检索结果-内蒙古大学图书馆

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Shirley, C.P. Berin Jeba Jingle, I. Abisha, M.B. Venkatesan, R. Yashvanth Ram, R.V. Elango, Elakkiya Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India Government Arts College for Woman Dept. of computer Science Sivaganga India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540364

The proliferation of deepfake technology poses a significant challenge to the authenticity of digital content. This research explores the application of multimodal fusion techniques to enhance deepfake detection accuracy. By combining visual and audio features, the proposed method leverages the complementary nature of different data types to detect discrepancies introduced by deepfake manipulation. An attention mechanism is incorporated to focus on salient regions within each modality, further improving detection accuracy. Convolutional Neural Networks (CNNs) and Mel-Frequency Cepstral Coefficients (MFCCs) are employed for feature extraction, followed by feature fusion for deepfake detection. This approach demonstrates the effectiveness of multimodal fusion in combating the evolving threat of deepfake technology. By advancing deepfake detection techniques, this research contributes to safeguarding the integrity of digital content and preserving trust in media. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Building Prediction for Smart City Surveillance 1

Enhanced Building Prediction for Smart City Surveillance

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Natarajan, Yuvaraj Wadhwa, Gitanjali Saravanan, Lekshmipriya Natarajan, Mathivathani KPR Institute of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore641407 India KPR Institute of Engineering and Technology Dept. of Artificial Intelligence and Data Science Coimbatore641407 India

ISBN: (纸本)9798350348057

Nearly three-quarters of the total power used in the world is consumed by the built environment sector. Therefore, looking for viable methods to reduce building energy needs and decrease negative environmental repercussions is vital. By incorporating intelligence into applications, everyone in the current situation has become intelligent, which lessens the load of constant interruption or human control. By using Machine to Machine interactions, intelligence enables the ability to connect more real-time parameters and make moral judgments in perilous circumstances. The current study examined the framework, approach, and performance of currently available AI-based techniques. According to the research, choosing the best machine and deep learning model for a given task can be difficult. Among the primary areas of study in relation to the vast amounts of data collected is the viability in the practice of the used algorithms, both standard machine learning and the more recent branch known as deep learning. Present a quantitative analysis contrasting the effectiveness of conventional deep learning and machine learning strategies using the direction of human movement in detecting the applications based on the analogue pyroelectric infrared sensor (PIR) outputs. Here, Random Forest is used as the machine learning method because of its great prediction accuracy. Over deeper datasets, deeper CNNs outperform shallow models as a deep learning method. The study demonstrates that traditional Machine Learning performs with detecting values within the first few seconds, improving real-time detection. Additionally, it might be used on more smart buildings without upgrades. © 2023 IEEE.

关键词： Intelligent buildings

来源：评论

学校读者我要写书评

暂无评论

A Mobile Application for the Crowdsensing of Road Pavements Conditions 22

A Mobile Application for the Crowdsensing of Road Pavements ...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Delnevo, Giovanni Bartolucci, Nicola Mirri, Silvia Salomoni, Paola Prandi, Catia University of Bologna Dept. of Computer Science and Engineering Italy University of Bologna Bachelor Degree in Computer Science and Engineering Italy

ISBN: (纸本)9798331508050

Urban environments face significant challenges due to deteriorating road pavements, affecting all transportation modes' safety and comfort. Traditional methods of road assessment are costly and infrequent, but advancements in mobile technology and crowdsensing offer real-time, large-scale data collection solutions. This paper introduces 'ShakeSensing', a mobile application that uses Android device sensors to measure vibrations experienced by cyclists and scooter users, providing insights into road quality. The collected data, analyzed to assess road conditions, can benefit both users and municipal authorities, promoting safer and more comfortable travel. © 2025 IEEE.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Deep Neural Network for Early Detection and Classification of Chicken Diseases 5

A Novel Hybrid Deep Neural Network for Early Detection and C...

引用

5th International Conference on Sustainable Technologies for Industry 5.0, STI 2023

作者： Uddin, Md Shihab Islam, Md Fakrul Rahman, Sharukh Foysal, Nasir Uddin Islam, Muhammad Nazrul Razzaque, Md. Abdur Al Faisal, Faiz Green University of Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh Military Institute of Science and Technology Dept. of Computer Science and Engineering Dhaka1216 Bangladesh University of Dhaka Dept. of Computer Science and Engineering Dhaka1000 Bangladesh

