检索结果-内蒙古大学图书馆

The Past, Present, and Future of Storage Technologies (Part 1 of 2)

ACM TRANSACTIONS ON STORAGE 2025年第1期21卷 1-3页

作者： Kuenning, Geoff Won, Youjip Zhao, Ming Computer Science Harvey Mudd College Claremont United States Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Korea (the Republic of) School of Computing and Information Sciences Arizona State University Tempe United States Computer Science Stony Brook University Stony Brook United States

来源：评论

学校读者我要写书评

暂无评论

A Modified Deep Learning Framework for Leaf Disease Detection in Millet Crops

A Modified Deep Learning Framework for Leaf Disease Detectio...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Mohan, R. Raj Sukumar, V. John Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India

ISBN: (纸本)9798331509828

Climate change is causing a rapid increase in millet crop disease, which poses a threat to food security. The technology behind this is deep learning, which is advanced and efficient and plays a crucial role in the classification of images, such as healthy and diseased crop leaves. Utilizing a web server program makes data upload automatic and enables rapid image processing and interpretation of crop images for disease diagnosis. We conduct the present work using a deep learning approach based on the AlexNet model to classify diseased and healthy millet crop leaves. We use a publicly available dataset with pictures of the two types of leaves and add to AlexNet by using its convolutional neural network (CNN) architecture to pull out features and tell leaf pictures apart based on how they look. Our approach consists of training the model after applying preprocessing steps to the images and testing it to detect whether the leaves are healthy or diseased. The results demonstrate that we can apply this deep learning-centered approach to tackle the issue of plant leaf disease detection on a large scale, enabling farmers to implement the necessary control measures promptly. © 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

Electric Vehicle Charging Demand Prediction using Machine Learning Algorithms 8

Electric Vehicle Charging Demand Prediction using Machine Le...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Hitesh, K. N. B. Sai Teja, P. Saran Kumar, J. Ram Srm Institute of Science and Technology Computing Technologies Chennai India

ISBN: (纸本)9798350386578

The increasing concerns regarding climate change, notably the surge in greenhouse gas emissions, have attained paramount significance in the agendas of both U.S. and global policy makers. Transportation, responsible for 29% of U.S. greenhouse gas emissions according to the U.S. Environmental Protection Agency (EPA), stands as the nation's leading contributor to this challenge. In parallel, substantial policy initiatives at the national and state levels are underway, and key automotive manufacturers like Ford, GM, and Volvo have committed to a complete transition to electric vehicles (EVs) within the next decade, heralding a profound shift in the automotive industry. This impending transformation, combined with public and private sector efforts, is poised to generate a substantial increase in EV demand. Governments and public utilities can use this research to build and manage public charging networks strategically by applying machine learning models to forecast energy consumption patterns inside EV charging infrastructure. By proactively forecasting future EV charger energy consumption, this study aims to pinpoint regions of high demand, facilitating optimized infrastructure expansion and resource utilization, aligning with sustainability goals and the evolving EV landscape. We harnessed a real-time dataset comprising 433,172 electric vehicle transactions, including 91,255 new vehicle registrations. We integrated data from the National Renewable Energy Laboratory's API, encompassing 1,686 charging stations in Washington. Our modeling process, applied uniformly across counties, included seasonal decomposition, training and testing data partitioning, gridsearch with pmdarima for parameter optimization, and SARIMAX modeling for forecasting. Visualization aided in assessing forecast accuracy, contributing to our overall study on EV charging demand prediction. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Face Detection and Identification of Criminal Suspects

引用

computers, Materials & Continua 2023年第2期74卷 2331-2343页

作者： S.Sandhya A.Balasundaram Ayesha Shaik School of Computer Science and Engineering Vellore Institute of Technology(VIT)Chennai600127India School of Computer Science and Engineering Center for Cyber Physical SystemsVellore Institute of Technology(VIT)Chennai600127India

Occurrence of crimes has been on the constant rise despite the emerging discoveries and advancements in the technological field in the past *** of the most tedious tasks is to track a suspect once a crime is *** most of the crimes are committed by individuals who have a history of felonies,it is essential for a monitoring system that does not just detect the person’s face who has committed the crime,but also their ***,a smart criminal detection and identification system that makes use of the OpenCV Deep Neural Network(DNN)model which employs a Single Shot Multibox Detector for detection of face and an auto-encoder model in which the encoder part is used for matching the captured facial images with the criminals has been *** detection and extraction of the face in the image by face cropping,the captured face is then compared with the images in the *** comparison is performed by calculating the similarity value between each pair of images that are obtained by using the Cosine Similarity *** plotting the values in a graph to find the threshold value,we conclude that the confidence rate of the encoder model is 0.75 and above.

