检索结果-内蒙古大学图书馆

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： R Shashidhar R Manasa K M Megha P Priyanga A S Manjunath M Roopa Department of Electronics and Communication Engineering JSS Science and Technology University Mysuru INDIA Department of Electronics and Communication Engineering Dayananda Sagar College of Engineering Bengaluru INDIA Department of Computer Science and Engineering(AI & ML) RNS Institute of Technology Bengaluru INDIA Department of Computer Applications JSS Science and Technology University Mysuru INDIA

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

In the field of medical diagnosis, the increasing occurrence of brain tumors calls for creative approaches to detect and intervene at early stages. This proposed work focus on the Efficient Net (EffNet) architecture to address the challenges associated with brain tumour recognition and sorting from Magnetic Resonance Imaging (MRI) scans. The main objectives are outlined to develop a robust model capable of discriminating between various tumour types and normal brain tissues. Four distinct classes—glioma tumour, pituitary tumour, meningioma tumour, and no tumour compose the dataset, providing diversity for training and evaluation. Using projected method got the accuracy of 98.08% accuracy. Our proposed method detects the all the four classes effectively.

关键词： Training Accuracy Image recognition Magnetic resonance imaging Brain modeling Medical diagnosis Information technology Medical diagnostic imaging Tumors Sorting

来源：评论

学校读者我要写书评

暂无评论

Investigating Large Language Models for Prompt-Based Open-Ended Question Generation in the Technical Domain

引用

SN computer science 2024年第8期5卷 1128页

作者： Maity, Subhankar Deroy, Aniket Sarkar, Sudeshna Centre of Excellence in Artificial Intelligence (AI) Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India

We explore the automated generation of open-ended questions from technical domain textbooks. These questions are more diverse than those typically examined in the field of question generation (QG) for reading comprehension. To facilitate this endeavor, we curate engineeringQ, a prompt-based QG dataset that contains triples of (1) Context: a segment from which the questions are formed;(2) Prompt: a prompt is a concise and specific keyphrase that serves as a short guiding reference to generate a question based on a given context;(3) Question: a question that aligns with the context and is coherent with the prompt. We evaluate the performance of several fine-tuned encoder-decoder based large language models (LLMs), including Pegasus, BART, Flan-T5, and T5 on engineeringQ. We introduce a novel prompt-tuning method for these encoder-decoder based LLMs. We also investigate the potential of general-purpose decoder-only LLMs such as GPT-3.5 Turbo, text-davinci-003, and GPT-4 in zero-shot setting. Evaluation involves automated metrics and human evaluation by domain experts. Extending our study beyond engineeringQ, we apply these methods to subjects such as biology, chemistry, earth science, and physics. Furthermore, we investigate the potential for domain adaptation by fine-tuning the best-performing LLM on school-level subjects and assessing its effectiveness on undergraduate-level computer science and information technology subjects for zero-shot and few-shot QG. To gain insights into generated question complexity, we also utilize Bloom’s revised taxonomy to categorize questions into different levels, enhancing our understanding of their educational value. Experimental results highlight T5_LARGE’s superiority in automated evaluation metrics and text-davinci-003’s excellence in human evaluation metrics in engineeringQ. For subjects such as biology, chemistry, earth science, and physics, Flan-T5_BASE excels in automated metrics, while GPT-4 leads in human

关键词： Automated question generation (AQG) Bloom’s revised taxonomy Education Large language models (LLMs) Prompt

来源：评论

学校读者我要写书评

暂无评论

Prognostic Phenotype Clustering of Uterine Sarcoma Patients

Prognostic Phenotype Clustering of Uterine Sarcoma Patients

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Zhang, Tuao Yuan, Suzhen Zhou, Xue Wang, Wenwen Zhu, Xin Graduate School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Wuhan China Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Tokyo Japan

