检索结果-内蒙古大学图书馆

Applied Intelligence and Sustainable Computing (ICAISC), International Conference on

作者： Annaiah Halappa A. Rajesh Dept. of Computer Science & Engineering Government Engineering College Hassan India Dept. of Computer Science & Engineering Jain Technological University Bengaluru India

The advancement of Information Technology has made cloud computing technology an innovative model for offering its consumers services on a rental basis at any time or location. Numerous firms converted to cloud technology by establishing new data centers because of the flexibility of cloud services. However, it has become necessary to ensure successful job execution and effective resource usage. Load balancing (LB) in cloud computing remains a complex challenge, specifically in the Infrastructure as a Service (IaaS) cloud architecture. A server being overloaded or underloaded is a problem that mustn’t happen in the process of cloud access because it would slow down processing or causes a system crash. Hence, to ignore these problems, a suitable resource schedule must be taken, so that system can load balance tasks over all accessible assists. This research suggests effective load-balancing approaches by analyzing the advantages, applications, and disadvantages of conventional LB techniques. The conclusions show that this research provides an exceptional path for researchers to overcome major drawbacks of existing LB techniques and achieves greater efficiency based on makespan, execution and response time, resource usage, efficiency, load balancing and throughput.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unified Face Matching and Physical-Digital Spoofing Attack Detection

arXiv

引用

arXiv 2025年

作者： Kunwar, Arun Rattani, Ajita Dept. of Computer Science and Engineering University of North Texas Denton United States

Face recognition technology has dramatically transformed the landscape of security, surveillance, and authentication systems, offering a user-friendly and non-invasive biometric solution. However, despite its significant advantages, face recognition systems face increasing threats from physical and digital spoofing attacks. Current research typically treats face recognition and attack detection as distinct classification challenges. This approach necessitates the implementation of separate models for each task, leading to considerable computational complexity, particularly on devices with limited resources. Such inefficiencies can stifle scalability and hinder performance. In response to these challenges, this paper introduces an innovative unified model designed for face recognition and detection of physical and digital attacks. By leveraging the advanced Swin Transformer backbone and incorporating HiLo attention in a convolutional neural network framework, we address unified face recognition and spoof attack detection more effectively. Moreover, we introduce augmentation techniques that replicate the traits of physical and digital spoofing cues, significantly enhancing our model robustness. Through comprehensive experimental evaluation across various datasets, we showcase the effectiveness of our model in unified face recognition and spoof detection. Additionally, we confirm its resilience against unseen physical and digital spoofing attacks, underscoring its potential for real-world applications. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Bridge-Less AC-DC Stacked-Switches Structured Bi-Directional On-Board High Voltage EV Charger with Minimal Storage Capacitances

A New Bridge-Less AC-DC Stacked-Switches Structured Bi-Direc...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Siamak Derakhshan John Lam Dept. Electrical Engineering and Computer Science York University Toronto Canada

This paper presents a new single-stage isolated bidirectional stacked switches-based CLLC resonant converter with reduced storage capacitances for High Voltage (HV) Electric Vehicle (EV) systems. In the proposed converter, two closed-loop ripple reduction control units implemented on both rectifier and inverter modes of the converter to minimize the output and DC-link voltage ripples without any additional circuit design. As a result, the bulky unreliable electrolytic-type DC-link and output filter capacitors are replaced with significantly smaller and more reliable ceramic capacitors. Moreover, a closed-loop duty ratio controller guarantees a high-quality sinusoidal input current in the rectifier mode, while output voltage regulation is realized using Variable Frequency Modulation (VFM) technique. In inverter mode, a Second Order Generalized Integrator (SOGI) Phase Lock Loop (PLL) along with a fixed-band Hysteresis Current Controller (HCC) is implemented for power transfer from the EV to the grid, making the converter robust against frequency disturbances. The converter’s performance is verified through a 1kW, 120Vrms/800Vdc design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based E-Voting System Hosted on Cloud

Blockchain Based E-Voting System Hosted on Cloud

引用

Disruptive Technologies (ICDT), International Conference on

作者： Prajwal Prakash Dalvi Jayant Mehare Amol Zade Amit Gaikwad dept. of Computer Science & Engineering G H Raisoni University Amravati India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Blockchain technology is becoming a great innovation at today's date due to its transparency, security and reliability. With the advancement in every aspect of life blockchain with its decentralized and distributed ledger system aims to provide immutability in digital transaction across the globe with the help of block structure joined together that stored the data in the form of hash. The data stored in block is next to immutable as if tried to change in a single block the hash of every block in the chain will change which makes it easy to identify. Due to its security and transparency the study describes its use in the e-voting system revolutionizing voting system with more security and transparency reducing logistic problem, solving storage issues, solves the problem of using extra man power in the large democracy like India.

