检索结果-内蒙古大学图书馆

CNN-HOG based hybrid feature mining for classification of coffee bean varieties using image processing

Multimedia Tools and Applications 2025年第2期84卷 749-764页

作者： Molla, Yirga Kene Mitiku, Emebet Abeje Department of Computer Science Gafat Institute of Technology Debre Tabor University Debre Tabor Ethiopia Department of Computer Science Faculty of Natural and Computational Science Debark University Debark Ethiopia

Ethiopia, known as the birthplace of coffee, relies on coffee exports as a major source of foreign currency. This research paper focuses on developing a hybrid feature mining technique to automatically classify Ethiopian coffee beans based on their provenance: Harrar, Jimma, Limu, Sidama, and Wellega, which correspond to their botanical origins. A dataset of coffee bean images is collected from various regions through the Ethiopian Commodity Exchange (ECX) in Addis Ababa. The proposed system incorporates preprocessing phases including image resizing, filtering, contrast enhancement, noise removal, grayscale conversion, and segmentation using a combined thresholding and K-means approach for grayscale and RGB images, respectively. Classification is performed using a radial basis function (RBF) kernel function of support vector machine (SVM). To address the color-feature similarity challenge, the study explores merging color and texture features using the histogram of oriented gradients (HOG) local feature descriptor. Performance evaluation is conducted for HOG feature extraction, CNN feature extraction, and a hybrid feature vector (HOG-CNN) using a multi-class SVM classifier, achieving accuracies of 74.17%, 85.83%, and 97.5%, respectively. The deep-shallow-based feature (CNN-HOG) combination demonstrates the highest accuracy of 97.5% in this study. The findings highlight the effectiveness of the proposed hybrid feature mining approach in automatically classifying Ethiopian coffee bean varieties, with potential applications in quality control and traceability within the coffee industry. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Head and Neck Tumors Using Dual PET/CT Imaging:Comparative Analysis of 2D,2.5D,and 3D Approaches Using UNet Transformer

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2351-2373页

作者： Mohammed A.Mahdi Shahanawaj Ahamad Sawsan A.Saad Alaa Dafhalla Alawi Alqushaibi Rizwan Qureshi Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Department of Computer and Information Sciences Universiti Teknologi PetronasSeri Iskandar32610Malaysia Center for Research in Computer Vision(CRCV) University of Central FloridaOrlandoFL 32816USA

The segmentation of head and neck(H&N)tumors in dual Positron Emission Tomography/Computed Tomogra-phy(PET/CT)imaging is a critical task in medical imaging,providing essential information for diagnosis,treatment planning,and outcome *** by the need for more accurate and robust segmentation methods,this study addresses key research gaps in the application of deep learning techniques to multimodal medical ***,it investigates the limitations of existing 2D and 3D models in capturing complex tumor structures and proposes an innovative 2.5D UNet Transformer model as a *** primary research questions guiding this study are:(1)How can the integration of convolutional neural networks(CNNs)and transformer networks enhance segmentation accuracy in dual PET/CT imaging?(2)What are the comparative advantages of 2D,2.5D,and 3D model configurations in this context?To answer these questions,we aimed to develop and evaluate advanced deep-learning models that leverage the strengths of both CNNs and *** proposed methodology involved a comprehensive preprocessing pipeline,including normalization,contrast enhancement,and resampling,followed by segmentation using 2D,2.5D,and 3D UNet Transformer *** models were trained and tested on three diverse datasets:HeckTor2022,AutoPET2023,and *** was assessed using metrics such as Dice Similarity Coefficient,Jaccard Index,Average Surface Distance(ASD),and Relative Absolute Volume Difference(RAVD).The findings demonstrate that the 2.5D UNet Transformer model consistently outperformed the 2D and 3D models across most metrics,achieving the highest Dice and Jaccard values,indicating superior segmentation *** instance,on the HeckTor2022 dataset,the 2.5D model achieved a Dice score of 81.777 and a Jaccard index of 0.705,surpassing other model *** 3D model showed strong boundary delineation performance but exhibited variability across datasets,while the

关键词： PET/CT imaging tumor segmentation weighted fusion transformer multi-modal imaging deep learning neural networks clinical oncology

