检索结果-内蒙古大学图书馆

Synergizing CNN and Random Forest for Accurate Cattle Disease Identification

Synergizing CNN and Random Forest for Accurate Cattle Diseas...

2024 IEEE International Conference on Information technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Yashu Kukreja, Vinay Srivastava, Prateek Garg, Ashish Hariharan, Shanmugasundaram Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Uttarakhand Dehradun India Vardhaman College of Engineering Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350382693

The current research focuses on the essential undertaking of multiclass classification in the context of diagnosing skin disorders in cattle. It aims to provide a thorough assessment of a complete model. The introduction underscores the need of rapid illness diagnosis in veterinary practises. The aim of this study is to construct a robust model that can successfully identify a wide range of skin diseases in cattle with high accuracy. The precision values, which range from 88.12% to 97.57%, serve as indicators of the model's proficiency in accurately predicting distinct classes. The model's ability to make accurate predictions across several categories is highlighted by its overall accuracy of 91.56%, indicating a high level of competency and reliability. The research use a comprehensive dataset and incorporates sophisticated machine learning methods to improve the detection of diseases. The attainment of a high level of precision and accuracy plays a significant role in enhancing the dependability of the model in real-world scenarios, hence enabling timely intervention and treatment. The results indicate that the model that was created has potential for effective use in actual situations, offering a significant resource for veterinarians in the management and treatment of skin disorders in cattle. This research makes a valuable contribution to the continuous endeavours in using machine learning techniques to enhance cattle health and emphasises the potential for further breakthroughs in disease identification strategies. © 2024 IEEE.

关键词： Animal CNN Deep Learning Disease Recognition Health Random Forest

来源：评论

学校读者我要写书评

暂无评论

Crop Quality Quantification: A Federated Learning CNN's Approach to Broccoli Leaf Disease Detection

Crop Quality Quantification: A Federated Learning CNN's Appr...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Suryavanshi, Ankita Mehta, Shiva Gopal, Lisa Thapliyal, Siddhant Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Uttarakhand Dehradun India Sharda University Computer Science and Engineering Sharda School of Engineering and Technology U.P. Greater Noida India

ISBN: (纸本)9798350361537

This article proposes a thorough research study between federated learning and CNNs, where both methods are utilized for the detection and severity categorization of broccoli leaf diseases. The algorithm uses the data, the separation of four clients' enthused, to point out the severity of diseases among four categories that start from mild to critical illness. A federated learning system has used client data instead of a global model to train a learning model where privacy issues have not arisen. The study of the results revealed that the FedAvg algorithm-based federated learning method, which is precisely featured with that property, kept each individual's observation data as an origin point to create a highly effective global model. The research depended on macro-economic, micro-economic, and weighted averages to reflect the model's accomplishments at both local and international levels. For all the intensely local ratings whatsoever, the customers SB-1, SB-2, and SB-3 showed a macro average score of 92.17 and 96.49, respectively, at a swell of 96.64 and 97.1. These scores reflect that the model's accuracy and recall are improving, which is constantly witnessed among clients. Scores were calculated by burden weighting. Since the first computation of the score was 92.26, sb-1. In the long term, scores for sb-2, sb-3, and sb-4 trended upward, with sb-4 finally peaking at 97.08. After the weighted averages, the micro averages are statistically one in line;the outcome is 92.24 in sb-1 and 97.08 in sb-4. This invariably drives the model to the correct result, implying data consistency. All the local areas had a macro average score of 97.65, a micro score of 97.63, and a weighted average score of 97.63. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fake review detection using transformer-based enhanced LSTM and RoBERTa

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 250-258页

作者： Mohawesh, Rami Bany Salameh, Haythem Jararweh, Yaser Alkhalaileh, Mohannad Maqsood, Sumbal College of Engineering Al Ain University Al Ain United Arab Emirates Hijjawi Faculty of Engineering Technology Yarmouk University Irbid Jordan Department of Computer Science Jordan University of Science and Technology Jordan College of Education Al Ain University Al Ain United Arab Emirates School of Information Technology University of Tasmania TAS Australia