关键词： Deep learning opencv deep neural network single shot multi-box detector auto-encoder cosine similarity

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Automatic Detection of Bike Riders with No Helmet 15

Deep Learning Based Automatic Detection of Bike Riders with ...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Sivasangari, A. Sasikala, T. Deepa, D. Gowri, S. Rani, Nirmal Sathyabama Institute of Science and Technology School of Computing Chennai India

ISBN: (纸本)9798350370249

Riding motorbikes with a helmet is very essential and important as they may help prevent fatal head injuries in case of an accident. Helmet detection is an important and challenging vision task in traffic surveillance to avoid accidents for bike riders. As motorbike accidents have been growing in many countries due to the lack of traffic law power and mainly due to the negligence of the bike rider. With the help of the proposed method, we can detect bikers with no helmet and extract their license number plate for issuing a fine. This paper presents an automatic helmet detection method combining, Feature descriptor and DNN-classifier. Where the system is trained with predefined datasets and DNN (Deep Neural Networks) classifier is used to classify the objects. Pre-processing, Feature extraction, and Classification make up the proposed method of operation. This study suggests a system for classifying whether or not the cyclist is wearing a helmet. Regarding robustness and effectiveness, this technique offers high rates of accurate detection. © 2024 IEEE.

关键词： Deep Learning DNN Classifier Feature Descriptor Helmet Detection License Plate Number Extraction

来源：评论

学校读者我要写书评

暂无评论

VisionAid: Enhancing Accessibility for the Visually Impaired with YOLO and gTTS

VisionAid: Enhancing Accessibility for the Visually Impaired...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Lakshmi Raghupathy, Bhagya Nithyashri, J. Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331521394

Daily environment navigating and accessing visual information are critical problems for people with vision disabilities. To reduce this discrepancy VisionAid, an assistive application was introduced to make visually challenged person have better accessibility via integration of YOLO for real-time object detection and gTTS which is library used for text-to-speech conversion. It recognizes objects, speaks text aloud and promotes good navigation skills that improve mobility and independence. VisionAid augments vision loss with modern technologies like GPS and SLAM for navigation, rather than traditional aids. This paper presents VisionAid as an end-to-end solution, fills the gaps in existing models and brings more autonomy to its users. © 2025 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

ReFF: Reinforcing Format Faithfulness in Language Models Across Varied Tasks 39

ReFF: Reinforcing Format Faithfulness in Language Models Acr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yao, Jiashu Huang, Heyan Liu, Zeming Wen, Haoyu Su, Wei Qian, Boao Guo, Yuhang School of Computer Science and Technology Beijing Institute of Technology China School of Computer Science and Engineering Beihang University China

ISBN: (纸本)157735897X

Following formatting instructions to generate well-structured content is a fundamental yet often unmet capability for large language models (LLMs). To study this capability, which we refer to as format faithfulness, we present FORMATBENCH, a comprehensive format-related benchmark. Compared to previous format-related benchmarks, FORMATBENCH involves a greater variety of tasks in terms of application scenes (traditional NLP tasks, creative works, autonomous agency tasks), human-LLM interaction styles (single-turn instruction, multi-turn chat), and format types (inclusion, wrapping, length, coding). Moreover, each task in FORMATBENCH is attached with a format checker program. Extensive experiments on the benchmark reveal that state-of-the-art open- and closed-source LLMs still suffer from severe deficiency in format faithfulness. By virtue of the decidable nature of formats, we propose to Reinforce Format Faithfulness (REFF) to help LLMs generate formatted output as instructed without compromising general quality. Without any annotated data, REFF can substantially improve the format faithfulness rate (e.g., from 21.6% in original LLaMA3 to 95.0% on caption segmentation task), while keep the general quality comparable (e.g., from 47.3 to 46.4 in F1 scores). Combined with labeled training data, REFF can simultaneously improve both format faithfulness (e.g., from 21.6% in original LLaMA3 to 75.5%) and general quality (e.g., from 47.3 to 61.6 in F1 scores). We further offer an interpretability analysis to explain how REFF improves both format faithfulness and general quality. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AQI Prediction Using Human-AI Teaming 2

