检索结果-内蒙古大学图书馆

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Priyadarsan, Soumendra Sethy, Soorjyakanta Xalxo, Basant Behera, Sasmita Veer Surendra Sai University of Technology Dept. of Computer Science and Engineering Odisha Burla India

ISBN: (纸本)9798331519582

Object identification is very important for modern defense systems because it helps ensure security and extends support in various operations. Realistic images come with issues of low contrast, motion blur, and noise, which ultimately affect detection performance. This research seeks to come up with ways of enhancing a procedure that enhances image quality and consequently detection. The method used here applies Histogram Equalization and Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve the contrast. Then, Gaussian Blur & Median Blur are used to mimic and reduce the motion blur effect and eliminate noise respectively. Finally, sharpening is done to highlight edges. As a result, the image quality has significantly improved. Sharper edges, improved contrast and less noise will help in better AI detection. In the future, we plan to add machine learning models to support real-time detection which will make the system adaptable to complex environments. © 2025 IEEE.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

A Method for De-Identification Analysis of Encrypted Video 9

A Method for De-Identification Analysis of Encrypted Video

引用

Joint 9th International Conference on Digital Arts, Media and technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2024

作者： Kim, Deok-Han Kim, Young-Gab Sejong University Dept. of Computer and Information Security and Convergence Engineering for Intelligent Drone Seoul Korea Republic of

ISBN: (纸本)9798350318241

As the variety of video content increases, so does the likelihood of data breaches of sensitive personal information. Consequently, several video de-identification techniques have been developed to protect personal data, alongside ongoing research into video encryption technology, which offers the advantage of decryption to obtain the original video without storing a separate video copy. While it is possible to visually evaluate whether individual encrypted frames have been correctly de-identified, human interpretation makes this method vulnerable to subjective bias. Many video encryption studies employ traditional image quality evaluation metrics, such as peak signal-to-noise ratio and structural similarity index measure (SSIM), to objectively demonstrate the de-identification of encrypted videos. However, these metrics prove to be insufficiently effective for this purpose. These image metrics can measure the de-identification rate of a single frame in encrypted videos, but not the entire video. This study introduces a quantitative analysis method to confirm de-identification in fully encrypted videos. In this study, we measured the de-identification rates of all frames of encrypted videos using a weighted sum of SSIM and edge differential ratio. We also measured the de-identification rate of a fully encrypted video. Finally, we graphically analyzed these data using line charts. This objective methodology enabled the identification of portions of the encrypted video where de-identification techniques may not have been appropriately applied. © 2024 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Landslide Prediction, Monitoring, and Early Warning with Explainable AI: A Comprehensive Approach 3

Dynamic Landslide Prediction, Monitoring, and Early Warning ...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Binu, Kristin Elizabeth Anoopkumar, Lakshmi Thampi Sunil, Maria Jose, Merin Preetha, K.G. Rajagiri School of Engineering & Technology Dept. of Computer Science and Engineering Rajagiri Valley PO Kochi India

ISBN: (纸本)9798350375190

Landslides are a major threat to infrastructure, human lives, and the environment. Therefore, early warning systems and precise forecasting are essential for reducing their effects. This study investigates how to enhance landslide prediction models using Explainable Artificial Intelligence (XAI) methodologies. Intending to improve complex machine learning models' interpretability and transparency, XAI seeks to improve comprehension and confidence in the model's predictions. XAI methodologies used are SHapley Additive exPlanations (SHAP), LIME (Local Interpretable Model-agnostic Explanations), and feature importance analysis. These techniques produce comprehensible explanations for each forecast and assist in determining the most significant variables in landslide prediction. The proposed XAI-enhanced landslide prediction model demonstrates promising results in terms of accuracy and interpretability. The research reported here helps to design more potent early warning systems for landslides by advancing explainable AI applications in geoscience and disaster risk reduction. © 2024 IEEE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

A Face Recognition-Based Smart Student Attendance and Activeness Monitoring System 4

A Face Recognition-Based Smart Student Attendance and Active...

引用

4th International Conference on Computation, Automation and Knowledge Management, ICCAKM 2023

作者： Ghodekar, Atharva Gunjal, Tejas Landage, Abhijeet Phapale, Abhijit Thorat, Dinesh Nikam, Rohit Sanjivani College of Engineering Dept. of Information Technology Kopargaon India

