检索结果-内蒙古大学图书馆

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Tiwari, Raj Gaurang Gautam, Vinay Trivedi, Naresh Kumar Jain, Anuj Kumar Sharma, Vikrant Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Deparment of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350302288

Classification of marine animals is essential for studying marine ecosystems, keeping track of biodiversity, and developing efficient conservation plans. The success of deep learning methods in picture classification tasks has increased dramatically in recent years. In this research, we propose a systematic investigation of the use of several deep learning models for the categorization of marine organisms;these models include Inception, ResNetV, ResNet50, VGG16, InceptionV3, Xception, DenseNet, MobileNet, and NASNet, among others. Models originally built on ImageNet were then fine-tuned using transfer learning before being applied to our marine animal dataset for training. Training and validation accuracy were used to rank the models, and the models' overall performance was compared to find the best one. Inception outperformed the other models in tests by a wide margin, with a training accuracy of 95.85% and a validation accuracy of 96.75. Inception's greater performance in marine animal categorization may be attributed to its deeper design and its ability to grasp complex spatial connections. When deep learning models are used to correctly categorize marine species, it may greatly improve taxonomic identification, aid conservation efforts, and make ecological study much easier. Additionally, the results highlight the significance of constructing domain-specific deep learning models for fields like marine biology, where distinct obstacles exist. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Preserving India's Rich Dance Heritage: A Classification of Indian Dance Forms and Innovative Digital Management Solutions for Cultural Heritage Conservation

Preserving India's Rich Dance Heritage: A Classification of ...

引用

2023 International Research Conference on Smart Computing and Systems Engineering, SCSE 2023

作者： Tiwari, Raj Gaurang Gautam, Vinay Sharma, Vikrant Jain, Anuj Kumar Trivedi, Naresh Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Deparment of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350341454

Deep connections exist between dance and cultural heritage. Dance is frequently passed down through generations as an essential component of a culture's identity and as a means of maintaining and honoring that culture's distinctive traditions and customs. A culture's history, beliefs, and values can be powerfully expressed via dance, which can also be used for communication and storytelling. For the purpose of protecting and promoting India's cultural legacy, it is crucial to comprehend how Indian dance styles are categorized. This paper proposes a hybrid Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) deep learning approach for the accurate classification of Indian dance style categories. The proposed model combines the strengths of both CNN and RNN to leverage spatial and temporal information, respectively, resulting in enhanced performance and improved accuracy. Extensive experiments were conducted to evaluate the performance of the proposed approach. The results demonstrate that the hybrid CNN-RNN model achieved an impressive accuracy of 97.74%, outperforming traditional methods and single-model architectures. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Does Image Anonymization Impact computer Vision Training?

arXiv

引用

arXiv 2023年

作者： Hukkelås, Håkon Lindseth, Frank Deparment of Computer Science Norwegian University of Science and Technology Norway

Image anonymization is widely adapted in practice to comply with privacy regulations in many regions. However, anonymization often degrades the quality of the data, reducing its utility for computer vision development. In this paper, we investigate the impact of image anonymization for training computer vision models on key computer vision tasks (detection, instance segmentation, and pose estimation). Specifically, we benchmark the recognition drop on common detection datasets, where we evaluate both traditional and realistic anonymization for faces and full bodies. Our comprehensive experiments reflect that traditional image anonymization substantially impacts final model performance, particularly when anonymizing the full body. Furthermore, we find that realistic anonymization can mitigate this decrease in performance, where our experiments reflect a minimal performance drop for face anonymization. Our study demonstrates that realistic anonymization can enable privacy-preserving computer vision development with minimal performance degradation across a range of important computer vision benchmarks. © 2023, CC BY-SA.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Advanced Tracking Algorithm for Multiple Dynamic Vehicles using Attention Mechanisms and Kinematic Models 3

Advanced Tracking Algorithm for Multiple Dynamic Vehicles us...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Ravikumar, Kishore Sutaria, Kamal Pathak, Ganesh Pandit Rastogi, Shailesh Chennai Institute of Technology Department of Mechanical Engineering Kundrathur India Parul University Faculty of Engineering and Technology Deparment of Computer Science and Engineering Vadodara India Balaji Institute of Modern Management Pune India Pune India

ISBN: (纸本)9798331508456

Efficient vehicle tracking in urban environments is crucial for intelligent transportation systems but faces challenges such as nonlinear motion, dynamic backgrounds, and frequent occlusions. To address these complexities, we propose the AM-Vehicle-Track system, designed under the tracking-by-detection paradigm. This system integrates the Lightweight Convolutional Block Attention Module (LCBAM), which enhances detection accuracy by refining feature maps through channel-wise and spatial attention, and the Noise-Adaptive Extended Kalman Filter (NSA-EKF), which dynamically adjusts observation noise based on detection confidence to handle nonlinear vehicle motion. Additionally, the Byte data association technique is employed to mitigate issues with low-confidence detections and reduce identity switches. Tested on the challenging VisDrone-MOT dataset, AM-Vehicle-Track achieves a mean object tracking accuracy (MOTA) of 42.2%, an identity F1 score (IDF1) of 51.2%, and processes at 72 frames per second (FPS), outperforming existing state-of-the-art systems. These results highlight its robustness and efficiency in real-time scenarios, making it suitable for intelligent transportation applications. By significantly improving detection accuracy, tracking precision, and scalability, AM-Vehicle-Track establishes a new benchmark in multi-object tracking technologies and demonstrates its potential to enhance the reliability and efficiency of vehicle tracking in complex urban environments. © 2025 IEEE.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Ethiopic Cryptography: An Efficient Hybrid Encryption Algorithm for Reducing Cybersecurity Attack 11th

