Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence最新文献_第2页

Efficient Adaptive Convolutional Model Based on Label Embedding for Text Classification Using Low Resource Languages 基于标签嵌入的高效自适应卷积模型在低资源语言文本分类中的应用

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596962

V. K. Agbesi, Chen Wenyu, Abush S. Ameneshewa, E. Odame, Koffi Dumor, Judith Ayekai Browne

{"title":"Efficient Adaptive Convolutional Model Based on Label Embedding for Text Classification Using Low Resource Languages","authors":"V. K. Agbesi, Chen Wenyu, Abush S. Ameneshewa, E. Odame, Koffi Dumor, Judith Ayekai Browne","doi":"10.1145/3596947.3596962","DOIUrl":"https://doi.org/10.1145/3596947.3596962","url":null,"abstract":"Text classification technology has been efficiently deployed in numerous organizational applications, including subject tagging, intent, event detection, spam filtering, and email routing. This also helps organizations streamline processes, enhance data-driven operations, and evaluate and analyze textual resources quickly and economically. This progress results from numerous studies on high-resource language-based text classification tasks. However, research in low-resource languages, including Ewe, Arabic, Filipino, and Kazakh, lags behind other high-resource languages like English. Also, the most difficult aspect of text classification using low-resource languages is identifying the optimal set of filters for its feature extraction. This is due to their complex morphology, linguistic diversity, multilingualism, and syntax. Studies that have explored these problems failed to efficiently use label information to better the performance of their methods. As a result, the label information for these languages needs to be adequately utilized to enhance classification results. To solve this problem, this study proposes an efficient adaptive convolutional model based on label embedding (EAdaCLE) to efficiently represent label information and utilize the learned label representations for various text classification tasks. EAdaCLE has adaptively engineered convolutional filters trained on inputs based on label embeddings generated in the same network as the text vectors. EAdaCLE ensures the adaptability of adaptive convolution and completely obtains label data as a supporting function to enhance the classification results. Extensive experiments indicate that our technique is more reliable than other methods on four low-resource public datasets.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133028105","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}

引用次数: 0

Set-based Particle Swarm Optimization for Data Clustering: Comparison and Analysis of Control Parameters 基于集的粒子群数据聚类优化:控制参数的比较与分析

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596956

Rijk Marius de Wet, A. Engelbrecht

引用次数: 0

Framework for Healthy/Hemorrhagic Brain Condition Detection using CT Scan Images 使用CT扫描图像检测健康/出血性脑状况的框架

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596963

Seifedine Kadry, A. Gandomi

{"title":"Framework for Healthy/Hemorrhagic Brain Condition Detection using CT Scan Images","authors":"Seifedine Kadry, A. Gandomi","doi":"10.1145/3596947.3596963","DOIUrl":"https://doi.org/10.1145/3596947.3596963","url":null,"abstract":"In human physiology, the brain plays a significant role as the control center of all regulatory processes. Any abnormality in the brain could lead to various physiological and psychological problems and, thus, demands early detection and treatment. Accurate identification of a brain condition is vital during treatment planning. Hence, medical imaging combined with Artificial Intelligence (AI) schemes is widely employed in hospitals to achieve better detection accuracy. Specifically, a brain hemorrhage is a medical emergency that needs immediate treatment to reduce its impact. Therefore, this research aimed to develop and implement a Lightweight Deep Learning (LDL) procedure to classify brain Computed Tomography (CT) slices into healthy/hemorrhagic classes. The various stages of this scheme involve: (i) image collection, resizing, and preprocessing; (ii) LDL feature extraction; and (iii) binary classification with 3-fold cross-validation. In this work, the CT slices were initially preprocessed with a threshold filter and then considered to verify the performance of the proposed scheme based on individual and dual features. The experimental outcome of this study con-firms that the dual features help to achieve a detection accuracy of >96% with the Support Vector Machine (SVM) classifier.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127488009","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}

引用次数: 0

Feedback-Circulating Design Space Exploration by Multi-Sampling Kriging Model: Exploitation for the Lift Rise by an Aircraft Flap with Yaw-Wise Rotation 基于多采样克里格模型的反馈循环设计空间探索:偏航旋转襟翼升力上升的研究

