检索结果-内蒙古大学图书馆

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Asha Varma, S. Pilli, Divya Monika Jamallamudi, Narendra Digumarthi, Mukesh Velagapudi Ramakrishna Siddhartha Engineering College Department of Artificial Intelligence and Data Science Vijayawada India

ISBN: (纸本)9798331528201

In recent decades, visual impairments have presented significant hurdles in individuals' daily lives, often necessitating help, which can be limited in availability. However They need equal access to resources that enable them to live independently and confidently navigate their surroundings. To address these challenges and aid visually impaired individuals in navigating safely and efficiently. This research introduces real-time object detection and audio feedback systems using YOLOv8 deep learning architecture. The system is designed to process live video feed from a webcam and detect objects in the frame using OpenCV library and provide instant audio feedback on detected objects with the help of gTTs(Google-Text-To-Speech) API. The YOLOv8 is selected because of its highly efficient and accurate object detection, leveraging its ability to process images in a single forward pass. The model is implemented using python, OpenCV, CVZone library for real-time object detection visualization with bounding boxes. To optimize user experience, the system is integrated with gTTs (Google-Text-To-Speech) API combined with playsound module to provide audio feedback and provide flawless user experience. The system provided an average object detection accuracy rate of 91% and audio response in 45ms. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PLASTIC IMAGE DETECTION FROM UAV IMAGES USING YOLOV8 2

PLASTIC IMAGE DETECTION FROM UAV IMAGES USING YOLOV8

引用

2nd International Conference on Computer Vision and Internet of Things, ICCVIoT 2024

作者： Nivaashini, M. Dhayal, S.R. Gokul, C. Sanjay, V.T. Sharan, M. Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Tamil Nadu India

ISBN: (纸本)9781837242672

Plastic pollution is a critical environmental issue that demands innovative monitoring solutions. This study utilizes the YOLOv8 deep learning algorithm in combination with Unmanned Aerial Vehicles (UAVs) equipped with high-resolution cameras to automate plastic detection in aerial imagery. A custom drone dataset, with 85% of the images containing plastic, was developed to evaluate detection performance. The results demonstrate that YOLOv8 can effectively identify plastic in complex environments, offering a scalable and efficient alternative to traditional ground surveys. However, challenges such as varied plastic types, sizes, and visual complexity remain. This UAV-based approach shows promise for large-scale applications, including tracking cleanup initiatives, mapping plastic distribution, and assessing environmental impacts. Future research could improve this methodology by incorporating advanced image processing techniques to address plastic variability and enhance detection accuracy. Overall, the findings highlight UAVs as a valuable tool for comprehensive plastic pollution monitoring and contribute to advancing environmental conservation efforts. © The Institution of engineering & Technology 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

An Effective Crop Recommendation using Ensemble Classifier 3

An Effective Crop Recommendation using Ensemble Classifier

引用

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

作者： Kandula, Ashok Reddy Vadapalli, Jai Srinivas Mannava, Srinivasa Sai Shanmukha Modugumudi, Sai Seetharam Mohammad, Irfan Dept. of Artificial Intelligence & Data Science Seshadri Rao Gudlavalleru Engineering College Gudlavalleru India

ISBN: (纸本)9798331527549

Modern expectations for efficiency and sustainability are sometimes not addressed by the existing approaches in the continually changing environment of agricultural activities. In order to fully address these difficulties, research investigates how precision farming practices may be integrated while utilizing technological improvements. Study attempts to estimate optimal crop choices by assessing important characteristics including area, rainfall, temperature, and district-specific data, giving farmers the power to make well-informed and data-driven decisions. Precision farming lowers risks related to climatic unpredictability, increases output, and minimizes resource waste. By using the strategy, encourage resilience and innovation in the agricultural industry while bridging the gap between current farming practices and the sustainable agriculture of the future. Employing advanced algorithms including LR, Ridge Regression, DTs, and classifiers, achieved a remarkable 96% accuracy rate. Additionally, the proposed system offers real-time alerts via email or SMS, delivering timely advice and actionable insights to enhance agricultural sustainability and productivity. © 2025 IEEE.

