检索结果-内蒙古大学图书馆

Multi-granularity feature enhancement network for maritime ship detection

CAAI Transactions on Intelligence Technology 2024年第3期9卷 649-664页

作者： Li Ying Duoqian Miao Zhifei Zhang Hongyun Zhang Witold Pedrycz Department of Computer Science and Technology Tongji UniversityShanghaiChina Project Management Office of China National Scientific Seafloor Observatory Tongji UniversityShanghaiChina Department of Electrical and Computer Engineering AlbertaEdmontonCanada System Research Institute Polish Academy of SciencesWarsawPoland

Due to the characteristics of high resolution and rich texture information,visible light images are widely used for maritime ship ***,these images are suscep-tible to sea fog and ships of different sizes,which can result in missed detections and false alarms,ultimately resulting in lower detection *** address these issues,a novel multi-granularity feature enhancement network,MFENet,which includes a three-way dehazing module(3WDM)and a multi-granularity feature enhancement module(MFEM)is *** 3WDM eliminates sea fog interference by using an image clarity automatic classification algorithm based on three-way decisions and FFA-Net to obtain clear image ***,the MFEM improves the accuracy of detecting ships of different sizes by utilising an improved super-resolution reconstruction con-volutional neural network to enhance the resolution and semantic representation capa-bility of the feature maps from *** results demonstrate that MFENet surpasses the other 15 competing models in terms of the mean Average Pre-cision metric on two benchmark datasets,achieving 96.28%on the McShips dataset and 97.71%on the SeaShips dataset.

关键词： object classification object recognition rough sets rough set theory

来源：评论

学校读者我要写书评

暂无评论

Lung sound disease detection using attention over pre-trained efficientnet architecture

引用

Multimedia Tools and Applications 2024年 1-35页

作者： Nair, Anuja Vadher, Himanshu Patel, Pal Vyas, Tarjni Bhatt, Chintan Bruno, Alessandro Department of Computer Science & amp Engineering School of Technology Nirma University Gujarat Ahmedabad382481 India Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar382007 India Department of Business Law Economics Consumer Behaviour ’Carlo A. Ricciardi’ Faculty of Communication IULM University Milan20143 Italy

Air pollution has been on the rise for quite a while now and with it is the increasing number of cases involving respiratory diseases. These respiratory diseases range from the mild ones to the most severe ones. Therefore, we need to detect these diseases. The most efficient way of checking the health of the lung is through the use of lung sounds. But the lung sounds carry with them the minute variations that a doctor or any human sometimes misses. To tackle the same, this paper proposes a deep learning model that detects a person’s lung disease by processing lung sounds. The ICBHI 2017 dataset comprising the lung sound audios and their corresponding labels is used to train the proposed model. The dataset consists of lung sounds and some additional background noise has been removed using the bandpass Butterworth filter, whose frequency range has been set to 250Hz - 2000Hz. Later, the amount of data is multiplied through data augmentation for audio signals. The augmented data is later converted to mel spectrograms, which are, in turn, fed into the deep learning model. The model that gives the best accuracy is EfficientNet-B0 + attention with a training accuracy of 99.72%, validation accuracy of 99.82%, precision, recall and f1-scores of 99.82% as well. Furthermore, a comparison of the pre-trained model’s training and inference times has been performed. Although the proposed model takes a significant amount of training time, it takes the least amount of inference time compared to the other pre-trained models that have been tested. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Butterworth filters

来源：评论

学校读者我要写书评

暂无评论

A Brief Comparative Study of Metaheuristic Approaches for Hyperparameter Optimization of Machine Learning Model 1

A Brief Comparative Study of Metaheuristic Approaches for Hy...

