Pub Date : 2023-01-09DOI: 10.1109/DeSE58274.2023.10099609
Aicha Idriss Hentati, L. Chaari, Lobna Krichen, A. Alanezi
During this last decade, Unmanned Aerial Vehicles (UAVs) are being useful in complex missions and critical scenarios in particular for hostile areas supervision. The integration between Space-Air-Ground Networks (SAGIN) is gaining more attention especially with the future generation of cellular networks (6G). In this context, mainly, we focus on the integration between aerial and terrestrial networks. The aerial network corresponds to the use of the multi-UAVs network, called Flying Ad Hoc Networks (FANETs), and the terrestrial networks correspond to the use of the Ground Control Station (GCS), Wireless Sensor Network (WSN), Internet of Things (IoT), cellular networks and cloud computing. Moreover, we propose a novel architecture named Multi-UAVs-based SDN, IoT, and Cloud Architecture (MUSICA), in which we use Software Defined Network (SDN) controller to manage the integration between terrestrial and aerial networks and we deploy cloud storage and computing resources. The detailed functional components of the proposed MUSICA architecture and the data flow between its different components are discussed and the benefits of MUSICA for scalable land supervision are pinpointed.
在过去的十年中，无人驾驶飞行器(uav)在复杂任务和关键场景中非常有用，特别是在敌对地区的监督中。随着下一代蜂窝网络(6G)的发展，空间-空地网络(SAGIN)的集成越来越受到人们的关注。在此背景下，我们主要关注空中和地面网络的融合。空中网络对应于多无人机网络的使用，称为飞行自组织网络(fanet)，地面网络对应于地面控制站(GCS)、无线传感器网络(WSN)、物联网(IoT)、蜂窝网络和云计算的使用。此外，我们提出了一种名为multi - uav -based SDN, IoT, and Cloud architecture (MUSICA)的新架构，其中我们使用软件定义网络(SDN)控制器来管理地面和空中网络之间的集成，并部署云存储和计算资源。讨论了所提出的MUSICA架构的详细功能组件及其不同组件之间的数据流，并指出了MUSICA对可扩展土地监管的好处。
{"title":"Multi-UAVs-based SDN, IoT, and Cloud Architecture for Hostile Areas Supervision","authors":"Aicha Idriss Hentati, L. Chaari, Lobna Krichen, A. Alanezi","doi":"10.1109/DeSE58274.2023.10099609","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099609","url":null,"abstract":"During this last decade, Unmanned Aerial Vehicles (UAVs) are being useful in complex missions and critical scenarios in particular for hostile areas supervision. The integration between Space-Air-Ground Networks (SAGIN) is gaining more attention especially with the future generation of cellular networks (6G). In this context, mainly, we focus on the integration between aerial and terrestrial networks. The aerial network corresponds to the use of the multi-UAVs network, called Flying Ad Hoc Networks (FANETs), and the terrestrial networks correspond to the use of the Ground Control Station (GCS), Wireless Sensor Network (WSN), Internet of Things (IoT), cellular networks and cloud computing. Moreover, we propose a novel architecture named Multi-UAVs-based SDN, IoT, and Cloud Architecture (MUSICA), in which we use Software Defined Network (SDN) controller to manage the integration between terrestrial and aerial networks and we deploy cloud storage and computing resources. The detailed functional components of the proposed MUSICA architecture and the data flow between its different components are discussed and the benefits of MUSICA for scalable land supervision are pinpointed.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"58 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":"117313129","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/DeSE58274.2023.10100318
Mahmoud H. Farhan, Khalid Shaker, Sufyan T. Faraj Al-Janabi
In recent years, the problem of fake image diffusion is on the rise mainly on social networks because of the development of different tools for image editing. Copy-move forgery (CMF) is one of the image forgeries types used for manipulating the image content. In CMF, the region in an image is copied and placed in a different location in the same image. In this paper, an algorithm for CMF detection based on a Double Dual Convolutional Neural Network (D2CNN) is proposed. A novel concatenation of two Dual Convolutional Neural Networks (DCNN) is used, where each DCNN is composed of two CNN networks. A fully connected network (FCN) is taking the result of the D2CNN and hence classifying the input images into either original or forged. The features extracted from the two DCNN and fusion of these features (D2CNN) have achieved good results according to the following metrics: Accuracy, f1-score, precision, and recall. Two standard datasets namely MICC F-220 and MICC F-2000 have been used to evaluate the proposed approach. Experimental analysis shows that the proposed approach achieves accuracy higher than 98.48% on the MICC F-220 dataset and 97.83% on the MICC F-2000 dataset.
