检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Boris Repasky Anthony Dick Ehsan Abbasnejad Australian Institute for Machine Learning (AIML) Department of Computer Science University of Adelaide

ISBN: (纸本)9798331314385

Recent advancements in pre-trained vision models have made them pivotal in computer vision, emphasizing the need for their thorough evaluation and benchmarking. This evaluation needs to consider various factors of variation, their potential biases, shortcuts, and inaccuracies that ultimately lead to disparate performance in models. Such evaluations are conventionally done using either synthetic data from 2D or 3D rendering software or real-world images in controlled settings. Synthetic methods offer full control and flexibility, while real-world methods are limited by high costs and less adaptability. Moreover, 3D rendering can't yet fully replicate real photography, creating a realism gap. In this paper, we introduce BLURD-Benchmarking and learning using a Unified Rendering and Diffusion Model-a novel method combining 3D rendering and Stable Diffusion to bridge this gap in representation learning. With BLURD we create a new family of datasets that allow for the creation of both 3D rendered and photo-realistic images with identical factors. BLURD, therefore, provides deeper insights into the representations learned by various CLIP backbones. The source code for creating the BLURD datasets is available at https://***/squaringTheCircle/BLURD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

6G-Enabled Internet of Things:Vision,Techniques,and Open Issues

引用

computer Modeling in Engineering & sciences 2022年第12期133卷 509-556页

作者： Mehdi Hosseinzadeh Atefeh Hemmati Amir Masoud Rahmani Pattern Recognition and Machine Learning Lab Gachon UniversitySeongnam13120Korea Department of Computer Engineering Science and Research BranchIslamic Azad UniversityTehran***Iran Future Technology Research Center National Yunlin University of Science and TechnologyYunlin64002Taiwan

There are changes in the development of wireless technology systems every decade.6G(sixth generation)wireless networks improve on previous generations by increasing dependability,accelerating networks,increasing available bandwidth,decreasing latency,and increasing data transmission speed to standardize communication *** purpose of this article is to comprehend the current directions in 6G studies and their relationship to the Internet of Things(IoT).Also,this paper discusses the impacts of 6G on IoT,critical requirements and trends for 6G-enabled IoT,new service classes of 6G and IoT technologies,and current 6G-enabled IoT studies selected by the systematic literature review(SLR)method published from 2018 to *** addition,we present a technical taxonomy for the classification of 6G-enabled IoT,which includes self-organization systems,energy efficiency,channel assessment,and ***,according to the articles reviewed,we consider the evaluation factors in this domain,including data transmission,delay,energy consumption,and ***,we focus on open issues and future research challenges in 6G-enabled *** mention important future challenges and directions,we can point to migration,data storage,data resource,data security,data sharing,data offloading,availability,scalability,portability,user experience,reliability,authentication,and authorization.

关键词： Internet of Things 6G wireless network machine learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning model for early diabetes risk prediction using attention-enhanced deep belief networks with highly imbalanced data

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 1933-1955页

作者： Olabanjo, Olusola Wusu, Ashiribo Olabanjo, Olufemi Asokere, Mauton Afisi, Oseni Akinnuwesi, Boluwaji Center for Equitable AI and Machine Learning Systems (CEAMLS) Morgan State University Baltimore 21251 MD United States Department of Mathematics Morgan State University Baltimore MD United States Department of Computer Science Lagos State University Lagos Nigeria Department of Mathematics Lagos State University Lagos Nigeria Department of Cybersecurity University of Derby Derby United Kingdom Department of Philosophy Lagos State University Lagos Nigeria Department of Computer Science Faculty of Science and Engineering University of Eswatini Kwaluseni Swaziland

Diabetes mellitus is a prevalent chronic illness with severe complications that demand timely diagnosis. This study introduces an attention-enhanced Deep Belief Network (DBN) for early diabetes risk prediction, designed to address challenges associated with highly imbalanced datasets. Using a dataset from Sylhet Diabetes Hospital, which includes symptom and demographic information from patients, we applied an ensemble feature selection approach to identify critical predictors. To address the class imbalance, Generative Adversarial Networks (GANs) were used to generate synthetic data, ensuring the model’s robustness in identifying underrepresented cases. Additionally, a hybrid loss function combining cross-entropy and focal loss was implemented to improve classification, especially for hard-to-detect instances. Our results show that the attention-based DBN model, augmented with synthetic data from GANs and optimized with a hybrid loss function, achieves an AUC of 1.00, F1-score of 0.97, precision of 0.98, and recall of 0.95, outperforming several baseline models. This research offers a novel and effective approach for early diabetes detection, demonstrating potential for use as a clinical tool in preventive healthcare settings. © The Author(s) 2025.