关键词： Technological innovation Privacy Distributed ledger Smart contracts Blockchains Security Reliability Problem-solving Electronic voting Logistics

来源：评论

学校读者我要写书评

暂无评论

Automated Explanation Quality Assessment based on Similarity Calculations of Representative Explanations of Different Qualities

Automated Explanation Quality Assessment based on Similarity...

引用

Educational Innovation (ECEI), IEEE Eurasian Conference on

作者： Chih-Yueh Chou Yu-Ting Chou Yu-Cheng Huang Dept. of Computer Science & Engineering Yuan Ze University Taoyuan Taiwan

Peer instruction is instructional in guiding students to learn by answering questions, and explaining and discussing their answers with peers. Researchers recommended asking students to write down their answers and explanations before discussion to prevent social loafing. In addition, text-based explanations can be recorded and analyzed. The quality of students’ explanations varies, ranging from superficial and low-quality to detailed and in-depth high-quality explanations. In tradition, the qualities of students’ explanations were assessed by experts. Recently, machine learning classification models have been developed and applied to classify texts. However, the level of explanations of questions are question-dependent. Thus, each question needs its classification model. Therefore, a feature transformation was applied in this study so that the explanations of different questions could be combined and applied to train the same classification model. An automated explanation quality assessment mechanism was developed based on the similarity of representative explanations of different qualities. Students’ text-based explanations were collected and assessed by experts into four levels, ranging from 0 (worst) to 3 (best). The four-level classifications were merged into binary classifications of low (0 and 1) and high (2 and 3). Different classification models, including Support Vector Machine (SVM), Naive Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF), and Bidirectional Encoder Representations from Transformers (BERT) were applied to train models and evaluate the accuracy of the models. In addition, three ensemble learning algorithms, including voting, stacking, and boosting, were applied to combine models chosen from SVM, NB, KNN, LR, and RF. The results showed that RF and RF+KNN+NB with stacking model showed the best accuracy (75.3%) among all four-level classification models whereas RF with boosting model showed the best accuracy (9

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Examination of Fake News Recognition Using an Ensemble of Numerous Machine Learning Algorithms 6

Comparative Examination of Fake News Recognition Using an En...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Saraswat, Shipra Faujdar, Neetu Sharma, Sachin Abesit Ghaziabad Affiliated to Aktu Dept. of Computer Science and Engineering Uttar Pradesh Lucknow India GLA University Dept. of Cea Uttar Pradesh Mathura India

ISBN: (纸本)9798350346961

The global approach in getting fraud material or data over several online platforms is really a problematic nowadays. Wide dispersion of phony news adversely affects people and society all in all. In this manner, identifying counterfeit news distributed on the different online media sites has of late become an advancing research region that is drawing extraordinary consideration. Identifying the in escapable fraud data or news on various online media platforms illustrates novel difficulties regarding calculations incapable or not relevant any longer. Authors of this paper investigates diverse basic features that can be employed to distinct fraud data material from genuine. By employing those properties, authors train several AI algorithms using diverse gathering approaches and evaluate their performance on four popular datasets. As this research is based on comparative study will be done from Ensemble of several Machine Learning Algorithms. While the instruments are helpful, to make a more complete finish to end arrangement. The aim of this paper is to represent more troublesome situations were solid sources and creators discharge counterfeit news.. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

“Advanced Anxiety Risk Stratification Using Regularized Deep Neural Networks”

“Advanced Anxiety Risk Stratification Using Regularized Dee...

引用

Progressive Innovations in Intelligent Systems and Data science (ICPIDS), International Conference on

作者： Parvez Rahi Sandeep Singh Kang Ajay Pal Singh Inderjeet Singh Dept. of Computer Science & Engineering Chandigarh University Mohali Punjab India

ISBN: (数字)9798331534691

ISBN: (纸本)9798331534707

Anxiety disorders are widespread and significantly impact daily life, necessitating accurate and timely assessment for effective intervention. Traditional methods of anxiety evaluation are often subjective and time-consuming. This study introduces a deep neural network (DNN) model with L2 regularization designed to classify anxiety into four categories: low, moderate, high, and no. For stable learning, the model employs batch normalization, dropout for regularization, and hidden layers with rectified linear unit (Re functions. Trained on a diverse Kaggle dataset, which includes psychological and physiological features, the DNN achieves a remarkable classification accuracy of 92%. Anxiety evaluations may be automated using deep learning techniques, as demonstrated in this paper, providing mental health professionals with an effective tool for developing customized treatment programs. By adding more data sources, future research attempts to improve the model's predicted accuracy and scalability, thereby advancing automated anxiety assessment in clinical settings.