{"title":"Double Dual Convolutional Neural Network (D2CNN) for Copy-Move Forgery Detection","authors":"Mahmoud H. Farhan, Khalid Shaker, Sufyan T. Faraj Al-Janabi","doi":"10.1109/DeSE58274.2023.10100318","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100318","url":null,"abstract":"In recent years, the problem of fake image diffusion is on the rise mainly on social networks because of the development of different tools for image editing. Copy-move forgery (CMF) is one of the image forgeries types used for manipulating the image content. In CMF, the region in an image is copied and placed in a different location in the same image. In this paper, an algorithm for CMF detection based on a Double Dual Convolutional Neural Network (D2CNN) is proposed. A novel concatenation of two Dual Convolutional Neural Networks (DCNN) is used, where each DCNN is composed of two CNN networks. A fully connected network (FCN) is taking the result of the D2CNN and hence classifying the input images into either original or forged. The features extracted from the two DCNN and fusion of these features (D2CNN) have achieved good results according to the following metrics: Accuracy, f1-score, precision, and recall. Two standard datasets namely MICC F-220 and MICC F-2000 have been used to evaluate the proposed approach. Experimental analysis shows that the proposed approach achieves accuracy higher than 98.48% on the MICC F-220 dataset and 97.83% on the MICC F-2000 dataset.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"43 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":"126630314","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/DeSE58274.2023.10100248
Tan Wen Zheng Ashley, Lim Jo Han, Derrick, Kowit Tan, Rong Kai Tech Avin, Ashlinder Kaur, Sahar Al-Sudani, Zhengkui Wang
The worldwide gaming peripheral market is expanding significantly due to the increasing popularity of online games, and it is predicted that this would increase demand for gaming peripherals. Brand recognition is just the start of the process because many sectors are vying to stand out and wrest mindshare away from rivals. In this paper, we presented a tool named BrandTrend, which enables automated insight discovery for game trending, gaming influencers, and gaming product promotion. The data used in this tool is gathered from social media platforms to analyse gaming contents to match gaming content creators with gaming peripheral brands to promote their brand products via social media. Utilizing data analysis and incorporating evidence from data to build predictions and develop strategies can unambiguously address the issue of distinguish oneself from other rivals and get recognition.
{"title":"BrandTrend: Understanding the Trending Games and Gaming Influencers for Better Gaming Peripheral Promotion","authors":"Tan Wen Zheng Ashley, Lim Jo Han, Derrick, Kowit Tan, Rong Kai Tech Avin, Ashlinder Kaur, Sahar Al-Sudani, Zhengkui Wang","doi":"10.1109/DeSE58274.2023.10100248","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100248","url":null,"abstract":"The worldwide gaming peripheral market is expanding significantly due to the increasing popularity of online games, and it is predicted that this would increase demand for gaming peripherals. Brand recognition is just the start of the process because many sectors are vying to stand out and wrest mindshare away from rivals. In this paper, we presented a tool named BrandTrend, which enables automated insight discovery for game trending, gaming influencers, and gaming product promotion. The data used in this tool is gathered from social media platforms to analyse gaming contents to match gaming content creators with gaming peripheral brands to promote their brand products via social media. Utilizing data analysis and incorporating evidence from data to build predictions and develop strategies can unambiguously address the issue of distinguish oneself from other rivals and get recognition.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"61 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":"125608041","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/DeSE58274.2023.10100274
M. Mahyoub, F. Natalia, S. Sudirman, P. Liatsis, A. Al-Jumaily
Automatic car damage detection and assessment are very useful in alleviating the burden of manual inspection associated with car insurance claims. This will help filter out any frivolous claims that can take up time and money to process. This problem falls into the image classification category and there has been significant progress in this field using deep learning. However, deep learning models require a large number of images for training and oftentimes this is hampered because of the lack of datasets of suitable images. This research investigates data augmentation techniques using Generative Adversarial Networks to increase the size and improve the class balance of a dataset used for training deep learning models for car damage detection and classification. We compare the performance of such an approach with one that uses a conventional data augmentation technique and with another that does not use any data augmentation. Our experiment shows that this approach has a significant improvement compared to another that does not use data augmentation and has a slight improvement compared to one that uses conventional data augmentation.