关键词： Attention mechanism Deep belief networks (DBN) Diabetes risk Generative adversarial networks (GANs) Hybrid loss function Imbalanced data

来源：评论

学校读者我要写书评

暂无评论

Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval 30

Knowledge Enhanced Pre-training for Cross-lingual Dense Retr...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Hang Gong, Yeyun Liu, Dayiheng Zhang, Shunyu He, Xingwei Lv, Jiancheng Guo, Jian College of Computer Science Sichuan University China Engineering Research Center of Machine Learning and Industry Intelligence China Beihang University China The University of Hong Kong Hong Kong IDEA Research China

ISBN: (纸本)9782493814104

In recent years, multilingual pre-trained language models (mPLMs) have achieved significant progress in cross-lingual dense retrieval. However, most mPLMs neglect the importance of knowledge. Knowledge always conveys similar semantic concepts in a language-agnostic manner, while query-passage pairs in cross-lingual retrieval also share common factual information. Motivated by this observation, we introduce KEPT, a novel mPLM that effectively leverages knowledge to learn language-agnostic semantic representations. To achieve this, we construct a multilingual knowledge base using hyperlinks and cross-language page alignment data annotated by Wiki. From this knowledge base, we mine intra- and cross-language pairs by extracting symmetrically linked segments and multilingual entity descriptions. Subsequently, we adopt contrastive learning with the mined pairs to pre-train KEPT. We evaluate KEPT on three widely-used benchmarks, considering both zero-shot cross-lingual transfer and supervised multilingual fine-tuning scenarios. Extensive experimental results demonstrate that KEPT achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Mitigating Light Detection and Ranging Spoofing Attacks in Connected Vehicle Systems Using machine learning-Based Anomaly Detection 2

Mitigating Light Detection and Ranging Spoofing Attacks in C...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Karthik, R. Marshal, S. Asmitha Shree, R. Vidhya, R. Saranya, N. Gomathy, A. Karunya Institute of Technology and Sciences Deemed to be University Division of Computer Science and Engineering Coimbatore India Kumaraguru College of Technology Department of Computer Science and Engineering Coimbatore India Hindusthan College of Engineering and Technology Department of Artificial Intelligence and Machine Learning Coimbatore India Sri Krishna College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

Light Detection and Ranging (LiDAR) technology is one of the integral parts of systems involving connected vehicles. It provides the necessary two-dimensional accuracy to enable proper navigation, object identification, and collision avoidance through LIDAR technology. However, it is highly used and highly susceptibility to spoofing attacks: interference on signals radiated by LIDAR technology to confuse the Vehicle Perception System. This paper proposes a machine learning-based anomaly detection framework which is capable of discernment and countering of spoofing attacks. The proposed framework collects data from a set of sensors, including cameras, radar, and LiDAR, and is used to formulate a holistic, multidimensional perception model. In that sense, the system utilizes advance machine learning methods, like ensemble classifiers, neural networks, and, more importantly, autoencoders, to find anomalies in real-time that might point to spoofing activity. Simulations and empirical experiments, both benign and adversarial, evaluate the systematic approach to spoofing sophistication levels where LiDAR systems indicate noteworthy improvements in detection accuracy and robustness compared with the traditional techniques, thereby reducing false positives and negatives. In addition, through sensor fusion, the system demonstrates resilience by sustaining consistent performance even through the most complex and dynamic environments. This type of study really highlights that how the power of machine learning would be important for improvement in the cybersecurity framework of connected vehicles scalable and adaptable toward the protection of LiDAR-based systems from growing threats. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

The Audiobook Project Based learning: An Approach Aimed at Improving Students' English Reading Fluency 9

The Audiobook Project Based Learning: An Approach Aimed at I...

