Pub Date : 2023-05-23DOI: 10.1109/SACI58269.2023.10158619
Martin Ferenc Dömény, Melánia Puskás, L. Kovács, D. Drexler
The combination of medicine with engineering has great potential. The currently used chemotherapy treatments usually use maximal tolerable doses, which can lead to harmful side effects. By using a mathematical approach, we are able to personalize chemotherapy treatments, using unique patient parameters. We propose an algorithm that is capable of generating a chemotherapy treatment plan to cure cancer patients. The objective of the algorithm is to create a treatment that shrinks the tumor while minimizing the injected doses to decrease treatment costs and prevent drug toxicity. In this paper, we used a genetic algorithm to find the optimal treatment. First, we optimized the therapy on a single patient, later we carried out therapy optimization on a population with predefined ranges for the patient model parameters. The parameters are acquired from in vivo mice experiments through parametric identification. According to the results, the generated treatment produced higher survival rates with slightly higher doses compared to the standard clinically used treatment.
{"title":"In silico chemotherapy optimization with genetic algorithm","authors":"Martin Ferenc Dömény, Melánia Puskás, L. Kovács, D. Drexler","doi":"10.1109/SACI58269.2023.10158619","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158619","url":null,"abstract":"The combination of medicine with engineering has great potential. The currently used chemotherapy treatments usually use maximal tolerable doses, which can lead to harmful side effects. By using a mathematical approach, we are able to personalize chemotherapy treatments, using unique patient parameters. We propose an algorithm that is capable of generating a chemotherapy treatment plan to cure cancer patients. The objective of the algorithm is to create a treatment that shrinks the tumor while minimizing the injected doses to decrease treatment costs and prevent drug toxicity. In this paper, we used a genetic algorithm to find the optimal treatment. First, we optimized the therapy on a single patient, later we carried out therapy optimization on a population with predefined ranges for the patient model parameters. The parameters are acquired from in vivo mice experiments through parametric identification. According to the results, the generated treatment produced higher survival rates with slightly higher doses compared to the standard clinically used treatment.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123029850","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158590
Zoltán Biczó, S. Szénási, I. Felde
There are many attempts to solve the Inverse Heat Conduction Problem, and nowadays a growing number of machine learning-based methods have emerged. One major drawback of these methods is that they are very sensitive to the size and quality of the training database. There are several data augmentation techniques for artificially increasing the size of training databases, but these techniques have not yet been investigated in the field of quenching. This paper presents the augmentation methods that can be used, and then evaluates them with a novel experience. As a final tough, we can conclude that modern synthetic data generation can develop the robustness of machine learning methods and play an effective role in the inverse heat conduction problem occurring during the quenching of steel.
{"title":"A Novel Machine Learning Solution for the Inverse Heat Conduction Problem with Synthetic Datasets","authors":"Zoltán Biczó, S. Szénási, I. Felde","doi":"10.1109/SACI58269.2023.10158590","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158590","url":null,"abstract":"There are many attempts to solve the Inverse Heat Conduction Problem, and nowadays a growing number of machine learning-based methods have emerged. One major drawback of these methods is that they are very sensitive to the size and quality of the training database. There are several data augmentation techniques for artificially increasing the size of training databases, but these techniques have not yet been investigated in the field of quenching. This paper presents the augmentation methods that can be used, and then evaluates them with a novel experience. As a final tough, we can conclude that modern synthetic data generation can develop the robustness of machine learning methods and play an effective role in the inverse heat conduction problem occurring during the quenching of steel.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"147 Pt 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126315387","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158565
Barnabás Erdei, S. Szénási
Content creation for games and movies is expensive and time-consuming. Meanwhile, there is always a demand by the market every year for improved graphics and effects from these companies. Therefore, automated technologies are a necessity in modern workflows. With the help of procedural techniques, it is possible to accelerate and decrease the cost of this creation process. These algorithms cannot replace content creation artists because of the lack of artistic details in models like landscapes, buildings, characters, and so forth. However, it can provide a great foundation to jumpstart production projects. Because of the diversity of this topic, this paper focuses on only one of the use cases of these techniques: the generation of urban environments.