Internet reviews significantly influence consumer purchase decisions across all types of goods and services. However, fake reviews can mislead both customers and businesses. Many machine learning (ML) techniques have been proposed to detect fake reviews, but they often suffer from poor accuracy due to their focus on linguistic features rather than semantic content. This paper presents a novel semantic- and linguistic-aware model for fake review detection that improves accuracy by leveraging advanced transformer architecture. Our model integrates RoBERTa with an LSTM layer, enabling it to capture intricate patterns within fake reviews. Unlike previous methods, our approach enhances the robustness of fake review detection and authentic behavior profiling. Experimental results on semi-real benchmark datasets show that our model significantly outperforms state-of-the-art methods, achieving 96.03 % accuracy on the OpSpam dataset and 93.15 % on the Deception dataset. To further enhance transparency and credibility, we utilize Shapley Additive Explanations (SHAP) and attention techniques to clarify our model's classifications. The empirical findings indicate that our proposed model can offer rational explanations for classifying specific reviews as fake. © 2024

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

MPTrack: Visual Tracking with Reliable Motion Prompts 24

MPTrack: Visual Tracking with Reliable Motion Prompts

引用

2024 International Conference on Artificial Intelligence of Things and Computing, AITC 2024

作者： Sun, Songtao Li, Lunbo Aerospace System Engineering of Shanghai Shanghai China School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China

ISBN: (纸本)9798400709869

Recently, the attention mechanism has been introduced into object tracking, making significant improvements in tracking performance. However, the tracking target often undergoes deformation during tracking, which can easily lead to the loss of the target. In this paper, we design the motion perception unit (MPU) to enhance tracking stability. The MPU generates motion prompts rich in dynamic target appearance information and integrates them into object modeling. This integration allows our tracker to better adapt to changes in target motion and appearance, improving the adaptability to the target motion. Extensive experiments demonstrate that our tracker MPTrack outperforms all state-of-the-art trackers on five widely recognized benchmarks, including GOT-10k, TrackingNet, LaSOText, UAV123, and TNL2K, while running at real-time speed. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Target motion

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Biodiversity: Remote Forest Poaching Camp Detection with CNN and Spatial Transformer Networks 1

Safeguarding Biodiversity: Remote Forest Poaching Camp Detec...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control technology, ICECCC 2024

作者： Yashu Kukreja, Vinay Kumar, Mukesh Manwal, Manika Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Graphic Era Hill University Uttrakhand Dehradun248002 India Graphic Era Deemed to be University Computer Science and Engineering Uttrakhand Dehradun India Sharda School of Engineering and Technology Sharda University Department of Computer Science and Engineering UP Greater Noida India

ISBN: (纸本)9798350371802

The increasing threat of poaching continues to endanger global biodiversity, calling for innovative and timely measures in detection as well as interventions. In response, this study presents a novel approach to methodology that utilizes high-resolution optical satellite imagery along with an advanced hybrid deep learning model comprising Convolutional Neural Networks (CNN) and Spatial Transformer networks (STN). The broad dataset of 25,000 images reflects the complexities of poaching activities which include temporary camps, human movement, vehicles, and abandoned camps. The hybrid model rises as an outstanding tool, which demonstrates great performance with an overall accuracy of 95.90%. Accordingly, precision, recall, and Fl-score measurements are diligently used for every class that show how well the model is performing in distinguishing complex patterns connected to various stages of poaching. Most significantly, the impressive recall of 96.52 % for detection temporary camps, is a testament to the model's proactive nature in early-onset threat mitigation - this being one of the key aspects of poaching threats control. Notably, a comprehensive analysis using confusion matrices not only verifies the accuracy of classification capabilities but also offers several subtle insights into model performance towards different classes. This fine-grained knowledge helps in the implementation of pertinent adjustments that improve model responsiveness to different environmental levels and types of comparative studies in the light of other models or baseline methods emphasizing how better is the proposed hybrid model about its several multi-classification tasks that are associated with poaching detection. © 2024 IEEE.