引用

1st International Conference on computer science and Emerging Technologies, CSET 2023

作者： Dilip, Kumar Ghantasala, G. S. Pradeep Rathee, Manisha Kallam, Suresh Bathla, Priyanka Alliance University Department of Computer Science and Engineering Bengaluru India School of Computer and System Sciences Jawaharlal Nehru University India School of Computer Science and Engineering Jain Deemed to Be University Bengaluru India Chandigarh University Punjab Mohali India

ISBN: (纸本)9798350341737

Machine learning models have been successfully applied in numerous fields. Training a model is the most important aspect of machine learning for its successful application for the problem. To improve the training of a machine learning model thereby improve the performance, the selection of features and setting optimal parameters is crucial. Mainly two kinds of parameters are required to deal with, namely internal and external parameters. Internal parameters are model parameters and configurable such as weights of neural networks and their estimation can be done using data set. The hyperparameters such as learning rate, size of layers, number of layers, loss function etc, are external parameters and its values cannot be determined using the data set and it is not the part of the model. Its estimation can be done by the domain expert or using some trial-and-error techniques until it achieves some acceptable values. However, these techniques are highly time-consuming and cannot ensure the optimal values for these hyperparameters. In recent years different metaheuristic techniques have been applied to determine the optimal values of hyper parameters for machine learning models. In this paper we have conducted a brief comparative study of a few popular metaheuristic approaches applied for the hyperparameter optimization for various machine learning models. In this paper various evaluation measures have been considered for comparative analysis of metaheuristic approaches for hyperparameter optimization for deep learning model. © 2023 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Disease Prediction through Ensemble Learning Techniques 18

Enhancing Disease Prediction through Ensemble Learning Techn...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Wani, Suhail Rashid Attri, Shree Harsh Setia, Sonia Sharda University School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9789380544519

The study demonstrates how technology has had a dramatic influence on healthcare, allowing for the analysis of large clinical datasets using machine learning for early illness identification. Chronic disorders such as cardiovascular disease (CVD), Chronic renal illness, and Chronic Mellitus Diabetes offer significant global health issues, using existing diagnostic procedures that are time-consuming and error-prone. The report emphasizes the rising burden of chronic illnesses, estimating that 73% of deaths will be related to these ailments by 2025. Recognizing the links between illnesses such as CKD and CVD is critical for optimal care, with a particular emphasis on the increased prevalence and health hazards associated with Chronic Diabetes Mellitus (CDM). The fundamental goal of the research is to create an effective prediction model for early illness diagnosis by employing an adaptable machine learning model that can adapt to a variety of datasets. The review of the literature looks at several machine learning algorithms that have been utilized in prior research, emphasizing their potential for automating illness identification. The methods section describes the procedures required in collecting data, preparing it, and modeling it using ensemble learning. Metrics of performance evaluation confirm the Extra tree classifier's advantage and it performs the best among all the four ensemble techniques and improves the accuracy of predicting diseases. Finally, the above investigation highlights the promise of computational learning in solving the complex issues faced by chronic illnesses, emphasizing the crucial need for accurate early disease prediction in the context of a growing global health crisis. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Cat Boost Chronic Diabetes Mellitus Chronic Disease Computational learning Ensemble Model Feature Selection Heart Disease Random Forest XG Boost

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Muzzle Matching for Cattle Identification Using Deep Learning

Non-Invasive Muzzle Matching for Cattle Identification Using...

引用

2023 Congress in computer science, computer engineering, and Applied Computing, CSCE 2023

作者： Sanjel, Arun Khanal, Bikram Rivas, Pablo Speegle, Greg School of Engineering and Computer Science Baylor University Department of Computer Science United States

ISBN: (纸本)9798350327595

Accurate cattle identification is an essential but complicated issue in the field of livestock management. Traditional identifying methods can involve invasive procedures, posing ethical difficulties and compromising animal welfare. This paper addresses this pressing issue by proposing a deep learning-based methodology for non-invasive cattle identification through muzzle matching. Our approach leverages a comprehensive dataset of 4923 cleaned and cropped muzzle images from 268 distinct cattle breeds. The model showcases exceptional performance with a training accuracy of 98.88 % and a test accuracy of 100 %. Importantly, our methodology avoids invasive procedures and exhibits adaptability, effectively handling introducing new animals into the system. This versatility ensures the model's reliability across diverse operational scenarios, making it a suitable candidate for insurance fraud prevention and animal trading applications. The paper also highlights critical future research directions, including expanding the dataset to encompass a broader range of cattle breeds and muzzle variations and the potential integration with other identification modalities. © 2023 IEEE.