{"title":"Data Augmentation Using Generative Adversarial Networks to Reduce Data Imbalance with Application in Car Damage Detection","authors":"M. Mahyoub, F. Natalia, S. Sudirman, P. Liatsis, A. Al-Jumaily","doi":"10.1109/DeSE58274.2023.10100274","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100274","url":null,"abstract":"Automatic car damage detection and assessment are very useful in alleviating the burden of manual inspection associated with car insurance claims. This will help filter out any frivolous claims that can take up time and money to process. This problem falls into the image classification category and there has been significant progress in this field using deep learning. However, deep learning models require a large number of images for training and oftentimes this is hampered because of the lack of datasets of suitable images. This research investigates data augmentation techniques using Generative Adversarial Networks to increase the size and improve the class balance of a dataset used for training deep learning models for car damage detection and classification. We compare the performance of such an approach with one that uses a conventional data augmentation technique and with another that does not use any data augmentation. Our experiment shows that this approach has a significant improvement compared to another that does not use data augmentation and has a slight improvement compared to one that uses conventional data augmentation.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"89 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":"134398254","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}
Predicting the criminals' behaviour is a difficult task to accomplish. It is unexpected in most cases and can possibly transpire at any time, which is challenging for police agencies and victims being affected by the offences. The proposed work presents a crime prediction model using the stop & search dataset and the demographic of those charged with possession of a weapon. The study is first of its kind using multiple publicly available datasets to predict the effectiveness of ‘stop & search’ interventions by the police. We employ multiple machine learning algorithms to predict whether a ‘further action’ is required following the stop & search by the police. We utilise several data science techniques mainly including pre-processing, feature engineering and appropriate use of model selection. The proposed model produced 93.20% accuracy using Random Forest classifier. The outcomes of this research can be useful by relevant authorities to anticipate the crime at a specific time and location through the analysis of patterns that will support decision-making and help on deterrent effective strategies to lower offences being committed.
{"title":"Predicting the Effectiveness of ‘Stop and Search’ Police Interventions Using Advanced Data Analytics","authors":"Bradley Marimbire, Abdulaziz Al-Nahari, Waris Khan Ahmadzai, D. Al-Jumeily, Wasiq Khan","doi":"10.1109/DeSE58274.2023.10100242","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100242","url":null,"abstract":"Predicting the criminals' behaviour is a difficult task to accomplish. It is unexpected in most cases and can possibly transpire at any time, which is challenging for police agencies and victims being affected by the offences. The proposed work presents a crime prediction model using the stop & search dataset and the demographic of those charged with possession of a weapon. The study is first of its kind using multiple publicly available datasets to predict the effectiveness of ‘stop & search’ interventions by the police. We employ multiple machine learning algorithms to predict whether a ‘further action’ is required following the stop & search by the police. We utilise several data science techniques mainly including pre-processing, feature engineering and appropriate use of model selection. The proposed model produced 93.20% accuracy using Random Forest classifier. The outcomes of this research can be useful by relevant authorities to anticipate the crime at a specific time and location through the analysis of patterns that will support decision-making and help on deterrent effective strategies to lower offences being committed.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"42 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":"133984113","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/DeSE58274.2023.10099877
I. Makarova, G. Mavlyautdinova, V. Mavrin, P. Buyvol, A. Alatrany, J. Mustafina
The strategy of spatial development of the country for the period up to 2024, based on the infrastructure of a specific type of transport, provides for the connection of the territories of settlements with modern communications; phased reconstruction and modernization; personnel, technical and technological support for interaction and digital transformation of the Russian transport complex. The development of the Russian Arctic is a priority area, since it has a significant natural resource, socio-economic and transport potential, which must be maximized, taking into account all the features of this region. It is important to develop the northern territories in such a way that the transport infrastructure of the Arctic meets the requirements in the field of comfort and safety of the human environment. This can be achieved through the use of vehicles of increased environmental friendliness and energy efficiency. In the study we analyse the possibility of converting shift buses used to deliver personnel involved in the development of fields in the Arctic zone to gas motor fuel using simulation models.
{"title":"Improvement of the Personnel Delivery System in the Mining Complex using Simulation Models","authors":"I. Makarova, G. Mavlyautdinova, V. Mavrin, P. Buyvol, A. Alatrany, J. Mustafina","doi":"10.1109/DeSE58274.2023.10099877","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099877","url":null,"abstract":"The strategy of spatial development of the country for the period up to 2024, based on the infrastructure of a specific type of transport, provides for the connection of the territories of settlements with modern communications; phased reconstruction and modernization; personnel, technical and technological support for interaction and digital transformation of the Russian transport complex. The development of the Russian Arctic is a priority area, since it has a significant natural resource, socio-economic and transport potential, which must be maximized, taking into account all the features of this region. It is important to develop the northern territories in such a way that the transport infrastructure of the Arctic meets the requirements in the field of comfort and safety of the human environment. This can be achieved through the use of vehicles of increased environmental friendliness and energy efficiency. In the study we analyse the possibility of converting shift buses used to deliver personnel involved in the development of fields in the Arctic zone to gas motor fuel using simulation models.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"83 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":"114782483","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/DeSE58274.2023.10099681
I. Makarova, G. Yakupova, P. Buyvol, E. Mukhametdinov, A. Abashev, J. Mustafina
When managing the transport system of an urbanized area, infrastructural changes cannot always solve transport problems. At the same time, organizational measures implemented within the framework of an intelligent transport system can be effective. To make operational and strategic decisions, it is necessary to form a base of typical emergency situations, having previously studied them on a simulation model. For this, we have chosen a micro-simulation method, which allows taking into account the stochastic nature of the traffic flow. As a result of a computer experiment, we have obtained estimates of changes in parameters (average time for a vehicle to cross an intersection in all directions, average speed) when emergencies of a given duration occur at a T-shaped intersection. The novelty of the proposed approach lies in the possibility of assessing the nature of the emergency situations' development for various values of influencing factors.
