检索结果-内蒙古大学图书馆

International Conference on computer and Applications (ICCA)

作者： Rozah Hassan M. Alkhater Somaya Al-Maadeed Moutaz Saleh Younes Akbari dept. Computer Science and Engineering Qatar university Doha Qatar

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

Breast cancer is a prevalent and potentially fatal malignancy in women, requiring continual improvements in diagnostic techniques. In order to help medical personnel accurately detect dangerous tumors, automated medical image analysis is essential. This paper presents a unique breast cancer detection model that makes use of deep learning and transfer learning approaches in order to improve the accuracy of diagnostics. The pre-trained ViTb-32 model is fine-tuned on a pre-processed dataset to produce cutting-edge results. The model was trained with a public histopathologic breast cancer dataset. The dataset is pre-processed to resize the images and normalize them to enhance the performance during the training and achieve convergence faster. The ViTb-32 model is optimized by fine-tuning the hyperparameters to achieve the best possible accuracy. The proposed model achieves an accuracy rate of 96.92%. The application of this paradigm in the clinical setting has the potential to improve patient outcomes by facilitating early detection and timely intervention, which could reduce the mortality rate of breast cancer patients by detecting the disease at an early stage.

关键词： Deep learning Training Analytical models Accuracy Transfer learning Transformers Breast cancer Real-time systems Personnel Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A Secure method of transferring confidential documents by leveraging Zero Trust Principles and Blockchain Technology

A Secure method of transferring confidential documents by le...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Hannah Thankam Alex Sarah Alex Swathi C G Chandrashekhar Pomu Chavan Dept. of Computer Science and Engineering PES University Bengaluru India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Ensuring regulatory compliance and maintaining client trust in the legal industry depend on the safe transfer and preservation of sensitive data. Maintaining the safety and security of confidential information is essential in a law business. The suggested concept combines zero-trust concepts with blockchain technology to develop a decentralized application (dApp) that facilitates secure document sharing between clients and law firms. To guarantee the safe transfer of private legal documents, the platform makes use of IPFS for decentralized file storage and MetaMask for authentication. OTP verification, document encryption using cryptographic methods, and MetaMask user authentication are some of its key features. Only authorized users are able to view or manage documents in the DApp thanks to smart contract access management. The requirements for security, immutability, and transparency are maintained by this method.

关键词： Industries Law Smart contracts Government Authentication Decentralized applications Blockchains Zero Trust Safety Peer-to-peer computing

来源：评论

学校读者我要写书评

暂无评论

Spatial Data Discovery Using Small Language Model

Spatial Data Discovery Using Small Language Model

引用

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

作者： Sujit Kumar Thakur Neha Tyagi Dept. of Computer Science & Engineering Amity University Noida India

The ubiquitous use of data in a plethora of use cases and different organizational dependence on it for various insight has made data a valuable resource across business and scientific domains. Data has attained much more significance than oil itself, unlike the British mathematician Clive Humby’s quote in 2006 “data is the new oil”. Every business and processes generate data and with the advent of AI and machine learning, all types of data have valuable use case attached. This also ensued a series of initiatives to clean, augment and provide data as data-products. This has given rise to businesses and solutions using inhouse data or data purchased from a dedicated data provider. Data consumers often face the challenge of inefficient data product discovery. More frequently than not they require active support from data product experts to point them to right dataset. The semantic meaning of the attributes and keywords of a data product is also heavily domain oriented. Data providers find it easy to update and augment metadata of a data set with details more feasible solution than modifying the dataset itself with attribute rename or adding composite attribute. The expected next step is that the metadata be self-explanatory enough to help in data cataloguing, but often we find consuming data scientist looking for help from data experts to make sense of the data in the context of the consumer’s use case. This research seeks to analyse if the role of a data expert can be reduced and a finetuned small language model can help a data consuming data scientist in discovering the right data product, based on the metadata of the data product. Overall, this research contributes to the advancement of data discovery techniques and highlights the potential of leveraging language models to streamline and democratize access to valuable data resources, thereby empowering organizations to make more informed and data-driven decisions.