ISBN: (纸本)9798350394290

Detection and classification of chicken diseases has been a longstanding concern for farmers. Relying solely on expert opinions could be a costly option. Moreover, there are certain chicken diseases that spread quickly, and necessary procedures are immediately needed to carryon. On the other hand, the lack of research activity or low availability of data on this topic leads to many misunderstandings and challenges so as to correctly detect a certain type of chicken disease. The existing techniques show low accuracy on disease classification, which leads to a complex engineering problem and critical analysis is required for sustainable development. In this paper, we develop a novel hybrid deep neural network, namely ChickenNet21, which combines a Convolutional Neural Network (CNN) and a fine-tuned Visual Geometry Group (VGG) model to address this challenge. Using a large dataset of 6,812 farm-labeled fecal images, we assess the effectiveness of ChickenNet21 and it achieves 98.83% accuracy in identifying chicken diseases. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Development of a Deep Learning-Based Model for Canine Skin Disease Diagnosis Using RandAugment and Patterned-GridMask

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第1期74卷 142-148页

作者： Kim, Min-Jun Park, Jae-Beom Cho, Hyun-Chong Dept. of Electronics Engineering Interdisciplinary Graduate Program for BIT Medical Convergence Dept. of Data Science Kangwon National University Korea Republic of Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

In contemporary society, pets are increasingly regarded as integral family members, contributing significantly to human quality of life. The growing prevalence of dog ownership has concurrently escalated the economic burden associated with veterinary care, particularly in managing common conditions like skin diseases. This study introduces an advanced deep learning-based diagnostic system for canine skin diseases, designed for practical application in home environments. We employed RandAugment to enhance data augmentation, thereby increasing the diversity of the training dataset. Furthermore, the implementation of Patterned-GridMask significantly improved the model's generalization capabilities. The use of the AdamW optimization algorithm was instrumental in mitigating overfitting, thus enhancing the model's overall learning efficiency. The proposed Transformer-based model, ViT/B-16, achieved an accuracy of 78.65% with the original dataset. With the integration of RandAugment and Patterned-GridMask techniques, the model's accuracy improved to 84.33%, underscoring its potential effectiveness for practical veterinary applications. Copyright © The Korean Institute of Electrical Engineers.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Automated Road Extraction in Urban and Rural Regions from Remote Sensing Imagery with U-Net and ResNet-Based Architectures 1

Automated Road Extraction in Urban and Rural Regions from Re...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Sharma, Palvi Kumar, Rakesh Gupta, Meenu Obaid, Ahmed J. Chandigarh University Dept. of Computer Science & Engineering Punjab India Chandigarh University Dept. of Computer Science & Engineering Punjab India University of Kufa Faculty of Computer Science and Mathematics Najaf Iraq National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350356816

Accurate road extraction from Remote Sensing Imagery (RSI) is crucial for various applications, including urban planning, navigation, and disaster response. This study investigates automated road extraction in rural, semi-urban and urban regions using deep learning architectures, specifically UNet and Deep Residual U-Net (ResNet) models. We leverage High-Resolution Satellite Imagery (HRSI) to train and validate our models, focusing on the distinct characteristics and challenges presented by urban and rural environments. Our methodology involves comprehensive data preprocessing and augmentation techniques to enhance model robustness. We evaluate the performance of both architectures using metrics and achieved an accuracy of 90.29%, recall of 80.95%, precision of 74.89%, and F1- score of 77.80% for the Deep Residual U-Net. Experimental results demonstrates that while both models perform well, the Deep Residual U-Net exhibits superior accuracy and generalization, particularly in complex urban landscapes. © 2024 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Earthquake Damage Prediction and Rapid Assessment of Building Damage Using Deep Learning 1

Earthquake Damage Prediction and Rapid Assessment of Buildin...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Natarajan, Yuvaraj Wadhwa, Gitanjali Ranganathan, Preethi Akshaya Natarajan, Karthika KPR Institute of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore641407 India KPR Institute of Engineering and Technology Dept. of Artificial Intelligence and Data Science Coimbatore641407 India

ISBN: (纸本)9798350348057

One of the most expensive natural disasters that affect people, earthquakes occur suddenly. As a result, earthquake prediction has grown in importance and difficulty for humanity. Although numerous existing approaches attempt to handle this problem, the majority rely on seismic indicators created by geologists or feature vectors extracted by the deep learning techniques to describe an earthquake for the earthquake prediction. Combining these two categories of characteristics to enhance ultimate Earthquake prediction performance is still a challenge. In order to achieve this, we put forth a deep learning model that successfully fuses explicit and implicit information for earthquake prediction. Here, we use a Convolutional Neural Network to extract implicit features while using eight precursory pattern-based indicators as the explicit features. After that, an attention-based approach is suggested to effectively combine these two categories of traits. A dynamic loss function is the additionally created to address the imbalance of category in seismic data. On a test picture dataset, the performances of multiple CNN models are contrasted. In order to classify earthquake damage, the model is further developed as a web application. Damage assessment values, which are determined using the Convolutional Neural Network model and gradient-weighted class activation mappings, are used to determine the extent of the damage. The web-based program can efficiently and automatically categorize earthquake-related structural damage, making it appropriate for decision-making in emergency response, resource allocation, and policy formation. © 2023 IEEE.

