE58274.2023.10099757","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099757","url":null,"abstract":"Information systems in businesses, organizations live through continuous evolution, including Centralized data centers, local area networks, and Internet access. Although Internet access offers myriad resources, it also enables the outside world to connect to and engage with local network resources. This generates a vulnerability to organizational information systems, which require security measures. To keep the network secure from unauthorized access and survive an attack without affecting the availability of services to legitimate users; various security measures were forged to provide protected network connection, including intrusion Detection and Prevention System (IDPS). IDPS aims to secure the network from both internal and external Intrusions; acting like a safety net and an additional layer of defense. Network IDPS can identify and mitigate numerous attacks by alerting security administrators, dropping malign packets and blocking offending IPs and potential attacks. Snort is a rule based IDPS. In this paper Snort is used to prevent probing, DoS and brute force attacks by utilizing inline mode and iptable and net filter library. New snort rules are proposed to block the three attacks by dropping their packets. The experimental results of this study show that all the attacks are halted and the prevention rate is about 99 percent for malicious packets.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132058399","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10099782
Rashad N. Razak, Hadeel N. Abdullah
Multi-Object Detection and Tracking (MODT) is crucial in various contexts. Despite this, significant advancements in detection and tracking speed were needed to meet the challenge during the implementation phase. Introduce a revised algorithmic framework for (MODT) to speed up processing and make it more stable for use in real-time settings. The object's position and velocity were predicted using a Kalman filter and a background subtraction detection approach. When the detector isn't actively searching for a new object, it can be beneficial to discard the successive two frames and replace them with the Kalman filter's prediction and estimated value for the monitored object to speed up the process. Adding some image filter-like aspect ratio object and motion which help to reduce the effectiveness of the shadow and variations of the lighting conditions in the scene, which improve the proposed algorithm detection and tracking, This is useful for daytime preprocessing in an automated traffic surveillance system and inside pedestrian monitoring, and it can be shown with the help of a video camera. The results of these preliminary tests indicate that the proposed algorithm for this vehicle monitoring system works. It demonstrates that when applied to a single camera, the proposed method can monitor, detect, and track many vehicles or human being simultaneous, with improved execution time by 22% over the standard background subtraction and tolerable complexity.
{"title":"Modify Multiple Object Detection and Tracking to Improve the Execution Time","authors":"Rashad N. Razak, Hadeel N. Abdullah","doi":"10.1109/DeSE58274.2023.10099782","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099782","url":null,"abstract":"Multi-Object Detection and Tracking (MODT) is crucial in various contexts. Despite this, significant advancements in detection and tracking speed were needed to meet the challenge during the implementation phase. Introduce a revised algorithmic framework for (MODT) to speed up processing and make it more stable for use in real-time settings. The object's position and velocity were predicted using a Kalman filter and a background subtraction detection approach. When the detector isn't actively searching for a new object, it can be beneficial to discard the successive two frames and replace them with the Kalman filter's prediction and estimated value for the monitored object to speed up the process. Adding some image filter-like aspect ratio object and motion which help to reduce the effectiveness of the shadow and variations of the lighting conditions in the scene, which improve the proposed algorithm detection and tracking, This is useful for daytime preprocessing in an automated traffic surveillance system and inside pedestrian monitoring, and it can be shown with the help of a video camera. The results of these preliminary tests indicate that the proposed algorithm for this vehicle monitoring system works. It demonstrates that when applied to a single camera, the proposed method can monitor, detect, and track many vehicles or human being simultaneous, with improved execution time by 22% over the standard background subtraction and tolerable complexity.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132258411","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10099833
Samar Taleb, L. Chaari, M. Fourati
Modern robots are already a common sight in our daily lives thanks to recent technology advancements. Particularly, assistive robotics has become a fascinating area of study that may hold the key to enhancing the lives of the elderly persons. In this context, this study does a comprehensive assessment of the literature to analyze the features and the architectures of several famous assistive systems dedicated to help elderly persons.
{"title":"Study on Communicative Robots Assisting Elderly Persons","authors":"Samar Taleb, L. Chaari, M. Fourati","doi":"10.1109/DeSE58274.2023.10099833","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099833","url":null,"abstract":"Modern robots are already a common sight in our daily lives thanks to recent technology advancements. Particularly, assistive robotics has become a fascinating area of study that may hold the key to enhancing the lives of the elderly persons. In this context, this study does a comprehensive assessment of the literature to analyze the features and the architectures of several famous assistive systems dedicated to help elderly persons.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122434011","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10100288
Hanan R. Salih, Talal H. Fadil, A. Mahmoud
This study aimed to evaluate the permanent deformation of asphalt mixtures employing two testing methods: the cyclic and static loading tests. In the cyclic loading test, the creep rate was determined using a locally manufactured SHRL machine, according to the BS EN 12647-25-2016 standard specification. While in the static loading test, the strength against deformation (SD) was investigated utilizing the Kim testing procedure was adopted. Four wearing course asphalt mixture were prepared using two types of aggregates (Thumail and Al-Nibaie) and two types of asphalt binders (Erbil and Al-Dora). Results from both tests demonstrated that the resistance to permanent deformation varies based on the type of asphalt and aggregate used in the mixture. Mixtures prepared by Thumail aggregates showed higher resistance to deformation than that prepared using Al-Nibaie aggregate. There was a good agreement between the results from both tests. From the result, it is proposed a new design equation that can be used in design the surface layer depend on the test type.