关键词： Technological innovation Accuracy Soft sensors Scalability Anxiety disorders Artificial neural networks Mental health Predictive models Data models Batch normalization

来源：评论

学校读者我要写书评

暂无评论

Leukaemia: A Comparative Analysis of Deep Learning Models Using ALL Dataset

Leukaemia: A Comparative Analysis of Deep Learning Models Us...

引用

IEEE Recent Advances in Intelligent Computational Systems (RAICS)

作者： Rhea Sudheer Rapaka Vivek Richa Ramesh Apoorva Sarvade Sada Kakarla Preethi P Dept. of Computer Science and Engineering PES University Bangalore Karnataka India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381696

White blood cells, also known as leukocytes, or WBCs, spread abnormally in the bone marrow and blood, resulting in leukaemia (blood cancer). Leukaemia can be identified by pathologists by examining a patient's blood sample under a microscope. By counting different blood cells and physical characteristics, they can identify and classify leukaemia. This method takes a lot of time to forecast leukaemia. The pathologist's professional qualifications and experiences may also have an impact on this process. Traditional machine learning and deep learning techniques in computer vision are useful road maps that improve the precision and speed of identifying and categorizing medical images, such as minuscule blood cells. This paper offers a thorough analysis of the different Deep CNN models for identification and classification of WBCs and acute leukaemia in microscopic blood cells.

关键词： Deep learning White blood cells Analytical models Accuracy Microscopy Roads Cells (biology) Blood Testing Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach

Towards Robust Event-guided Low-Light Image Enhancement: A L...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Guoqiang Liang Kanghao Chen Hangyu Li Yunfan Lu Lin Wang AI Thrust HKUST(GZ) Dept. of Computer Science and Engineering HKUST

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Event camera has recently received much attention for low-light image enhancement (LIE) thanks to their distinct advantages, such as high dynamic range. However, current research is prohibitively restricted by the lack of large-scale, real-world, and spatial-temporally aligned event-image datasets. To this end, we propose a real-world (indoor and outdoor) dataset comprising over 30K pairs of images and events under both low and normal illumination conditions. To achieve this, we utilize a robotic arm that traces a consistent non-linear trajectory to curate the dataset with spatial alignment precision under 0.03mm. We then introduce a matching alignment strategy, rendering 90% of our dataset with errors less than 0.01s. Based on the dataset, we propose a novel event-guided LIE approach, called EvLight, towards robust performance in real-world low-light scenes. Specifically, we first design the multiscale holistic fusion branch to extract holistic structural and textural information from both events and images. To ensure robustness against variations in the regional illumination and noise, we then introduce a Signal-to-Noise-Ratio (SNR)-guided regional feature selection to selectively fuse features of images from regions with high SNR and enhance those with low SNR by extracting regional structure information from events. Extensive experiments on our dataset and the synthetic SDSD dataset demonstrate our EvLight significantly surpasses the frame-based methods, e.g., [4] by 1.14 dB and 2.62 dB, respectively.

关键词： Fuses Robot vision systems Urban areas Lighting Feature extraction Cameras Trajectory

来源：评论

学校读者我要写书评

暂无评论

Structured Implementation of ML Algorithms for Cardiovascular Disease Detection

Structured Implementation of ML Algorithms for Cardiovascula...

引用

Computing, Power and Communication Technologies (IC2PCT), IEEE International Conference on

作者： Drishti Arora Farhan Asif Dept. of Computer Science & Engineering Amity University Uttar Pradesh India

Cardiovascular diseases encompass a range of medical conditions that impact the heart and blood vessels The prediction of heart disease pose considerable complexity and present a formidable challenge within the medical field According to the WHO, heart diseases are the leading cause of death worldwide, claiming approximately 17.9 million lives each year, accounting for around 31% of all global deaths To address the need for accurate heart disease prediction, extensive research has employed advanced machine learning models This study conducted a comprehensive evaluation of seven distinct classification models, combining various physiological factors with well-known machine learning algorithms The model employed in this study includes Naïve Bayes, Logistic Regression, Decision Trees, Random Forest, XGBoost, CatBoost, and Voting Classifiers Using these models, a robust heart disease prediction system is designed, facilitating precise evaluation of an individual’s risk The observation shows that through meticulous evaluation and comparison, the Random Forest algorithm, which is a bagging technique, outperforms the existing state-of-the-art methods It exhibited remarkable accuracy, yielding prediction results of approximately 90.16% This exceptional accuracy establishes the random forest algorithm as the pre-eminent model for precise and reliable heart disease prediction within the scope of this study.

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：