检索结果-内蒙古大学图书馆

Enhanced SMOTE Strategy for Handling Imbalanced Data in Machine Learning Classification

Enhanced SMOTE Strategy for Handling Imbalanced Data in Mach...

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： Shivam Tiwari Satvik Vats Barkha Bhardwaj Pramod Vishwakarma Yogesh Singh Rathore Department of Computer Science & Engineering Sharda University Greater Noida Computer Science & Engineering Graphic Era Hill University Dehradun India Department of Computer Science and Engineering NIET Greater Noida Computer Science & Engineering (AIT) Chandigarh University Gharuan Mohali Punjab India Computer Science and Application Sharda University Greater Noida

Most real-time datasets have class instances scattered across the data in a non-uniform fashion. Certain classes have an abnormally high number of instances when compared to the rest of the classes. The term "class imbalance problem" is used to describe this occurrence (CIP). Due to its inaccuracy in projecting weak class data samples, this skewed information impacts the reliability of forecasts as a whole. Many businesses make use of CIP's data mining experts who employ CIP. Both ML and deep learning have substantial difficulties with the classification of skewed data (DL). Several researchers are curious in how to overcome the major hurdle presented by the widespread adoption of sample techniques to improve classifier performance. In this research, we provide a survey of state-of-the-art approaches currently being used in studies of data classification, and we contrast and compare the numerous algorithms used at each stage of the process. Talk about the challenges and limitations that come up in investigations of imbalanced data classification. Taken as a whole, this work not only provides an in-depth analysis of the uneven data categorization industry but also inspires more study in this space.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Sybil Attack Detection Approach for Vehicular Ad-Hoc Networks 7

An Efficient Sybil Attack Detection Approach for Vehicular A...

引用

7th International Conference on Parallel, Distributed and Grid Computing, PDGC 2022

作者： Lohar, Durgesh Panda, Sanjaya Kumar Padhi, Slokashree Nayak, Sanjib Kumar National Institute of Technology Warangal Department of Computer Science and Engineering Telangana Warangal5060004 India Veer Surendra Sai University of Technology Burla Department of Computer Application Odisha Burla768018 India

ISBN: (纸本)9781665454018

Vehicular ad-hoc networks (VANETs) play a vital role in next-generation wireless communication. It consists of a set of moving vehicles, stationary vehicles, and roadside units (RSUs) that are connected through a wireless network. However, security and privacy issues are always challenging in VANETs as they lead to attacks. One such attack is the detection of the Sybil attack. This attack makes use of a vehicle or node to create multiple fake identities, at a time, to take advantage of a particular network. This attack leads to traffic congestion, rerouting, and accident. Many researchers have proposed solutions to identify the Sybil attack. Recently, Ayaida et al. [1] have presented an approach to detect the Sybil attack based on a macroscopic traffic flow model. This approach calculates the estimated speed and real speed, and their difference. If the difference is more than a predetermined threshold, then it suspects an attack and sends a message to nearby vehicles. This paper modifies their approach to provide a better solution by estimating the speed of vehicles and by RSU, thereby averaging their speed. The proposed approach is simulated using network simulator (ns) 3 and simulation of urban mobility (SUMO) to show its effectiveness. © 2022 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Study Of Various Scraping Tools: Pros And Cons

Comparative Study Of Various Scraping Tools: Pros And Cons

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Matta, Priya Sharma, Sonal Uniyal, Nitin Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Uttaranchal University Department of Computer Application Dehradun India University of Petroleum and Energy Studies Department of Mathematics Dehradun India

ISBN: (纸本)9781665458832

As technology keeps on improving and data is still considered the topmost priority, people need to know how they can make the use of old data available, and impact their worlds. The data these days may be raw data, refined data, structured or even the unstructured data. These data finally result into a huge amount of data with varying volume and velocity, generating the concept of Bigdata. Data Extraction has shifted the way we view the world and as it is so necessary, we need to know certain tools available for this service. Web scraping has become so important for businesses to grow, scientific research, or even to get the knowledge of the most read article on the internet. In this paper, we cover the most powerful known web scraping tools available to date and study them. We have compared these tools and clarified their benefits as well as drawbacks concerning various applications. © 2022 IEEE.

