检索结果-内蒙古大学图书馆

9th IEEE International Conference for Convergence in technology, I2CT 2024

作者： Koundinya, Anjan K. Patil, S.S. Chandu, b.R. B M S Institute of Technology And Management Department of Information Science And Engineering Karnataka Bengaluru India B M S Institute of Technology And Management Information Technology Solutions Karnataka Bengaluru India B M S Institute of Technology And Management Department of Electronics And Communication Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350394474

Data poisoning attacks pose a significant threat to the integrity of machine learning (mL) models, impacting their ability to generate accurate predictions. This research delves into the realm of adversarial mL [1], specifically focusing on poisoning attacks [4] during the training phase. A taxonomy of adversarial mL techniques is presented, classifying poisoning attacks into different categories. Real-world examples, including incidents involving Google's VirusTotal [8] scanning service, highlight the practical implications of data poisoning. The study explores defense mechanisms such as training data sanitization and robust optimization, acknowledging the nuanced balance required between model robustness and accuracy. The paper concludes with recommendations for safeguarding mL models against evolving adversarial threats, underscoring the ongoing importance of vigilance and education in the cybersecurity landscape. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Survey of 3D Gaussian Splatting: Optimization Techniques, Applications, and AI-Driven Advancements 3

A Survey of 3D Gaussian Splatting: Optimization Techniques, ...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Santosh Reddy, P. Abhiram, H. Archish, K.S. B.N.M. Institute of Technology Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798331515911

3D Gaussian Splatting (3DGS) has emerged as a transformative technique for real-time, high-quality 3D rendering. This paper surveys the advancements in 3DGS, focusing on optimization strategies, applications across diverse domains, and AI-driven innovations that enhance its utility. Optimization techniques, such as mini-Splatting and sparsification frameworks, address challenges like computational overhead and memory inefficiency while maintaining visual fidelity. AI has further expanded the capabilities of 3DGS through frameworks like SceneTeller, ART3D and GaussianEditor, enabling text-to-3D generation, object-level manipulation, and artistic scene creation with multi-view consistency. Applications of 3DGS range from autonomous driving and robotics to virtual and augmented reality, highlighting its adaptability and efficiency. This survey underscores the importance of continued research to refine 3DGS's scalability and applicability, solidifying its role at the intersection of computer graphics and artificial intelligence. © 2025 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection Using Convolutional Neural Network (CNN) 6

Plant Disease Detection Using Convolutional Neural Network (...

引用

6th International Conference on Computational Intelligence and Communication Technologies, CCICT 2024

作者： malik, manav Ronit Rana, Hardik Rani, Yatu Kaur, Gurminder B.M. Institute of Engineering and Technology Sonipat India BMIET Sonipat India

ISBN: (纸本)9798350374629

In today’s world AI is becoming more popular, to improve the quality, and result of their product. So, we have also taken some groundbreaking step in the realm of plant disease detection, utilizing the cutting-edge power of (CNNs). The proposed project aims to address the pressing issue of plant diseases and their detrimental impact on farmers in India. by leveraging deep learning tools and natural language processing techniques, the system provides quick and accurate analysis of plant health based on leaf images, assisting farmers in combating diseases and preventing losses. ©2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

breaking barriers: Unearthing the hindrances to embracing energy economics principles in Nigerian building projects

引用

Energy and built Environment 2025年第3期6卷 534-544页

作者： Oke, Ayodeji Emmanuel Aliu, John Akinpelu, Taiwo marcus Ilesanmi, Oluwadamilare Olamide Alade, Kehinde Temitope Department of Quantity Surveying Federal University of Technology Akure P.M.B. 704 Akure Nigeria Institute for Resilient Infrastructure Systems College of Engineering University of Georgia P.M.B. 200 AthensGA30602-5301 United States Department of Project Management Technology Federal University of Technology Akure P.M.B. 704 Akure Nigeria

The implementation of energy economics principles (EEPs) in sustainable construction and environmental mitigation is widely acknowledged. However, limited research has focused on the hindrances faced in implementing these principles in the context of developing countries. To address this research gap, this study examines these hindrances from the perspective of professionals in the Nigerian construction industry. Existing hindrances were extracted from extant studies using a systematic literature review with predefined inclusion/exclusion criteria which helped formulate the questionnaire. Through the application of exploratory factor analysis, five clusters of hindrance factors were identified, encompassing financial constraints, inadequate policies and regulations, insufficient technological infrastructure, lack of awareness and education and stakeholder-related challenges. Furthermore, the multinomial regression analysis confirmed that the hindrances related to financial constraints, inadequate policies and regulations and insufficient technological infrastructure are the most significant barriers. This study advances scientific knowledge on the hindrances to the adoption of EEPs in Nigerian building projects, providing a comprehensive understanding of the challenges faced in the context of the Nigerian construction industry. Findings from the study will inform policymakers, industry professionals and other stakeholders about the key challenges that require attention and intervention, facilitating the development of targeted strategies and initiatives to overcome these barriers effectively. © 2024

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Early recognition of Alzheimer’s disease using machine learning

Early recognition of Alzheimer’s disease using machine lear...