关键词： Adaptability Cattle recognition Deep Learning Muzzle point Non-invasive Techniques

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Scheduling and Optimization in Edge Computing based on Deep Q-Networks 15

Energy-Efficient Scheduling and Optimization in Edge Computi...

引用

15th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2025

作者： Madiyev, Askar Bulegenov, Daulet Karzhaubayev, Anuar Murzabulatov, Meiram Bui, Dinh Mao School of Engineering and Digital Sciences Nazarbayev University Department of Computer Science Astana Kazakhstan

ISBN: (纸本)9798331507695

Mobile Edge Computing (MEC) became a promising paradigm that provides computational and storage capabilities for enhancing user devices that run heavy mobile applications. MEC brings computational resources closer to the network's edge, reducing latency and bandwidth consumption by processing data without transporting computational tasks to distant cloud servers. Reduced latency, guaranteed by MEC because of the geographical proximity, allows improved quality of service (QoS). Although MEC solves the problem of limited computational capabilities of user devices, this computing paradigm requires a strategic approach to manage power consumption, especially in contemporary MEC environments that are characterized by dynamic client workloads on the system, increasing the complexity of the problem. In order to deal with this issue, we proposed a Deep Q-Network (DQN)-based offloading technique to reduce power consumption with such dynamic workloads considerably. This work also highlighted the potential of reinforcement learning in dynamic and heterogeneous MEC environments. © 2025 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing sound pressure output in graphene-based hybrid bone conduction hearing aids through electromagnetic and electrostatic integration

引用

Nano Research 2025年第4期18卷 425-434页

作者： Dong-Kwan Lee Hyunwoo Baek Byung-Ho Kang § Jongchan Yoo Kun-Woo Nam Sang Hyun Lee Illsoo Sohn Eunjung Han June Choi Sung-Hoon Park Department of Mechanical Engineering Soongsil UniversitySeoul 06978Republic of Korea Department of Otorhinolaryngology-Head and Neck Surgery Korea University College of MedicineAnsan HospitalAnsan 15355Republic of Korea School of Electrical Engineering Korea UniversitySeoul 02841Republic of Korea Department of Computer Science and Engineering Seoul National University of Science and TechnologySeoul 01811Republic of Korea

Bone conduction hearing aids(BCHA)actively serve patients with conductive hearing loss or external auditory canal problems,including auditory canal atresia,ossicular dislocation,*** are typically categorized into surgically implanted devices,embedded directly into the skull,and adhesive devices,which transmit sound through the *** latter are advantageous for being noninvasive and suitable for children under ***,adhesive devices,due to their sound transmission method,require enhanced sound output performance compared to implanted ***,known for its low mass density yet excellent mechanical and electrical properties,finds application in various electronic ***,it serves as a diaphragm in electroacoustic transducers,enabling stable vibrations across broad frequency *** electroacoustic transducers of BCHA are typically driven by electromagnetic methods,which may be effective in low-frequency ranges but not in high-frequency *** study successfully introduced a hybrid approach that combines the complementary advantages of both electromagnetic and electrostatic modes by utilizing a graphene sheet as the diaphragm for a hybrid graphene *** electrostatic mode,which performs better in highfrequency ranges compared to the electromagnetic mode,was implemented in this hybrid *** to the measured frequency response data,the hybrid mode showed up to an 11 dB improvement compared to the electromagnetic mode and up to a 21 dB improvement compared to the electrostatic mode,exhibiting a relatively flat shape over a wide frequency ***,the device’s effectiveness as a BCHA is confirmed through experiments on rabbits,showcasing its potential in auditory aid advancement.

关键词： graphene bone conduction hearing aid loudspeaker frequency response

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Classroom Using Convolutional Neural Networks 6th

Anomaly Detection in Classroom Using Convolutional Neural Ne...

