检索结果-内蒙古大学图书馆

International Conference on Robotics, Control, Automation and Artificial Intelligence, RCAAI 2023

作者： Geetha Rani, E. Tukkoji, Chetana Anusha, D. Dhanalakshmi, M. Bharath, B. Department of Computer Science Engineering Alliance University Karnataka Bengaluru India Department of Computer Science Engineering Gitam University Karnataka Bengaluru India Department of CSE- Artificial Intelligence and Machine Learning SRKIT Andhra Pradesh Vijayawada India Department of Computer Science Engineering NHCE Karnataka Bengaluru India Department of Canteen Stores Department MVJ College of Engineering Karnataka Bengaluru India

ISBN: (纸本)9789819746491

Agriculture relies substantially on water. The IoT-based farm water management system explains how IoT technology can control irrigation intelligently. This system may be used to collect data by connecting several sensors such as soil moisture, temperature, and PIR motion sensors, among others. The collected data will be transferred to the user's mobile phone and sent to the users, ensuring crops receive the appropriate quantity of water and optimize irrigation schedules. By monitoring water levels, farmers may detect possible water loss locations and take action to prevent them. The primary goal of our article is to increase productivity, efficiency, and water use through live monitoring, water management, crop growth development, and the potential use of virtual water. Furthermore, breakthroughs in machine learning, such as crop prediction and recommendation, fertilizer detection, and leaf disease detection, will allow for more complex analysis of agricultural data, resulting in even great gains in water management and crop yield. However, it is important to ensure that these technologies are accessible to all farmers, regardless of the location or resources. If giving detailed information on soil properties and crop genetics, machine learning algorithms can forecast agricultural yields and find the best crops for a giving region. Now, farmers can maximize their crops by making data-driven decisions. This one system’s capability to exactly predict crops yields and resources requirements be one of its key advantages. To promote more sustainable and productive farming, farmers should also control the quantity of water and other resources used by them. By assuring a sufficient supply and reducing the likelihood of crops failure, crops forecast, leaf disease diagnosis, and guidance systems can assist address concern related to global food securities in addition to enhancing productivity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 20

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?

Medical Adaptation of Large Language and Vision-Language Mod...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Jeong, Daniel P. Garg, Saurabh Lipton, Zachary C. Oberst, Michael Machine Learning Department Carnegie Mellon University United States Mistral AI France Department of Computer Science Johns Hopkins University United States Abridge AI United States

ISBN: (纸本)9798891761643

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare seven public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering (QA) tasks. For instance, across the tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 12.1% of cases, reach a (statistical) tie in 49.8% of cases, and are significantly worse than their base models in the remaining 38.2% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model;(ii) optimizing the prompts for each model separately;and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Investigation of Red Fox Algorithm for Solving Task Assignment Problem in Heterogeneous Unmanned Aerial Vehicle Swarm 3

Investigation of Red Fox Algorithm for Solving Task Assignme...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Manaswitha, K. Issac, Titus Silas, Salaja Terance, J Sebastian Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798350372120

In recent years, there have been significant advancements in Unmanned Aerial Vehicles (UAVs), leading to their integration into everyday life. UAVs are constrained by limited energy, communication, and localization. The various challenges in UAV research include localization, routing, navigation, and task assignment. Recently, UAV swarms have been employed across a wide range of applications. This study focuses on solving task assignment problems within UAV swarms, considering the unique multi-objective resource constraints of UAVs. The work explores the feasibility of adopting the Red Fox Algorithm to address the task assignment problem in UAV swarms. The investigation examines two primary input parameters: Task Energy Demand and distance. The evaluation includes energy utilization and shortest distance as performance metrics. Notably, the proposed approach outperforms the Particle Swarm Optimization Algorithm (PSO), resulting in a 17.47% lower energy utilization while maintaining a 17.83% reduction in the shortest distance travelled. By leveraging the Red Fox Algorithm, the work aims to enhance the efficiency and effectiveness of task allocation in UAV swarms, contributing to their broader adoption across various applications. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Image Processing for Automobile Accident Detection Using Deep learning 3

Enhanced Image Processing for Automobile Accident Detection ...

