Systems and Soft Computing最新文献_第9页

Nonlinear PID controllers improved based on the quad rotor aircraft 基于四旋翼飞行器的非线性PID控制器改进

Systems and Soft Computing Pub Date : 2025-02-07 DOI: 10.1016/j.sasc.2025.200197

Hongcheng Zhou

引用次数: 0

Citrus diseases detection and classification based on efficientnet-B5 基于efficientnet-B5的柑橘病害检测与分类

Systems and Soft Computing Pub Date : 2025-02-07 DOI: 10.1016/j.sasc.2025.200199

Abdullahi Lawal Rukuna , F.U. Zambuk , A.Y. Gital , Umar Muhammad Bello

{"title":"Citrus diseases detection and classification based on efficientnet-B5","authors":"Abdullahi Lawal Rukuna , F.U. Zambuk , A.Y. Gital , Umar Muhammad Bello","doi":"10.1016/j.sasc.2025.200199","DOIUrl":"10.1016/j.sasc.2025.200199","url":null,"abstract":"<div><div>The detection and classification of citrus diseases are critical for ensuring the health and productivity of citrus fruits. This research focuses on enhancing the accuracy and effectiveness of citrus disease detection and classification using the EfficientNet-B5 model. The dataset, sourced from Kaggle, includes images of various citrus diseases: black spot, canker, huanglongbing (greening), and healthy instances. To address class imbalance and improve data diversity, synthetic minority oversampling technique (SMOTE) and augmentation fusion were employed, resulting in 970 images per class. The preprocessed data were partitioned into training, validation, and test sets. The efficientNet-B5 model was trained and validated, achieving a remarkable accuracy of 99.22 %. The study also includes a comprehensive comparison with existing systems based on accuracy and loss curves, confusion matrices, and classification reports. The proposed system demonstrated superior performance, outperforming other models in terms of both accuracy and robustness, highlighting its potential for practical applications in citrus disease management.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200199"},"PeriodicalIF":0.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A systematic assessment of sentiment analysis models on iraqi dialect-based texts 伊拉克方言语篇情感分析模型的系统评价

Systems and Soft Computing Pub Date : 2025-02-07 DOI: 10.1016/j.sasc.2025.200203

Hafedh Hameed Hussein, Amir Lakizadeh

引用次数: 0

Application of improved particle swarm optimization algorithm combined with genetic algorithm in shear wall design 改进粒子群优化算法结合遗传算法在剪力墙设计中的应用

Systems and Soft Computing Pub Date : 2025-02-07 DOI: 10.1016/j.sasc.2025.200198

Wei Gao

{"title":"Application of improved particle swarm optimization algorithm combined with genetic algorithm in shear wall design","authors":"Wei Gao","doi":"10.1016/j.sasc.2025.200198","DOIUrl":"10.1016/j.sasc.2025.200198","url":null,"abstract":"<div><div>In order to achieve the rationality and economy of shear wall layout, an improved algorithm was designed in the architectural design program. The improved algorithm is based on the basic framework of genetic algorithm and particle swarm optimization algorithm, first adjusting the inertia weight, and then introducing elimination mechanism and mutation rate control. A shear wall design model was constructed using an improved algorithm, which was applied to determine the layout of shear walls in a 28 story high-rise building in a certain city. The example results show that when using the designed shear wall design program for scheme design, the success rate reaches 100 %, which is 38.47 % higher than the original particle swarm optimization algorithm. The obtained optimization scheme has interlayer displacement angles of 1/2096 and 1/1800 in the vertical and horizontal directions, respectively, while the torsional displacement ratio in both directions is 1.0908 and the torsional period ratio is 0.7125. After optimizing the algorithm, the length of the shear wall material was saved by 10.97 %, effectively reducing the use of materials. This not only reduces construction costs, but also brings higher space utilization efficiency. The building design scheme obtained from this study not only meets national standards, but also has lower computational time costs. This study demonstrates the potential application of this design algorithm in solving traditional architectural design problems. This not only provides new tools for the field of architectural design, but also stimulates more interdisciplinary cooperation, integrating computer science, artificial intelligence technology more closely with building engineering.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200198"},"PeriodicalIF":0.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of basic sports actions for students based on DTW posture matching algorithm 基于DTW姿态匹配算法的学生基本运动动作评价