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

An oceanographic data collection scheme using hybrid optimization for leakage detection during oil mining in mobility assisted UWSN

引用

Multimedia Tools and Applications 2024年第42期83卷 89723-89741页

作者： Choudhary, Monika Goyal, Nitin Gupta, Deepali Sharma, Bhanu Sharma, Nonita Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Seth Jai Parkash Mukandlal Institute of Engineering and Technology Haryana Radaur India Department of Computer Science and Engineering School of Engineering and Technology Central University of Haryana Haryana Mahendragarh India Department of Information Technology Indira Gandhi Delhi Technical University for Women Delhi India Immersive and Interactive Technology Lab Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Data acquisition is the process of collecting, measuring and analysing information using standardised, validated techniques for application-specific tasks. In mobility-assisted underwater wireless sensor networks (UWSNs), where nodes are not fixed due to water current of 3 m/sec, data collection becomes an arduous task. There are few works that provide a mobile sink with optimised data transmission path planning and scheduling. These systems do not transmit the data fast enough to provide real-time data transmission as these methods do not consider the buffer occupancy rate and latency in data acquisition. In this paper, a stimulating transmission path planning technique for mobile sinks using the hybrid Grey Wolf Optimizer Whale Optimization Algorithm (GWOWOA) is proposed. In contrast to other optimization techniques, this hybrid technique includes a number of update processes such as random position update, prey search by the Grey Wolf Optimizer (GWO) and prey search by the Whale Optimization Algorithm (WOA). In this paper, the fitness function is calculated in terms of distance to the mobile sink, buffer occupancy rate, energy level and data acquisition latency. The use of these variables makes the proposed technique innovative. To prove the efficiency of the proposed system, GWOWOA is compared with existing systems. The simulation results show that the proposed system increases the residual energy and accuracy of the collected data and minimises the delay. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Clisp: A Robust Interactive Segmentation Framework for Pathological Images 46

Clisp: A Robust Interactive Segmentation Framework for Patho...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Wang, Hannan Shi, Jun Zhao, Minfan Qiao, Liang Wang, Zhaohui Dai, Yue Ma, Yuchen An, Hong University of Science and Technology of China School of Computer Science and Technology Hefei China University of Virginia School of Engineering & Applied Science Charlottesville United States

ISBN: (纸本)9798350371499

Recently, automatic segmentation algorithms based on deep learning have achieved promising results on various pathological image segmentation tasks. However, the inherent data-hungry nature of these methods and the high cost of annotating pathological images make them difficult to apply to practical clinical tasks. To address this problem, many studies have explored interactive segmentation methods to reduce the cost of annotating pathological images, which replace pixel-by-pixel annotation operations with clicks or other user instructions. Despite their effectiveness, most of these methods only utilize small-scale data resulting in poor generalization ability for different tasks or segmentation objects. In this paper, we propose a robust Click-based Interactive Segmentation framework for low-cost and interactive annotation of Pathological images, named Clisp. To improve the generalization ability, we construct a multi-source pathological image annotation dataset including around 79,000 images for supervised training of the proposed method. Besides, we adopt a heavy-parameter vision transformer as the image encoder to learn feature representations for large-scale data. We evaluate the proposed method on 7 open-source datasets, and the experimental results show that Clisp is superior to the baseline method in segmentation performance on most datasets and has outstanding generalization ability. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Metaphor Detection through Soft Labels and Target Word Prediction

arXiv

引用

arXiv 2024年

作者： Jia, Kaidi Li, Rongsheng College of Computer Science and Technology Harbin Engineering University Harbin150001 China