引用

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Usharani, S. Dhanushkumar, J. Manju Bala, P. Balachandar, A. IFET College of Engineering An Autonomous Institution Department of Artificial Intelligence and Machine Learning Villupuram India IFET College of Engineering An Autonomous Institution Department of Computer Science and Engineering Villupuram India

ISBN: (纸本)9798350391565

Road safety can be creatively increased by utilizing systems for reporting and detecting accidents use the YOLO algorithm. Yolo, which stands for "You Only Look Once,"is a sophisticated object recognition system that can identify and pinpoint objects in live video streams. By identifying accidents and notifying emergency services, the system lowers the reaction times and increases the possibility of saving lives by utilizing the YOLO algorithm. The object detection and alarm systems are the two primary parts of the proposed system. The YOLO method is employed by the object recognition module to look for accidents in live video broadcasts. A module of accident photos was used to teach the system to accurately identify incidents. When an accident is discovered, an alert system is activated. The location of the accident and a brief account of what transpired are communicated to the emergency services by the alert system. This information is communicated to emergency services through a wireless communication network, which expedites response times and increases the likelihood of saving lives. Positive results were obtained by testing the system using the images and an accident module. It was shown that the warning system could react in a couple of seconds and that the YOLO algorithm could identify accidents having a precision of around 94. Highways, busy intersections, and other high-risk areas may have systems in place to increase traffic safety and lower the number of accidents. Developing crash detection and warning systems using deep learning using the YOLO technique is one way to potentially increase road safety. With the use of technology, problems may be precisely identified in real-time video feeds, alerting emergency services and potentially increasing survival rates and reaction times. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

IoT-based Efficient Waste Management on University Campus: Enhancing Monitoring and Optimization through machine learning 3

IoT-based Efficient Waste Management on University Campus: E...

引用

3rd International Conference on machine learning and data Engineering, ICMLDE 2024

作者： Sumathi, M. Hanumanthappa, J. Santhosh Kumar, K.S. Shiva Prakash, S.P. Meghana, J. Department of Studies in Computer Science University of Mysore Manasagangothri Campus Mysuru Karnataka570006 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering University of Mysore Manasagangothri Campus Mysuru Karnataka570006 India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru Karnataka570006 India Department of Computer Science Mahajana Post Graduate Center Mysuru Karnataka570016 India

The introduction of an IoT-based smart waste management system is proposed to optimize various aspects of university campus waste recycle management processes, such as garbage collection scheduling, waste type identification, and collection routes. This system utilizes advanced data analytics algorithms, wireless communication protocols, and sensors to measure and document variations in trash levels, enabling real-time monitoring of waste accumulation. Through this IoT-based infrastructure, university administrators and waste management staff gain fine-grained visibility and control over garbage collection processes. The implications for sustainability advocacy and environmental stewardship in academic environments are significant. By fostering a culture of environmental awareness and accountability, universities can instill ideals of conservation and resourcefulness in their student populations and staff. The proposed IoT-enabled waste bin system exemplifies the synergy between technological innovation and environmental responsibility, serving as a model for institutions worldwide. Collaboration among universities can leverage IoT technology to drive positive change, mitigate environmental degradation, and promote sustainable practices beyond campus boundaries. Efficient waste management is crucial for nurturing sustainability on college and university campuses, as evidenced by the urgent need for the collection and recycling of compost, general waste, and recyclables. Our models consistently achieve high performance, with perfect scores (1.000) across all split ratios, indicating flawless classification of waste types. Although the Artificial Neural Network (ANN) demonstrates slightly lower accuracy, ranging from 0.973 to 0.997 depending on data splits, it still performs well. As a result, Naive Bayes produces less accurate results, typically surpassing 0.93 but falling short of Random Forest, K-Nearest Neighbors (KNN), and Support Vector machine (SVM)'s flawless

