检索结果-内蒙古大学图书馆

Optimised EfficientNet for multi-class skin cancer diagnosis: integrating chaotic grey wolf algorithms

Current science 2025年第7期128卷 728-736页

作者： Rama, P. Angayarkanni, V. Theresa, W. Gracy Pandiaraj, A. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai600 123 India

The detection of skin cancer holds paramount importance worldwide due to its impact on global health. While deep convolutional neural networks (DCNNs) have shown potential in this domain, current approaches often struggle with fine-grained variability in skin lesion features, imbalanced datasets and inadequate augmentation. The objectives of our study encompass building a model that not only enhances accuracy but also reduces training time and cost, improves dimensionality reduction during classification and segmentation, and is evaluated on larger datasets for robustness. We enhance the learning process using an improved nature-inspired optimisation algorithm tailored specifically for skin cancer classification tasks. This algorithm optimises model parameters to maximise classification accuracy while minimising computational overhead. Our proposed architecture leverages a gold standard dermatological image dataset meticulously curated and validated by experts. This dataset spans eight distinct classes, including actinic keratosis, basal cell carcinoma, melanoma, nevus, and others, ensuring a diverse representation of skin conditions. The balanced class distribution in the training and test sets enables fair evaluation and robustness assessment of our deep learning models. The developed algorithm showcases novelty in its approach, contributing to advancements in early skin cancer detection technologies. This study introduces an optimised deep learning model designed for the early detection of skin cancer, achieving a notable accuracy of 97.48%. Our study aims to contribute significantly to the medical field by providing a reliable and efficient tool for dermatologists and healthcare practitioners to assist in diagnosing skin conditions accurately and promptly, ultimately improving patient outcomes and healthcare efficiency. © (2025), (Indian Academy of sciences). All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 236-248页

作者： Zhen-Hong Shang Long Chen Zhen-Ping Qiang Yi Bi Run-Xin Li Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology College of Big Data and Intelligent Engineering Southwest Forestry University Yunnan Observatories Chinese Academy of Sciences

Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar *** paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar *** proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow ***,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow *** apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar *** experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index ***,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity *** code is available at https://***/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.

关键词： methods: data analysis techniques: image processing Sun: fundamental parameters

来源：评论

学校读者我要写书评

暂无评论

Enhancing the security of cross-chain by reputation-incentive mechanism with trustrank algorithm 4

Enhancing the security of cross-chain by reputation-incentiv...

引用

4th International Conference on Digital Signal and Computer Communications, DSCC 2024

作者： Dou, Yinyan Zheng, Yukun Liu, Yuanzhe Hu, Shanwen Cai, Zhiming Faculty of Data Science City University of Macau China Faculty of Digital Science and Technology Macau Millennium College China

ISBN: (纸本)9781510681538

The development of cross-chain technology has opened possibilities for interoperability within the blockchain transactions. However, security concerns regarding cross-chain transactions have remained a key issue in this field. This paper introduces an innovative TrustRank algorithm aiming at enhancing cross-chain security by optimizing reputation-incentive mechanisms. Specifically, the study concentrated on the reputation-incentive mechanism of the TrustRank algorithm, evaluating the intrinsic value of nodes based on their transaction history within a single chain and their significance as notaries in cross-chain interactions. In the algorithm proposed in this paper, TrustRank propagation weights are introduced to establish relationships between nodes. Through experiment and performance evaluation, the effectiveness of the TrustRank improved algorithm in enhancing cross-chain security is demonstrated. The results illustrate preventing malicious activities and attacks, as well as in the security of cross-chain smart contracts. © 2024 SPIE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Chatbots in Academia: A Retrieval-Augmented Generation Approach for Improved Efficient Information Access 16

Chatbots in Academia: A Retrieval-Augmented Generation Appro...

引用

16th International Conference on Knowledge and Smart technology, KST 2024

作者： Maryamah, Maryamah Irfani, Muhammad Maula Tri Raharjo, Edric Boby Rahmi, Netri Alia Ghani, Mohammad Raharjana, Indra Kharisma Universitas Airlangga Data Science Technology Faculty of Advanced Technology and Multidiscipline Surabaya Indonesia Universitas Airlangga Informations Systems Faculty of Science and Technology Surabaya Indonesia

ISBN: (纸本)9798350370737

In today's digital age, higher education utilizes chatbots as virtual assistants to assist users, especially prospective students to access information easily. A chatbot is an application in natural language conversations to simulate intelligent interactions. Intelligent chatbots are needed to understand user needs and answer questions relevantly. We propose a chatbot with Retrieval Augmented Generation approach involving a retriever with cosine similarity search using OpenAI Ada embeddings to obtain relevant documents. The LLM OpenAI GPT-3.5- Turbo then generates the final answer. The chatbot mechanism begins with the retrieval module systematically identifying documents stored in the vector database that contain relevant information related to the user's query. The selected documents and query are provided to the LLM as part of the prompt to generate responses based on the knowledge provided in the relevant documents. The retrieval method is evaluated based on two criteria: the search method and the embedding model. The comparison method uses similarity search with Maximum Marginal Relevance (MMR) Search and the proposed embedding method against other models such as Google Embedding-001 and MPNet-Multilingual. The retrieval process is assessed using an evaluation dataset that incorporates Recall and Precision metrics, while answer generation is measured with BLEU and ROUGE Score. The observed disparity result between similarity search and MMR is not notably significant. Nonetheless, our chatbot holds an advantage in referencing past conversations due to its ability to store conversation history. Furthermore, potential enhancements are identified by augmenting the knowledge provided to the LLM in forthcoming iterations. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Retinal Disease Classification: Binary and Multiclass Perspectives 4