关键词： Sustainable agriculture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Patient Care Through NLP-Based Realtime Bidirectional Voice Translation in Healthcare

Enhancing Patient Care Through NLP-Based Realtime Bidirectio...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Kanchanadevi, P. Ilakkia, A. Janane, S. Dheepika, I. Aiswarya, S. Abitha, S. Sri Manakula Vinayagar Engineering College Department of Artificial Intelligence and Data Science Puducherry India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

In healthcare settings, the language barrier between patients and medical professionals poses a significant challenge, impacting the quality of care and patient outcomes. Patients that struggle with language barriers to properly connect with their healthcare providers may face obstacles in receiving timely and accurate treatment. The proposed solution leverages bidirectional voice translation capabilities to facilitate communication between individuals who do not share a common language. This research introduces bidirectional voice translation technology as a solution to the language barrier in healthcare. Through the application of Natural Language Processing (NLP) and Speech Recognition algorithms, this mobile application enables real-time translation of spoken input between patients and medical professionals. By employing a mobile application accessible to both medical professionals and patients, this technology enables seamless communication in diverse linguistic settings. This innovation enhances communication, enabling accurate diagnosis, treatment, and explanation of medical procedures across diverse linguistic backgrounds. With multilingual support, sentiment analysis, and offline capabilities, this technology offers a promising avenue to improve patient care, health outcomes, and inclusivity in healthcare delivery. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Convolutional Neural Networks for Breast Cancer Detection

Enhanced Convolutional Neural Networks for Breast Cancer Det...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Kandula, Ashok Reddy Ganta, Pujitha Gali, Grace Apoorva Kasagani, Sandeep Tikkisetti, Devi Venkata Karthik Seshadri Rao Gudlavalleru Engineering College Department of Artificial Intelligence and Data Science Gudlavalleru India

ISBN: (纸本)9798350375237

For women all around the world, breast cancer is a serious concern. Catching it early is like having a superhero move - it can make all the difference, turning a potentially life-threatening situation into one with a shot at successful treatment. So, finding it sooner rather than later is a real lifesaver. To evaluate the performance of the proposed model, the researchers trained and tested the model on the Breast ultrasound Images dataset. These images, meticulously prepared through resizing, normalization, and augmentation, have been widely utilized in prior studies focusing on breast cancer prediction. The study focuses on refining accuracy through the utilization of Convolutional Neural Networks (CNNs) in combination with Transfer Learning for initial improvement. Following this, the approach shifts to leveraging the potential of the Adam optimizer with the CNN and Transfer Learning architecture to further boost accuracy. The implications of this study transcend the conventional confines of traditional medical image analysis, providing a glimpse into a prospective era where intelligent algorithms harmoniously collaborate with medical professionals. This collaboration serves to elevate the benchmarks of diagnostic accuracy. With the augmentation of early detection potential, patient outcomes stand to witness marked enhancement, thus underscoring the transformative prowess embedded within the capabilities of deep learning in the domain of breast cancer diagnosis. © 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

Altered Image Detection in E-commerce Products Using Feature Fusion Model 5

Altered Image Detection in E-commerce Products Using Feature...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Deva Sundar, M. Ansgar, V. Atchaya, S. Ananthi, S. St. Joseph's College of Engineering Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331504403

In today's world, e-commerce websites have become the go-to choice for shoppers. Unfortunately, scammers exploit this by using altered or filtered photos to deceive customers, leading to dissatisfaction and financial losses. This study addresses this issue by introducing a novel approach for detecting altered images on e-commerce platforms. The proposed model employs a feature-level fusion method that combines traditional feature extraction with a Convolutional Neural Network (CNN)-based model to identify manipulated images effectively. This approach leverages the strengths of both traditional image processing techniques and modern deep learning architectures. Extensive experimentation has shown that this model significantly enhances accuracy, achieving a 95% improvement over standalone CNN models. The model's robustness and accuracy have been validated across various product categories, confirming its suitability for different types of e-commerce images. The primary objective is to increase the reliability of product images, thereby boosting customer satisfaction and reducing return rates. © 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

Harnessing RNN for Omicron Prediction via CT Scan Analysis 15

Harnessing RNN for Omicron Prediction via CT Scan Analysis

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Koreddi, Venkatesh Kumar, K. Nikhil Ayesha, Sk. Bibi Rao, V. Jaya Rama Jaithra, K. Lakireddy Bali Reddy College of Engineering Artificial Intelligence & Data Science Department Mylavaram India

