检索结果-内蒙古大学图书馆

The impact of backbone selection in YOLOv8 models on brain tumor localization

Iran Journal of computer science 2025年 1-23页

作者： Ranjbarzadeh, Ramin Crane, Martin Bendechache, Malika School of Computing Faculty of Engineering and Computing Dublin City University Dublin Ireland ADAPT Research Centre School of Computer Science University of Galway Galway Ireland

This study investigates the utilization of the You Only Look Once (YOLOv8) deep learning framework for accurately identifying the location of brain tumors in medical imaging. We investigate the effects of model size and pretraining on the accuracy and computational efficiency of tumor detection by utilizing different setups of the YOLOv8 model. These setups include various configurations, ranging from very small to large, and can be pretrained on the COCO dataset or not. The experimental results, carried out on Google Colaboratory using NVIDIA Tesla T4 GPUs, show that pretrained models often achieve better performance by utilizing the extensive feature representations learned from the COCO dataset, resulting in increased precision in tumor location. For instance, the YOLOv8-XS model pretrained on COCO achieves an IoU of 0.278 and a Dice coefficient of 0.435, whereas its non-pretrained counterpart attains only 0.241 IoU and 0.388 Dice, indicating a 15% improvement in tumor localization accuracy. Similarly, pretrained YOLOv8-L achieves 0.269 IoU, outperforming standard object detection models such as Mask R-CNN (IoU: 0.212) and Faster R-CNN (IoU: 0.228). These results highlight the impact of pretraining on model performance, particularly for lightweight architectures, while also revealing diminishing returns for larger models. The research uncovers a subtle connection between the complexity of the model, pretraining, and the time required for training. It emphasizes the possible advantages and constraints of pretraining for various sizes of models. © The Author(s) 2025.

关键词： Brain tumor localization COCO dataset Deep learning Object detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Smart Parking System 3rd

Collaborative Smart Parking System

引用

3rd International Conference on Advanced computing and Intelligent Technologies, ICACIT 2023

作者： Yougesh Raj, S. Velu Prasad, B.A. Vishvakar, S. Hirthik, G. Nair, Prashant R. Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819719600

The escalating number of cars on the roads is directly contributing to the exacerbation of traffic congestion, making it increasingly challenging to secure suitable parking spots within cities. Currently, manual labor is primarily responsible for managing the majority of parking spaces in urban areas. However, having the industrial landscape embraces automation to streamline operations and enhance human convenience, the development of intelligent systems has become crucial. This study aims to introduce a collaborative smart parking system that leverages the power of automation. Our goal is to alleviate the laborious process of finding parking spots by designing an Internet of things (IoT)-based collaborative smart parking system that integrates all available parking spaces into a single application. Each parking spot is equipped with an IoT module comprising a proximity sensor to detect the presence of vehicles and a camera to capture and process their number plates. Moreover, our system allows users to reserve parking spots through a cloud-based application. To prevent unauthorized parking in reserved spaces, we employ a camera module and a buzzer. When a vehicle enters a reserved spot, the camera module processes its number plate, and if it identifies the car as unauthorized, both the person who reserved the spot and the central monitoring system receive an alert. While certain cities already have some of these facilities in place, the problem lies in the fragmented nature of the parking spaces. Our solution proposes to consolidate all parking spaces within a single application and harness the efficiency of cloud systems. By offering an application that people can utilize on a daily basis, we aim to simplify their lives and enhance their parking experience. The integration of various parking spaces into a unified platform, combined with the utilization of cloud technology, provides a seamless and efficient solution that individuals can rely on consistently. © The

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Semantic Analysis Using Deep Learning for Predicting Stock Trends 2

Semantic Analysis Using Deep Learning for Predicting Stock T...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Galphade, Manisha Nikam, V.B. Yedurkar, Dhanalekshmi Singh, Prabhishek Stephan, Thompson Department of Computer Science & Engineering School of Computing MIT Art Design & Technology University Pune India Department of Computer Engineering & IT Veermata Jijabai Technological Institute Mumbai India Department of Computer Science & Engineering School of Computing MIT Art Design & Technology University Pune India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science & Engineering Graphic Era Deemed to Be University Uttarakhand Dehradun India