关键词： Technology transfer

来源：评论

学校读者我要写书评

暂无评论

Fringing Effects in a Capacitive Micromachined Ultrasonic Transducer with a SiC Actuation Layer Insulated by High Dielectric Material 3

Fringing Effects in a Capacitive Micromachined Ultrasonic Tr...

引用

3rd IEEE International Conference of Electron Devices Society Kolkata Chapter, EDKCON 2024

作者： Ahamed, Sk. Sohel Pal, Moumita Chakraborty, Pritam Neogi, Biswarup Maity, Niladri Das, Reshmi Future Institute of Engineering and Management Dept. of electronics and communication kolkata India JIS College of Engineering Dept. of electronics and communication Kalyani India Institute of Engineering and Management Dept. of computer science and application Kolkata India NITTTR Dept. of technical education Kolkata India Mizoram University Dept. of electronics and communication Mizoram India

ISBN: (纸本)9798350374643

Sealed capacitive micromachined ultrasonic transducer (CMUT) mostly consists of two parallel electrodes separated by a structural layer of silicon nitride (Si3N4) and a vacuum cavity. Biasing the transducer element generates electrostatic force of attraction where the lines in the field bulge at the boundaries of the layers contributing to fringing effects. These fringing capacitances result in overall increment of the device capacitance. To capture this effect a very simple model of Landau and Lifschitz is incorporated, where the analytical model outputs are well matched with commercially available PZFlex FEM simulated results. Because silicon carbide (SiC) has a higher Young's modulus and lower residual stress than Si3N4, it is used as a structural material in the CMUT. The improvement in device capacitance is approximately 13.1% through adjustments in the thickness of gaps and insulation. However, factoring in the relative dielectric constant and the electrode radius, this improvement reduces to around 7.9%. Additionally, introducing a high-k insulating layer enables the upper electrode to be structured on the lower face of the SiC layer. This modification leads to an augmentation in the device's total capacitance. This article also examines HfO2 materials of varied thicknesses. © 2024 IEEE.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Leveraging Grey Wolf Optimizer for Reliable Data Transmission in Underwater Wireless Sensor Networks

Leveraging Grey Wolf Optimizer for Reliable Data Transmissio...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Umamahesh, G. Senthurya, S. Khatarkar, Poonam Alsalami, Zaid Kaur, Jaspal Ramesh, P.S. Aditya Engineering College Department of Computer Science & Engineering India Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Ies College of Technology Department of Electrical & Electronics Engineering M.P. Bhopal India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq The Islamic University Of Al Diwaniyah College Of Technical Engineering Department Of Computers Techniques Engineering Al Diwaniyah Iraq Chandigarh Group of Colleges Chandigarh Engineering College Department of Computer Application Punjab Jhanjeri Mohali140307 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Cse Chennai India

ISBN: (纸本)9798350390759

This research investigates the application of the Grey Wolf Optimizer (GWO) to enhance reliable data transmission in Underwater Wireless Sensor Networks (UWSNs). UWSNs are critical for various applications, including environmental monitoring and underwater exploration, but face challenges such as high propagation delays, limited bandwidth, and energy constraints. The GWO algorithm, inspired by the social hierarchy and hunting behavior of grey wolves, is employed to optimize routing paths, minimize energy consumption, and improve packet delivery ratio. The methodology includes simulating UWSNs with different network configurations using synthetic and real-world datasets, and implementing the GWO algorithm in Python within the NS-3 simulation framework. Comparative analysis with traditional routing protocols, AODV and DSR, demonstrates that the GWO-based routing algorithm significantly reduces energy consumption, increases packet delivery ratio, lowers latency, and extends network lifetime. These results underscore the effectiveness of GWO in enhancing UWSN performance. The study concludes that GWO offers a robust and adaptable solution for reliable data transmission in UWSNs, with potential for further enhancements through hybrid optimization techniques and real-world validations. This research provides a comprehensive understanding of GWO's application in UWSNs, contributing to advancements in underwater communication technologies. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Development of China's spaceborne SAR satellite,processing strategy,and application:take Gaofen-3 series as an example