Retinal Disease Classification: Binary and Multiclass Perspe...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Lanjewar, Rutuja Nitin Pacharaney, Utkarsha Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India

ISBN: (纸本)9798331523923

Retinal diseases, among which diabetic retinopathy, age-related macular degeneration, and glaucoma account for the greatest number of blindness cases worldwide, affect more than 338 million people. It is essential that early detection leads to timely intervention to preserve vision, but it is limited due to the ever-increasing demand for ophthalmic care and a shortage of specialists. Machine learning-driven systems, especially Convolutional Neural Networks (CNNs), have shown great promise in overcoming these challenges, achieving high accuracy in medical imaging tasks. This paper explores a unified framework for both multiclass and binary classification of retinal diseases, addressing issues like class imbalance and inter-class similarity while leveraging CNNs for robust feature extraction. Techniques like Grad-CAM also increase model interpretability, allowing clinicians to understand and trust AI-driven diagnostic processes. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Long-term spatiotemporal changes in nitrate contamination of municipal groundwater resources after sewerage network construction in the Hungarian Great Plain

引用

Environmental science and Pollution Research 2024年第51期31卷 61114-61137页

作者： Mester, Tamás Szabó, György Kiss, Emőke Balla, Dániel Department of Landscape Protection and Environmental Geography Faculty of Science and Technology University of Debrecen DebrecenH‑4032 Hungary Department of Data Science and Visualization Faculty of Informatics University of Debrecen DebrecenH‑4028 Hungary

Over the last decades, as a consequence of wastewater discharges and other anthropogenic sources, severe nitrate (NO3−) pollution has developed in municipal environment causing global concern. Thus, eliminating the potential sources of pollution is one of the major challenges of the twenty-first century, whereby sanitation services are essential for ensuring public health and environmental protection. In the present study, long-term monitoring (2011–2022) of shallow groundwater NO3− contamination in municipal environment was carried following the construction of the sewerage network (2014) in the light of the pre-sewerage situation. Our primary aim was to assess the long-term effects of sewerage on nitrate NO3− levels in the shallow groundwater and evaluate the efficiency of these sanitation measures over time. Based on the results, significant pollution of the shallow groundwater in the municipality was identified. During the pre-sewer period, NO3− concentrations exceeded the 50 mg/L limit in the majority of monitoring wells significantly, upper quartile values ranged between 341 and 623 mg/L respectively. Using Nitrate Pollution Index (NPI) and interpolated NO3− pollution maps, marked spatial north–south differences were detected. In order to verify the presence of wastewater discharges in the monitoring wells, the isotopic ratio shifts (δ) for 18O and D(2H) were determined, confirming municipal wastewater effluent. Variations in NO3−/Cl− molar ratios suggest also contamination from anthropogenic sources, including septic tank effluent from households and the extensive use of manure. data series of 7 years (2015–2022) after the investment indicate marked positive changes by the appearance of decreasing trends in NO3− values confirmed by Wilcoxon signed rank test and ANOVA. By comparing the pre- and post-sewerage conditions, the mean NO3− value decreased from 289.7 to 175.6 mg/L, with an increasing number of monitoring wells with concentrations below the limit. Our

关键词： Groundwater pollution

来源：评论

学校读者我要写书评

暂无评论

Optimal path planning based on ACO in intelligent transportation

International Journal of Cognitive Computing in Engineering

引用

International Journal of Cognitive Computing in Engineering 2025年 6卷 441-450页

作者： Zhu, Wenyan Cai, Wenzheng Kong, Hoiio Faculty of Data Science City University of Macau Macau999078 China College of Mechanical and Electrical Engineering Guangdong University of Science & Technology Dongguan523083 China Department of Academic Affairs Guangdong University of Science & Technology Dongguan523083 China

In the current intelligent transportation system, traffic congestion has become increasingly prominent. There is an urgent need for efficient path planning algorithms to solve this problem. The research aims to explore the optimal path planning scheme for intelligent transportation systems, improve traffic efficiency, shorten vehicle travel time, and allocate traffic resources reasonably. The study adopts an innovative approach that combines the global search capability of genetic algorithms with the local search advantage of ant colony algorithms. Simultaneously, the reward and punishment strategy is introduced, forming a new algorithm. The results show that the algorithm performs well in iteration time, path length, and convergence stability. Compared with traditional ant colony algorithm and genetic algorithm, the new algorithm reduces the iteration time from 45 s and 116 s to 34 s and the path length from 15,940 and 15,758 to 14,578 in the optimal path planning of 16 city coordinates. In actual distribution path planning, the optimal path length is reduced from 109.6 km to 99.2 km, and the number of iterations is reduced from 49 to 36. The research has confirmed that this algorithm effectively overcomes the slow convergence speed and susceptibility to local optima in traditional ant colony algorithms, significantly improving the accuracy and computational efficiency of path planning. It is of great significance for optimizing traffic flow management and reducing resource consumption, providing an efficient and accurate solution for path planning in intelligent transportation systems. © 2025