引用

9th International Conference on Education and Technology, ICET 2023

作者： Perdani, Yella Dezas Faculty of Humanities Bina Nusantara University Digital Language Learning Center Computer Science Department Bandung Indonesia

ISBN: (纸本)9798350358292

Since one of the objectives of the English in Focus (EIF) class was to help students improve their reading fluency, the research aimed to investigate the effects of an audiobook project on students' reading fluency in the EIF class based on students' perception. The participants were students from two EIF classes, for a total of eighty-three students. The investigation was conducted using a qualitative approach, and the data were gathered using a questionnaire. The questionnaire was divided into two parts: the first consisted of fifteen statements accompanied by a Likert scale, and the second contained two open-ended questions designed to collect more detailed information. Within 7 meetings, the audiobook implementation project was successfully finished. After finishing the audiobook project, the students' reading fluency and experience were significantly enhanced, as demonstrated by the results of the research. During the course of working on the audiobook project, students were able to demonstrate correct intonation and articulation when reading English text, learned new words, and improved their ability to work together on the project by discussing it with the other members of their group. In conclusion, based on students' perception, the research findings indicate that implementing an audiobook project to improve reading fluency is viable. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Utilising SkyScript for Open-Vocabulary Categorization, Extraction, and Captioning to Enhance Multi-Modal Tasks in Remote Sensing

引用

Remote Sensing in Earth Systems sciences 2024年第3期7卷 149-158页

作者： Nagaraj, Saranya Sivakumar, Shanmuga Priya Annabel, Lawrence Sherly Puspha Joshi, Vilas Ramrao Patil, Mithun Baswaraj Patil, Vishal Ratansing SRM Institute of Science and Technology School of Computing SRM Institute of Science and Technology Department of Artificial Intelligence and Machine Learning St. Joseph’s College of Engineering Department of Computer Engineering ISBM College of Engineering Department of Computer Science and Engg N K Orchid College of Engg and Technology Solapur Department of CSE (AIML) Pimpri Chinchwad College of Engineering Nigdi

The SkyScript dataset was developed by integrating large-scale remote sensing images from Google Earth Engine with geo-tagged semantic data from OpenStreetMap. This open-access dataset, consisting of 2.6 million image-text pairs covering 29,000 unique tags, facilitates various remote sensing tasks such as cross-modal retrieval, image captioning, and classification. The dataset ensures global representation and semantic diversity, although it exhibits a higher concentration of high-resolution images from the USA and Europe due to licencing constraints. The images, sourced from multiple collections with varying ground sampling distances, are paired with captions generated using a combination of rule-based methods and logistic regression models for tag classification. Experiments demonstrate that models pre-trained on SkyScript outperform those trained on other datasets in zero-shot classification and fine-grained attribute recognition, highlighting its potential for advancing vision-language models in remote sensing applications. Future improvements could involve enhancing geographic coverage and refining caption quality using advanced language models. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Image captioning Remote sensing Sampling distance Vision language

来源：评论

学校读者我要写书评

暂无评论

Decoding Sentiments: Harnessing the Power of NLP for Comparative Analysis of ML Algorithms

Decoding Sentiments: Harnessing the Power of NLP for Compara...

引用

International Conference on Computing and machine learning, CML 2024

作者： Varma, Nadimpallli Madana Kailash Harshini, Marisetti Madhan Mohan, R. Arora, Gagandeep Singal, Swati Student Department of Artificial Intelligence & Machine Learning Vardhaman College of Engineering Telangana Hyderabad501286 India Department of Computer Science and Engineering Faculty of Engineering Annamalai University Chidambaram India Head of the Department Professor Department of Artificial Intelligence & Machine Learning Vardhaman College of Engineering Telangana Hyderabad501286 India Sharda University Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819765874