{"title":"Procedural City Generation","authors":"Barnabás Erdei, S. Szénási","doi":"10.1109/SACI58269.2023.10158565","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158565","url":null,"abstract":"Content creation for games and movies is expensive and time-consuming. Meanwhile, there is always a demand by the market every year for improved graphics and effects from these companies. Therefore, automated technologies are a necessity in modern workflows. With the help of procedural techniques, it is possible to accelerate and decrease the cost of this creation process. These algorithms cannot replace content creation artists because of the lack of artistic details in models like landscapes, buildings, characters, and so forth. However, it can provide a great foundation to jumpstart production projects. Because of the diversity of this topic, this paper focuses on only one of the use cases of these techniques: the generation of urban environments.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132815108","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158589
Olivér M. Balogh, Z. Vámossy
Jigsaw puzzles are a popular form of entertainment. Solving them with the help of computers raises several interesting problems, and has been the subject of many published papers in the past. In this paper, an approach to creating a program that uses pictures of real puzzle pieces to reconstruct the full puzzle image is presented. A photography technique is described that results in consistently recognizable images, which are used to extract features of the puzzle pieces. These features are then compared using two similarity algorithms - Hausdorff distance and Dynamic Time Warping. Three different puzzle assembly strategies that use these comparisons are presented, along with additional logic rules to solve the full puzzle. Using these the final program is capable of solving two different, 25-piece jigsaw puzzles. A comparison of the different similarity measures and assembly algorithms in the scope of the problem is also presented.
{"title":"Solving Jigsaw Puzzles Using Computer Vision and Curve Similarity Measures","authors":"Olivér M. Balogh, Z. Vámossy","doi":"10.1109/SACI58269.2023.10158589","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158589","url":null,"abstract":"Jigsaw puzzles are a popular form of entertainment. Solving them with the help of computers raises several interesting problems, and has been the subject of many published papers in the past. In this paper, an approach to creating a program that uses pictures of real puzzle pieces to reconstruct the full puzzle image is presented. A photography technique is described that results in consistently recognizable images, which are used to extract features of the puzzle pieces. These features are then compared using two similarity algorithms - Hausdorff distance and Dynamic Time Warping. Three different puzzle assembly strategies that use these comparisons are presented, along with additional logic rules to solve the full puzzle. Using these the final program is capable of solving two different, 25-piece jigsaw puzzles. A comparison of the different similarity measures and assembly algorithms in the scope of the problem is also presented.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134242034","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158556
Júlia Zombori, J. Lukács, R. Horváth
Forecasting rainfall is a major challenge, but it would be important as rainfall has a huge effect on the economy and food crises around the world. Currently, there are many mathematical models for weather forecast and for precipitation. Due to the phenomenon of desertification, precipitation forecasting is becoming increasingly important. In this article, a case study is presented on estimating the probability of rainfall using response surface method (RSM). After analyzing real data, a third-order surface model is presented for estimating the rainfall probability (the input parameters are the daily average temperature and the daily average humidity, and the output parameter is the summarized amount of the daily rainfall). It can be revealed that the presented method can be suitable for describing the real-time data used with sufficient accuracy. This study shows the efficiency and the applicability of RSM method for rain predicting.
{"title":"Determination of Rainfall Probability Using Response Surface Method","authors":"Júlia Zombori, J. Lukács, R. Horváth","doi":"10.1109/SACI58269.2023.10158556","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158556","url":null,"abstract":"Forecasting rainfall is a major challenge, but it would be important as rainfall has a huge effect on the economy and food crises around the world. Currently, there are many mathematical models for weather forecast and for precipitation. Due to the phenomenon of desertification, precipitation forecasting is becoming increasingly important. In this article, a case study is presented on estimating the probability of rainfall using response surface method (RSM). After analyzing real data, a third-order surface model is presented for estimating the rainfall probability (the input parameters are the daily average temperature and the daily average humidity, and the output parameter is the summarized amount of the daily rainfall). It can be revealed that the presented method can be suitable for describing the real-time data used with sufficient accuracy. This study shows the efficiency and the applicability of RSM method for rain predicting.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128644804","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158611
J. Varga, Ágnes Csiszárik-Kocsir
The success of any project lies in its acceptance by the end users. For novel initiatives, user acceptance is an even greater risk than for other, ordinary, normal projects. For a novelty to be accepted by users, adopted by other organisations, economic actors and widely used, it needs to be a resounding success. Innovative initiatives affect all sectors of the economy, and education is no exception. The aim of this paper is to illustrate the role of innovative projects and their perception by users through the example of a project considered to be an international example. The project will be presented from the users’ point of view, from the stakeholders’ point of view, through some characteristics of the project scope, highlighting the factors that make it usable and attractive, based on the results of a questionnaire survey.