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address these issues, we integrate knowledge distillation and prompt learning into metaphor detection. Our approach revolves around a tailored prompt learning framework specifically designed for metaphor detection. By strategically masking target words and providing relevant prompt data, we guide the model to accurately predict the contextual meanings of these words. This approach not only mitigates confusion stemming from the literal meanings of the words but also ensures effective application of language rules for metaphor detection. Furthermore, we've introduced a teacher model to generate valuable soft labels. These soft labels provide a similar effect to label smoothing and help prevent the model from becoming over confident and effectively addresses the challenge of data sparsity. Experimental results demonstrate that our model has achieved state-of-the-art performance, as evidenced by its remarkable results across various datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Skin Lesion Decode A CNN-SVM Convergence for Enhanced Diagnostic Accuracy

Skin Lesion Decode A CNN-SVM Convergence for Enhanced Diagno...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Suryavanshi, Ankita Mehta, Shiva Rana, Samir Manwal, Manika Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Uttarakhand Dehradun India Sharda University Computer Science and Engineering Sharda School of Engineering and Technology U.P. Greater Noida India

ISBN: (纸本)9798350361537

This research study investigates the development and evaluation of a merged CNN and SVM model for detecting and classifying skin lesions. The research systematically divides skin lesions into five categories that allow a thorough analysis of the model's diagnostic skills. The CNN-SVM model is developed and tested using a high-quality dataset, and its accuracy, recall, and F1 scores provide insights into specific performance aspects of the model. The results show a high level of precision for all the classes that vary from 92.95% for Class 1 to 95.95% for Class 5, which suggests that the model is good at making optimistic predictions. The recall measure, a sensitivity measure of the model, varies from 91.44% for Class 3 to 98.47% for Class 1, indicating the model's capability to recognize true positives correctly. The F1-score, which balances precision and recall, is always high, fluctuating from 93.00% for Class 3 to 96.28% for Class 5, reflecting the model's well-balanced categorization. Several types of averages are computed to assess the model's performance thoroughly. The macro average indicates accuracy of 94.70%, recall of 94.81%, and F1-score of 94.73%, with equal weight given to each class. With class distribution, the weighted average is as follows: accuracy - 94.74%, recall - 94.72%, F1-score - 94.71%. The micro average indicating the sum of contributions from all classes is 94.72% for all three parameters across the board. The model is entirely accurate, with an overall accuracy of 94.72397, showing the model's strong ability to generalize across different skin lesion types. The statistical measures confirm the CNN-SVM model as a practical approach to accurate and reliable classification of skin lesions, revealing high clinical potential. The paper's impressive experimental and statistical analyses demonstrate the power of the model and its ability to improve dermatological diagnostic procedures. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

DDT-Net:Deep Detail Tracking Network for Image Tampering Detection

引用

computers, Materials & Continua 2025年第5期83卷 3451-3469页

作者： Jim Wong Zhaoxiang Zang Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China College of Computer and Information Technology ChinaThree Gorges UniversityYichang443002China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650504China

In the field of image forensics,image tampering detection is a critical and challenging *** methods based on manually designed feature extraction typically focus on a specific type of tampering operation,which limits their effectiveness in complex scenarios involving multiple forms of *** deep learningbasedmethods offer the advantage of automatic feature learning,current approaches still require further improvements in terms of detection accuracy and computational *** address these challenges,this study applies the UNet 3+model to image tampering detection and proposes a hybrid framework,referred to as DDT-Net(Deep Detail Tracking Network),which integrates deep learning with traditional detection *** contrast to traditional additive methods,this approach innovatively applies amultiplicative fusion technique during downsampling,effectively combining the deep learning feature maps at each layer with those generated by the Bayar noise *** design enables noise residual features to guide the learning of semantic features more precisely and efficiently,thus facilitating comprehensive feature-level ***,by leveraging the complementary strengths of deep networks in capturing large-scale semantic manipulations and traditional algorithms’proficiency in detecting fine-grained local traces,the method significantly enhances the accuracy and robustness of tampered region *** with other approaches,the proposed method achieves an F1 score improvement exceeding 30% on the DEFACTO and DIS25k *** addition,it has been extensively validated on other datasets,including CASIA and *** results demonstrate that this method achieves outstanding performance across various types of image tampering detection tasks.

关键词： Image forensics image tampering detection image manipulation detection noise flow Bayar

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：