检索结果-内蒙古大学图书馆

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Parashar, Jyoti Upreti, Kamal Fatima, Iram Gangwar, Divya Saini, Ashok Kumar Vats, Prashant Department of Computer Science & Engineering Dr. Akhilesh Das Gupta Institute of Technology & Management New Delhi India Department of Computer Science Christ University Delhi NCR Campus Ghaziabad India Department of AI & ML Dr. Akhilesh Das Gupta Institute of Technology & Management New Delhi India Department of Management Babu Banarasi Das Institute of Technology & Management New Delhi India Department of Computer Science & Engineering School of Computer Science & Engineering Manipal University Jaipur Rajasthan Jaipur India

ISBN: (纸本)9789819751990

Models based on machine learning are optimization models that collect data, assess it, and deliver the reports required by specialists and management to make the best decisions. The application of contemporary machine learning allows the organization to quickly analyze photographs, differentiate voices assist in providing customer service, assess the information that is at hand, and uncover connections to aid in decision-making processes. The results of this investigation use quantitative methodologies to collect data and analyze it using mathematical procedures such as regression modeling as well as analysis of variance. Deep learning techniques applied to digital imaging, particularly in medical treatment, can increase picture quality, aid in modeling, aid in making the best possible diagnosis, and successfully address demands from patients. To analyze the hypothesis, investigators intend to utilize statistical approaches such as descriptive data analysis, regression evaluation, and analysis of variance (ANOVA). The authors employ the purposive sample approach to choose respondents from the healthcare industry. Purpose sampling is a non-probability sampling approach. Researchers collected data from 193 respondents working at hospitals that are privately owned in Southern Asia. As stated by the study, all factors, including efficiently meeting patient needs, have a probability value of under 0.05, indicating that they are statistically noteworthy. Following the study, the coefficient of variance (R squared) is 0.744, or 74.4%. According to the study, there is a high association between better image quality and ML-based digital picture identification systems. The recognition of patterns and the application of artificial intelligence to computerized recognition of pictures also have a close link. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Leveraging Biomedical Ontologies to Boost Performance of BERT-Based Models for Answering Medical MCQs 14

Leveraging Biomedical Ontologies to Boost Performance of BER...

引用

14th International Conference on Biomedical Ontologies, ICBO 2023

作者： Sahil Kumar, P. Sreenivasa Department of Computer Science & Engineering Indian Institute of Technology Madras Chennai India

Large-scale pretrained language models like BERT have shown promising results in various natural language processing tasks. However, these models do not benefit from the rich knowledge available in domain ontologies. In this work, we propose BioOntoBERT, a BERT-based model pretrained on multiple biomedical ontologies. We also introduce the Onto2Sen system to process various ontologies to generate lexical documents, such as entity names, synonyms and definitions, and concept relationship documents. We then incorporate these knowledge-rich documents during pretraining to enhance the model’s "understanding" of the biomedical concepts. We evaluate our model on the MedMCQA dataset, a multiple-choice question-answering benchmark for the medical domain. Our experiments show that BioOntoBERT outperforms the baseline model BERT, SciBERT, BioBERT and PubMedBERT. BioOntoBERT achieves this performance improvement by incorporating only 158MB of ontology-generated data on top of the BERT model during pretraining, just 0.75% of data used in pretraining PubMedBERT. Our results demonstrate the effectiveness of incorporating biomedical ontologies in pretraining language models for the medical domain. © 2023 Copyright for this paper by its authors.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

DCT based robust coverless information hiding scheme with high capacity 7

DCT based robust coverless information hiding scheme with hi...

引用

7th International Conference on Trends in Electronics and informatics, ICOEI 2023

作者： Kulkarni, Tejas Debnath, Sourabh Kumar, Jitendra Mohapatra, Ramesh Kumar National Institute of Technology Department of Computer Science and Engineering Odisha Rourkela India

ISBN: (纸本)9798350397284

For a considerable time, individuals have been searching for the most effective way to secretly transmit information, making it challenging for anyone without authorization to decode it. Steganography is a method that conceals confidential information from unauthorized users. The message is encrypted, allowing only the intended recipient to access the message. In the case of image steganography, the message is hidden within a cover image. One technique involves modifying the image, so the receiver can still decode the information, even though it is not visible to the human eye. However, statistical analysis can uncover concealed information, even if it is not noticeable. To counter this issue, researchers developed a technique called Coverless Information Steganography, which sends the recipient an image that already contains a hidden message, thus reducing the possibility of steganalysis. A novel technique based on the direct current (DC) coefficient of the cover image is discussed here, where a hash sequence is created by computing the DC coefficient of each 8×8 sub-block and then XORed with a secret message to form a bit sequence. The capacity and robustness of the method are evaluated to determine its efficiency compared to other implementation strategies. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Data-Filtered Prediction with Decomposition and Amplitude-Aware Permutation Entropy for Workload and Resource Utilization in Cloud Data Centers