AQI Prediction Using Human-AI Teaming

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Jha, Abhinav Gupta, Harshit Sandhia, G.K. Srm Institute of Science and Technology School of Computing Chennai India

ISBN: (纸本)9798350368109

The paper aims to enhance the prediction of the Air Quality Index (AQI) by incorporating human-AI interaction in conjunction with Random Forest Regression (RFR). Although ML techniques have been applied in PA, these methods are highly susceptible to the complexity of variables in domains like air quality. To tackle this problem, the approach proposed in this paper relies on the Human-In-the-Loop approach where the confidence levels of the ML predictions are evaluated in conjunction with their accuracy. In situations where the output of the ML model is below a certain dynamic value, which is an indication that the model is not certain about the next course of action, the system reroutes the control back to a Human Expert for manual intervention. This approach is beneficial as it is more accurate than the base model when no human input is required in the algorithm's prediction process. In addition, it also opens channels for feedback where the base model can improve itself over time through learning and modification. In the present work, we are concerned with Using a Historical Air Pollution Dataset for Oragadam, Tamil Nadu and we are particularly focusing on the year 2023. This choice is made based on the Random Forest regression's ability to provide more stability and better capture of the non-linear nature of the data inherent in air quality. Our approach aims to address the weakness of purely automated prediction systems while addressing the strong points of both human knowledge and computational modeling to improve the accuracy of the AQI forecast. This study provides value to the enhancement of the field of collaboration between Human and Artificial Intelligence in environmental prediction with the prospect of enhancing the health of the public and the environment. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Reliable Real-Time Traffic Sign Detection Model for Diverse Environmental Challenges 5

A Reliable Real-Time Traffic Sign Detection Model for Divers...

引用

5th IEEE International Conference on Communication, computing and Industry 6.0, C2I6 2024

作者： Jayan, Keerthi Muruganantham, B. Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chengalpattu India

ISBN: (纸本)9798350379884

This paper presents the development and evaluation of the Real-Time Traffic Sign Detection Model (RTTSDM), lever-aging the YOLOv4 framework with a CSPDarknet53 backbone, trained on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. The RTTSDM exhibits significant advancements in traffic sign detection, showing substantial improvements across key performance metrics including average Intersection over Union (IoU), precision, recall, F1 Score, and mean Average Precision (mAP) throughout training. Notably, the model achieves a peak mAP of 0.9685 at iteration 4000, reflecting its superior ability to accurately identify and classify traffic signs. The model demonstrates robust performance under various lighting conditions, effectively detecting prohibitory, danger, mandatory, and priority signs with high accuracy. The RTTSDM shows strong potential to improve road safety and traffic management through its precise and reliable traffic sign detection capabilities. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

End-to-End Optimized Lossy Compression for Neural-Morphic Spiking Camera Captured Data

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 6074-6086页

作者： Feng, Kexiang Jia, Chuanmin Pan, Jingshan Ma, Siwei Gao, Wen Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing100049 China Peking University National Engineering Research Center of Visual Technology Beijing100871 China Peking University Wangxuan Institute of Computer Technology Beijing100080 China Shandong Computer Science Center National Supercomputer in Jinan Jinan250014 China Peking University National Engineering Research Center of Visual Technology School of Computer Science Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Chinese Academy of Sciences Beijing100190 China

Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic. Such imaging feature results in huge data storage and transmission burden compared to that of traditional camera, raising severe challenge and imminent necessity in compression for spike camera captured content. Existing lossy data compression methods could not be applied for compressing spike streams efficiently due to integrate-and-fire characteristic and binarized data structure. Considering the imaging principle and information fidelity of spike cameras, we propose a novel Reconstruction-based Contextual Spike Compression (RCSC) framework, which contains scene reconstruction, contextual image compression and spike generation. To our knowledge, it is the first learning-based model for efficient and robust spike stream compression with informative fidelity. Extensive experimental results show that our model outperforms the state-of-the-art conventional codec VVC intra by 6.14% and surpasses the state-of-the-art learned codec by 2.53% in BD-rate reduction, establishing a strong baseline for spike compression. © 1991-2012 IEEE.

关键词： Image compression

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：