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

SmartCitrus: An Efficient Deep Learning Approach for Real-Time Detection and Classification of Citrus Leaf Diseases

SmartCitrus: An Efficient Deep Learning Approach for Real-Ti...

引用

2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems, iCACCESS 2024

作者： Emon, Shaharear Hossain Islam, Iftea Khairul Nahin, Tasfia Jahan Ahmed, Ahnaf Mahdin Orchi, Nabiha Tasnim Alam, Md Ashraful Dipto, Shakib Mahmud Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh Brac University Cvis Research Lab Dept. of Computer Science and Engineering Dhaka Bangladesh University of Liberal Arts Dept. of Computer Science and Engineering Dhaka Bangladesh Brac University Cvis Research Lab Dhaka Bangladesh

ISBN: (纸本)9798350350289

Bangladesh is a prominent citrus exporter. Annually, the country has been exporting citrus fruits to over 60 countries. Distinguishing various diseases affecting citrus leaves requires a significant investment of time, effort, and specialized knowledge. Consequently, it is essential to create an innovative method for detecting citrus diseases. In this study, we have devised a valuable methodology by employing CNN models to identify diseases in citrus leaves. By employing a distinctive ensemble strategy, we successfully trained the model using varying numbers of classes in each stage. In reality, it allowed us to utilize suitable varieties of leaves for various ailments. Furthermore, it has enhanced the rate at which models learn during the later stages. In addition, it has reduced the level of model intricacy in comparison to frequently employed ensemble models. The identification of plant diseases in the present study involved the utilization of leaf photographs and algorithms for segmentation and feature extraction. Ultimately, we have successfully attained a 96 % accuracy rate for each class, signifying a substantial potential for mitigating production losses. © 2024 IEEE.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

Earthquake Damage Prediction and Rapid Assessment of Building Damage Using Machine Learning. 2

Earthquake Damage Prediction and Rapid Assessment of Buildin...

引用

2nd International Conference for Advancement in Technology, ICONAT 2023

ISBN: (纸本)9781665475174

A quick forecast of the region's structural damage following an earthquake is crucial for community relief and rescue efforts. Following an earthquake, getting detailed information about buildings in seismic disaster zones is frequently impossible. The information available is essential to estimate seismic damage to urban structures accurately. To address the aforementioned issues, we propose a novel method for quickly assessing building damage through extensive use of field research and data collected from earth observation. A model is created and trained to predict building damage from an earthquake. The algorithm used to indicate the building damage from the quake is Elastic net regression. The elastic net is a regularized regression method used to predict building damage from an earthquake. The proposed Elastic net regression is validated with standard accuracy and effectiveness compared with the Random forest and decision tree methods. The proposed model's outcomes show that elastic net regression is the most effective predictive model for predicting building damage. © 2023 IEEE.

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

Adchat-TVQA: Innovative Application of LLMs-Based Text-Visual Question Answering Method in Advertising Legal Compliance Review 5

Adchat-TVQA: Innovative Application of LLMs-Based Text-Visua...

引用

5th International Conference on Machine Learning and computer Application, ICMLCA 2024

作者： Gao, Ruiling Hou, Yingqi Tang, Weijie Zhang, Jin Hu, Yanbo Huang, Haiyun Tan, Wen'an Li, Liping Shanghai Polytechnic University Dept. of Computer Engineering Shanghai China Donghua University Dept. of Computer Science Shanghai China Tufts University Dept. of Computer Science MedfordMA United States

ISBN: (纸本)9798331530334

Advertising legal compliance reviews have always been time-consuming and labor-intensive, and existing Large Language Models(LLMs) are far worse performing than senior industry experts. In this paper, we propose a novel LLMs-based text-visual question answering method called Adchat-TVQA for advertising legal compliance review. After reading an advertising image and the corresponding review question, it will first understand the content on the image through multimodal learning, then optimize the question with Zero-Shot Chain-of-Thought (CoT) prompting method based on predefined industry expert experience, and finally input the augmented question into the large language model for inquiry. The feasibility of this method is verified through system prototype implementation and end-to-end functional tests. In addition, we summarized the characteristics of advertising images and added image segmentation and text box transpose to the data processing process for system performance improvement. Performance testing of the text visual cognitive question task on the AIWIN2021 dataset shows that the method scores higher than Microsoft's LayoutLM, with an increasement of the score from 51.52% to 52.74%. © 2024 IEEE.

关键词： Marketing

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：