引用

IEEE Internet of Things Journal 2025年第12期12卷 19189-19201页

作者： Yuan, Haitao Hu, Qinglong Wang, Meijia Wang, Shen Bi, Jing Buyya, Rajkumar Shi, Shuyuan Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Hong Kong999077 Hong Kong Beijing University of Technology School of Software Engineering The Faculty of Information Technology Beijing100124 China Lab School of Computing and Information Systems MelbourneVIC3010 Australia Beihang University School of Integrated Circuit Science and Engineering Beijing China CSSC Systems Engineering Research Institute Beijing China Southern Methodist University Department of Computer Science The Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

In recent years, cloud computing has witnessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and interdependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVAPI for achieving high-accuracy workload prediction in cloud computing systems. SVAPI employs the Savitzky-Golay filter, Variational mode decomposition, and the mode selection based on Amplitude-aware Permutation entropy for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVAPI improves the prediction accuracy by 37.7% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVAPI enhances the prediction accuracy of workload, CPU, and memory by 65.6%, 66.9%, and 70.8%, respectively, demonstrating that SVAPI owns strong abilities in noise filtering, feature processing, and multivariate joint analysis for achieving higher prediction accuracy. © 2014 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Face Recognition-Based Door Locking System with OTP Verification 6th

Face Recognition-Based Door Locking System with OTP Verifica...

引用

6th International Conference on Smart Computing and informatics, SCI 2024

作者： Rajavel, M. Santhosh Kumaar, R. Suvedha, D. Dharani, S. Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Chennai India

ISBN: (纸本)9789819619801

In the world of the digital era, AI has had a major influence. With the advancement of technology, people can experience extraordinary innovations that not only make life more comfortable, but also make it simpler. As a part of AI, we have created a door locking mechanism that uses face recognition with OTP verification using OpenCV. At the stage of identification of faces, Histogram of oriented Gradients algorithm [HOG] is used for finding the face at the backend. This project is developed using both hardware and software. With the help of smart doorbells, homeowners can get notifications when a visitor is at the door and identify the visitor. They significantly raise people’s quality of life and advance the development of smart homes. The purpose of this project is to make the home or office area secure and can also be used to minimize criminality. Only one form of authentication is offered by the existing systems, which makes them less secure. Thus, for secure access, we have proposed a safe door locking system with two factor authentication that can authenticate and validate the user as well as open the door in real time. We have come up with an idea which should recognize the guest, relatives or a stranger and alert the user. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Data Quality Driven Design Patterns for Internet of Things 9th

Data Quality Driven Design Patterns for Internet of Things

引用

9th International Symposium on Applied Computing for Software and Smart systems, ACSS 2022

作者： Rath, Chouhan Kumar Mandal, Amit Kr Sarkar, Anirban Department of Computer Science and Engineering National Institute of Technology Durgapur Durgapur India Department of Computer Science and Engineering SRM University AP Amaravati India

ISBN: (纸本)9789811967900

Many IoT applications are now using microservices design concepts and have developed as an emergent technology by leveraging containerization, modularity, autonomous deployment and loose coupling. The requirement of different software design patterns is essential to aid in the creation of scalable, interoperable and reusable solutions. In IoT systems and software development, several IoT patterns, such as IoT design patterns and IoT architectural patterns, have been studied. But, most of the studied design patterns are domain-specific, and they do not consider the impact of data quality in the design process. Also, in IoT environment data quality plays an important role while processing the data to produce accurate and timely decisions. Therefore, this paper presents a formal approach to incorporate the data quality dimensions in design patterns for the microservice based IoT applications. Here, data quality evaluation parameters are integrated with various microservice design patterns suitable to IoT applications such as event sourcing pattern, chained microservice pattern, API gateway pattern etc. to ensure the effective data communication and high-quality services provided by the IoT applications. Further, the proposed quality driven design patterns are systematically defined using Event-B language and validated through Rodin platform. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Enhancing Environmental Sounds Classification through Deep Learning Techniques 2

Enhancing Environmental Sounds Classification through Deep L...