Company Investors and financial professionals mostly rely on quarterly reports to help them decide the ways to invest in stocks and assess the company's current performance. Quarterly company reports offer an abstracted perspective of the company's overall past performance, as well as its present situation and the market value of its market share. Financial text streams in quarterly report are unstructured naturally, but they represent cooperative expressions that are of important in any financial decision for stake holder. It will be both daunting and necessary to procedure intelligence of unstructured textual data. In this study, we address important queries related with the explosion of interest in a method to extract useful information from unstructured data and the way to work out if such insight provides any hints regarding the trends of financial markets. There is a lack of availability in the labeled dataset for financial sentiment analysis applications. The pre-trained language model employs very little labeled parameters that is used for a variety of domain specific corpora including financial sentiment analysis. In this paper, FinBERT, a model built on the BERT framework, to address linguistics challenges in the financial domain. The proposed work uses twelve transformer layers and twelve attention layers with several million parameters. The design of encoder and decoder comprises of several attention layers along with RNN. This arrangement aids to recognize instances processing the strongest relation between the words within a particular sentence. The experimentation results shows that the presented method surpass the state-of-the-art methods for financial datasets. The results are also compared with other existing models using the same financial dataset. It is observed that the FinBERT attains an accuracy of 84.77% on quarterly reports despite using a lesser training set. © 2024 Elsevier B.V.. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy Usage and Data Storage in Industrial IoT Settings Through Heuristic-Based Data-Rate Processors 2

Optimizing Energy Usage and Data Storage in Industrial IoT S...

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Bharathi Kannan, B. Sriramulu, Srinivasan Gopal, Vidhya Karthick, M. Reddy, Yanna Nithin Natarajan, B. Galgotias University School of Computing Science and Engineering India Sona College of Technology Computer Science and Engineering Salem India K Ramakrishnan College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Tiruchirappalli India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India VIT University School of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350383287

The Internet of Things (IoT) is a fast-expanding field, with applications in areas as diverse as transportation, aviation, automation, electricity, and healthcare. Sensors, protocols, actuators, cloud services, and layers are just few of the components that make up an IoT architecture. The architecture of the Internet of Things is crucial in delivering the goods. The research community now provides dozens of IoT architectures. interoperability, security, privacy, dependability, energy limits, scalability, and a lack of shared standards are only some of the problems that have been recognized by the research community. The proposed IoT architecture should also consider issues of interoperability, scalability, dependability, and trust. By fixing these issues, this research work builds an IoT ecosystem that can accommodate a wide range of devices and services, guarantee smooth communication and scalability, and lay the groundwork for secure, dependable IoT offerings. In effective offloading and resulting interruptions in task execution might result from high latency or network outages. However, because of the importance of a select few delay-sensitive applications, it is important to guarantee their safety. Therefore, this research work aims to unload data at edge and cloud servers, Heuristic based Energy Efficient Data Rate Controller for Offloading has been developed for sensor networks. The bio-inspired NSGA-2 method is used to assess the performance of the suggested algorithm within the context of the problem's multi-objective function formulation. When compared to the current energy aware scheduling approach, the results show that the offloading method can decrease the amount of time and energy needed to run edge servers, maintain load balancing, and maximize resource utilization while still allowing applications that require delays to meet their deadlines. Finally, simulation results demonstrate the proposed approach outperforms 20% high efficiency compared to the

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Automated Attendance Monitoring: Harnessing Ambient Sensitivity and RSSI-based Proximity Analysis 15

Next-Generation Automated Attendance Monitoring: Harnessing ...