ISBN: (纸本)9798331300579

In recent trends we are again hearing the name SARS Cov-2, it underscored the urgent need for rapid and accurate diagnostic tools to combat the ongoing pandemic. This research introduces a fresh approach utilizing deep learning techniques to detect Omicron infection early, achieved through the analysis of CT scans.. Our research leverages a substantial dataset comprising 14,482 CT images obtained from diverse sources, including individuals with confirmed Omicron infection. A Convolutional Neural Network (CNN) is frequently utilized for image detection along with classification.. CNN are inspired by the structure of human brain. In CNNs, artificial neurons or nodes, similar to neurons in the brain, receive input, undergo processing, and produce output. However another challenge encountered when dealing with infection detection in terms of execution time and performance of prediction. Lack of inputs is the main cause for this, the proposed RNN technique using 14,482 CT scan images outperformed the existing in terms of accuracy and execution time. RNNs have the ability to examine temporal patterns found in CT images illustrating viral infections. Analyzing temporal patterns allows our model to grasp intricate patterns present in the dataset. © Grenze Scientific Society, 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

MAG molten pool edge detection algorithm based on a fusion of dark channel prior dehazing and image enhancement

引用

Optoelectronics Letters 2024年第10期20卷 607-613页

作者： LIU Weipeng QU Zepeng GONG Xiangrui WANG Yuheng ZHOU Zhengkui School of Electrical Engineering Hebei University of TechnologyTianjin300401China School of Artificial Intelligence and Data Science Hebei University of TechnologyTianjin300401China

Metal active gas(MAG)welding is one of the widely applied welding techniques using argon and carbon dioxide as shielding *** response to the problem of welding halo and drag shadow during the image acquisition process of it,which makes it difficult to accurately extract the contour of the molten pool,this paper proposes a molten pool edge detection method that combines dark channel prior dehazing(DCPD)and improved single scale Retinex image enhancement *** method overcomes the problem of excessive edge noise in the original molten pool image and the difficulty in feature extraction caused by the dark part of the molten pool after DCPD *** comparative experiments and ablation experiments,it has been shown that the algorithm proposed in this paper has significantly improved the enhancement effect and feature extraction effect,extracting accurate and complete molten pool contours.

关键词： welding image algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cardiovascular Risk Assessment Through Machine Learning 9

Enhancing Cardiovascular Risk Assessment Through Machine Lea...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Kandula, Ashok Reddy Kalyanapu, Srinivas Vamsi Krishna Alapati, V.M.S. Mokshagna, Adivanna Kumar, Ganta Karthik Satya Sai, Chalamala Seshadri Rao Gudlavalleru Engineering College Department of Artificial Intelligence And Data Science Gudlavalleru India

ISBN: (纸本)9798350394474

Heart disease is the reason, for mortality. When it comes to addressing concerns, in a facility one of the major challenges is that numerous healthcare professionals lack the necessary expertise and confidence to handle such cases. As a result they tend to make decisions leading to progress and unfortunately fatal outcomes. In order to address this, cardiac issues have been predicted using ML methods. In this study, many methods like Naïve Baiyes, K-Nearest Neighbour, Logistic Regression, Support Vector Machine, and Random Forest been applied. By the findings of this study, KNN has a maximum accuracy of 84.33% in predicting cardiac complaints based on health factors. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Screening for Diabetes Risk Prediction 3

Machine Learning based Screening for Diabetes Risk Predictio...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Kandula, Ashok Reddy Samhitha, Velevela Veda Harshitha, Vilasagarapu Sindhuri, Ragam Naga Nagavalli, Sangireddy Aarathi Department of Artificial Intelligence and Data Science Seshadri Rao Gudlavalleru Engineering College AndhraPradesh India

ISBN: (纸本)9798331532420

Diabetes Mellitus (DM) poses a major global health issue,impacting millions and significantly affecting quality of life. Early detection and risk prediction are crucial, but conventional diagnostic methods are often costly and limited by the availability of clinical markers. Machine Learning (ML) approaches, however, have shown higher predictive accuracy, reaching 77.9%, compared to traditional methods. This study examines ML techniques, such as Support Vector Machines (SVM) and Logistic Regression (LR), applied to datasets encompassing lifestyle, clinical, and demographic factors. Additionally, it explores the potential of integrating ML with wearables and electronic health records (EHR) to enable personalized, real-time risk assessments. These ML models consistently demonstrate improved accuracy, sensitivity, and specificity in predicting diabetes risk, with an accuracy rate of 77.9%, exceeding that of conventional diagnostic tools. © 2024 IEEE.

关键词： Electronic health record

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：