来源：评论

学校读者我要写书评

暂无评论

COMPARING WSN PERFORMANCE: TRADITIONAL VS. SDN APPROACH

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第4期86卷 81-94页

作者： Hamad, Diyar Jamal Yalda, Khirota Gorgees Okumus, Ibrahim Taner Tapus, Nicolae Faculty of Automatic Control and Computer Science University of Science and Technology POLITEHNICA Bucharest Soran Technical college Erbil Polytechnic University Erbil Iraq Computer Engineering Kahramanmaras Sutcu Imam University Kahramanmaras Turkey Dept. of Computer Science University of Science and Technology POLITEHNICA Bucharest Romania

The proliferation of Wireless Sensor Networks (WSN) in various applications has necessitated the exploration of network architectures that can ensure efficient, scalable, and reliable communication. This study presents a comparative performance evaluation of traditional networking paradigms and Software-Defined Networking (SDN)-based architectures within WSN. Utilizing the Floodlight SDN controller and Mininet-WiFi emulator, we conducted a series of experiments across three different network topologies, varying the number of hosts and access points. The performance metrics focused on are average latency, packet loss percentage, and throughput. The results demonstrate a considerable improvement in all measured parameters under the SDN-based environment compared to the traditional setup. Specifically, SDN environments consistently showcased lower latency, minimal packet loss, and higher throughput, with the most notable difference observed in smaller network configurations. The findings suggest that SDN, with its centralized control plane, can significantly enhance the performance of WSNs, particularly in scenarios demanding rapid scalability and dynamic traffic management. This study underscores the potential of SDN architectures in optimizing WSN operations and lays the groundwork for future research in this domain. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Floodlighting

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection System on The Internet of Things Using Deep Learning and Multi-objective Enhanced Gorilla Troops Optimizer

引用

Journal of Bionic engineering 2024年第5期21卷 2658-2684页

作者： Hossein Asgharzadeh Ali Ghaffari Mohammad Masdari Farhad Soleimanian Gharehchopogh Department of Computer Engineering Urmia BranchIslamic Azad UniversityUrmia63896-57169Iran Department of Computer Engineering Technical and Vocational University(TUV)TehranIran Department of Computer Engineering Tabriz BranchIslamic Azad UniversityTabriz***Iran Department of Computer Engineering Faculty of Engineering and Natural ScienceIstinye University34010IstanbulTurkey Department of Computer Engineering Khazar UniversityAZ1096BakuAzerbaijan

In recent years,developed Intrusion Detection Systems(IDSs)perform a vital function in improving security and anomaly *** effectiveness of deep learning-based methods has been proven in extracting better features and more accurate classification than other *** this paper,a feature extraction with convolutional neural network on Internet of Things(IoT)called FECNNIoT is designed and implemented to better detect anomalies on the ***,a binary multi-objective enhance of the Gorilla troops optimizer called BMEGTO is developed for effective feature ***,the combination of FECNNIoT and BMEGTO and KNN algorithm-based classification technique has led to the presentation of a hybrid method called *** the next step,the proposed model is implemented on two benchmark data sets,NSL-KDD and TON-IoT and tested regarding the accuracy,precision,recall,and Fl-score *** proposed CNN-BMEGTO-KNN model has reached 99.99%and 99.86%accuracy on TON-IoT and NSL-KDD datasets,*** addition,the proposed BMEGTO method can identify about 27%and 25%of the effective features of the NSL-KDD and TON-IoT datasets,respectively.

关键词： Intrusion detection Internet of Things-Convolutional neural network Multi-objective Gorilla troops optimizer

来源：评论

学校读者我要写书评

暂无评论

Advancing Bankruptcy Forecasting With Hybrid Machine Learning Techniques: Insights From an Unbalanced Polish Dataset

引用

IEEE Access 2024年 12卷 9369-9381页

作者： Ainan, Ummey Hany Por, Lip Yee Chen, Yen-Lin Yang, Jing Ku, Chin Soon Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur50603 Malaysia National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia

The challenge of bankruptcy prediction, critical for averting financial sector losses, is amplified by the prevalence of imbalanced datasets, which often skew prediction models. Addressing this, our study introduces the innovative hybrid model XGBoost+ANN, designed to leverage the strengths of both ensemble learning and artificial neural networks. This model integrates a comprehensive set of features with parameters optimized through genetic algorithms, eschewing traditional feature selection approaches. Our research focuses on an unbalanced dataset of Polish companies and reveals that the XGBoost+ANN model, in particular, exhibits outstanding performance. Optimized using genetic algorithms and without feature selection, this model achieved the highest AUC (0.958), sensitivity (0.752), and accuracy (0.983) scores, surpassing other models in our study. This remarkable outperformance, along with the robust results, marks a substantial advancement in the field of bankruptcy prediction. It underscores the efficacy of our approach in addressing the persistent challenge of data imbalance, offering a more reliable and accurate solution for financial risk assessment. © 2013 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep-BERT:Transfer Learning for Classifying Multilingual Offensive Texts on Social Media