引用

International Conference on Artificial Intelligence, blockchain, Computing and Security, ICAbCS 2023

作者： Nagaraj, Prajwal Koundinya, Anjan K. Thippeswamy, G. Computer Science and Engineering B.M.S Institute of Technology and Management Bangalore India

ISBN: (纸本)9781032669663

Alzheimer’s Disease (AD), a neurological disorder, is the most common cause of dementia in those over the age of AD must be precisely and soon identified in order to halt the progression of this lethal condition. This article focuses on a machine learning method for mRI images to identify The condition Alzheimer’s. The brain’s hippocampus region is the fundamental objective of the recommended tactic. Use a Gray Level Concidence matrix to extract the hippocampus region’s textural characteristics, including entropy, uniformity, energy, contrast, correlation, and variance (GLCm). Using moment invariants, area and form elements are retrieved. A classifier is utilised to identify distinct phases of AD using error propagation (EbP) of an artificial neural network. An average accuracy of 86.8% is offered by the proposed technique. © 2024 The Author(s).

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Empirical techniques for effort estimation in designing effective mL models

引用

International Journal of Computers and Applications 2025年第2期47卷 226-234页

作者： Padmanabha Reddy, Y.C.A. Kosuru, Sai Sathwik Sirisalla, Nageswara Rao Vivekananda, G.N. Perala, Venkata Akanksha Department of Artificial Intelligence and Machine Learning Chaitanya Bharati Institute of Technology Telangana Hyderabad India Department of CSE B V Raju Institute of Technology Telangana Narsapur India Department of Computer Science and Engineering K.S.R.M. College of Engineering AP Kadapa India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design mL algorithms). The study is novel in terms of how the effort required to create mL models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize mL models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pipeline codes

来源：评论

学校读者我要写书评

暂无评论

Surface properties of friction stir welded dissimilar joints of AA7075 and mg-WE43 alloys:Effect of positional arrangement

引用

Journal of magnesium and Alloys 2025年第1期13卷 398-413页

作者： Tariq Ahmad Nadeem Fayaz Lone Noor Zaman Khan babar Ahmad Arshad Noor Siddiquee Daolun Chen Department of Mechanical Engineering National Institute of Technology SrinagarSrinagar 190006India Department of Mechanical Industrialand Mechatronics EngineeringToronto Metropolitan UniversityTorontoM5B 2K3Canada Department of Mechanical Engineering Jamia Millia IslamiaNew Delhi 110025India

This study investigates the surface properties of the dissimilar AA7075/mg-WE43 joints wherein the effect of positioning the AA7075 on the advancing or retreating sides during friction stir welding(FSW)was *** EbSD analysis revealed that the average grain size reduced from 4.11±0.7μm to 2.04±0.9μm when AA7075 was shifted from advancing to retreating *** results showed that positioning AA7075 on the retreating side significantly reduced the wear rate from 0.41 mm^(3)/Nm to 0.27 mm^(3)/Nm and mitigates the problem of brittle intermetallic compound(ImC)formation,consequently reducing the average *** resistance improved from 77.59 mpy to 56.299 *** higher grain refinement improved wear resistance due to higher grain boundary density and greater chances of formation of protective oxide *** current work thus enhances the practical applicability of AA7075/mg-WE43 welds for lightweighting of automotive structures.