{"title":"Using Simulation for Investigating Emergency Traffic Situations","authors":"I. Makarova, G. Yakupova, P. Buyvol, E. Mukhametdinov, A. Abashev, J. Mustafina","doi":"10.1109/DeSE58274.2023.10099681","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099681","url":null,"abstract":"When managing the transport system of an urbanized area, infrastructural changes cannot always solve transport problems. At the same time, organizational measures implemented within the framework of an intelligent transport system can be effective. To make operational and strategic decisions, it is necessary to form a base of typical emergency situations, having previously studied them on a simulation model. For this, we have chosen a micro-simulation method, which allows taking into account the stochastic nature of the traffic flow. As a result of a computer experiment, we have obtained estimates of changes in parameters (average time for a vehicle to cross an intersection in all directions, average speed) when emergencies of a given duration occur at a T-shaped intersection. The novelty of the proposed approach lies in the possibility of assessing the nature of the emergency situations' development for various values of influencing factors.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"40 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":"114291525","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/DeSE58274.2023.10100200
Tshun Kong Chan, I. F. Kamsin, S. Amin, N. Zainal
Tamper-proof log files has always been desired in any business settings as it is usually the prime target of bad actors to eliminate their presence in a cyber-attack, while the current log files solutions are mostly insufficient when it comes to practicality and efficiency. The research aims to propose a complete log files solution to prevent hackers from tampering with a system log record using blockchain technology and minimizes the scalability issues of current blockchain-based log files solution with anomaly detection frameworks. The research will focus on gathering data using purposive sampling method by distributing surveys to carefully selected populations to draw conclusions based on the information gathered. In conclusion, the proposed system will feature a blockchain-based log files security solution with anomaly detection built on top to minimize the scalability issues of blockchain technology and to act as a secondary intrusion detection system to achieve defense-in-depth. Future recommendations for the proposed system involve the use of a better anomaly detection framework or more efficient blockchain technology.
{"title":"A Complete Log Files Security Solution Using Anomaly Detection and Blockchain Technology","authors":"Tshun Kong Chan, I. F. Kamsin, S. Amin, N. Zainal","doi":"10.1109/DeSE58274.2023.10100200","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10100200","url":null,"abstract":"Tamper-proof log files has always been desired in any business settings as it is usually the prime target of bad actors to eliminate their presence in a cyber-attack, while the current log files solutions are mostly insufficient when it comes to practicality and efficiency. The research aims to propose a complete log files solution to prevent hackers from tampering with a system log record using blockchain technology and minimizes the scalability issues of current blockchain-based log files solution with anomaly detection frameworks. The research will focus on gathering data using purposive sampling method by distributing surveys to carefully selected populations to draw conclusions based on the information gathered. In conclusion, the proposed system will feature a blockchain-based log files security solution with anomaly detection built on top to minimize the scalability issues of blockchain technology and to act as a secondary intrusion detection system to achieve defense-in-depth. Future recommendations for the proposed system involve the use of a better anomaly detection framework or more efficient blockchain technology.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"33 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":"124775598","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/DeSE58274.2023.10099796
M. Mahyoub, Shatha Ghareeb, J. Mustafina
Home Loan plays a pivotal role in today's age when one steps into purchasing their home. It has been witnessed that in many cases users are unable to pay the after taking the loan and thus the loan is slipped to NPA(Non-Performing Asset) from Standard Asset for the bank or any lending institution. The revenue generation is ceased. As the housing loan is taken against property the lenders have right to sell the property and close the dues, but the process is lengthy as judicial procedures are involved. In most cases, the property value is much less than the calculated loan amount (Principal + Interest). In this study we examined the several ML methods to identify the loan default before disbursing the loan to the applicant. This matter has been studied widely and used the predictive analytics to find out the relationship between attributes and the target variable. Predictive Analytics enables us to feed optimal set of features to the ML models. The study started with 122 attributes and ended up with around 30% of features as the ideal subset for housing loan default prediction. Then, five ML models were fit into the dataset and the champion model came up with roc score 0.94, Recall 0.90 and Precision 0.94. LIME and SHAP were applied on the champion model along with the dataset for global and local interpretability. The experimental procedure concluded that ML models along with predictive analytics can arrest the loan disbursal to the ineligible applicants and will also provide the insight of such prediction with the help of model interpretability.