关键词： Ant Colony Optimization (ACO) Reward and punishment strategy Genetic algorithm Intelligent transportation Optimal path planning

来源：评论

学校读者我要写书评

暂无评论

A Method to Localize Defects in Source Codes Using Segments in Programming Exercises

Computer Software

引用

Computer Software 2023年第4期40卷 29-36页

作者： Sawada, Yuki Umeda, Yuichiro Hachisu, Yoshinari Yoshida, Atsushi Kuwabara, Hiroaki Graduate School of Science and Engineering Nanzan University Japan Faculty of Science and Engineering Nanzan University NTT DATA MSE CORPORATION Japan Faculty of Science and Technology Nanzan University Japan

In programming exercises, we propose a method to localize defects based on automatic program repair. Localizing defects is accomplished by comparing a learner’s program and model answers using program segments, which are sequences of statements with no branches, and replacing a learner’s segments with model answers’ segments until all test cases are passed. We implemented a prototype tool for localizing defects and confirmed that our tool can find defects for practical use. © 2023 Japan Society for Software science and technology. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning to Predict Mental Health Disorders and Interpret Feature Importance 3

Application of Machine Learning to Predict Mental Health Dis...

引用

3rd International Symposium on Computer technology and Information science, ISCTIS 2023

作者： Li, Yifan Faculty of Science and Technology Department of Statistics and Data Science Zhuhai China

ISBN: (纸本)9798350325386

The mental health and mental illness crisis has become increasingly acute in recent years, and many digital solutions with artificial intelligence at their core offer hope for reversing the deterioration of our mental health. Machine deep learning techniques can be used to analyse big data to build predictive models for psycho-education, assessment and screening to assess the mental health status of subjects, and can help the clinical community discover information that is not available to many traditional psychological research tools. This paper presents an in-depth analysis of a mental health survey and examines how it can be applied to the Al/ML domain of mental health research and how machine learning models can be used in this domain for fitting and prediction. Based on this, the importance of the presence or absence of current mental health disorders on other characteristics of respondents is assessed and visualised. It was found that the Cross Gradient Booster (Random Forest) model gave the best prediction fit among the various types of machine learning models, and the Grid Search algorithm was used to confirm that the final model had the highest accuracy of 0.79784 at a learning rate of 0.1. The Permutation Importance analysis revealed that the most important characteristic is whether or not the person has suffered from a mental health disorder in the past. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Influence of Tartaric Acid in the Silver Nanoparticle Synthesis Using Response Surface Methodology

引用

Journal of Renewable Materials 2024年第2期12卷 245-258页

作者： Yatim Lailun Ni’mah Afaf Baktir Dewi Santosaningsih Suprapto Suprapto Chemistry Department Faculty of Science and Data AnalyticsInstitut Teknologi Sepuluh NopemberSurabayaIndonesia Chemistry Department Faculty of Science and TechnologyAirlangga UniversitySurabayaIndonesia Department Clinical Microbiology Faculty of MedicineBrawijaya UniversityMalangIndonesia

Silver nanoparticles(AgNPs)synthesized using tartaric acid as a capping agent have a great impact on the reaction kinetics and contribute significantly to the stability of *** protective layer formed by tartaric acid is an important factor that protects the silver surface and reduces potential cytotoxicity *** attributes are critical for assessing the compatibility of AgNPs with biological systems and making them suitable for drug delivery *** aim of this research is to conduct a comprehensive study of the effect of tartaric acid concentration,sonication time and temperature on the formation of silver *** Response Surface Methodology(RSM)with Face-Centered Central Composite Design(FCCD),the optimization process identifies the most favorable synthesis ***-Vis spectrum regression analysis shows that AgNPs stabilized with tartaric acid are more stable than AgNPs without tartaric *** highlights the increased stability that tartaric acid provides in AgNP *** size distribution analysis showed a multimodal distribution for AgNPs with tartaric acid and showed the smallest size peak with an average size of 20.53 *** second peak with increasing intensity shows a dominant average size of 108.8 nm accompanied by one standard deviation of 4.225 nm and a zeta potential of−11.08 *** contrast,AgNPs synthesized with polyvinylpyrrolidone(PVP)showed a unimodal particle distribution with an average particle size of 81.62 nm and a zeta potential of−2.96 *** more negative zeta potential of AgNP-tartaric acid indicates its increased *** of antibacterial activity showed that AgNPs stabilized with tartaric acid showed better performance against *** and *** bacteria compared with *** summary,this study highlights the potential of tartaric acid in AgNP synthesis and suggests an avenue for the development of stable AgNPs with versatile applications.

关键词： Tartaric acid silver nanoparticle polyvinyl pyrrolidone response surface methodology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：