machine learning algorithms have become pervasive in diverse applications, revolutionizing various domains. However, the abundance of algorithms, each designed for specific purposes, poses a challenge for both novice users and experts in selecting the most suitable model. This research addresses this issue through a comprehensive analysis, leveraging Natural Language Processing (NLP) techniques and the powerful Sentiment decoding libraries. Researcher’s comments from published papers were analyzed using the various approaches, presenting a novel approach that maps algorithm scores based on adjectives. Results indicate that Support Vector machine consistently outperforms other algorithms, providing valuable insights for practitioners. Our research contributes to a systematic evaluation framework, aiding researchers in algorithm selection. This paper presents a study focused on sentiment analysis, aimed at identifying the most effective machine learning algorithm among various contenders. Traditional conclusions regarding the superiority of specific algorithms are often based on their performance on specific datasets or tasks, which may not provide a comprehensive comparison due to the diverse nature of algorithms. To address this, a standard dataset encompassing the advantages and disadvantages of all algorithms is utilized. Three approaches employing VADER, TextBlob, and transformers are employed for sentiment analysis. Results consistently highlight SVM as the top-performing algorithm, followed by Associative analysis. This standardized conclusion contributes to the broader understanding of sentiment analysis within the realm of machine learning algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Smart Vehicle Monitoring System Using Real-Time Data Processing and Advanced Sensor Integration 5

A Smart Vehicle Monitoring System Using Real-Time Data Proce...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Sathish, M. Prabha Devi, D. Kanchana, R. Pranesh, R.K. Kumaraguru College of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Department of Computer Science and Engineering Tamil Nadu Sathyamangalam India Sphoorthy Engineering College Department of Artificial Intelligence and Machine Learning Telangana Hyderabad India Kumaraguru College of Technology Department of Information Science and Engineering Tamil Nadu Coimbatore India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379945

The 'Smart Vehicle Monitoring System' presents a comprehensive solution for enhancing road safety and user authentication in the realm of modern transportation. This system integrates advanced technologies to monitor crucial aspects of vehicle usage, ensuring both the rider's safety and the vehicle's safety. The core functionalities encompass monitoring the usage of safety gear such as helmets and detecting alcohol consumption. User authentication is achieved through a combination of fingerprint recognition and Radio-frequency identification (RFID). This multi-layered approach ensures that only authorized individuals can operate the vehicle. The proposed system further extends its capabilities to monitor essential vehicle parameters, including tire pressure and fuel levels. In the event of an accident, a vibration sensor is employed to swiftly detect impact, triggering an alert system through GSM communication. This timely notification ensures prompt assistance and emergency response. Wireless communication plays a vital role in the system, with the helmet connected to an Arduino Mega via the ESP protocol. This acilitates real-time data exchange, allowing for seamless integration of various components. To enhance user interface and information dissemination, the system utilizes an LCD to present real-time status updates. Additionally, the integration of a GPS module enables the sharing of live location data, contributing to improved navigation and overall safety. In conclusion, the Smart Vehicle Monitoring System not only prioritizes the safety of the rider but also addresses authentication concerns and provides a holistic approach to vehicle monitoring. Through the amalgamation of cutting-edge technologies, this system aims to redefine the standards of safety and security in contemporary transportation. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Titanic Survivors Prediction Analysis Using machine learning Algorithms 1

Titanic Survivors Prediction Analysis Using Machine Learning...

引用

1st International Conference on Computational Intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Devamane, Shridhar B. Abhijith, B.H. Purushotham, Bhushan Ravindranath, R.C. Lakshmikantha, G.C. Udayaprasad, P.K. Global Academy of Technology Department of Computer Science and Engineering Bangalore India Global Academy of Technology Department of Artificial Intelligence and Machine Learning Bangalore India Global Academy of Technology Department of Ai and Ml Bangalore India

ISBN: (纸本)9798350365405

machine learning algorithms are computational models that allow computers to acquire knowledge and improve performance on a task by automatically learning patterns and rules from input data provided by the user. In this work we are predicting the Titanic disaster survivors based on a particular dataset. Based on characteristics such as age, sex, ticket class, etc., we applied the Support Vector machine, K-Nearest Neighbors, Decision Tree, and Random Forest algorithm to identify which passenger would survive. © 2024 IEEE.

关键词： Adversarial machine learning

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：