引用

6th International Conference on Soft Computing and Signal Processing, ICSCSP 2023

作者： Vidhyasagar, B.S. Doppalapudi, Harshith Chowdary, Sritej Dagumati, VishnuVardhan Charan Kumar Reddy, N. Department of Computer Science and Engineering Amrita School of Computing AmritaVishwaVidyapeetham Chennai India

ISBN: (纸本)9789819984503

Anomaly detection is a task that involves identifying patterns or events that deviate significantly from the expected or normal behavior. In the context of classroom settings, it is essential to identify mischievous behavior exhibited by students to ensure a productive and conducive learning environment. This paper proposes a new method to identify abnormal behavior in a classroom setting using computer vision and deep learning techniques. This method uses convolutional neural networks (CNNs) and recurrent neural networks (RNN) algorithms to detect hand-raising, sleeping, talking, and fighting behaviors in the classroom with live video surveillance. It involves using the You Only Look Once (YOLO) algorithm to locate the position of students in the frame and an RNN algorithm to classify their behavior as normal or anomalous. RNN algorithm is trained on a labeled image and video dataset containing examples of normal and abnormal behaviors. This system can trigger real-time alerts, allowing teachers to act appropriately to maintain a conducive learning environment. It also helps to identify and address disruptive behaviors. Real-time, revolutionizing classroom monitoring: Our algorithm has the potential to improve student safety and well-being, as well as their academic performance. This research could lead to further developments in the field of the classroom. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An intelligent active probing and trace-back scheme for IoT anomaly detection

引用

Digital Communications and Networks 2024年第1期10卷 168-181页

作者： Luying Wang Lingyi Chen Neal N.Xiong Anfeng Liu Tian Wang Mianxiong Dong School of Computer Science and Engineering Central South UniversityChangsha 410083China Department of Computer Science and Mathematics Sul Ross State UniversityAlpineTX 79830USA Artificial Intelligence and Future Networks Beijing Normal University&UICZhuhai 519087China Department of Information and Electronic Engineering Muroran Institute of TechnologyMuroran 050-8585Japan

Due to their simple hardware,sensor nodes in IoT are vulnerable to attack,leading to data routing blockages or malicious tampering,which significantly disrupts secure data *** Intelligent Active Probing and Trace-back Scheme for IoT Anomaly Detection(APTAD)is proposed to collect integrated IoT data by recruiting Mobile Edge Users(MEUs).(a)An intelligent unsupervised learning approach is used to identify anomalous data from the collected data by MEUs and help to identify anomalous nodes.(b)Recruit MEUs to trace back and propose a series of trust calculation methods to determine the trust of nodes.(c)The last,the number of active detection packets and detection paths are designed,so as to accurately identify the trust of nodes in IoT at the minimum cost of the network.A large number of experimental results show that the recruiting cost and average anomaly detection time are reduced by 6.5 times and 34.33%respectively,while the accuracy of trust identification is improved by 20%.

关键词： Anomaly detection Internet of things Integrating data collection Mobile edge users Intelligent

来源：评论

学校读者我要写书评

暂无评论

An Exploration on Big Data Analytical Techniques: A Review 18

An Exploration on Big Data Analytical Techniques: A Review

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Prajapati, Abhinav Gupta, Ayush Mishra, Sanskar Raj, Dharm Singh, Murari Kumar Goyal, Mayank Kumar Sharda School of Engineering and Technology Department of Computer Science and Engineering UP Greater Noida India

ISBN: (纸本)9789380544519

The exponential growth of large, complex, and dynamic datasets, known as big data, required the development of robust analytical techniques beyond conventional tools. This article examines the landscape of big data processing techniques like LSTM, CNN, and more identifying their suitability for different application domains like social media, finance, healthcare, and agriculture. Recognizing the frequent time-sensitive nature of big data analysis, we emphasize the importance of data quality considerations within the processing pipeline. Through a structured analysis of existing literature, we present a comprehensive overview of diverse big data analytical techniques, challenges, technologies, and applications, including statistical methods, machine learning algorithms, and distributed computing frameworks. Our key findings reveal the strengths and limitations of each approach, highlighting the need for hybrid solutions and domain-specific adaptations. Furthermore, we discuss the broader implications of big data processing on knowledge extraction, decision-making, and ethical considerations for responsible data analysis in various fields. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Big Data Big Data Analysis Data mining

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：