{"title":"Perception of innovation and innovative projects at user level through the example of the Atala Prism project","authors":"J. Varga, Ágnes Csiszárik-Kocsir","doi":"10.1109/SACI58269.2023.10158611","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158611","url":null,"abstract":"The success of any project lies in its acceptance by the end users. For novel initiatives, user acceptance is an even greater risk than for other, ordinary, normal projects. For a novelty to be accepted by users, adopted by other organisations, economic actors and widely used, it needs to be a resounding success. Innovative initiatives affect all sectors of the economy, and education is no exception. The aim of this paper is to illustrate the role of innovative projects and their perception by users through the example of a project considered to be an international example. The project will be presented from the users’ point of view, from the stakeholders’ point of view, through some characteristics of the project scope, highlighting the factors that make it usable and attractive, based on the results of a questionnaire survey.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128656998","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158612
X. Jiang, István Bíró
Cushioned or stability running shoes is currently a highly debated topic among runners and researchers. Several footwear companies have developed running shoes to simulate different hardness but few studies have compared a triple density running shoe to deduce the injuries of running. The primary goal of this study was to compare acute changes in three-dimensional (3D) ground reaction forces (GRFs) and lower limb kinematics of habitually shod rear-foot strike (RFS) runners between different hardness and density running shoes. Lower limb joint biomechanical variables of fifteen recreational runners were analyzed using a 3D motion capture system and a force platform. The loading rate at the first impact peak showed no difference between the two shoe conditions. The first impact peak was significantly larger in the triple density shoe condition than in the single density shoe. Combining the inversion and eversion of the ankle during the pushing-off phase, a single midsole showed a bigger eversion angle than a density midsole. The innovative running shoes enhanced the rear-foot stability of runners compared to the control running shoe during the loading (eversion) phase of running.
{"title":"The effects of shoes with a triple density midsole on lower limb kinematics and kinetics in male recreational runners","authors":"X. Jiang, István Bíró","doi":"10.1109/SACI58269.2023.10158612","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158612","url":null,"abstract":"Cushioned or stability running shoes is currently a highly debated topic among runners and researchers. Several footwear companies have developed running shoes to simulate different hardness but few studies have compared a triple density running shoe to deduce the injuries of running. The primary goal of this study was to compare acute changes in three-dimensional (3D) ground reaction forces (GRFs) and lower limb kinematics of habitually shod rear-foot strike (RFS) runners between different hardness and density running shoes. Lower limb joint biomechanical variables of fifteen recreational runners were analyzed using a 3D motion capture system and a force platform. The loading rate at the first impact peak showed no difference between the two shoe conditions. The first impact peak was significantly larger in the triple density shoe condition than in the single density shoe. Combining the inversion and eversion of the ankle during the pushing-off phase, a single midsole showed a bigger eversion angle than a density midsole. The innovative running shoes enhanced the rear-foot stability of runners compared to the control running shoe during the loading (eversion) phase of running.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129281902","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158609
K. Dsouza, Lin Zhu, P. Varma-Nelson, S. Fang, S. Mukhopadhyay
Active learning methodologies in higher education benefit students by reinforcing learning and critical skills during the class. In active pedagogical models such as Peer-Led Team Learning (PLTL) students have stronger course outcomes. The instructor is not present in a PLTL workshop and may not receive sufficient feedback from peer leaders. Additionally, these classes have large enrollments. There is a lack of AI-enabled tools that monitor or provide feedback during cPLTL workshops. The current study addresses this gap by proposing an AI-based multimodal solution using recordings of cyber Peer-Led Team Learning (cPLTL) classes. The machine learning model analyzes audio and text features to predict the outcome of a workshop. The results using multimodal learning show potential for further development of the tool. Such improved modeling will help reduce the instructor’s workload facilitating the integration of AI in education. This novel multimodal approach aims to enhance the student’s learning experience by providing an automated feedback mechanism to the instructor.