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596950

Kazuhisa Chiba, Masahiro Kanazaki

{"title":"Feedback-Circulating Design Space Exploration by Multi-Sampling Kriging Model: Exploitation for the Lift Rise by an Aircraft Flap with Yaw-Wise Rotation","authors":"Kazuhisa Chiba, Masahiro Kanazaki","doi":"10.1145/3596947.3596950","DOIUrl":"https://doi.org/10.1145/3596947.3596950","url":null,"abstract":"This study has investigated whether adding yaw-wise rotation to an aircraft flap improves lift performance and elucidated its improvement mechanism. The aircraft is optimized for cruising conditions and lacks takeoff and landing performance. Hence, high-lift devices, such as slats and flaps, compensate for the lift performance. Since flaps move along rails, the gap between the wing and the flap is spanwise constant. However, since the flow field is three-dimensional, the gap should also have a spanwise distribution to raise the lift. Thus, this study defined a design problem for lift maximization with the gap and the yaw-wise rotation angle as design variables. This problem adopted a surrogate model because of the small number of objective functions and design variables. A Kriging model modified to add multiple sample points optimized this problem. Furthermore, the study utilized a feedback-circulating exploration to reach the physical essence of the problem. The result eventually revealed that adding a rotation angle ameliorated the lift. The acceleration of the flow velocity through the gap at the appropriate spanwise position causes the separation of the flap’s upper surface to recede, further reducing the pressure on the wing’s upper surface and growing the lift on both the flap and the wing.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124645415","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}

引用次数: 0

Machine Learning for Socially Responsible Portfolio Optimisation 面向社会责任投资组合优化的机器学习

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596966

Taeisha Nundlall, Terence L van Zyl

引用次数: 0

Habitat Prediction and Knowledge Extraction for Marine Bivalves using Machine Learning Techniques 基于机器学习技术的海洋双壳类生境预测与知识提取

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596964

A. B. Maravillas, L. Feliscuzo, J. A. Nogra

{"title":"Habitat Prediction and Knowledge Extraction for Marine Bivalves using Machine Learning Techniques","authors":"A. B. Maravillas, L. Feliscuzo, J. A. Nogra","doi":"10.1145/3596947.3596964","DOIUrl":"https://doi.org/10.1145/3596947.3596964","url":null,"abstract":"Species distribution models (SDMs) are powerful tools for analyzing the relationships between species and the environment. SDM results can provide insights into a species’ response to a given habitat condition, making it crucial to compare SDMs based on their predictive performance and habitat information. The marine bivalves’ habitat has been highly threatened due to anthropogenic activities and natural disturbances and continues to lose their rich biodiversity resources. Protection for these species requires detailed spatial distribution of these habitats such as habitat suitability maps. Three machine learning methods (Maximum Entropy, Random Forest, and Support Vector Machine) and Artificial Neural Network (ANN) models were used to predict the habitat suitability for marine bivalves, comparing their predictive performance and ecological relevance. A spatial modeling approach was used, incorporating 1200 occurrence data points and ten environmental factors. The study used five performance metrics to estimate the accuracy of the habitat suitability models. All of the four SDMs methods showed significant relationship between the marine bivalves distribution and environmental factors. Results indicate that Random Forest (RF) model is the best predictor of potential bivalve habitat, with an area under curve (AUC) value of 0.98 compared to SVM (0.87), MaxEnt (0.97) and ANN (0.87) models. The most important environmental factors that affect the bivalve’s distribution in the area were pH, diffuse, and calcite. Finally, a potential area for cultivating the marine bivalves with high and very suitability was suggested based on the RF model.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123210206","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}

引用次数: 0

Chaos Gray Wolf global optimization algorithm based on Opposition-based Learning 基于对立学习的混沌灰狼全局优化算法

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596960

Zhiyong Luo, Mingxiang Tan, Zhengwen Huang, Guoquan Li

{"title":"Chaos Gray Wolf global optimization algorithm based on Opposition-based Learning","authors":"Zhiyong Luo, Mingxiang Tan, Zhengwen Huang, Guoquan Li","doi":"10.1145/3596947.3596960","DOIUrl":"https://doi.org/10.1145/3596947.3596960","url":null,"abstract":"Gray wolf optimizer (GWO) is a new heuristic algorithm. It has few parameters and strong optimization ability and is used in many fields. However, when solving complex and multimodal functions, it is also easy to trap into the local optimum and premature convergence. In order to boost the performance of GWO, a tent chaotic map and opposition-based learning Grey Wolf Optimizer (CO-GWO) is proposed. Firstly, some better values of the population in the current generation are retained to avoid deterioration in the next generation. Secondly, tent chaotic map and opposition-based (OBL)are introduced to generate values that can traverse the whole feasible region as much as possible, which is conducive to jumping out of local optimization and accelerating convergence. Then, the coefficient is dynamically adjusted by the polynomial attenuation function of the 2-decay method. Finally, the proposed algorithm is tested on 23 benchmark functions. The results show that the proposed algorithm is superior to the conventional heuristic algorithms, GWO and its variants in search-efficiency, solution accuracy and convergence rate.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125141520","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}