引用

2nd International Conference on Sustainable Computing and Data Communication Systems, ICSCDS 2023

作者： Dasari, Siva Krishna Kella, Sarath Kumar Manda, Raghava Gmr Institute of Technology Department of Computer Science & Engineering Vizianagaram Rajam India

ISBN: (纸本)9781665491990

Environmental sound classification has become an important application for the research process in recent years, as it has many applications in several fields such as urban noise management, wildlife monitoring, and intelligent sound system. Sound classification involves mainly classifying the different sounds and predicting the class of that sound by using deep learning techniques. These techniques have proven to be very effective in many sound analysis and classification areas. This study uses neural networks to learn high-level features from audio clips, then build some layers, and finally make a fully connected layer to know the final classification. Generally, Mel-Frequency Cepstral Coefficients (MFCCs) have been taken as a feature representation for audio signals. These features can be generated from the spectrograms, which are inputs to the organized model. The model can be built using networks like artificial neural networks and convolution neural networks. The architecture of the neural network is designed to effectively capture similar features of environmental sounds by reducing the competition of complexity. To implement the sound classification, a UrbanSoundDataset8k is used to predict the individual classes. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A False Data Injection Attack on Data-Driven Strategies in Smart Grid Using GAN 36th

A False Data Injection Attack on Data-Driven Strategies in...

引用

36th International Conference on Industrial, engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2023

作者： Dash, Smruti P. Khandeparkar, Kedar V. Department of Computer Science and Engineering Indian Institute of Technology Dharwad Dharwad India

ISBN: (纸本)9783031368219

The smart grid is a critical cyber-physical infrastructure;attackers may exploit vulnerabilities to launch cyber attacks. The smart grid control system relies heavily on the communication infrastructure among sensors, actuators, and control systems, making it vulnerable to cyber-attacks. We propose a method for injecting a false data injection attack (FDIA) into the smart grid using generative adversarial networks (GAN). A sample of disturbance vectors generated using deep temporal convolutional GAN (DTCGAN) is superimposed on the original phasor measurement unit (PMU) measurements to generate compromised data. The performance results show a significant impact of the developed attack on data-driven methods for grid monitoring. Specifically, we demonstrated the attack on a transient stability application. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

An Efficient Diabetes Prediction Model using Machine Learning 4

An Efficient Diabetes Prediction Model using Machine Learnin...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Daniel, Esther Johnson, Jobin Victor, Ujjal Amitya Aditya, G.V. Sibby, Steve Abraham Karunya Institute of Technology & Sciences Department of Computer Science & Engineering Coimbatore India

ISBN: (纸本)9798350300093

Diseases are the ones that affect the continual life of human beings. One such illness which affects millions of people worldwide is diabetes. By examining huge datasets of patients, machine learning models offer a viable answer to the problems associated with diabetes detection. The proper management of diabetes depends on early identification This article aims to assess the effectiveness of diverse machine learning methodologies and strategies utilized for forecasting diabetes, utilizing the PIMA Indian Diabetes dataset as a reference. The dataset contains information about crucial factors such as the patient's age, BMI, blood pressure, and blood sugar levels, which are utilized for the analysis. The models which were taken into account in this research were compared to one another and then LightGBM was chosen as the primary model on the basis of its high accuracy. The Hyper parameters were then modified to produce the best performance possible. The results show that machine learning models can accurately detect diabetes and provide insights into the factors that contribute to the disease. This work provides a foundation for future research on diabetes prediction using machine learning models. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Automated Interview through Online Video Interface

Automated Interview through Online Video Interface

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Joshila Grace, L.K. Asha, P. Shabu, Jany Refonaa, J. Selvan, Mercy Paul Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350333244

Automated Video Interview Interface is a streamlined approach to job interviews that uses AI and video conferencing. This system can evaluate candidates and make hiring decisions by utilizing natural language processing, facial recognition, and machine learning algorithms, dispensing with the need for physical interviews while enhancing the recruitment process efficiency and decision quality. This technology allows organizations to conduct video interviews with candidates remotely, using pre-recorded or live questions, and also provides the added ability to evaluate and score the candidate's responses. Additionally, it offers the added benefit of personalized feedback for candidates and detailed performance reports for employers. In today's fast-paced recruitment environment, managing effective human interaction, recognizing candidates' facial expressions and body language, and resolving technical issues such as network connectivity, camera and microphone access can be challenging. However, this innovative application offers a solution by providing an efficient interface for accurate candidate assessment and valuable insights. The system not only facilitates the creation, analysing, and evaluating a large number of candidates, but also generates performance reports and personalized feedback based on their performance. This research paper provides an overview of the concept, benefits, and limitations of AVII, and discusses the potential impact of this technology on the recruitment process. It delves into the numerous advantages of implementing an Automated Video Interview Interface, as well as addressing potential challenges and the future impact of this technology on the job market. By utilizing this application, candidates can perform in a secure and private environment with efficient responses of candidate's performance. © 2023 IEEE.

关键词： Video conferencing

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：