{"title":"AI-Augmented Peer Led Team Learning for STEM Education","authors":"K. Dsouza, Lin Zhu, P. Varma-Nelson, S. Fang, S. Mukhopadhyay","doi":"10.1109/SACI58269.2023.10158609","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158609","url":null,"abstract":"Active learning methodologies in higher education benefit students by reinforcing learning and critical skills during the class. In active pedagogical models such as Peer-Led Team Learning (PLTL) students have stronger course outcomes. The instructor is not present in a PLTL workshop and may not receive sufficient feedback from peer leaders. Additionally, these classes have large enrollments. There is a lack of AI-enabled tools that monitor or provide feedback during cPLTL workshops. The current study addresses this gap by proposing an AI-based multimodal solution using recordings of cyber Peer-Led Team Learning (cPLTL) classes. The machine learning model analyzes audio and text features to predict the outcome of a workshop. The results using multimodal learning show potential for further development of the tool. Such improved modeling will help reduce the instructor’s workload facilitating the integration of AI in education. This novel multimodal approach aims to enhance the student’s learning experience by providing an automated feedback mechanism to the instructor.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131868714","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158656
Maria C. Brad, A. A. Brad, M. Micea
This paper presents a machine learning-based method for detecting lanes on roads. The proposed approach includes several processing steps such as preprocessing of the original image frames, application of the Hough Line Transform for an initial detection of lanes, computation of the vanishing point to determine the horizon line, and region of interest (ROI) determination. Additionally, the method compensates for the unknown position of the camera facing the road by cropping a triangle-shaped perspective area. To correct errors caused by road discoloration and cracks, a color mask for white and yellow pixels is used. The orientation of the lanes is determined by analyzing the slope of the lines, and the lane coordinates are linked to the image center. The proposed method uses the U-Net neural network and the implementation is based on the Python programming language and OpenCV image processing library. In the final section we also present a comparison with a lane detection method based on convolutional neural networks and discuss the results.
{"title":"Method for Autonomous Lane Detection in Assisted Driving","authors":"Maria C. Brad, A. A. Brad, M. Micea","doi":"10.1109/SACI58269.2023.10158656","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158656","url":null,"abstract":"This paper presents a machine learning-based method for detecting lanes on roads. The proposed approach includes several processing steps such as preprocessing of the original image frames, application of the Hough Line Transform for an initial detection of lanes, computation of the vanishing point to determine the horizon line, and region of interest (ROI) determination. Additionally, the method compensates for the unknown position of the camera facing the road by cropping a triangle-shaped perspective area. To correct errors caused by road discoloration and cracks, a color mask for white and yellow pixels is used. The orientation of the lanes is determined by analyzing the slope of the lines, and the lane coordinates are linked to the image center. The proposed method uses the U-Net neural network and the implementation is based on the Python programming language and OpenCV image processing library. In the final section we also present a comparison with a lane detection method based on convolutional neural networks and discuss the results.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129420943","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 : 2023-05-23DOI: 10.1109/SACI58269.2023.10158628
S. Ardabili, Amir H. Mosavi, I. Felde
Deep learning (DL) is a promising technology for enhancing the development of fifth generation (5G) and sixth generation (6G) mobile networks, as it can improve their capabilities, security, and performance. However, there are still significant challenges to be addressed in the implementation of DL techniques in these networks. To address these challenges, we conducted a systematic review of the literature on DL techniques in 5G and 6G applications following the PRISMA guidelines. The review was conducted in three stages: data collection, analysis, and reporting of primary findings. After evaluating and reviewing the databases, we found that hybrid DL and ensemble techniques show promise in optimizing 5G and 6G networks, given proper implementation. Finally, we discussed the open issues and challenges in this field. This review provides important insights into the potential of DL techniques in improving 5G and 6G networks, and it highlights the need for further research to overcome the remaining challenges. The results of this primary communication will be further developed and extended into a journal article.
{"title":"Deep learning for 5G and 6G","authors":"S. Ardabili, Amir H. Mosavi, I. Felde","doi":"10.1109/SACI58269.2023.10158628","DOIUrl":"https://doi.org/10.1109/SACI58269.2023.10158628","url":null,"abstract":"Deep learning (DL) is a promising technology for enhancing the development of fifth generation (5G) and sixth generation (6G) mobile networks, as it can improve their capabilities, security, and performance. However, there are still significant challenges to be addressed in the implementation of DL techniques in these networks. To address these challenges, we conducted a systematic review of the literature on DL techniques in 5G and 6G applications following the PRISMA guidelines. The review was conducted in three stages: data collection, analysis, and reporting of primary findings. After evaluating and reviewing the databases, we found that hybrid DL and ensemble techniques show promise in optimizing 5G and 6G networks, given proper implementation. Finally, we discussed the open issues and challenges in this field. This review provides important insights into the potential of DL techniques in improving 5G and 6G networks, and it highlights the need for further research to overcome the remaining challenges. The results of this primary communication will be further developed and extended into a journal article.","PeriodicalId":339156,"journal":{"name":"2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129942671","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：