引用次数: 0

A self-adaptive system of systems architecture to enable its ad-hoc scalability: Unmanned Vehicle Fleet - Mission Control Center Case study 一种自适应的系统架构系统，使其具有特别的可扩展性:无人驾驶车队-任务控制中心案例研究

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-23 DOI: 10.1145/3596947.3596949

Ahmed R. Sadik, B. Bolder, Pero Subasic

{"title":"A self-adaptive system of systems architecture to enable its ad-hoc scalability: Unmanned Vehicle Fleet - Mission Control Center Case study","authors":"Ahmed R. Sadik, B. Bolder, Pero Subasic","doi":"10.1145/3596947.3596949","DOIUrl":"https://doi.org/10.1145/3596947.3596949","url":null,"abstract":"The concept of System of Systems (SoS) refers to a collection of Constituent Systems (CSs) that interact to deliver an emergent behavior that cannot be achieved by any individual CS on its own. The focus of this research is on the ad-hoc scalability of SoS, meaning that the size of the system can change during operation by adding or removing a CS or changing the size of existing CSs. The Unmanned Vehicle Fleet (UVF) is selected as a practical example to showcase the challenge and solution of ad-hoc scalability. UVF has various applications in fields such as search and rescue, intelligent transportation and mobility, but it operates in a dynamic environment that is prone to uncertainties like changing missions, increasing range and capacity, UV failures, and battery requirements. The proposed solution to overcome these uncertainties is a self-adaptive system that can dynamically change the UVF architecture in real-time, allowing for upscaling or downscaling the size of the UVF. The Mission Control Center (MCC) can control this change either through fully-automatic mode based on performance criteria like battery utilization and communication traffic, or through manual mode where the operator makes the decision. A multi-agent environment and rule management engine are implemented to simulate the UVF behavior and validate the proposed solution in both automatic and manual modes.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115128612","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}

引用次数: 1

A Learnheuristic Approach to A Constrained Multi-Objective Portfolio Optimisation Problem 约束多目标投资组合优化问题的启发式学习方法

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-13 DOI: 10.1145/3596947.3596965

Sonia Bullah, Terence L van Zyl

{"title":"A Learnheuristic Approach to A Constrained Multi-Objective Portfolio Optimisation Problem","authors":"Sonia Bullah, Terence L van Zyl","doi":"10.1145/3596947.3596965","DOIUrl":"https://doi.org/10.1145/3596947.3596965","url":null,"abstract":"Multi-objective portfolio optimisation is a critical problem researched across various fields of study as it achieves the objective of maximising the expected return while minimising the risk of a given portfolio at the same time. However, many studies fail to include realistic constraints in the model, which limits practical trading strategies. This study introduces realistic constraints, such as transaction and holding costs, into an optimisation model. Due to the non-convex nature of this problem, metaheuristic algorithms, such as NSGA-II, R-NSGA-II, NSGA-III and U-NSGA-III, will play a vital role in solving the problem. Furthermore, a learnheuristic approach is taken as surrogate models enhance the metaheuristics employed. These algorithms are then compared to the baseline metaheuristic algorithms, which solve a constrained, multi-objective optimisation problem without using learnheuristics. The results of this study show that, despite taking significantly longer to run to completion, the learnheuristic algorithms outperform the baseline algorithms in terms of hypervolume and rate of convergence. Furthermore, the backtesting results indicate that utilising learnheuristics to generate weights for asset allocation leads to a lower risk percentage, higher expected return and higher Sharpe ratio than backtesting without using learnheuristics. This leads us to conclude that using learnheuristics to solve a constrained, multi-objective portfolio optimisation problem produces superior and preferable results than solving the problem without using learnheuristics.","PeriodicalId":183071,"journal":{"name":"Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129296339","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}

引用次数: 0

Leveraging Deep Learning Approaches for Deepfake Detection: A Review 利用深度学习方法进行深度伪造检测:综述

Proceedings of the 2023 7th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence Pub Date : 2023-04-04 DOI: 10.1145/3596947.3596959

Aniruddha Tiwari, Rushit Dave, Mounika Vanamala

引用次数: 6