引用

地球空间信息科学学报（英文版） 2024年第1期27卷 221-236页

作者： Guo Zhang Shunyao Wang Zhenwei Chen Yuzhi Zheng Ruishan Zhao Taoyang Wang Yu Zhu Xinzhe Yuan Wei Wu Weitao Chen State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina School of Law Wuhan UniversityWuhanChina School of Geomatics Liaoning Technical UniversityFuxinChina School of Remote Sensing and Information Engineering Wuhan UniversityWuhanChina Institute of Spacecraft System Engineering China Academy of Space TechnologyBeijingChina National Disaster Reduction Center of China Ministry of Emergency ManagementBeijingChina School of Computer Science China University of GeosciencesWuhanChina Key Laboratory of Space Ocean Remote Sensing and Application Ministry of Natural Resources of the People's Republic of ChinaBeijingChina

After mastering the key technologies of manufacturing spaceborne Synthetic Aperture Radar(SAR),China's SAR satellites have been successfully launched into *** the only civil microwave satellite listed in the"National High-resolution Earth Observation System Major Project,"the Gaofen-3(GF-3)01 satellite is the first C-band multi-polarization SAR satellite with a resolution of 1 ***-3 series satellites stand out among civil SAR satellites worldwide because of their high resolution,wide swath,high geometric radiation quality,multiple imaging modes,and long operation *** GF-3 series satellites as an example,this study introduces the development of China's civil SAR satellites,as well as their processing strategies and *** success of the GF-3 series satellites shows that China's SAR remote sensing technology has stepped into a new era of high-quality and high-precision Earth observations.

关键词： High-resolution Synthetic Aperture Radar(SAR) GaoFen-3(GF-3)satellites earth observation

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Model to Indicate Heart Health Status Using Phonocardiogram

引用

computers, Materials & Continua 2021年第12期69卷 4151-4168页

作者： Vinay Arora Karun Verma Rohan Singh Leekha Kyungroul Lee Chang Choi Takshi Gupta Kashish Bhatia Department of Computer Science and Engineering Thapar Institute of Engineering and TechnologyPatialaPunjabIndia Associate Application ITConcentrixGurugramHaryanaIndia School of Computer Software Daegu Catholic UniversityGyeongsanKorea Department of Computer Engineering Gachon UniversitySeongnam13120Korea Information Security Engineering Soonchunhyang UniversityKorea Department of Computer Engineering University College of EngineeringPunjabi UniversityPatialaPunjabIndia

The early diagnosis of pre-existing coronary disorders helps to control complications such as pulmonary hypertension,irregular cardiac functioning,and heart ***-based learning of heart sound is an efficient technology which can help minimize the workload of manual auscultation by automatically identifying irregular cardiac ***(PCG)and electrocardiogram(ECG)waveforms provide the much-needed information for the diagnosis of these *** this work,the researchers have converted the heart sound signal into its corresponding repeating pattern-based *** 2016 and PASCAL 2011 have been taken as the benchmark datasets to perform *** existing models,***,Xception,Visual Geometry Group(VGG16),ResNet,DenseNet,and InceptionV3 of Transfer Learning have been used for classifying the heart sound signals as normal and *** PhysioNet 2016,DenseNet has outperformed its peer models with an accuracy of 89.04 percent,whereas for PASCAL 2011,VGG has outperformed its peer approaches with an accuracy of 92.96 percent.

关键词： PCG signals transfer learning repeating pattern-based spectrogram biomedical signals internet of things(IoT)

来源：评论

学校读者我要写书评

暂无评论

Real-time Glass Recycling Quality Assurance and Contamination Reduction with IoT and Random Forest algorithm 7

Real-time Glass Recycling Quality Assurance and Contaminatio...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Balasubadra, K. Shadaksharappa, B. Seeni, Senthil Kumar Sridevi, V. Thamizhamuthu, R. Srinivasan, C. R.M.D. Engineering College Department of Information Technology Chennai Tamil Nadu Kavaraipettai India Sri Sairam College of Engineering Department of Computer Science And Engineering Bengaluru Karnataka Anekal India Cognizant Technology Solutions Department of Mobile Application Development Buffalo GroveIL United States Academy of Maritime Education And Training Deemed To Be University Electrical And Electronics Engineering Tamil Nadu Chennai India Srm Institute of Science And Technology Department of Computing Technologies Kattankulathur Campus Chennai Tamil Nadu Chengalpattu India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences Department of Computer Science And Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350359299