ISBN: (纸本)9798350393248

A Face Recognition-Based Smart Student Attendance and Activeness Monitoring System represents a transformative solution to revolutionize attendance management within educational institutions. This project introduces a new way of tracking student attendance in schools, moving away from traditional methods like calling names or using cards. We're using advanced facial recognition technology, specifically the OpenFace model, to make attendance more accurate and easier. This system corrects mistakes intelligently and refines its data for better performance. A distinctive feature of the system involves the incorporation of the Haar Cascade model to monitor student engagement. Which does more than just track attendance. It watches students' facial expressions and head movements in real-time. This gives teachers insights into how engaged students are in class, helping them improve participation. Teachers get immediate feedback, allowing them to adjust their teaching methods for a more interactive and enjoyable learning experience. Our system doesn't just focus on attendance, it takes a broader approach by monitoring student engagement. By simplifying tasks for school staff and giving helpful information, this system has the potential to change how schools operate. It uses cutting-edge technology to make attendance and engagement monitoring easy, promising to create better classroom experiences for everyone involved. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Real-time Posture Correction System in sitting using Deep Learning Techniques 14

Real-time Posture Correction System in sitting using Deep Le...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Dewang, Rupesh Kumar Ali, Abid Kumar, Divya Ranvijay Kumar, Atul Omar, Sanskar Dept. Computer Science & Engineering Motilal Nehru National Institute of Technology Allahabad Prayagraj India

ISBN: (纸本)9798331531935

In today’s workplace, desk employees often spend long hours sitting in front of computers, leading to issues such as poor posture, back pain, neck strain, and other musculoskeletal problems. This research presents a solution using wearable devices and computer vision technology to tackle these health concerns. The system monitors the user’s body position in real-time by analyzing images captured by the wearable device. It calculates body angles and relevant data to evaluate posture and offers corrective feedback when poor posture is detected. Maintaining good posture is important not only for physical well-being but also for enhancing productivity. Recognizing this, researchers and developers are creating technological solutions to help desk workers develop healthier posture habits throughout the workday. This paper introduces a system designed to promote better posture using computer vision. The camera capture real-time images of the user, and the system uses algorithms to identify key body points and calculate posture angles. If improper posture is identified, t he s ystem p rovides t he u ser w ith guidance to make adjustments, helping prevent posture-related health *** technology offers a practical approach to reducing the physical strain associated with prolonged sitting, benefiting both individual health and workplace efficiency. © 2025 IEEE.

关键词： Desk Workers Posture Correction Wearable Devices

来源：评论

学校读者我要写书评

暂无评论

Integrating Artificial Intelligence and Educational technology for Inclusive and Ethical Education Practices 3

Integrating Artificial Intelligence and Educational Technolo...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Ilayaraja, Lathika Yukthika, S.S. Prabakaran, Subramani Pavithra, S. Dept. of Computer Science and Engineering Chennai Institute of Technology Tamil Nadu Chennai600069 India

ISBN: (纸本)9798331527549

AI and EdTech are transforming education by making it more accessible, personalized, and assessable, even in low and middle income countries (LMICs) facing resource constraints. However, challenges come with unequal access, issues in data privacy, and bias in AI model creations. As AI continues to become more popular, the issue of whether the work made by the students will be original. This paper focuses on the impact of artificial intelligence on learning in both its ethical and practical dimensions while highlighting the themes of inclusivity, fairness, and authenticity. Guidelines and policies for responsible AI in integration will be proposed further, alongside teacher training. Results should depict that this moral framework, policies, and teacher education should aid in ensuring that the implications of AI are positive and fruitful for learning. Ideal AI guidelines would foster an educational system that is inclusive, transparent, and considers uniqueness and innovation. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning of Large Language Models for Solving DSA Problems Using QLoRA

Fine-Tuning of Large Language Models for Solving DSA Problem...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Pavan Kalyan, S. Arun Kumar, B.R. Satish Kumar, T. Prem Raj, S. Patil, Pratik B. Harshini, Pothireddy Bms Institute of Technology and Management Dept. Computer Science and Engineering Karnataka Bangalore5600119 India

ISBN: (纸本)9798331538538

Fine-tuning large language models (LLMs) for domain specific tasks is often an expensive resource intensive procedure requiring large computing and memory resources. In this paper, We introduce finetuned-leetcode-CodeLlama-7b, a version of CodeLlama that was fine tuned for solving LeetCode problems, specifically. Using QLoRA (Quantized Low Rank Adaptation) techniques, we show that smaller models achieve high performance when solving Data Structure and Algorithm (DSA) problems, providing a cost effective alternative to larger models. The proposed incremental approach reduces memory and computational needs, keeping high accuracy while providing advanced problem-solving in resource constrained environments. © 2025 IEEE.