Ethiopic Cryptography: An Efficient Hybrid Encryption Algori...

引用

11th EAI International Conference on Advancement of science and technology, ICAST 2023

作者： Akele, Tadesse Birara Bahiru, Tadesse Kebede Molla, Tibebu Legesse Fentie, Shambel Dessale Belay, Tadesse Destaw Marye, Almaz Yemataw Getaneh, Mersha Derese Department of Information System Kombolcha Institute of Technology Wollo University Kombolcha Ethiopia Department of Information Technology Kombolcha Institute of Technology Wollo University Kombolcha Ethiopia Deparment of Software Engineering Kombolcha Institute of Technology Wollo University Kombolcha Ethiopia Department of Computer Science Kombolcha Institute of Technology Wollo University Kombolcha Ethiopia

ISBN: (纸本)9783031641503

Cryptography is an essential tool in ensuring the security of data during network communication. Network and service providers prioritize data security to ensure secure data exchanges. Ethiopic cryptography is a unique encryption method that utilizes the Amharic language, prevalent in Ethiopia. Unlike Latin alphabets, Amharic consists of 287 characters, making decryption challenging. The encryption process involves converting the text to Amharic and then mapping it to a pair of randomly chosen two-bit English alphabets, creating an intermediate cipher. The Ethiopic cryptography algorithm employs a hybrid approach, using the RSA algorithm for secure key exchange and the Advanced Encryption Standard algorithm for text confidentiality. The algorithm comprises three phases—translation, mapping, and encryption—contributing to its effectiveness in securing data over the network. Decryption requires familiarity with the Amharic language and mapping details. The algorithm demonstrates a stronger avalanche effect (97%) in comparison with Blowfish and DES. The algorithm is proposed and evaluated using the design science research methodology, and its performance is validated through simulation using MATLAB and BunnaScript tools, considering factors like the avalanche effect, time complexity, and memory consumption. The evaluation shows that the suggested solution operates faster, requires lesser time for data encryption, and uses less memory than other methods in use. Overall, the proposed Ethiopic cryptography algorithm proves to be an efficient and effective method for securing data during network communication, offering stronger text confidentiality and an improved avalanche effect. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

The Novel Protocol Uses Low Computational Complexity to Authenticate Edge Devices on Smart Grid Systems 9

The Novel Protocol Uses Low Computational Complexity to Auth...

引用

9th IEEE India International Conference on Power Electronics, IICPE 2023

作者： Kuppuswamy, Prakash Al Khalidi, Sayed Q.Y. Kumar, Purushottam Meeran, Ahmed Ali Shaik Sonia Varshini, Vijaya Computer Science Engineering SRM University Haryana Delhi-NCR India King Khalid University Department of Information Technology Abha Saudi Arabia Jazan University Department of Information Technology Jazan Saudi Arabia Bharathiyar University Computer Science Deparment Tamil Nadu Coimbatore India

ISBN: (纸本)9798350307252

Grid computing has emerged as a powerful paradigm for harnessing distributed computing resources to solve complex problems. In grid computing, various devices across different administrative domains collaborate to provide computational power and storage capacity. Sensor agent devices have become the backbone of modern technological systems such as Internet of Things (IoT), smart homes, industrial automation, and autonomous vehicles. These devices collect and process real-time data from the surrounding environment, providing crucial insights for decision-making, monitoring, and control purposes. However, the performance of these devices depends on space complexity and time complexity. Achieving optimum performance in sensor agent devices requires a delicate balance between space complexity and time complexity. Reducing one complexity may increase the other, and vice versa. Light weight authentication device-based algorithms play a vital role in verifying the identity of devices and ensuring secure communication within the grid and that needs to satisfy complexity. These protocols verify the identity of devices and users, ensuring that only authorized entities can access and interact with the data. In this article, we will explore a new light weight authentication protocol based on a block cipher i.e ELBC (Extended Linear Block cipher algorithm). The new authentication protocols are easy to implement and deploy in any kind of environment. The algorithm divides the authentication message into blocks and encrypts them using matrix multiplication. By generating an invertible key matrix and applying encryption and decryption equations, the proposed algorithm ensures secure communication. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Progression of Disease Forecasting in Recurrence Cervical Cancer Using Logistic Regression 7

