检索结果-内蒙古大学图书馆

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Kadam, Shubhan Jani, Jay Kudtarkar, Aniket Mulla, Nikahat Sardar Patel Institute of Technology Department of Computer Engineering Mumbai India Sardar Patel Institute of Technology Department of Computer Science Engineering Mumbai India

ISBN: (纸本)9798350375190

This research paper explores the impact of Generative Adversarial Networks (GANs) on logo generation, focusing on three variants: Deep Convolutional GAN (DCGAN), Wasserstein GAN (WGAN), and Conditional GAN (cGAN). The study evaluates their strengths and weaknesses, aiming to contribute insights to the ongoing discourse on GANs. Results indicate that DCGAN excels in capturing fine details but faces mode collapse, limiting diversity, while WGAN demonstrates enhanced training stability, consistently delivering diverse and visually appealing logos. Numerical results reveal a mean rating of 3.173/5 across sample sets, with approximately 14/64 images deemed useful, resulting in a usability rating of 2.2/10. The survey findings, based on assessments from 57 participants, consistently rate DCGAN-generated images slightly higher in terms of visual appeal and usage preferences compared to those produced by WGAN. While DCGAN exhibits superior image quality, WGAN offers more variety. This suggests a trade-off between variety and image quality, underscoring the specific strengths of each model in meeting subjective criteria for visual excellence. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

High Utility Periodic Frequent Pattern Mining in Multiple Sequences

引用

computer Modeling in engineering & sciences 2023年第10期137卷 733-759页

作者： Chien-Ming Chen Zhenzhou Zhang Jimmy Ming-Tai Wu Kuruva Lakshmanna College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China Department of Information Technology Vellore Institute of TechnologyVellore632014India

Periodic patternmining has become a popular research subject in recent years;this approach involves the discoveryof frequently recurring patterns in a transaction sequence. However, previous algorithms for periodic patternmining have ignored the utility (profit, value) of patterns. Additionally, these algorithms only identify periodicpatterns in a single sequence. However, identifying patterns of high utility that are common to a set of sequencesis more valuable. In several fields, identifying high-utility periodic frequent patterns in multiple sequences isimportant. In this study, an efficient algorithm called MHUPFPS was proposed to identify such patterns. To addressexisting problems, three new measures are defined: the utility, high support, and high-utility period sequenceratios. Further, a new upper bound, upSeqRa, and two new pruning properties were proposed. MHUPFPS usesa newly defined HUPFPS-list structure to significantly accelerate the reduction of the search space and improvethe overall performance of the algorithm. Furthermore, the proposed algorithmis evaluated using several *** experimental results indicate that the algorithm is accurate and effective in filtering several non-high-utilityperiodic frequent patterns.

关键词： Decision making frequent periodic pattern multi-sequence database sequential rules utility mining

来源：评论

学校读者我要写书评

暂无评论

NeuroSafe-Advancing Mental Health using AI, ML and Blockchain 3

NeuroSafe-Advancing Mental Health using AI, ML and Blockchai...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Gujarathi, Parth Menon, Kartik Patel, Jai Halbe, Aparna Sardar Patel Institute of Technology Department of Computer Engineering Mumbai India Sardar Patel Institute of Technology Department of Computer Science and Engineering Mumbai India

ISBN: (纸本)9798350381931

This study offers a novel platform for mental health support that incorporates state-of-the-art technology to improve user experience. The platform analyzes user journals using BERT-based emotion analysis, and it generates weekly reports that show emotional trends. By utilizing blockchain technology, individuals can grant and withdraw therapist access as needed, while also ensuring safe record-keeping. Therapists can promote cooperative and private treatment by safely uploading session recordings to the blockchain. Real-time help is provided via a generative AI-based chatbot that makes use of LSTM and Seq2Seq architectures, and peer interactions are facilitated by a community chat app. The platform's usefulness is demonstrated by the results, and user feedback validates its influence on mental health assistance. This project creates a user-centric framework that integrates blockchain security, emotion analysis, and AI-driven interactions to provide a holistic approach to mental health. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Method to avert vehicle collision based on driver’s attention lapse predicted using BCI

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Mishra, Unnati Chauhan, Hitesh Maru, Madhuri Parikh, Saurin Computer Science and Engineering Department Institute of Technology Nirma University Sarkhej Gandhinagar Highway Near Gota Gujarat Ahmedabad382481 India

