检索结果-内蒙古大学图书馆

MobileDNN: Leveraging the Potential of Hybrid MobileNetV2-DNN for Advanced Image Analysis

MobileDNN: Leveraging the Potential of Hybrid MobileNetV2-DN...

2024 International Conference on Science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ogundokun, Roseline Oluwaseun Maskeliunas, Rytis Damasevicius, Robertas Adebiyi, Marion Olubunmi Landmark University Department of Computer Science Omu Aran Nigeria Kaunas University of Technology Department of Multimedia Engineering Lithuania Kaunas University of Technology Faculty of Informatics Kaunas Lithuania

ISBN: (纸本)9798350358155

computer vision systems designed for posture recognition could offer valuable solutions in the healthcare sector, improving healthy ageing and supporting elderly individuals in their daily routines. One area of interest is the automatic detection of falls, which has garnered attention from computer vision and pattern recognition communities. While many existing methods rely on wearable sensors, which demonstrate high accuracy in fall detection, some individuals may be reluctant to wear such devices. Consequently, alternative approaches, such as vision-based techniques, have been developed. The proposed method utilizes a vision-based system that employs a convolutional neural network (CNN) to recognize and categorize various postures (e.g., sitting, lying, standing) in each frame, if available. This approach begins by detecting the person in the frame, applying background subtraction for human body shape extraction, and associating each daily activity with the extracted shape. The proposed model achieved an accuracy of 93.75%, which shows an outstanding performance over existing models. Subsequently, it estimates bounding boxes encompassing the predicted person's body shape. Overall, the proposed technique shows promising results for indoor monitoring systems. © 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

Efficient Method for Detecting Abnormal Growth of Blood Vessels Using Convolutional Neural Network

Efficient Method for Detecting Abnormal Growth of Blood Vess...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent engineering, ICECONF 2023

作者： Kumar, A. Deepak Sasipraba, T. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai600 119 India Department of Computer Science and Engineering St. Joseph s Institute of Technology Chennai600119 India Faculty of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai600119 India

ISBN: (纸本)9798350334357

Diabetic Retinopathy is the main problem in human life because of high sugar levels present in the blood. Various organs get affected due to this reason. The eye is the one of the parts of the human eye which goes to vision problems sometimes blindness. The early stages of detection need to protect the human eye. Existing model uses various methods which do not solve the problem completely. Machine learning based approach introduced for detection of the affected area of eye. The Blood Vessels of the eye get affected as a result bleeding in the eye and excess growth in the eye. Traditional algorithms are not suitable for detecting this growth rate due to the less resolution images. The CNN based model with integrated data sets are used to classify and detect the blood vessel. The high resolution images are used for detecting the location and exact difference in normal vessels. Various algorithms are used with different data sets for making multidimensional analysis. The objective of this method is to identify the heterogeneous vessels from the normal vessel with a high level of accuracy. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Malware from the Network Traffic Using Hybrid and Deep Learning Based Approach

引用

SN computer Science 2024年第1期5卷 162页

作者： Pardhi, Praful R. Rout, Jitendra Kumar Ray, Niranjan Kumar Sahu, Santosh Kumar School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneshwar India Department of Computer Science and Engineering National Institute of Technology Chattisgarh Raipur India Department of Computer Science and Engineering Shri Ramdeobaba College of Engineering and Management Maharashtra Nagpur India GEOPIC Oil Natural Gas Corporation Ltd. Uttarakhand Dehradun India

Mobile connectivity and smart devices are spreading worldwide. As a result, the use of mobile devices and applications is rising exponentially. Therefore, nowadays hackers target such smart devices to steal information and misuse it for malicious purposes. It becomes absolutely essential to protect sensitive information such as app. permissions, login credentials, browse history, media contents etc. from intruders. Security can be breached easily if smart techniques are not devised to safeguard mobile data. In this article, an attempt is made to classify the different types of malware and to protect the sensitive information on Android devices that significantly reduce network congestion and improve network throughput by increasing data transmission. The proposed hybrid approach consists of AdaBoost, random forest and deep learning methods jointly classify the sophisticated malware. The empirical results indicate that this achieves better classification and detection accuracy and is capable of identifying the potential threat more efficiently. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Machine learning Malware classification Mobile computing Network security Threats

来源：评论

学校读者我要写书评

暂无评论

Analysis of Cs2TiBr6 Single-Halide Perovskite Solar Cell by Introducing IDL 24

Analysis of Cs2TiBr6 Single-Halide Perovskite Solar Cell by ...