引用

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

作者： Harish, Vibha Joshi, Pallavi Muruganandam, Narendran Sobanapuram Das, Soumik Rao, Apeksha Mukhopadhyay, Adwitiya Amrita School of Computing Department of Computer Science Mysore India Amrita School of Computing Department of Sciences Mysore India

ISBN: (纸本)9798350370249

Automated attendance monitoring is essential across various fields, offering efficient and precise alternatives to traditional manual methods. This paper presents an innovative approach to attendance tracking by utilizing a Raspberry Pi, microphone, audio input, and machine learning techniques. The system integrates LSTM-based ambient sensitivity and RSSI-based proximity analysis to achieve heightened accuracy in attendance monitoring. The Raspberry Pi acts as the central component, capturing ambient audio with a microphone and collecting RSSI data via a Wi-Fi module. MFCC is employed for audio preprocessing to extract relevant features for training an LSTM model, capable of classifying diverse audio inputs. Simultaneously, RSSI data undergoes preprocessing and analysis to estimate device proximity accurately using machine learning algorithms. This paper presents a particular combination of current methods (RSSI, LSTM, and Raspberry Pi) for dual-audio attendance monitoring. With two distinct audio inputs for the teacher and pupils, it may be possible to analyse the presence of the teacher differently and to discern ambient noise based on location. By comparing audio inputs quantitatively, this method gives the attendance monitoring system an extra degree of accuracy. The proposed system's student module records attendance by analyzing ambient sound and RSSI data processed by LSTM with MFCC. This comprehensive approach reduces manual efforts, enhances accuracy, and delivers real-time attendance information to the teacher module, facilitating efficient attendance management in educational environments. © 2024 IEEE.

关键词： Ambient Audio Audio Comparison LSTM MFCC Raspberry Pi RSSI

来源：评论

学校读者我要写书评

暂无评论

Credit Card Fraud Detection Using Machine Learning- A Comprehensive Review 3

Credit Card Fraud Detection Using Machine Learning- A Compre...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Jaswant, T. Venkata Manoj, G. Sai Vamisdhar, V. Aravind, A. Reddy, S. Vasudeva Patni, Jagdish Chandra Bahadure, Nilesh Kumar, Rohit Alliance School of Advanced Computing Alliance University Dept. of Computer Science Engineering Bengaluru India School of Technology Gsfc University Department of Computer Science and Engineering Gujarat India

ISBN: (纸本)9798331518592

Credit card fraud is an omnipresent threat in the digital era that cannot be effectively managed without complex detection and prevention strategies. Machine learning has become instrumental for the industry, principally, due to providing tools to analyze transactional information and identify patterns of fraud. The article dwells on the methods, problems, and prospects of their future use. The algorithms are analyzed according to their potential applicability, scalability, and interpretability for fraud detection. This study includes convolutional neural networks and recurrent neural networks are used for utilization of anomaly exposure detection methods to detect unseen fraud with models. © 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

A novel brain tumor segmentation and classification model using deep neural network over MRI-flair images

引用

Multimedia Tools and Applications 2025年第17期84卷 17645-17676页

作者： Rajendirane, Rajmohan Ananth Kumar, T. Sandhya, S.G. Hu, Yu-Chen Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Kattankulathur India Department of Computer Science and Engineering IFET College of Engineering Tamil Nadu Villupuram India Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

Brain tumors pose a significant health concern globally, with their detection and diagnosis being crucial for timely intervention and treatment planning. These abnormal growths can develop within the brain or originate from other parts of the body, spreading to the brain. They can be benign or malignant, and their impact on cognitive and physical function can vary widely depending on their location, size, and type. Detecting brain tumors involves a combination of imaging techniques and clinical assessment. Magnetic Resonance Imaging (MRI) is one of the primary imaging modalities used for this purpose due to its ability to provide detailed images of the brain's anatomy and pathology. Advanced image processing techniques and machine learning algorithms play an increasingly important role in enhancing the accuracy and efficiency of brain tumor detection. This study presents a comprehensive approach for enhancing brain tumor detection in MRI images using a combination of advanced techniques. Firstly, an improved K-means clustering algorithm is introduced to segment tumor regions effectively. Following this, Median Filtering is applied to refine image quality and reduce noise interference. Subsequently, a deep neural network architecture is employed for precise tumor classification utilizing the BRATS dataset. The proposed methodology aims to improve the accuracy and efficiency of brain tumor detection, offering potential advancements in medical image analysis and diagnosis. Experimental results demonstrate promising outcomes, indicating the effectiveness of the proposed approach in accurately identifying tumor regions in MRI scans. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Adaptive iterated local search algorithm for dynamic patient admission scheduling problems