关键词： Digital differential analyzers

来源：评论

学校读者我要写书评

暂无评论

Multispectral Satellite Data Classification Using Rank Correlation Similarity Index and Automatic Labeling Technique

引用

SN computer Science 2024年第8期5卷 1073页

作者： Ain, Arindom Gogoi, Minakshi Chutia, Dibyajyoti Dept. of Computer Science and Engineering GIMT Under Assam Science and Technology University Assam Guwahati India Dept. of Computer Science and Engineering Girijananda Chowdhury University Assam Guwahati India NESAC Umium Shillong India

Multispectral satellite image classification is crucial in remote sensing and image analysis, serving various applications like water area extraction, urban region classification, and vegetation monitoring. Model-based classification, particularly supervised learning approaches, heavily relies on manually annotated training samples, which are labor-intensive and subject to human bias. However, solely depending on features derived from individual pixels may fail to capture spatial contextual information effectively and manage mixed pixels and various types of noise, resulting in classification inaccuracies. To address these challenges, this research proposes a novel unsupervised learning approach and automatic labeling technique (ALT). This approach utilizes collective information from groups of pixels instead of relying solely on individual pixels for identification and extraction of meaningful unique patterns which serves as the most significant factor for satellite image classification. A new similarity index, the patch similarity index (PSI), is generated by incorporating the rank correlation similarity index (RCSI). The PSI is used to determine the similarity factor both between the patches and within the patch. Subsequently, a clustering algorithm is employed to group pixels into four distinct classes: vegetation, water, built-ups, and open land. Additionally, ALT streamlines the post-classification process by reducing the need for manual intervention in mapping clusters to the actual class label. The proposed method offers a more accurate and reliable unsupervised classification for multispectral satellite imagery, promising enhanced efficiency and reduced manual labor. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automatic labeling technique Frequent masking Multispectral Patch similarity index Rank Correlation

来源：评论

学校读者我要写书评

暂无评论

Developing and Training a Mathematical Model for Optimizing a Given Interior Space of a Supermarket

Developing and Training a Mathematical Model for Optimizing ...

引用

2023 International Research Conference on Smart Computing and Systems engineering, SCSE 2023

作者： Alahakon, Shalitha Siriwardana, Tharindu Udupihilla, Deshan Wickramasinghe, Tharukshi Rajapaksha, Samantha Sri Lanka Institute of Information Technology Dept. Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350341454

Retailers are crucial in supply chains, acting as the bridge between consumers and resources. However, there is limited analytic-based literature on block design in grocery stores. This paper employs an algorithmic approach with optimization techniques to efficiently design the interior space of a provided supermarket. The objective is to create an analytical method for handling design issues without relying on human-centered approaches. Using data from supermarket store arrangements, the paper showcases efficient space utilization by aligning item measurements with customer needs. Decision variables offer decision makers a precise collection of non-dominated designs. Previous studies demonstrate the effectiveness of this approach in analytically designing a data-driven structure for supermarket block layouts. The model identifies layouts that maximize space utilization while meeting industry standards. Although primarily focused on Asian retailers, the approach is generally applicable due to the similarity of grocery store layouts worldwide. The method and results are easily translatable for other retailers. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Land Use Land Cover Classification Using Machine Learning and Remote Sensing Data: A Case Study of Karnaprayag, Uttarakhand, India 1

Land Use Land Cover Classification Using Machine Learning an...

引用

1st International Conference on Electronics, Communication and Signal Processing, ICECSP 2024

作者： Saini, Rashmi Singh, Suraj Govind Ballabh Pant Institute of Engineering and Technology Dept. of Computer Science and Engineering Pauri Garhwal India

ISBN: (纸本)9798350364590

Land use and land cover (LULC) classification is crucial for planning and sustainable development, especially in mountainous regions. This study focuses on the Tehsil Karnaprayag, situated in the vicinity of the Greater Himalaya. With a total area of 1858.903 km2 and elevations ranging from 647m to 7641m. Using multispectral Sentinel-2 imagery and Machine Learning techniques i.e. Extreme gradient boosting (XGBoost) and K-nearest neighbor (KNN). This study aims to classify seven distinct land cover classes: snow, forest, water bodies, grassland, agricultural land, fallow land, and built-up areas. The classification results demonstrate the effectiveness of XGBoost classifier achieving an accuracy of 90.22% and a kappa value of 0.882, while KNN achieved an accuracy of 88.59% with a kappa value of 0.862. The analysis reveals that forest and fallow land are the predominant land cover types in the study area, constituting nearly 60% and 15% of the total area respectively. Notably, XGBoost exhibits the highest class-specific accuracy of 97.60% for the snow class, demonstrating its utility in discriminating between challenging land cover types. This research highlights the importance of LULC classification in informing land management strategies and facilitating sustainable development initiatives in mountainous regions. The findings provide valuable insights into the spatial distribution and composition of land cover in Tehsil Karnaprayag, essential for effective planning and conservation efforts in the Himalayan ecosystem. © 2024 IEEE.

关键词： Sustainable development

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：