引用

computer Systems science & engineering 2023年第2期44卷 1775-1791页

作者： Md.Anwar Hussen Wadud M.F.Mridha Jungpil Shin Kamruddin Nur Aloke Kumar Saha Department of Computer Science and Engineering Bangladesh University of Business and TechnologyDhakaBangladesh School of Computer Science and Engineering University of AizuAizuwakamatsuJapan Department of Computer Science American International University-BangladeshDhakaBangladesh Department of Computer Science and Engineering University of Asia PacificDhakaBangladesh

Offensive messages on social media,have recently been frequently used to harass and criticize *** recent studies,many promising algorithms have been developed to identify offensive *** algorithms analyze text in a unidirectional manner,where a bidirectional method can maximize performance results and capture semantic and contextual information in *** addition,there are many separate models for identifying offensive texts based on monolin-gual and multilingual,but there are a few models that can detect both monolingual and multilingual-based offensive *** this study,a detection system has been developed for both monolingual and multilingual offensive texts by combining deep convolutional neural network and bidirectional encoder representations from transformers(Deep-BERT)to identify offensive posts on social media that are used to harass *** paper explores a variety of ways to deal with multilin-gualism,including collaborative multilingual and translation-based ***,the Deep-BERT is tested on the Bengali and English datasets,including the different bidirectional encoder representations from transformers(BERT)pre-trained word-embedding techniques,and found that the proposed Deep-BERT’s efﬁcacy outperformed all existing offensive text classiﬁcation algorithms reaching an accuracy of 91.83%.The proposed model is a state-of-the-art model that can classify both monolingual-based and multilingual-based offensive texts.

关键词： Offensive text classiﬁcation deep convolutional neural network(DCNN) bidirectional encoder representations from transformers(BERT) natural language processing(NLP)

来源：评论

学校读者我要写书评

暂无评论

Extended linear regression model for vessel trajectory prediction with a-priori AIS information

引用

地球空间信息科学学报（英文版） 2024年第1期27卷 202-220页

作者： Christiaan Neil Burger Waldo Kleynhans Trienko Lups Grobler Computer Science Division Stellenbosch UniversityStellenboschSouth Africa Electrical Electronic and Computer EngineeringUniversity of PretoriaPretoriaSouth Africa

As maritime activities increase globally,there is a greater dependency on technology in monitoring,control,and surveillance of vessel *** of the most prominent systems for monitoring vessel activity is the Automatic Identification System(AIS).An increase in both vessels fitted with AIS transponders and satellite and terrestrial AIS receivers has resulted in a significant increase in AIS messages received *** resultant rich spatial and temporal data source related to vessel activity provides analysts with the ability to perform enhanced vessel movement analytics,of which a pertinent example is the improvement of vessel location *** this paper,we propose a novel strategy for predicting future locations of vessels making use of historic AIS *** proposed method uses a Linear Regression Model(LRM)and utilizes historic AIS movement data in the form of a-priori generated spatial maps of the course over ground(LRMAC).The LRMAC is an accurate low complexity first-order method that is easy to implement operationally and shows promising results in areas where there is a consistency in the directionality of historic vessel *** areas where the historic directionality of vessel movement is diverse,such as areas close to harbors and ports,the LRMAC defaults to the *** proposed LRMAC method is compared to the Single-Point Neighbor Search(SPNS),which is also a first-order method and has a similar level of computational complexity,and for the use case of predicting tanker and cargo vessel trajectories up to 8 hours into the future,the LRMAC showed improved results both in terms of prediction accuracy and execution time.

关键词： Automatic Identification System(AIS)data Linear Regression Model(LRM) trajectory mining spatial map historic data trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Agronomy: Enhancing Crop Yield and Market Profits 4

AI-Driven Agronomy: Enhancing Crop Yield and Market Profits

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Mourya, Kona Chandra, Sai Reddy, N Abhinay Kumar, Aiswarya S Department of Computer Science and Engineering Department of Computer Science and Engineering