引用

24th IEEE International Conference on Numerical Simulation of Optoelectronic Devices, NUSOD 2024

作者： Kaur, Jaspinder Gupta, Syamantak Basu, Rikmantra Sharma, Ajay Kumar National Institute of Technology Delhi Department of Electronics and Communication Engineering New Delhi India National Institute of Technology Delhi Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350390537

Lead-based perovskite solar cells (PSCs) are popular in the photovoltaic industry for their remarkable properties, but issues like toxicity and instability limit their use. To address these problems, eco-friendly, lead-free, and stable Cesium Titanium Bromide (Cs2TiBr6) absorber material has been introduced. This work simulates an FTO/SnO2/IDL1/Cs2TiBr6/IDL2/MoOX/Au structure using SCAPS-1D incorporating the use of interfacial defect layer (IDL), examining factors such as layer thickness, doping, defect density, and quantum efficiency. The optimized structure achieves a power conversion efficiency (PCE) of 20.11%, having a fill factor of 82.17, VOC of 1.488 V, and JSC of 16.34 mA/cm2. This research supports the development of efficient, low-toxic, and stable PSCs for the solar industry. © 2024 IEEE.

关键词： Perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Machine Learning and Deep Learning Based Product Recommendation System 5th

A Comprehensive Analysis of Machine Learning and Deep Learni...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Chakravarthi, GKalyan Kumar, Raghvendra Addagarla, Ssvr Kumar Department of Computer Science and Engineering School of Engineering and Technology GIET University Odisha Gunupur India Nadimpalli Satyanarayana Raju Institute of Technology Visakhapatnam India

ISBN: (纸本)9783031770746

Recommender Systems (RS) have been widely applied in various real-time applications to support identifying valuable information. The RS tries to give actual suggestions to every user based on their behavior as well as interests. Recommendations generated by these systems often contend with the unique personal interests of individual users, thereby playing a pivotal role in their decision-making processes. Recommender Systems (RS) act as efficient tools for filtering vast amounts of online data, shaping the behaviors of smartphone users, personalization trends, and the evolution of internet access. RS are generally classified into three primary types: Hybrid Filtering, Content-Based Filtering (CBF), and Collaborative Filtering (CF). These systems find wide application across various fields including online education systems, e-commerce, marketing, tourism, food service, movies, business, and beyond. Although the recent RS are well-known in providing valuable recommendations, they suffer from a number of limitations as well as challenges such as scalability, sparsity, and cold-start and so on. Due to the various approach’s existence, the selection of these approaches becomes challenging during the development of application-based RS. Moreover, every approach comes with its individual feature sets, advantages as well as limitations, which must be addressed. This survey reviews the research inclinations which integrates the progressive technical characteristics of the RS. The aim of this survey is to ensure a systematic review on recent contributions in RS domain, and concentrated on various applications such as education, food, products and so on. This survey provides a comprehensive review of these types of RS, recent literature, and applications of visual RS. © ICST institute for computer Sciences, Social informatics and Telecommunications engineering 2025.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Soil Data Analytics using Machine Learning Techniques - A Survey 3

Soil Data Analytics using Machine Learning Techniques - A Su...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Raghavendra Rao, R.V. Srinivasulu Reddy, U. Mohan Reddy, Ch Ram BMS College of Engineering Department of Computer Applications Bangalore India National Institute of Technology Department of Computer Applications Tiruchirappalli India

ISBN: (纸本)9798350338607

Food security is the most basic need with any individual all over the globe. With food security we can reduce malnutrition in children, who are the backbone of nation's development. To achieve this using machine learning techniques in agriculture domain is the new beginning. Machine learning techniques successfully implemented in innumerable domains, now entered in agriculture. Machine learning techniques establishes a novel way in data processing and data analytics, producing good results with larger data. In this work we carried out survey on machine learning technique's role in agriculture domain and challenges involved in it. We examined the models developed based on agricultural soil. In addition, we analyzed the associations between soil nutrients, which help in crop yield. These results specify that the accuracy of the model is more with ensemble methods. © 2023 IEEE.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Developing an ML Model for Detecting the Cyber Attacks in Electric Vehicles 1

Developing an ML Model for Detecting the Cyber Attacks in El...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Roopesh Albert, Bertia Manuel, Alan Shine Hemram, Saimon Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Karunya Nagar Coimbatore641114 India