Systems and Soft Computing Pub Date : 2025-02-07 DOI: 10.1016/j.sasc.2025.200196

Zhonghai Chen , Tengyu Zhang

{"title":"Evaluation of basic sports actions for students based on DTW posture matching algorithm","authors":"Zhonghai Chen , Tengyu Zhang","doi":"10.1016/j.sasc.2025.200196","DOIUrl":"10.1016/j.sasc.2025.200196","url":null,"abstract":"<div><div>In the evaluation of basic sports movements for students, traditional evaluation methods are usually limited by static indicators, making it difficult to comprehensively capture students' performance in dynamic sports movements. Therefore, the study proposes a student sports basic action evaluation method based on the dynamic time warping posture matching algorithm, focusing on the action recognition, and the method is verified. These experiments confirmed that the average error of this proposed method in positioning accuracy testing was significantly smaller than the other two comparison algorithms, with an average error of 11.43 mm, 15.35 mm, and 20.38 mm on the X, Y, and Z axes, respectively. Moreover, its recognition rate for broadcast gymnastics was as high as 99.5 %. To verify the practical application significance of the research, the score of student S8 reached 9.95. After 8 weeks of training, the average muscle mass was increased by 52.9 %, and the maximum oxygen uptake was increased by 34.1 %. In contrast, student S9 with a score of 5.56 showed a relatively small improvement, with a 25.8 % increase in muscle mass and only a 19.1 % increase in maximum oxygen uptake. The innovative application of the posture matching algorithm in the evaluation of basic sports movements of students provides a feasible and effective method for improving the level of physical education and sports health management.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200196"},"PeriodicalIF":0.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Personalized icon design model based on improved Faster-RCNN 基于改进型 Faster-RCNN 的个性化图标设计模型

Systems and Soft Computing Pub Date : 2025-01-30 DOI: 10.1016/j.sasc.2025.200193

Zhikun Wang , Jiaqian Wang

{"title":"Personalized icon design model based on improved Faster-RCNN","authors":"Zhikun Wang , Jiaqian Wang","doi":"10.1016/j.sasc.2025.200193","DOIUrl":"10.1016/j.sasc.2025.200193","url":null,"abstract":"<div><div>In the digital age, as an important element of visual communication, icons have an increasing demand for personalized design. In order to meet the personalized icon design needs of students, education, management, and design fields, a personalized icon design model based on a faster regional suggestion network is proposed. Firstly, the convolutional neural network is improved to extract the multi-attribute features of icons. The transfer learning is used to optimize model parameter sharing. Then, the improved faster region-Convolutional network model is adopted for object detection, enhancing the ability to classify and recognize icons. The designed method had a recognition accuracy of over 80% in different types of icons. Among different types of icon data, the recognition accuracy of office type icons was the worst, with a recognition accuracy of 81.3%. The recognition accuracy of traffic type icons was the highest, with a recognition accuracy of 98.3%. The model had a processing time of less than 350 ms for different types of icons, with the shortest processing time of 233 ms for social media icons. The research results indicate that the proposed model has high practicality in icon personalized design, and can provide convenient tool support for designers, students, teachers, and users in the field of education management, promoting the popularization and application of personalized icon design.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200193"},"PeriodicalIF":0.0,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Path planning of factory handling robot integrating fuzzy logic-PID control technology 融合模糊逻辑- pid控制技术的工厂搬运机器人路径规划

Systems and Soft Computing Pub Date : 2025-01-22 DOI: 10.1016/j.sasc.2025.200188

Guobin Si , Ruijie Zhang , Xiaofeng Jin

{"title":"Path planning of factory handling robot integrating fuzzy logic-PID control technology","authors":"Guobin Si , Ruijie Zhang , Xiaofeng Jin","doi":"10.1016/j.sasc.2025.200188","DOIUrl":"10.1016/j.sasc.2025.200188","url":null,"abstract":"<div><div>Mobile robots have been widely used in various fields to assist people in completing various tasks. This study aims to enhance the efficiency of mobile robots in factory transportation tasks by improving the A-star algorithm and combining it with the dynamic window approach. Additionally, a fuzzy proportional-integral-differential (PID) controller is developed for adaptive path correction. To address the issue of robot driving deviation on complex roads, a PID controller is fused with fuzzy logic to adaptively adjust the implementation parameters and construct a path correction model. The test results show that the average time for A-star algorithm to search for a path is 5.19 s, the average number of grids searched is 160, and the average length of the search path is 30.2 cm. The average search path time of the improved A-star algorithm is 2.45 s, the average number of grids searched is 98, and the average length of the search path is 27.9 cm. On a 20 × 20 cm map, the fused algorithm improves the shortcomings of both algorithms and can smoothly avoid obstacles to find the global optimal path. The fuzzy PID control algorithm's convergence time is 0.042 s, and after adding the load of external forces, the fuzzy PID controller does not experience significant turbulence. The results indicate that the robot controlled by the adaptive fuzzy PID controller has stability and effectiveness in path correction control.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200188"},"PeriodicalIF":0.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143386931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application of an intelligent English text classification model with improved KNN algorithm in the context of big data in libraries 基于改进KNN算法的智能英语文本分类模型在图书馆大数据背景下的应用