引用

Soft computing 2025年第7期29卷 1-11页

作者： Turky, Ayad Sabar, Nasser R. Song, Andy Hussain, Abir Liatsis, Panos Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Science and Information Technology La Trobe University MelbourneVIC3086 Australia School of Computing Technologies RMIT University Melbourne Australia Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates

Healthcare resource management is essential for ensuring the quality of patient care. However, it can be a complex and costly task. This work addresses the patient admission scheduling (PAS) problem, a complex aspect of healthcare resource management. PAS aims to allocate patients to hospital beds within a planning horizon, subject to a variety of healthcare constraints. The goal is to maximize management efficiency and patient comfort to improve medical treatment. In this work, we consider a practical variant of PAS known as dynamic PAS (DPAS). DPAS considers several factors and constraints, such as the daily registration of new patients, urgent patients, uncertainties in stay lengths, operating theatre resources, and the surgery scheduling process. An effective and efficient adaptive iterated local search (AILS) algorithm is proposed to solve DPAS. To enable the search to explore the search space efficiently, the proposed AILS adaptively integrates a number of components. Two adaptive perturbation strategies are devised to locate unexplored areas in the search space. To exploit the newly discovered areas effectively, we propose an adaptive local search mechanism as an intensification strategy to find a high-quality solution. The proposed AILS algorithm is compared to benchmark problems used by existing algorithms. The experimental results demonstrate the effectiveness and efficiency of the proposed approach. Specifically, out of 30 tested instances, AILS obtains 17 of the best-known results using less computational time. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Precaution Chatbot for Epilepsy Patients using Natural Language Processing and Deep Learning Sequential Model 5

Precaution Chatbot for Epilepsy Patients using Natural Langu...

引用

5th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2024

作者： Kasthuri, E. Subbulakshmi, S. Sreedharan, Rajasree Department of Computer Science and Engineering Amrita School of Computing Amritapuri India Department of Computer Science and Applications Amrita School of Computing Amritapuri India Division of Nephrology Department of Pediatrics Medical College of Wisconsin MilwaukeeWI United States

Epilepsy is a brain disorder that can affect people of all ages which is one of the most common neurological disorders affecting around 50 million individuals. Healthcare Chatbots schedule appointments, respond to patient inquiries, and offer relevant information, freeing medical staff to handle life crises. This paper implements a chatbot for epilepsy patients to increase awareness about epilepsy. Patients may easily access this AI-based healthcare chatbot whenever they have queries regarding precautions to be taken by epilepsy patients. Chatbot uses a rich set of epilepsy-related datasets collected from trusted websites which are preprocessed with NLP techniques to prepare the data for model ***, LSTM, and RNN models are created and evaluated to produce answers to user queries related to possible precautions to avoid seizures, safety measures to be taken by patients with seizure history, etc. Evaluation of models shows that the RNN model generates more accurate answers with 94% accuracy. Finally, the epilepsy question answering Chatbot for precaution is concluded with the RNN model. © 2024 The Authors. Published by Elsevier B.V.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Driver Safety Using Deep Learning Models 5

Enhancing Driver Safety Using Deep Learning Models

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Shokeen, Ishaan Uday, Krishnendu M Venugopalan, Manju Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Electronics and Computer Engineering Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376685

This proposed work emphasizes the critical role of eye movement detection, particularly open and closed eye states, in identifying drowsiness, providing a clear focus on the project's main technological approach and its importance for road safety. The proposed model ensures constant checks on the driver's safety and provides necessary observations on their behavioral activities. To ensure effective drowsiness detection, different methodologies such as Convolutional Neural Networks (CNN), customized Neural Networks and Recurrent Neural Networks (RNN) were employed for image processing. The CNN model achieved the best results. Two different data sources from Kaggle provided various training images for the model to operate in different scenarios. The proposed model aims to achieve accurate predictions across various case scenarios and to develop the most efficient model for real-time detection and alert systems, ensuring driver safety. Among the models our system gives the best result using CNN reporting an accuracy of 98.53%, and precision, recall and F-score of 98.71%, 98.04% and 98.37% respectively. © 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

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：