In this paper, a BCI-based machine learning method is proposed to predict the attention lapse of the driver. An EEG headset is used to capture brain activity from different regions of the human brain. The data is further pre-processed and various machine learning classifiers such as KNN, decision tree, and naive Bayes are trained using the data to classify the attention state of the driver as in-attention, attention lapse or attention regain. The KNN model is the best performer showing 97% accuracy, wherein the true positive rate (TPR) of 85.5% is measured to predict attention lapse and 82% to predict attention regain states. Besides this, a sensor-based model is also proposed to avert the vehicle’s collision by alerting the driver about the attention lapse. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A fast verifiable fully homomorphic encryption technique for secret computation on cloud data

引用

International Journal of Information technology (Singapore) 2025年第4期17卷 2193-2207页

作者： Mahato, Ganesh Kumar Chakraborty, Swarnendu Kumar Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Jote 791113 India

In the domain of cloud computing, safeguarding the confidentiality and integrity of outsourced sensitive data during computational processes is of utmost importance. This paper introduces a pioneering verifiable homomorphic encryption (VFHE) scheme, combining data encryption with the ability to verify computation integrity through homomorphic operations. The proposed approach leverages a fast lattice-based reduction key generation method, drastically reducing key generation time and resulting in a substantial reduction in key size while maintaining security. By integrating this innovation into a fully homomorphic encryption scheme, cloud data computations are expedited while preserving data security. The efficiency of the proposed scheme is highlighted through analyses of key generation time, encryption, decryption, and verification processes across varying security parameters. Verification time remains minimal, showcasing the practical applicability of our approach. Furthermore, novel metrics such as privacy cost and amortized cost are introduced to evaluate the efficiency and overhead associated with incorporating privacy into the verifiable computation scheme. The proposed VFHE scheme not only ensures data security but also substantially improves computation speed, making it a promising solution for enhancing privacy and efficiency in cloud computing applications. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Cloud security Homomorphic encryption Key generation Lattice-based encryption Secret computation Verifiable computation

来源：评论

学校读者我要写书评

暂无评论

High Dynamic Range Imaging for Dynamic Scenes Based on Multi-Level Spike Camera

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5394-5406页

作者： Zhu, Zhenkun Xiong, Ruiqin Zhao, Jing Zhao, Rui Fan, Xiaopeng Zhu, Shuyuan Huang, Tiejun Peking University School of Computer Science Beijing100871 China Harbin Institute of Technology Department of Computer Science and Technology Harbin150001 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China

Spike camera is a retina-inspired neuromorphic camera which can capture dynamic scenes of high-speed motion by firing a continuous stream of spikes at an extremely high temporal resolution. The limitation in the current design is that each spike only represents the arrival of a fixed amount of photons. It can not deal with strong light areas in which the amount of accumulated photons reaches the pre-specified threshold multiple times within a single readout interval. In this paper, we propose a new spike camera model of high-speed imaging for high dynamic range scenarios. In this scheme, each pixel accumulates the incoming photons persistently and generates a new type of spike stream in which each spike symbol may be associated with different levels, indicating the arrival of different amounts of photons since the last readout. This enables the camera to support dynamic scenes with wider dynamic range. To achieve this, we propose a two-level buffer mechanism, one for photon accumulation and one for spike-firing encoding. We use a register to hold the number of spike-firings which has not been read out yet. At each readout time, the major part in the counter is read out via a carefully designed exponential encoding and the counter is updated. Such encoding and readout strategy enables a very efficient expansion of the dynamic range using a small number of encoding bits. Furthermore, we propose an image reconstruction scheme for the proposed camera, utilizing both spike intervals and spike levels to recover the light intensity. We incorporate Mamba and propose a temporal-spatial selective scan mechanism to extract temporal-spatial correlation within spike streams. We employ a pyramid adaptive filtering and alignment module to achieve coarse-to-fine feature alignment. Experimental results show that the proposed scheme can achieve better imaging quality and outperform the existing spike camera in high dynamic range scenarios. © 1991-2012 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Two-Level Image Augmentation with Deep-Learning for Single Sample Face and Ear Recognition

Two-Level Image Augmentation with Deep-Learning for Single S...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Tomar, Vivek Kumar, Nitin Deshmukh, Maroti Singh, Maheep University Computer Science & Engineering Department Dehradun India Computer Science & Engineering Department Chandigarh India National Institute of Technology Computer Science & Engineering Department UttarakhandGarhwal Srinagar India National Institute of Technology Uttarakhand Doon University Computer Science Department Dehradun India