Systems and Soft Computing Pub Date : 2025-01-17 DOI: 10.1016/j.sasc.2025.200186

Qinwen Xu

{"title":"Application of an intelligent English text classification model with improved KNN algorithm in the context of big data in libraries","authors":"Qinwen Xu","doi":"10.1016/j.sasc.2025.200186","DOIUrl":"10.1016/j.sasc.2025.200186","url":null,"abstract":"<div><div>In the era of big data, libraries manage huge electronic text resources, of which English text resources are particularly critical for academic research, student learning, and professional knowledge acquisition. This paper aims to improve the K-nearest neighbor algorithm and design an intelligent classification model to improve the efficiency and quality of library services. An improved method based on in-class K-means clustering and class mean distance is used to characterize and extract text information with a vector space model. The results showed that the improved K-nearest neighbor algorithm achieved significant improvement in the precision, recall, and F1 values, reaching 90.50 %, 89.95 %, and 89.37 %, respectively. The classification time was significantly reduced to 1034.57 s. In addition, the improved algorithm had a classification accuracy of 94 %, surpassing other popular text classification algorithms. The research successfully realizes the efficient classification of text. The research results not only improve the classification efficiency of library English text resources but also provide strong support for readers to quickly obtain the required information, which has important application value and wide application prospects.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200186"},"PeriodicalIF":0.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143148527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analyzing the quality evaluation of college English teaching based on probabilistic linguistic multiple-attribute group decision-making 基于概率语言多属性群体决策的大学英语教学质量评价分析

Systems and Soft Computing Pub Date : 2025-01-17 DOI: 10.1016/j.sasc.2025.200191

Ruoxi Hu , Qingmao Wang

{"title":"Analyzing the quality evaluation of college English teaching based on probabilistic linguistic multiple-attribute group decision-making","authors":"Ruoxi Hu , Qingmao Wang","doi":"10.1016/j.sasc.2025.200191","DOIUrl":"10.1016/j.sasc.2025.200191","url":null,"abstract":"<div><div>The evaluation of college English teaching quality aims to comprehensively assess the achievement of teaching objectives and effectiveness through the analysis and feedback on teachers' teaching abilities, course design, and students' learning outcomes. The evaluation combines both quantitative and qualitative methods, focusing not only on the scientific and practical aspects of teaching content but also on the improvement of students' language proficiency and overall development. A scientific evaluation system encourages teachers to refine their teaching methods, enhances teaching efficiency, and provides data support for curriculum optimization, thereby continuously improving the quality of college English teaching to meet students' academic and career development needs. The quality evaluation of college English teaching is multiple-attribute group decision-making (MAGDM). To address this, combined TODIM (Logarithmic TODIM and Exponential TODIM) and PROMETHEE approaches are utilized to propose a MAGDM framework. Considering the need to capture fuzzy information during the quality evaluation process, probabilistic linguistic term sets (PLTSs) are employed. In this study, we construct the probabilistic linguistic combined TODIM-PROMETHEE (PL-Com-TODIM-PROMETHEE) approach to tackle MAGDM under PLTSs. To determine the weight values within the PLTSs framework, we employ the MEREC approach. Finally, a numerical example is presented to validate the effectiveness of the PL-Com-TODIM-PROMETHEE approach for quality evaluation of college English teaching. Through this approach, the study contributes to the advancement of quality evaluation methodologies by integrating combined TODIM and PROMETHEE within the PLTSs framework. It addresses the challenges posed by fuzzy information and provides a practical and effective approach for decision-making in the context of quality evaluation of college English teaching.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200191"},"PeriodicalIF":0.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143148528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interior design assistant algorithm based on indoor scene analysis 基于室内场景分析的室内设计辅助算法

Systems and Soft Computing Pub Date : 2025-01-17 DOI: 10.1016/j.sasc.2025.200190

Lu Zhang

{"title":"Interior design assistant algorithm based on indoor scene analysis","authors":"Lu Zhang","doi":"10.1016/j.sasc.2025.200190","DOIUrl":"10.1016/j.sasc.2025.200190","url":null,"abstract":"<div><div>The scene analysis algorithm in interior design is widely used in computer vision. To achieve superior interior design outcomes, it is essential to accurately identify and locate indoor objects and structures. However, the common algorithms currently rely too much on color images and manual annotation. Accordingly, the objective of the research is to enhance the interior scene analysis algorithm in interior design, thereby optimizing its performance in the domain of computer vision. In light of the shortcomings of existing algorithms that rely excessively on color images and manually labeled data, this paper employs a dual feature encoder to conduct a comprehensive mining of deep image features, thereby markedly enhancing the precision of semantic segmentation. Then, the accuracy of indoor scene analysis is further improved by integrating the texture features of color images into the modal knowledge distillation of depth images. In addition, to reduce the dependence on manually labeled data, an unsupervised cooperative segmentation algorithm is proposed, which realizes automatic image semantic segmentation through the segmentation process from superpixel to block and then to object. The experimental results showed that the proposed algorithm based on modal knowledge distillation had an average accuracy of 48.29 % in the four types of output. The FIoU value of the unsupervised image cooperative segmentation algorithm reached 66.20, which is superior to the existing algorithms and can better match the real indoor scene. The proposed indoor scene analysis algorithm using color images as privileged information significantly improves the accuracy of indoor scene analysis and reduces reliance on manually annotated data. Moreover, the research algorithm effectively identifies indoor objects, protects personal privacy, and provides a better solution for indoor object analysis.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200190"},"PeriodicalIF":0.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143149505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0