ISBN: (纸本)9798350350548

Uterine sarcoma is a rare but highly aggressive malignancy with poor prognosis. In this study, prognostic phenotypes corresponding to the end point of mortality were explored by unsupervised machine learning (ml) on training (n = 1985) and validation (n = 498) datasets. The data were extracted from patients with uterine sarcoma in the Surveillance, Epidemiology, and End Results (SEER) database. A decision-making process of phenotype identification was performed and the findings were compared with existing research. Three phenotypes associated with stratified levels of mortality risks (high, intermediate and low) were identified. Kaplan-Meier survival analysis revealed significant differences among these phenotypes (pairwise comparison p © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Development and Implementation of a Virtual Reality Simulation for an Immersive College Environment Using the Unity Game Engine

Development and Implementation of a Virtual Reality Simulati...

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Ashwin Raj Lendalay Rupesh Pabba Sudheer Reddy Katta Mohd Afnan Ahmed R U Karthik Kowdodi Siva Prasad Computer Science With AI & ML Hyderabad Institute of Technology and Management Hyderabad India Mechanical Engineering Hyderabad Institute of Technology and Management Hyderabad India

ISBN: (数字)9798350364569

ISBN: (纸本)9798350364576

Virtual Reality (VR) simulation has emerged as a transformative technology with applications spanning various fields such as education, healthcare, training, and entertainment. This research paper explores the advancements, methodologies, and impacts of VR simulation, providing a comprehensive review of current technologies and their *** paper details the development and implementation of a Virtual Reality (VR) walkthrough simulation of a college environment using the Unity game engine. The project aims to offer users an immersive and interactive experience that closely mirrors the sensation of navigating through a physical establishment. The simulation integrates lifelike visuals, intuitive navigation, and interactive elements to create a compelling virtual environment. Through this innovative approach, users can experience a realistic and engaging representation of the college, enhancing their understanding and exploration of the space. Traditional architectural models, typically rendered with pen-and-paper blueprints or clay models, often lack detailed visualization and feasibility for quick modifications. This research explores the advantages of utilizing Virtual Reality (VR) for visualizing architectural models of college environments with significantly enhanced detail, both exterior and interior. VR technology allows for the immediate identification and correction of errors, facilitating rapid and efficient updates. Unlike traditional methods, which require redrawing entire blueprints for minor changes, VR’s layered structure permits individual modifications without impacting the whole model. Leveraging the Unity game engine, multiple architects can collaborate seamlessly, working together with clients to develop a satisfactory and detailed VR model of the building. This approach not only improves design accuracy but also enhances collaborative efforts, demonstrating the substantial benefits of VR in modern architectural practices.

关键词： Solid modeling Visualization Accuracy Navigation Virtual environments Games Space exploration Stakeholders Engines Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cybersecurity Through Combined Convolutional Neural Network-Gated Recurrent Unit Approach for Distributed Denial of Service Attack Detection

Enhancing Cybersecurity Through Combined Convolutional Neura...

引用

Innovative engineering sciences and Technological Research (ICIESTR), International Conference on

作者： Shilpa Choudhary Chris Harry Kandikattu Sandeep Kumar MVV Prasad Kantipudi Munish Kumar Department of Computer Science and Engineering(AI & ML) Neil Gogte Institute of Technology Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Educational Foundations Vijayawada India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune

ISBN: (数字)9798350348637

ISBN: (纸本)9798350348644

In cyber-security, integrating GRU with CNN has proven to be a solid and effective method for detecting Distributed Denial of Service (DDoS) attacks. This work presents a robust approach that combines the temporal sequence modelling capabilities of GRUs with the spatial feature extraction capabilities of CNNs. Integrating these two deep learning architectures provides a comprehensive solution, allowing precise detection and reduction of harmful activity inside network traffic. This work enhances DDoS detection methods and emphasizes the increasing importance of using advanced deep learning techniques to strengthen cyber-security measures. The suggested methodology effectively tackles the dynamic nature of DDoS attacks by leveraging the strengths of CNNs and GRUs. This approach offers a diverse and efficient way to protect network integrity. Integrating CNN and GRU in DDoS detection is crucial in strengthening network security against emerging attacks in the ever-changing digital ecosystem. This study highlights the flexibility and effectiveness of incorporating sophisticated neural network structures to improve the robustness of cyber-security systems in response to changing threats.