ISBN: (纸本)9798331540821

Single-sample face and ear recognition is a challenging sub-problem in biometric recognition, as only one sample is available for training. This article presents a method to recognise the subject from a single face or ear image with two-level image augmentation, followed by using a pre-trained deep learning model for feature extraction and classification. First, sampling is used for generating additional samples, and then mirroring and rotation are used. Pre-trained VGG16 model is used for parameter estimation and classification. The proposed method is tested on three face and two ear databases. The proposed method achieves classification accuracy of 84.83 %, 77.08 %, and 88.52 % on ORL, Yale, and FeedTum databases and 66.69% and 78.29% on AMI and IITD databases, respectively. The image quality of the generated samples is also found to be in an acceptable range. The proposed method can be helpful and effective when smaller databases and fewer training images are available. © 2024 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Design and evaluation of Swift routing for payment channel network

引用

Blockchain(Research and Applications) 2024年第2期5卷 62-72页

作者： Neeraj Sharma Kalpesh Kapoor V.Anirudh Department of Computer Science and Engineering Indian Institute of Technology GuwahatiGuwahati 781039AssamIndia Department of Mathematics Indian Institute of Technology GuwahatiGuwahati 781039AssamIndia

Payment Channel Networks(PCNs)are a promising alternative to improve the scalability of a blockchain network.A PCN employs off-chain micropayment channels that do not need a global block confirmation procedure,thereby sacrificing the ability to confirm transactions *** uses a routing algorithm to identify a path between two users who do not have a direct channel between them to settle a *** performance of most of the existing centralized path-finding algorithms does not scale with network *** rapid growth of Bitcoin PCN necessitates considering distributed ***,the existing decentralized algorithms suffer from resource *** present a decentralized routing algorithm,Swift,focusing on fee *** concept of a secret path is used to reduce the path length between a sender and a receiver to optimize the ***,we reduce a network structure into combinations of cycles to theoretically study fee optimization with changes in cloud *** secret path also helps in edge load sharing,which results in an improvement of *** routing achieves up to 21%and 63%in fee and throughput optimization,*** results from the simulations follow the trends identified in the theoretical analysis.

关键词： Blockchain Payment channel networks Bitcoin Lightning network Routing protocols Layer 2 protocols

来源：评论

学校读者我要写书评

暂无评论

Smart Home Security Enhancements with Cisco Packet Tracer 1

Smart Home Security Enhancements with Cisco Packet Tracer

引用

1st IEEE International Conference on Computing and Data science, ICCDS 2024

作者： Nanthini, N. Lakshmi Priya, S. Jeslene Sugee, A.G. Sathyabama Institute of Science and Technology Department Of Computer Science and Engineering Chennai India

ISBN: (数字)9798350365337

ISBN: (纸本)9798350365337

Modern households are increasingly adopting smart home devices powered by the Internet of Things (IoT). From smart thermostats and security systems to voice assistants, connected IoT devices enable seamless and responsive control through Wi-Fi, Bluetooth and other wireless technologies Whena home appliance a intelligent consumption is accelerating, driven by its undeniable benefits, the need for robust security solutions becomes paramount. This paper delves into the potential of EIGRP (Enhanced Interior Gateway Routing Protocol) as a powerful tool for securing smart homes. While challenges remain to ensure compatibility with all smart devices to improve network performance, EIGRP capabilities offer promising prospects for the coming years of smart home security If received greater adoption of this policy along with other security measures, can pave the way for more secure and connected smart home products to reap the full benefits, and find peace in your digital paradises. © 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

An IoT based Application for Real-Time Detection of Rotten Fruits 2

An IoT based Application for Real-Time Detection of Rotten F...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Raj, Jeberson Retna Srinivasulu, Senduru Jabez Gowri Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350387933

Food packaging serves several purposes, including food preservation, shelf-life extension, and upholding quality and safety requirements throughout manufacturing and storage. Intelligent food packaging, on the other hand, goes a step further by including sensors that continually check food quality throughout the supply chain. This enables food-borne sickness and waste to be analyzed and reduced. The existing systems are limited in accuracy and they are unable to extract the actual state of the food. Furthermore, the practical implementations remain restricted. In this paper, an IoT based food quality checking system is designed to check the quality of the food and ensures whether it can be edible or not in a real-time environment. This helps the food producers and consumers to indicate the status of food for further processing for intelligent packaging. © 2024 IEEE.

关键词： Supply chains

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：