关键词： Electronic Waste

来源：评论

学校读者我要写书评

暂无评论

Passive RFID Encryption and Decryption using CLI 7

Passive RFID Encryption and Decryption using CLI

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Sailesh Kumar, K.L. Srivatsan, M. Suhas Kumar, S.J. Satyaa, Sudarshan Vishwamalyan, J.S. Vellore Institute of Technology Department of Computer Science and Engineering Vellore India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798350341485

The implementation of the concept of RFID encryption to make a system that prevents the attack on the data of any user or organization on the cloud. The built application has a command line interface. The command line interface is used here instead of a web server to prevent data leakage during data transmission and reduce the risk of a rogue web server. The command line interface takes in an input image and encrypts it, producing an encrypted image and a key file. The CLI also decrypts the previously encrypted image using the key file. This app as a whole solves the problem of users and organizations that store images on the cloud, using this app the user can store encrypted images on the web while the low storage key file is on the user/organization's on-site server. This provides a 2-tier security mechanism via which an adversary will need to hack both the organization server and the cloud server to compromise the data, this way the image data is secure without any additional cost or overhead to the organization. an RFID encryption algorithm is developed along with a non-network-based CLI that secures the organization's RFID data and helps implement a secure cloud-bursting architecture. In this project, an algorithm is developed by combining both the XOR-based encryption algorithm and non-network-based CLI to secure the RFID of the user/organization. Most encryption algorithms nowadays use web-based servers to encrypt the RFID and produce the key file. This makes web-based encryption insecure and vulnerable to a man-in-the-middle attack. Therefore, this app comes to the rescue as it provides a non-network-based CLI by which there is no need for the actual RFID to go outside of the local machine, thus making this app and its architecture secure and robust. © 2023 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection in Chest X-Rays Using Combined Approach of Deep learning 2

Pneumonia Detection in Chest X-Rays Using Combined Approach ...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Aditya Pai, H. Pareek, Piyush Kumar Guruprasad, M.S. Chandrappa, S. Bhargava, Krishna Mit Art Design and Technology University Mit School of Computing Pune India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Department of Computer Science and Engineering Dehradun India School of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350372892

A respiratory infection like pneumonia faces a serious health challenge across the globe, especially in the poor and underdeveloped countries. The pneumonia is affected by various factors like bacteria or viruses. The reason for the affection is due to higher level of pollution, poor air quality, excess of population, poor infrastructure etc. To reduce the threat from pneumonia, there is a need for early and accurate detection of the infection by using chest X-ray images as the most effective diagnostic method. The paper proposes an automated chest X-ray analysis system by using VGG16 architecture and a weighted average ensemble method to enhance diagnostic accuracy. By integrating deep transfer learning, the system overcomes data scarcity issues, achieving a remarkable 99% accuracy on a publicly available dataset. The research underscores the potential of automated systems in improving pneumonia diagnosis, highlighting the urgent need for advanced diagnostics in resource-limited settings. © 2024 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Advanced sound-based pest detection in agriculture using deep learning and adaptive optimization

引用

International Journal of Information Technology (Singapore) 2025年 1-11页

作者： R, Sahana Lokesh SailajaKumar, K. S.Soundariya, R. K S, Kavitha Reshma, S. Department of Computer Science & Engineering (Cyber Security) Ramaiah Institute of Technology Bengaluru India SoCSE RV University Bangalore India Department of Computer Technology Bannari Amman Institute of Technology Tamil Nadu Sathyamangalam India Department of Computer Science and Engineering Dayananda Sagar College of Engineering Bengaluru India Department of Artificial Intelligence and Machine Learning Dayananda Sagar College of Engineering Bengaluru India