ISBN: (纸本)9798350372748

This study shows that electric cars (EVs) are a viable replacement for conventional combustion-engine vehicles, providing lower carbon emissions and more environmentally friendly modes of transportation. Depite the hype, the challenges like cybersecurity flaws and possible cyberattacks are also emerging in EVs. In addition to jeopardizing user privacy and vehicle safety, a number of issues seriously jeopardize the integrity and security of electric cars (EVs). This research offers a unique machine learning (ML)-based detection and prevention system designed to identify cyber threats in electric vehicles (EVs) in response to these problems. The suggested solution examines Controller Area Network (CAN) traffic data using cutting-edge ML algorithms to find unusual patterns suggestive of cyber threats. The solution improves the cybersecurity resilience of electric vehicles (EVs) by including proactive preventive measures and real-time threat detection capabilities. This ensures vehicle safety and guards against new and existing cyber-attacks. Through thorough evaluation and validation procedures, the efficacy of the suggested system is proven, underscoring its strong performance in identifying and averting cyberattacks in electric vehicles. This research helps to create safer and more secure mobility solutions for electric vehicles by implementing proactive cybersecurity measures and integrating cutting-edge ML technology. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Nodule Detection in Computed Tomography Images Using Deep Learning 1

Pulmonary Nodule Detection in Computed Tomography Images Usi...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Longkumer, Akumlong Walling, Supongmen Kalita, Shobhanjana Icfai University Department of Computer Science Dimapur India National Institute of Technology Department of Computer Science and Engineering Dimapur India Tezpur University Department of Computer Science and Engineering Tezpur India

ISBN: (纸本)9798350348057

the well-being of individuals is seriously threatened by lung cancer, which has one of the highest fatality rates of all cancers. Therefore, to increase patient life expectancies, early diagnosis of lung nodules is essential. For many years, the science of machine vision and medical diagnostics has used convolution neural networks. Early diagnosis can significantly lower the patient's mortality, and computer-aided diagnosis has emerged as a vital tool for medical professionals. computer-aided diagnosis depends on the ability to identify pulmonary nodules in computed tomography images. In the Computed Tomography scans, it is difficult to find the lump inside the lungs. This project uses U-Net to implement automated lung nodule identification. Furthermore, the data sets used for pulmonary nodule recognition from CT scan images are from the freely accessible LIDC/IDRI database. © 2023 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Systematic Approach for Securing and Preserving the Privacy of Blockchain Systems 18

Systematic Approach for Securing and Preserving the Privacy ...

引用

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

作者： Rajamanickam, Ramya Chaturvedi, Saumya National Informatics Centre Lodhi Road New Delhi India Sharda University School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9789380544519

Blockchain technology provides a decentralized, irreversible, and verifiable ledger for recording digital asset transactions. This technology has the potential to drastically alter several cutting-edge scenarios. But recently, blockchain has found itself under scrutiny over security and privacy. Multiple heists and hacks have taken place in blockchain systems in this short period of blockchain evolution. Innovative secure privacy blockchain solutions utilizing the crypto-privacy approaches have become the need of the hour to handle privacy issues. The below work discusses ways to bring in state-of-the-art technologies to exculpate the concerns raised on privacy and security uncertainties. Here, the primary emphasis is given to combat the chaos arising in blockchain privacy and security thus contributing to the users and developers of blockchain. We categorically explain that blockchain alone is not sufficient in the current era of heists and attacks, giving the recommendation of the framework in the coming sections, thereby placing the techniques for privacy-preserving blockchain tightly bound to the system. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Blockchain Blockchain Security Privacy Privacy-Preserving

来源：评论

学校读者我要写书评

暂无评论

Test-Driven Development (TDD) in Small Software Development Teams: Advantages and Challenges 5

Test-Driven Development (TDD) in Small Software Development ...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Ramzan, Hafiz Arslan Ramzan, Sadia Kalsum, Tehmina Institute of Computer and Software Engineering Khwaja Fareed University of Engineering and Information Technology Rahim Yar Khan Pakistan National University of Modern Languages Department of Computer Science Multan Pakistan University of Engineering and Technology Department of Software Engineering Taxila Pakistan

ISBN: (纸本)9798350394764

In the context of small software development teams, this research article gives a thorough investigation of the adoption of test-driven development (TDD) approaches. It aims to highlight the benefits that TDD offers, such as improved code quality through modularization and proactive defect spotting which results in effective debugging and development processes. It also discusses the complex issues that arise when TDD is implemented in smaller teams, such as the learning curve and resource constraints. This study significantly advances the understanding of how TDD can be used to optimize software development techniques in organizations or software houses having small development teams. It also explores the possible advantages and challenges. © 2024 IEEE.

关键词： Modular construction

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：