关键词：

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

arXiv

引用

arXiv 2024年

作者： Liang, Guoqiang Chen, Kanghao Li, Hangyu Lu, Yunfan Wang, Lin China Dept. of Computer Science and Engineering HKUST Hong Kong

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. © 2024, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Water Quality Prediction using Classification techniques on XGBoost, KNeighbors, SVC, Random Forest, AdaBoost, and GaussianNB Classifier

Water Quality Prediction using Classification techniques on ...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Gill, Kanwarpartap Singh Tuteja, Gaurav Anand, Vatsala Gupta, Rupesh Hsiung, Pao-Ann Chitkara University Institute of Engineering and Technology Chitkara University Punjab India National Chung Cheng University Dept. of Computer Science and Information Engineering Chiayi County Taiwan

ISBN: (纸本)9798350308167

A key environmental problem that is extensively researched for academic purposes is water contamination. To understand the origins, impacts, and potential solutions to water contamination, researchers look into a variety of issues. Environmental science, chemistry, biology, engineering, and policy are essential for study of water pollution. Classifiers as proposed help create early warning systems for probable pollution events by categorising water quality based on previous and current data. These systems aid in prompt reactions to occurrences of pollution prevention or mitigation. It is essential to tackling one of the most urgent issues affecting the wellbeing of ecosystems and human communities. By training models to predict the degree of pollution or the category of pollutants based on input characteristics, machine learning classifiers can classify water contamination. This study focuses on XGBoost, KNeighbour, SVC, Random Forest, Adaboost, and GaussianNB classifiers' various classification methodologies for predicting water quality. The XGBoost classifier, which may be used for future study, emerges as the best classifier out of all of these. © 2023 IEEE.

关键词： Artificial Intelligence Classification Data science Deep Learning Machine Learning ROC Curve Water Pollution

来源：评论

学校读者我要写书评

暂无评论

Hybrid Quantum-Classical Encryption (HQCE) Algorithm: A Post-Quantum Secure Solution for Data Encryption

Hybrid Quantum-Classical Encryption (HQCE) Algorithm: A Post...

引用

Information Technology (OCIT), OITS International Conference on

作者： Mahesh Babu Chittem Ashok Kumar Pradhan Dept of Computer Science and Engineering SRM University AP Amaravati India

ISBN: (数字)9798331510404

ISBN: (纸本)9798331510411

While currently in practice, classical encryption methods such as RSA and AES-256 are opportunities in the age of quantum computing, algorithms such as Shor's are capable of bringing down their fundamental security. Unfortunately, these threats have not been well addressed by current technologies and hence Post-Quantum Cryptography (PQC) seeks to offer solutions that provide protections from quantum attacks. HQCE, the Hybrid Quantum-Classical Encryption algorithm combines AES-256 for encryption of data with LWE problem for quantum secure keying. HQCE derives a 256-bit AES key for data encryption and for protecting this generated AES key, it employs LWE making sure that the data is safe from any miscreants. In the decryption process the LWE layer decode the AES key so that only authorized personnel can decrypt the data. In this paper, I present the encryption and decryption mechanisms of HQCE with a security assessment and demonstrate that HQCE is a post-quantum security solution that is resistant to both classical and quantum adversaries.

关键词： Resistance Quantum computing Encryption Personnel Protection Information technology

来源：评论

学校读者我要写书评

暂无评论

Malicious Traffic Classification in WSN using Deep Learning Approaches 2

Malicious Traffic Classification in WSN using Deep Learning ...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Gupta, Chhote Lal Prasad Rajassekharan, Dinesh Sharma, Dilip Kumar Elangovan, Mohanraj Myilsamy, Varatharaj Upreti, Kamal Bansal Institute of Engineering and Technology Dept. of Computer Science and Engineering Lucknow India Peninsula College Faculty of Computer Science Peninsula Malaysia Jaypee University of Engineering and Technology Department of Mathematics Madhya Pradesh Guna473226 India K. S. Rangasamy College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Tiruchengode637215 India V.S.B College of Engineering Technical Campus Department of Electrical and Electronics Engineering Tamil Nadu Coimbatore642109 India Department of Computer Science Delhi-NCR Ghaziabad India

ISBN: (纸本)9798350369960

Classifying malicious traffic in Wireless Sensor Networks (WSNs) is crucial for maintaining the network's security and dependability. Traditional security techniques are challenging to deploy in WSNs because they comprise tiny, resourceconstrained components with limited processing and energy capabilities. On the other hand, machine learning-based techniques, such as Deep Learning (DL) models like LSTMs, may be used to detect and categorize fraudulent traffic accurately. The classification of malicious traffic in WSNs is crucial because of security. To protect the network's integrity, data, and performance and ensure the system functions properly and securely for its intended use, hostile traffic categorization in WSNs is essential. Classifying malicious communication in a WSN using a Long Short-Term Memory (LSTM) is efficient. WSNs are susceptible to several security risks, such as malicious nodes or traffic that can impair network performance or endanger data integrity. In sequential data processing, LSTM is a Recurrent Neural Network (RNN) appropriate for identifying patterns in network traffic data. © 2023 IEEE.