Implementing sound-based pest detection systems in large fields comes with challenges, including the complexity of acoustic data, interference from environmental noise, and the need for scalable, real-time solutions capable of processing data over vast areas. To address these challenges, we propose an innovative pest detection system that integrates advanced sound analytics with deep learning techniques. This study proposes a feature selection technique that includes the real-valued discrete Gabor transform algorithm and linear frequency Cepstrum coefficients (LFCC) algorithm, which helps analyze the frequency spectrum and capture critical features. The approach operates in four stages: pre-processing, feature selection, feature matrix generation and sound classification. This study proposes primarily, that data is collected and pre-processed, followed by the feature selection technique including the Real-Valued Discrete Gabor Transform algorithm and Linear Frequency Cepstrum Coefficients (LFCC) algorithm, which help analyze the frequency spectrum and capture critical features. These selected features are then generated as a feature matrix. After that, the pest sound is classified using Modified EfficientNet. To optimize the model’s parameters and enhance its performance and accuracy, the Hippopotamus Optimization Algorithm (HOA) is integrated with EfficientNet. The dataset was utilized to validate the suggested approach, with accuracy levels of over 98% and specificity is 97%, respectively. These results demonstrate superior classification efficiency compared to existing pest detection systems. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Feature matrix Hippopotamus Optimization Algorithm Linear Frequency Cepstrum Coefficients algorithm Modified EfficientNet Real-Valued Discrete Gabor Transform algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Air Quality Forecasting Using machine and Deep learning Based Approaches

Comparative Analysis of Air Quality Forecasting Using Machin...

引用

2025 International Conference on Artificial Intelligence and data Engineering, AIDE 2025

作者： Sowmya, H.K. Chandresh, Koyal Jesy Janet Kumari, J. D'souza, Sonia Maria Artificial Intelligence and Machine Learning New Horizon College of Engineering Bangalore India Visvesvaraya Technological University The Oxford College of Engineering Department of Computer Science and Engineering Belagavi Bangalore India

ISBN: (纸本)9798331527518

Many emerging nations are experiencing severe air pollution on account of the growing urbanization and industry. Because air pollution has an impact on global human health and sustainable development, governments and it is becoming source of concern in society. Anticipating air pollution thus became essential. Prediction of air quality has gained popularity by virtue of the volume and a range of data that air quality surveillance systems have collected. This paper uses a Python framework to analyze the air quality, implementing historical air quality data analysis for Bangalore city and predicting its quality exercising a number of machine and deep learning (D-learning) models. In the proposed work, 5 distinct machine learning(M-learning) models including Random Forest regression (RFR), Support Vector Regression (SVR), Linear regression (LR), Decision Tree (DT), and Long Short- Term Model of D-learning Technique (D-LSTM) have been accustomed to compute the Air Quality Index (AQI) of Bangalore city. This strategy has been put into practice in Google Collab with GPU run time. As stated by the measures including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), D-learning- based LSTM model has demonstrated better reliability than other M-learning models. Performance metrics values for LSTM is superior compared to the rest of M-learning models © 2025 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Video Chat using WebRTC with In-built Sign Language Detection 3

Video Chat using WebRTC with In-built Sign Language Detectio...

引用

3rd International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2023

作者： Sailesh Kumar, K.L. Srivatsan, M. Sendhan, A. Saran, J.U. Vidhya Sagar, P.V. Vellore Institute of Technology Department of Computer Science and Engineering Vellore India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798350306989

Many research efforts into video conferencing technology have focused on audio-only interactions. Text chat, on the other hand, has many uses and is often used in conjunction with the audio channel in multimedia conferencing systems because of the many benefits it offers to users in a variety of contexts. Video chat on the other hand has been providing participants to participate not only through voice but also through visual clues, creating a richer and more immersive communication experience. With the development of technology, video chat has transformed how people cooperate and communicate across distances by becoming more accessible and user-friendly. This study details a prototype program that uses video chat with in-built sign language identification to help the hearing-impaired and the speech-impaired. The prototype is constructed from WebRTC to provide realtime communication for the application, on top of which the object detection model from Tensor Flow is integrated to provide hand sign detection and recognition for the user. We focus our testing on the bandwidth and sign language detection needs of customers in order to provide improved support for video chat. We then talk about how this evaluation's findings can inform the evolution of video chatting software. © 2023 IEEE.

关键词： Object detection

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

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

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：