Progression of Disease Forecasting in Recurrence Cervical Ca...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Geeitha, S. Renuka, P. Ramya, S. Sinduja, K. M.Kumarasamy College of Engineering Department of Information Technology Karur India Paavai Engineering College Deparment of Computer Science and Engineering Namakkal India Sri Krishna College of Engineering and Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350340600

Cervical cancer is the fourth most prevalent disease in women globally as well as main cause of cancer- related mortality among women. The overall survival rates of cervical carcinoma patients are significantly impacted by the detection of recurrence. The disease is entirely treatable, though, if it is found in its early, precancerous levels. According to current figures, the death percentage a few decades ago was excessive. Women who have previously had treatment with CIN3 are most at riskof developing cervical cancer once more. The dataset includes information on the effects of various treatments on post- recurrence survival. The progression of a disease is detected in this research. Of the 4913 patients who were diagnosed withcervical cancer overall, 260 women with the disease suffered recurrences. The Data has been roughly categorized into 27 characteristics that are important for illness staging and therapy. Thevery important attributes selected are FIGO 2009, chemotherapy,radiotherapy, recurrence confirmed by a pathologist, etc. Five different models are trained to predict the progression. Logistic regression is finally predicted with a high level of accuracy of 96.3%. Two hundred and sixty patients with 27 attributes consistof a number of missing values. Research is implemented through the Orange platform. The missing values are balanced through Average and Most frequent data imputation method. Important attributes are selected through the ReliefF technique, and then disease progression is predicted by 5 different algorithms Logistic regression, Support vector machine, Naive Bayes, Stochastic gradient decent and neural network. Finally logistic regression predict the progression of a disease with highest accuracy of 96.3%. © 2023 IEEE.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art in Multi-faceted Feature Matching for E-Commerce: A Comprehensive Analysis

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第12期48卷 97-106页

作者： Zareena, Noorbasha Rao, B. Tarakeswara Department of Computer Science and Systems Engineering AUTDR HUB Andhra University India Deparment of Computer Science and Engineering Kallam Haranadhareddy Institute of Technology Andhra Pradesh Guntur India

In this paper we provided an insightful exploration into the critical role of feature matching in enhancing the efficacy of e-commerce recommendation systems. By meticulously analyzing user data and product characteristics, feature matching significantly improves the personalization of product suggestions, thereby augmenting user experience and engagement in online shopping platforms. The paper reviews existing methodologies, including collaborative filtering, content-based filtering, hybrid models, and advanced deep learning approaches, which have collectively advanced the domain of personalized recommendations. Despite these advancements, the paper identifies key limitations such as scalability challenges, the cold start problem, over-specialization versus diversity in recommendations, and concerns over user privacy and data security. Through this comprehensive analysis, the survey makes substantial contributions by delineating the current state of the art, pinpointing critical gaps, and suggesting avenues for future research. The paper particularly emphasizes the need for dynamic adaptation in recommendation systems to keep pace with the fast-evolving e-commerce sector and changing consumer behaviors. Future research directions highlighted include the exploration of unsupervised and reinforcement learning models, the development of cross-domain recommendation systems, and the integration of emerging technologies, all aimed at fostering more nuanced, adaptable, and ethically responsible recommendation mechanisms. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The Role of Bio Informatics in Identifying Cancer Informatics 2

The Role of Bio Informatics in Identifying Cancer Informatic...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Gole, Harshada Daronde, Subodh Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Deparment of Computer Science and Medical Engineering Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Biomedical Enginering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

With the advent of bioinformatics, cancer research has entered a new age wherein vast amounts of complex biological data can be interpreted to create powerful treatments. This approach has exceptionally improved the identification of biomarkers, deciphering hidden patterns contained within data, and developing personalized treatment modalities by incorporating bioinformatics-based strategies with artificial intelligence and machine learning. Advances in bioinformatics will soon give insight into the cancer process at cellular levels and offer a better understanding of tumor heterogeneity and evolution. Increased reliance on bioinformatics has directly affected the development of newer immunotherapy forms. In the last year, there have been 13 new FDA-approved immunotherapy treatments for 10 different drugs and 11 types of cancers specific to each one. The future of bioinformatics in cancer research is bright, and the field is likely to be further revolutionized with the continued progress in artificial intelligence, machine learning, and single-cell analysis techniques © 2025 IEEE.

关键词： Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Fundamental Spatial Parameters of Human Mobility

Fundamental Spatial Parameters of Human Mobility

引用

computer science, computer Engineering, & Applied Computing (CSCE), Congress in

作者： Sasha Knezevic Ivica Kostanic Zaid Matloub Deparment of Computer Science and Engineering Florida Institute of Technology Melbourne FL USA

A set of parameters for characterizing spatial aspects of human mobility are presented. The parameters are extracted from a large set of crowd-sourced cellular data which were collected in a major metropolitan area of United States. Each parameter is analyzed at three different time scales (daily, weekly, and monthly time scale). The results demonstrate that human mobility on a population scale has a high degree of statistical regularity. The mobility may be described to a great extend using a limited number of judiciously selected parameters.

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：