The recycling industry is crucial to environmental protection and resource conservation. Glass recycling has great sustainability potential, but quality assurance and contaminant reduction are major challenges. Integrating the Internet of Things (IoT) with the Random Forest algorithm, this work offers a new solution to these difficulties. IoT devices are used in glass recycling collection, transportation, sorting, and processing. These devices measure glass quality, contaminants, temperature, humidity, and other parameters in real-time. Data is sent to a central system for analysis and decision-making. Random Forest, a machine learning method that handles complicated, multidimensional datasets, powers the system. This algorithm learns from past data and updates with real-time data. It detects contaminants, foreign elements, and faults in recycled glass. This permits fast remedial action, enhancing recycled glass quality and decreasing contamination. application of this mechanism yields two outputs. First, it improves glass recycling efficiency and produces high-quality glass for remanufacturing. Second, it significantly minimizes the environmental and economic implications of contamination and low-quality glass, which may limit recycling yields and increase waste disposal. In comparison to traditional approaches, the proposed approach that utilizes the IoT and the Random Forest algorithm reduces contamination and ensures the quality of glass recycling by 30%. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5690-5704页

作者： Hou, Sizai Li, Songze Jahani-Nezhad, Tayyebeh Caire, Giuseppe Hong Kong University of Science and Technology Hong Kong Southeast University School of Cyber Science and Engineering Nanjing China Supervision and Management (Southeast University) Ministry of Education Engineering Research Center of Blockchain Application China Technische Universität Berlin Department of Electrical Engineering and Computer Science Berlin 10587 Germany

Federated learning (FL), as a promising machine learning paradigm for large-scale distributed data, faces two security challenges of privacy and robustness: the transmitted model updates potentially leak sensitive user information, and the lack of central control over local model updates leaves the global model susceptible to malicious attacks. Current solutions attempting to address both problems under the one-server FL setting fall short in the following aspects: 1) design for simple validity checks that are insufficient against advanced attacks (e.g., checking norm of individual update);and 2) have partial privacy leakage for more complicated robust aggregation algorithms (e.g., distances between model updates are leaked for multi-Krum). In this work, we formalize a novel security notion of aggregated privacy that characterizes the minimum amount of user information, in the form of aggregated statistics of users’ updates, that is necessary to be revealed to accomplish more advanced robust aggregation. We develop a general framework PriRoAgg, utilizing Lagrange coded computing and distributed zero-knowledge proof, to execute a wide range of robust aggregation algorithms while satisfying aggregated privacy. As concrete instantiations of PriRoAgg, we construct two secure and robust protocols based on state-of-the-art robust algorithms, for which we provide full theoretical analyses on security and complexity. Extensive experiments are conducted for these protocols, demonstrating their robustness against various model integrity attacks, and their efficiency advantages over baselines. © 2005-2012 IEEE.

关键词： Byzantine Resilience Federated Learning Privacy Preservation Secure and Robust Aggregation

来源：评论

学校读者我要写书评

暂无评论

A Survey of Dynamic Exploration Symmetric Encryption with Backward & Forward Secrecy

A Survey of Dynamic Exploration Symmetric Encryption with Ba...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Satendra Singh Samriti Bhagat Department of Computer Science Engineering Vivekananda Global University Jaipur India Department of Master of Computer Application Chandigarh School of Business

A sophisticated type of symmetric encryption is called Multiuser Dynamic Searchable Symmetric Encryption. It expands the capabilities of conventional symmetric encryption to enable actions such as adding and removing encrypted data as well as the ability for a verified set of information users to access their preferred encrypted data within the dynamic database. The latter can use using erased data and search results to comprehend the content, while the former allows attackers to discover by performing file injection attacks, keywords from the injected data were exposed. can do. To our knowledge, the available literature has not completely addressed these privacy problems for M-DSSE. In light of this, our attention is directed toward multiuser dynamic searchable symmetric encryption that satisfies the requirements for forwarding and backward security. It uses Inverted indexes are created and updated using random number generator Functions (RNG) and Authenticator primitives search tokens to suggest specific solutions. In the accidental model, the suggested approach is shown to be secure. Additionally, the performance study demonstrates that the suggested approach provides increased security assurances at a fair cost to efficiency.

关键词：

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：