关键词： data routing deep learning LSTM malicious transmission neural network Traffic data transmission WSN

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Customer Reviews on Food Ordering Portals of Bangladesh using Natural Language Processing

Sentiment Analysis of Customer Reviews on Food Ordering Port...

引用

Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), IEEE International Conference on

作者： Priom Deb Asibur Rahman Bhuiyan Farhan Ahmed Md. Rakib Hossain Habiba Mahrin Md Faisal Ahmed Dewan Ziaul Karim Dept. of Computer Science and Engineering BRAC University Dhaka Bangladesh

ISBN: (数字)9798331505790

ISBN: (纸本)9798331505806

In recent years, the popularity of online food ordering services has surged, offering consumers a convenient way to order food from restaurants and have it delivered to their doorstep. During this period, HungryNaki and Foodpanda Bangladesh have been identified as key contributors to the growth and advancement of the online food delivery market. This study aims to anticipate the sentiments of Bangladeshi customers towards online meal ordering services, with a specific focus on Foodpanda Bangladesh and HungryNaki. We created a new dataset for this research, subjected it to preprocessing and employed six machine learning models and three deep neural network models. In the machine learning approach, the Random Forest Classifier demonstrated excellence in accuracy, precision, and recall, achieving an accuracy rate of 80.31%. On the other hand, the BERT Classifier performed effectively in the deep learning approach, reaching a peak accuracy of 89%. Despite challenges such as data ambiguity and imbalances in the dataset, our findings underscore the potential of the BERT model in sentiment analysis, offering valuable insights for future research in this field.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Reviews Artificial neural networks Manuals Random forests Portals Optimization

来源：评论

学校读者我要写书评

暂无评论

A Study on Deep Fake Face Detection Techniques

A Study on Deep Fake Face Detection Techniques

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Mudit Arya Priyanshu Upwan Akash Umang Goyal Simran Chawla Dept. of Computer Science and Engineering Chandigarh University Punjab India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Advanced technology and the widespread use of deep fake technology has rendered the digital landscape vulnerable to deceptive manipulations, particularly through the creation of synthetic face images. This comprehensive review precisely traces the historical trajectory of deep fake faces, encompassing their evolution and its impact on various domains. It also investigates into the growing concerns regarding misinformation and privacy breaches. The literature review analyzes important works, pivotal milestones, and notable case studies, providing a complete understanding of the dynamic landscape of deep fake faces. This study analyzes existing detection techniques, ranging from neural networks to machine learning approaches, offering insights into the complexities of current methodologies. It sheds light on both the strengths and limitations of these techniques, emphasizing the need for robust solutions to counter adversarial attacks and address data scarcity. Building on this analysis, this study explores breakthroughs within the field of deep fake detection, highlighting instances where identification has been successful. It also underscores the ethical considerations that come with the evolution of these technologies. In proposing innovative solutions and discussing potential optimizations for existing techniques, the review explores interdisciplinary approaches and emerging technologies like blockchain and explainable AI. The findings provide a summary of key insights collected from the literature, identify research gaps, and project the future of deep fake face detection. This study concludes by emphasizing the ongoing societal impact of these developments in the digital era.

关键词： Deepfakes Ethics Reviews Explainable AI Neural networks Privacy breach Trajectory

来源：评论

学校读者我要写书评

暂无评论

Using an Adaptive Neuro Fuzzy Inference System to Improve the Calibration Accuracy of Modeless Robots

Using an Adaptive Neuro Fuzzy Inference System to Improve th...

引用

2022 International Symposium on Power Electronics, Electrical Drives, Automation and Motion, SPEEDAM 2022

作者： Bai, Ying Wang, Dali Johnson C. Smith University Dept of Computer Science and Engineering CharlotteNC United States Christopher Newport University Dept of Physics and Computer Science Newport NewsVA United States

ISBN: (数字)9781665484596

ISBN: (纸本)9781665484596

This paper is our extended research described a technique used for position error compensations of the robot and manipulator calibration process based on an Adaptive Neuro Fuzzy Inference System (ANFIS) method. Traditional robots calibration implements either model or modeless method. The compensation of position error in modeless method is to move the robot's end-effector to a target position in the robot workspace, and to find the target position error based on the measured neighboring 4-point errors around the target position. A camera or other measurement device is attached on the robot's end-effector to find and measure the neighboring position errors, and compensate the target position with the error interpolation results. By using the ANFIS technique provided in this paper, the accuracy of the position error compensation can be greatly improved, which has been confirmed by the simulation results given in this paper. Compared with some other popular traditional interpolation methods, this ANFIS technique is a better choice. The simulation results show that more accurate compensation result can be achieved using this technique compared with the interval type-2 fuzzy interpolation method. © 2022 IEEE.

关键词： Error compensation

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：