本文采用循环和静载试验两种试验方法对沥青混合料的永久变形进行了研究。在循环加载试验中，根据BS EN 12647-25-2016标准规范，使用本地制造的SHRL机器确定蠕变速率。在静载试验中，采用Kim试验程序进行抗变形强度(SD)试验。采用两种集料(Thumail和Al-Nibaie)和两种沥青粘结剂(Erbil和Al-Dora)制备了四种耐磨层沥青混合料。两项试验的结果表明，根据混合料中使用的沥青和骨料的类型，抗永久变形的能力有所不同。与Al-Nibaie骨料相比，用Thumail骨料制备的混合料具有更高的抗变形能力。两次试验的结果很吻合。根据试验结果，提出了一种新的设计公式，可根据试验类型对表层进行设计。
{"title":"Estimation the Design Paramters of Surface Course Asphalt Concrete by Cyclic and Static Loading","authors":"Hanan R. Salih, Talal H. Fadil, A. Mahmoud","doi":"10.1109/DeSE58274.2023.10100288","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100288","url":null,"abstract":"This study aimed to evaluate the permanent deformation of asphalt mixtures employing two testing methods: the cyclic and static loading tests. In the cyclic loading test, the creep rate was determined using a locally manufactured SHRL machine, according to the BS EN 12647-25-2016 standard specification. While in the static loading test, the strength against deformation (SD) was investigated utilizing the Kim testing procedure was adopted. Four wearing course asphalt mixture were prepared using two types of aggregates (Thumail and Al-Nibaie) and two types of asphalt binders (Erbil and Al-Dora). Results from both tests demonstrated that the resistance to permanent deformation varies based on the type of asphalt and aggregate used in the mixture. Mixtures prepared by Thumail aggregates showed higher resistance to deformation than that prepared using Al-Nibaie aggregate. There was a good agreement between the results from both tests. From the result, it is proposed a new design equation that can be used in design the surface layer depend on the test type.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128278596","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}
News articles play a crucial role in helping humans know about many important events, developments, and inventions worldwide. The busy chores of our day-to-day life have made it quite challenging to consume important information from lengthy news articles. Therefore, short summaries of news articles are not only crucial but essential as well. Deep learning has revolutionized the field of natural language processing research. A lot of research has been done using pre-trained transformer-based models, and it has significantly improved the text sum-marization performance. In this paper, efforts were made to analyze transformer-based models such as BERT, GPT-2, XL Net, BART, and T5 for extractive and abstractive summarizations. This research investigates various methods through observation and experimentation. It also proposes methods that produce better summaries than comparable methods.
{"title":"A Comparative Study on Transformer-based News Summarization","authors":"Ambrish Choudhary, Mamatha Alugubelly, Rupal Bhargava","doi":"10.1109/DeSE58274.2023.10099798","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099798","url":null,"abstract":"News articles play a crucial role in helping humans know about many important events, developments, and inventions worldwide. The busy chores of our day-to-day life have made it quite challenging to consume important information from lengthy news articles. Therefore, short summaries of news articles are not only crucial but essential as well. Deep learning has revolutionized the field of natural language processing research. A lot of research has been done using pre-trained transformer-based models, and it has significantly improved the text sum-marization performance. In this paper, efforts were made to analyze transformer-based models such as BERT, GPT-2, XL Net, BART, and T5 for extractive and abstractive summarizations. This research investigates various methods through observation and experimentation. It also proposes methods that produce better summaries than comparable methods.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125360613","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 : 2023-01-09DOI: 10.1109/DeSE58274.2023.10099502
Hessam Rastegari, H. Kolivand, Peter Hawkins
Looking to the future is always something people have been interested in from the old days. What people can do using their current ability is ambiguous, but this can be achieved psychologically. In this study, a systematic Augmented Reality (AR) system named iCan has been proposed to reveal the ability of what we can do and which way we should choose when facing any junction of choices. iCan has been developed in four steps: basic AR development implementation, building 3D-Models, making the best interaction UX(User-Experience) and test-debug-publish. In the first step, booklet pages have been chosen for AR development instruction. Next, 3D models have made and have been presented. Next, interaction methods are under development. Some individuals have tested the system, and the results show the robustness of the presented system, which there is a hope to change people's future soon.
{"title":"iCan: Psychological Look in Future Using Augmented Reality Technology","authors":"Hessam Rastegari, H. Kolivand, Peter Hawkins","doi":"10.1109/DeSE58274.2023.10099502","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099502","url":null,"abstract":"Looking to the future is always something people have been interested in from the old days. What people can do using their current ability is ambiguous, but this can be achieved psychologically. In this study, a systematic Augmented Reality (AR) system named iCan has been proposed to reveal the ability of what we can do and which way we should choose when facing any junction of choices. iCan has been developed in four steps: basic AR development implementation, building 3D-Models, making the best interaction UX(User-Experience) and test-debug-publish. In the first step, booklet pages have been chosen for AR development instruction. Next, 3D models have made and have been presented. Next, interaction methods are under development. Some individuals have tested the system, and the results show the robustness of the presented system, which there is a hope to change people's future soon.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117206506","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：