{"title":"A Novel Predictive Model for Housing Loan Default using Feature Generation and Explainable AI","authors":"M. Mahyoub, Shatha Ghareeb, J. Mustafina","doi":"10.1109/DeSE58274.2023.10099796","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099796","url":null,"abstract":"Home Loan plays a pivotal role in today's age when one steps into purchasing their home. It has been witnessed that in many cases users are unable to pay the after taking the loan and thus the loan is slipped to NPA(Non-Performing Asset) from Standard Asset for the bank or any lending institution. The revenue generation is ceased. As the housing loan is taken against property the lenders have right to sell the property and close the dues, but the process is lengthy as judicial procedures are involved. In most cases, the property value is much less than the calculated loan amount (Principal + Interest). In this study we examined the several ML methods to identify the loan default before disbursing the loan to the applicant. This matter has been studied widely and used the predictive analytics to find out the relationship between attributes and the target variable. Predictive Analytics enables us to feed optimal set of features to the ML models. The study started with 122 attributes and ended up with around 30% of features as the ideal subset for housing loan default prediction. Then, five ML models were fit into the dataset and the champion model came up with roc score 0.94, Recall 0.90 and Precision 0.94. LIME and SHAP were applied on the champion model along with the dataset for global and local interpretability. The experimental procedure concluded that ML models along with predictive analytics can arrest the loan disbursal to the ineligible applicants and will also provide the insight of such prediction with the help of model interpretability.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"17 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":"115243839","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/DeSE58274.2023.10099694
Mee Chun Loo, R. Logeswaran, Zailan Arabee bin Abdul Salam
Automated optical inspection (AOI) is a visual defect inspection system. The semiconductor industry has a strong dependency on AOI for defects screening. Conventional AOI is inadequate for some inspections, especially surface defects like crack, chip and void, and the algorithms are inefficient in isolating the defects from product variants. Convolutional Neural Network (CNN) had been broadly studied and adopted to replace the conventional AOI in surface inspection. There are many CNN architectures developed in the past decade for image classification, such as AlexNet, GoogLeNet, ResNet, VGGNet, etc.; each with its own strength in terms of accuracy and speed. The training process could be speeded up too using techniques such as transfer learning from pre-trained CNN models. Newer techniques in vector programming on kernels, e.g., Single Instruction Multiple Data (SIMD) and depth wise separable method can further increase the efficiency of convolutional layer activation functions. CNN algorithms for surface inspection are found to be very promising, with defect classification able to achieve accuracies of 91-99% on the wide range of products. The CNN result outperforms conventional surface inspection methods like edge detection and machine learning algorithms.
{"title":"CNN Aided Surface Inspection for SMT Manufacturing","authors":"Mee Chun Loo, R. Logeswaran, Zailan Arabee bin Abdul Salam","doi":"10.1109/DeSE58274.2023.10099694","DOIUrl":"https://doi.org/10.1109/DeSE58274.2023.10099694","url":null,"abstract":"Automated optical inspection (AOI) is a visual defect inspection system. The semiconductor industry has a strong dependency on AOI for defects screening. Conventional AOI is inadequate for some inspections, especially surface defects like crack, chip and void, and the algorithms are inefficient in isolating the defects from product variants. Convolutional Neural Network (CNN) had been broadly studied and adopted to replace the conventional AOI in surface inspection. There are many CNN architectures developed in the past decade for image classification, such as AlexNet, GoogLeNet, ResNet, VGGNet, etc.; each with its own strength in terms of accuracy and speed. The training process could be speeded up too using techniques such as transfer learning from pre-trained CNN models. Newer techniques in vector programming on kernels, e.g., Single Instruction Multiple Data (SIMD) and depth wise separable method can further increase the efficiency of convolutional layer activation functions. CNN algorithms for surface inspection are found to be very promising, with defect classification able to achieve accuracies of 91-99% on the wide range of products. The CNN result outperforms conventional surface inspection methods like edge detection and machine learning algorithms.","PeriodicalId":346847,"journal":{"name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","volume":"54 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":"115249592","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：