关键词： Neural networks Ecosystems Telecommunication traffic Network security Denial-of-service attack Solids Feature extraction Robustness Convolutional neural networks computer crime

来源：评论

学校读者我要写书评

暂无评论

Multi-camera Enhanced Real-Time Content-Aware Vehicle Detection 7th

Multi-camera Enhanced Real-Time Content-Aware Vehicle Detect...

引用

7th IFIP TC 12 International Conference on Computational Intelligence in Data science, ICCIDS 2024

作者： Mafaz, Mohamed Karthiga, I. Priya, S. Sharon Department of AI and Data Science GST Rd Perungalathur Chennai600063 India Department CSE Grand Southern Trunk Rd Vandalur Chennai603210 India Department Computer Science Engineering Grand Southern Trunk Rd Vandalur Chennai603210 India

ISBN: (纸本)9783031699818

This paper introduces an open-source solution for real-time object awareness in the context of intelligent vehicles, designed to seamlessly adapt to simulation environments. The system transcends traditional vehicle detection, offering a comprehensive framework that includes object classification, precise location, and rotation estimation. Leveraging a multi-camera setup, our approach provides a comprehensive understanding of the surrounding environment, extending beyond vehicle recognition to include various other objects. What sets our solution apart is its capability to efficiently reformat and transition to simulation environments like Blender, enabling integration and testing within virtual contexts. The core components of our system encompass data collection, preprocess-ing, deep learning model selection, Use of Look up table, model training, efficient inference, and post-processing techniques. Designed for open-source collaboration, this solution is positioned for continuous improvement, adaptation to evolving needs, and addressing emerging challenges in the field of intelligent transportation and related domains. This paper represents a foundational step towards establishing an accessible and adaptable real-time object awareness system, encouraging innovation and research in the realm of intelligent vehicles and their applications, both in the real world and in simulated environments. © IFIP International Federation for Information Processing 2024.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Intrusion Prediction Using Machine Learning Techniques

Intrusion Prediction Using Machine Learning Techniques

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： D. Divya Priya Sabitha Valaboju D Paulraj Ajmeera Kiran Nagaram Ramesh Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Department of Computer Science and Engineering (AI & ML) CVR College of Engineering Hyderabad Department of Computer Science and Engineering R.M.K. Engineering College Tamil Nadu India Department of Information Technology BVRIT Narsapur

In this day and age, substantial advances in the realm of security are being achieved at a quick pace. Because of the unexpected increase in the number of internet users, there is an increase in issues connected to hardware failure, software deployment failure, and memory allocation, which directly or indirectly results in data loss. [1] Network invasions entail the theft of important network resources, usually always through exploiting flaws in the group of networks and/or their data. Several hardware, software, and network elements can all contribute to network intrusion. Ineffective communication protocols, certain devices following their own protocol, proper file size constraints not defined, and poor firing are all software factors. Outdated routers, too many devices connected to a single router, and incompatible hardware are all examples of hardware factors. Network hacking, bad network architecture, and oversubscription are examples of unrelated factors. Our study intends to analyse the dataset, which includes all of the aforementioned parameters, using Ad boost classification, Stacking classification, Random Forest classifier, and Gaussian Nave Bayes Classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Mood Detection: Real-Time Emotion Analysis for Human-computer Interaction Using Deep Learning

Smart Mood Detection: Real-Time Emotion Analysis for Human-C...