ISBN: (纸本)9798350307757

The agriculture sector plays an important role to the nation's economy, contributing significantly to GDP and employing a sizable section of the labour force. Nonetheless, precisely projecting food production and demand remains a difficult task. Traditional prediction approaches are time-consuming and prone to errors, resulting in inefficient resource allocation and financial losses. To solve these issues, we offer an innovative platform that uses machine learning algorithms to predict the best crops for production based on environmental conditions, as well as forecast market demand and pricing patterns for those *** comparing the effectiveness of various crop forecast classification models, the Voting Classifier, which incorporates numerous models, scored an amazing accuracy rate of 0.986. This predictive power can help farmers and stakeholders make more informed decisions, resulting to better profitability and resource efficiency. Furthermore, for price estimate, we used a Stacking Regressor model, which combines the top two models, the Random Forest Regressor and the XGBoosting Regressor. The Stacking Regressor performed better than the individual regression models, earning an optimised MSE of 277.58. This ensemble approach greatly improved price estimation accuracy, allowing stakeholders to make more informed decisions and increase profitability in the agriculture industry. Finally, the suggested intelligent platform offers a promising option for precise crop forecast and price estimation, benefiting farmers and stakeholders by optimising resource allocation, increasing profitability, and contributing to the agriculture sector's longterm growth. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Classification of Skin Cancer Diseases Based on Deep Learning: Challenges and Future Directions

引用

IEEE Access 2025年 13卷 90163-90184页

作者： Khalaf, Abdulrahman Dira Hamdan, Hazlina Abdul Halin, Alfian Manshor, Noridayu Serdang Faculty of Computer Science and Information Technology Department of Computer Science Selangor 43400 Malaysia University of Fallujah Al-Fallujah Department of Computer Centre Anbar31002 Iraq Faculty of Computer Science and Information Technology Department of Multimedia Serdang43400 Malaysia

Deep Learning (DL) techniques have significantly improved the diagnostic accuracy in healthcare, particularly for detecting and classifying skin cancer. Such technological advancements will assist healthcare professionals in delivering more accurate, efficient, and timely diagnoses, ultimately improving patient outcomes and facilitating early detection and treatment. Medical imaging technologies such as magnetic resonance imaging (MRI) and computed tomography (CT) are critical for diagnosing dermatological conditions. However, interpreting these images can be challenging due to overlapping structures and varying image quality. This study explores the application of DL in skin cancer diagnosis, focusing on advances in image segmentation and classification. DL-based models are reviewed specifically by convolutional neural networks (CNNs), and evaluations on their effectiveness for skin lesion detection are provided. This study also examines the critical challenges of deploying DL models in clinical practice, covering issues including dataset diversity, model interpretability, and real-world implementation feasibility. It further explores the selection of network architectures and data preprocessing techniques, emphasizing their influence on model performance. In summary, this study identifies research gaps and suggests future directions for enhancing DL models for dermatological applications. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Evolution and Prospects of Foundation Models: From Large Language Models to Large Multimodal Models

引用

computers, Materials & Continua 2024年第8期80卷 1753-1808页

作者： Zheyi Chen Liuchang Xu Hongting Zheng Luyao Chen Amr Tolba Liang Zhao Keping Yu Hailin Feng College of Mathematics and Computer Science Zhejiang A&F UniversityHangzhou311300China Computer Science Department Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Mathematics and Computer Science Department Faculty of ScienceMenofia UniversityShebin El KomMenoufia Governorate32511Egypt School of Computer Science Shenyang Aerospace UniversityShenyang110136China Graduate School of Science and Engineering Hosei UniversityTokyo184-8584Japan

Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language *** modeling,crucial for AI development,has evolved from statistical to neural models over the last two ***,transformer-based Pre-trained Language Models(PLM)have excelled in Natural Language Processing(NLP)tasks by leveraging large-scale training *** the scale of these models enhances performance significantly,introducing abilities like context learning that smaller models *** advancement in Large Language Models,exemplified by the development of ChatGPT,has made significant impacts both academically and industrially,capturing widespread societal *** survey provides an overview of the development and prospects from Large Language Models(LLM)to Large Multimodal Models(LMM).It first discusses the contributions and technological advancements of LLMs in the field of natural language processing,especially in text generation and language ***,it turns to the discussion of LMMs,which integrates various data modalities such as text,images,and sound,demonstrating advanced capabilities in understanding and generating cross-modal content,paving new pathways for the adaptability and flexibility of AI ***,the survey highlights the prospects of LMMs in terms of technological development and application potential,while also pointing out challenges in data integration,cross-modal understanding accuracy,providing a comprehensive perspective on the latest developments in this field.

关键词： Artificial intelligence large language models large multimodal models foundation models

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：