关键词： Surface properties Wear microhardness Corrosion

来源：评论

学校读者我要写书评

暂无评论

Investigating the role of graphic pressure and temporal measures in influencing graphic skills of individuals with autism using a digital platform

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14249-14259页

作者： Verma, Pragya Khandelwal, Kumar bhanu Sharma, Prachi Lahiri, Uttama Centre for Cognitive and Brain Sciences Indian Institute of Technology Gandhinagar Gandhinagar India Electrical Engineering Department Indian Institute of Technology Gandhinagar Gandhinagar India B.M. Institute of Mental Health Ahmedabad India

An ability to create good graphic output requires effective transitive movements related to the use of a tool, e.g., a pen. There is evidence that individuals with autism spectrum disorder (ASD) and neurotypicals show differences in graphic skill. Such differences can be due to anomalies in one’s transitive movements. One needs to quantify such differences through indices e.g., those related to pen-tip pressure and temporal aspects. To study such indices, researchers are shifting their focus to use of digital medium, e.g., pressure tablets from the pen-and-paper based settings for which acquiring these indices might be a challenge. Though pressure tablets have been used by various research groups for graphic execution by individuals with ASD, none have explored these indices for a spiral drawing task that needs precision of performance and is more difficult than drawing of simple shapes. In our present work, we have designed a digitized dot-guided spiral (DDoS) drawing platform offering clockwise spiral drawing task. We chose the clockwise spiral since individuals with ASD may demonstrate torque i.e., a tendency to draw shapes in the clockwise direction. Results of our study with 20 individuals with ASD and 17 typically developing individuals using DDoS platform indicated that for a clockwise spiral drawing, the pen-tip pressure and temporal indices were differentiated among the two participant groups. The indices offered by DDoS platform can provide information to the caregivers and therapists while assisting in identifying deficits and designing individualized intervention, that can benefit the children. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Study on the Effect of Alccofine on the Stability of Soil Slopes

A Study on the Effect of Alccofine on the Stability of Soil ...

引用

NProceedings of the National conference on Advances in Construction materials and management (ACmm 2022)

作者： Vinod, b.R. Sumalatha, J. Akshit Jain, J. Department of Civil Engineering B M S Institute of Technology and Management Bangalore India Department of Civil Engineering M S Ramaiah Institute of Technology Bangalore India

ISBN: (纸本)9789819925513

Slope stability issues have existed throughout history, due to human interference with the natural slope balance of soil. As manmade slopes are increasing, the estimation of factor of safety is the important factor to stabilize the soil slopes. This research work consists of laboratory and software evaluation of a stabilized red soil. The soil was treated with Alccofine with varying stabilizer dosages. Unconfined compression tests were performed to establish the stabilizer’s optimum dosage. The soil slopes were prepared with the ideal dosage of (4%) for 90, 80, 70 and 60 Degree slopes using cube mould of size 150 mm. The samples were then tested using compression machine corresponding to 7 and 3 days of curing periods. From laboratory studies, it was noticed that stabilization of red soil using Alccofine escalates its strength with increasing curing period. The factor of safety was estimated using Plaxis software and also verified with Taylor’s method. The highest values of factor of safety of 2.77 and 2.59 were obtained respectively with Taylor’s method and Plaxis 2D software corresponding to a slope angle of 70 Degree. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Smart question answering system using vectorization approach and statistical scoring method

引用

materials Today: Proceedings 2023年 80卷 3719-3725页

作者： manjunath, T.N. Yogish, Deepa mahalakshmi, S. Yogish, H.K. Information Science & Engineering B M S Institute of Technology &Management Karnataka Bangalore560064 India K S School of Engineering & Management Computer Science & Engineering Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of Master of Computer Applications M S Ramaiah Institute of Technology Karnataka Bangalore560054 India

In this digital era, internet users are increasing day by day to extract information related to various fields such as health, economic, educational, politics and daily needs from Information Retrieval Systems (IRS) such as Google, Ask, Yahoo etc. Information Retrieval (IR) is a conventional method which depends on metadata searching method that is searching of adocuments for information within documents and information about documents. Lot of research in the IR area improves accessing the quality of information. most of the search engines such as Google, Yahoo, Ask Jeeves depends on keyword based query processing mechanism internally which can't handle natural language questions which results in returning long list of documents for a query. The task of users is to manually explore each document to retrieve correct answer which is a time consuming process. To overcome the problems of conventional search engines, smart question answering system comes to play. The objective of Smart Automated Answering system is to impart accurate and valid answers to user question in natural language rather than set of full documents. The Smart Question answering system which accepts user question in Natural language in specific domain and provide short and precise answer using Natural language processing technique, used for pre-processing, normalized term weighting-TF-IDF with cosine similarity approach for document retrieval and enhanced bm25 ranking function to extract answer. The main focus is on decreasing the response time, designing ranking function and giving the pertinent responses to the users’ intent. The system achieved an overall Precision of 93.2%, Recall of 84.3% and F-measure of 88.5% with 80% of Accuracy. © 2021

关键词： Information retrieval

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：