引用

2025 International Conference on Artificial Intelligence and Data engineering, aiDE 2025

作者： Chandrappa, S. Banerjee, Tapabrata Saha, Sohan Zaid, Mohd Aditya Pai, H. Guru Prasad, M.S. Rajesh, I.S. Dept. of Computer Science and Engineering Bengaluru India Bengaluru India MIT Art Design and Technology University Department of CSE Pune India Department of Computer Science and Engineering Dehradun India BMS Institute of Technology and Management Dept. of AI & ML Bengaluru India

ISBN: (纸本)9798331527518

A convolutional neural network (CNN)-based face emotion recognition system that analyzes human emotions in real-time, including happy, sorrow, rage, and surprise, is described. Existing approaches often struggle with accurately recognizing subtle or complex emotions due to limited feature extraction capabilities and the need for large, diverse training datasets. Additionally, they face challenges in adapting to real-world conditions, such as variations in lighting, angles, and occlusions. In order to improve the model's generalizability, the proposed research used a preprocessing pipeline that included gray scale conversion, scaling, normalization, and augmentation techniques including rotation and flipping on a labeled and balanced dataset of facial photos. Dropout and regularization techniques were used to reduce over fitting, and the CNN architecture was meticulously adjusted to maximize speed. High accuracy and resilience across emotion categories are demonstrated by preliminary results, indicating the model's potential for real-world uses in security surveillance, healthcare, and human-computer interaction. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent ai within a Metamodel Control System for Financial Crisis Management System 5

Intelligent AI within a Metamodel Control System for Financi...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Raajya Vardhini, A. Rawat, Ruchira Supreeth, B.R. Murugan, V.G. Krishna Reddy, P. Manikandan, G. V.S.B Engineering College Department of Computer Science and Engineering Karur India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Oxford Degree and PG College Sir. M. Visveshwaraiah Layout Department of Computer Science Ullal Bangalore India Department of Management Studies Andhra Pradesh Madanapalle India St. Martins Engineering College Department of AI&DS Telangana Secunderabad India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Thandalam India

ISBN: (纸本)9798350351378

In an effort to revolutionize the detection, management, and prevention of financial crises, this study investigates the use of Intelligent ai inside a Metamodel Control System for Crisis Management. Data collection and preprocessing, metamodeling, real-time monitoring and alerting, case studies, simulations, optimization, regulatory compliance, and ethical concerns are all part of the study's approach. The results show the strong performance of the metamodel, with high values for accuracy, precision, recall, and F1-score. Consistent with the concepts of adaptive control, real-time monitoring and alerting provide instantaneous early warnings of potential crises. The framework has been shown by case studies to be consistent with conventional economic models. The framework's potential to promote financial resilience and the educated decision-making process is underlined. Real-world applications, cutting-edge ai methods, ethical issues, and global cooperation are all potential next steps. More stable and prosperous economic futures are within reach, according to the insights gained from this study on the role technology plays in financial resilience. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Choi, Euntae Lim, Youshin Kim, Byeong-Yeol Kim, Hyung Yong Lee, Hanbin Lim, Yunkyu Yu, Seung Woo Yoo, Sungjoo Seoul National University Department of Computer Science and Engineering Korea Republic of 42dot.ai Hyundai Motor Company Seoul Korea Republic of

ISBN: (纸本)9781728163277

Recent self-supervised automatic speech recognition (ASR) models based on transformers are showing best performance, but their footprint is too large to be trained on low-resource environments or deployed to edge devices. Knowledge distillation (KD) can be employed to reduce the model size. However, setting embedding dimension of teacher and student network to different values makes it difficult to transfer token embeddings for better performance. To mitigate this issue, we present a novel KD method in which student mimics the prediction vector of teacher under our proposed masked token similarity transfer (MTST) loss where the temporal relation between a token and the other unmasked ones is encoded into a dimension-agnostic token similarity vector. Under our transfer learning setting with a fine-tuned teacher, our proposed methods reduce the model size of student to 28.3% of teacher's while word error rate on test-clean subset in LibriSpeech corpus is 4.93%, which surpasses prior works. Our source code will be made available. © 2023 IEEE.

关键词： Distillation

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：