检索结果-内蒙古大学图书馆

Global Conference for Advancement in Technology (GCAT)

作者： V. Saravanan Talluri Upender E. D. Kanmani Ruby P. Deepalakshmi Desidi Narsimha Reddy Ananthi S N Department of Nano Electronics Materials and Sensors Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Department of CSE CMR College of Engineering and Technology. Medchal Hyderabad Telangana Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science Technology School of Computing Director - Accreditation and Ranking Kalasalingam Academy of Research and Education Krishnankoil Tamil Nadu India Data Consultant (Data Governance Data Analytics: Enterprise Performance Management AI&ML) Soniks Consulting LLC Texas USA Department of Computer Science and Engineering S.A. Engineering College Chennai

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

The dynamic nature of cyber threats demands that threat detection mechanisms be continuously improved in order to protect digital assets and infrastructures. In cybersecurity, this study investigates the use of machine learning (ML) algorithms for enhanced threat detection. This work intends to improve threat detection systems' accuracy, speed, and adaptability by utilizing ML algorithms' capabilities. The abstract begins by outlining the significance of machine learning in transforming traditional cybersecurity measures. It highlights the limitations of conventional signature-based methods, which often fail to detect novel and sophisticated threats. In contrast, ML-based approaches offer dynamic and proactive defenses capable of identifying previously unseen attack vectors. Furthermore, the paper delves into the practical implementation of ML models in real-world cybersecurity environments. It covers data collection and preprocessing techniques critical for training accurate and reliable models, as well as the challenges associated with maintaining and updating these models to adapt to evolving threat landscapes. The importance of feature selection and engineering in improving model performance is also emphasized. To validate the effectiveness of ML approaches, the study presents case studies and experimental results from various cybersecurity applications. The abstract concludes by addressing the future prospects and potential advancements in machine learning for cybersecurity. It discusses the role of emerging technologies, such as deep learning and federated learning, in enhancing threat detection capabilities. Additionally, it considers the ethical and privacy concerns associated with deploying ML models in cybersecurity and the need for robust governance frameworks. In summary, this study presents a thorough analysis of machine learning techniques for enhanced threat detection in cybersecurity, including useful applications, advantages, and difficulties.

关键词： Adaptation models Machine learning algorithms Accuracy Heuristic algorithms Machine learning data collection Threat assessment data models Vectors computer security

来源：评论

学校读者我要写书评

暂无评论

A preliminary approach to evolutionary multitasking for dynamic flexible job shop scheduling via genetic programming 20

A preliminary approach to evolutionary multitasking for dyna...

引用

2020 Genetic and Evolutionary Computation Conference, GECCO 2020

作者： Zhang, Fangfang Mei, Yi Nguyen, Su Zhang, Mengjie School of Engineering and Computer Science Victoria University of Wellington New Zealand Centre for Data Analytics and Cognition La Trobe University Melbourne Australia

ISBN: (纸本)9781450371278

Genetic programming, as a hyper-heuristic approach, has been successfully used to evolve scheduling heuristics for job shop scheduling. However, the environments of job shops vary in configurations, and the scheduling heuristic for each job shop is normally trained independently, which leads to low efficiency for solving multiple job shop scheduling problems. This paper introduces the idea of multitasking to genetic programming to improve the efficiency of solving multiple dynamic flexible job shop scheduling problems with scheduling heuristics. It is realised by the proposed evolutionary framework and knowledge transfer mechanism for genetic programming to train scheduling heuristics for different tasks simultaneously. The results show that the proposed algorithm can dramatically reduce the training time for solving multiple dynamic flexible job shop tasks. © 2020 Owner/Author.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Robust and Secure Resource Allocation for ISAC Systems: A Novel Optimization Framework for Variable-Length Snapshots

arXiv

引用

arXiv 2022年

作者： Xu, Dongfang Yu, Xianghao Kwan Ng, Derrick Wing Schmeink, Anke Schober, Robert Germany Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The School of Electrical Engineering and Telecommunications The University of New South Wales Australia Information Theory and Data Analytics RWTH Aachen University Germany

In this paper, we study the robust resource allocation design for secure communication in an integrated sensing and communication (ISAC) system. A multi-antenna dual-functional radar-communication (DFRC) base station (BS) serves multiple single-antenna legitimate users and senses for targets simultaneously, where already identified targets are treated as potential single-antenna eavesdroppers. The DFRC BS scans a sector with a sequence of dedicated beams, and the ISAC system takes a snapshot of the environment during the transmission of each beam. Based on the sensing information, the DFRC BS can acquire the channel state information (CSI) of the potential eavesdroppers. Different from existing works that focused on the resource allocation design for a single snapshot, in this paper, we propose a novel optimization framework that jointly optimizes the communication and sensing resources over a sequence of snapshots with adjustable durations. Besides, artificial noise (AN) is exploited by the BS for joint sensing and physical layer security provisioning. To this end, we jointly optimize the duration of each snapshot, the beamforming vector, and the covariance matrix of the AN for maximization of the system sum secrecy rate over a sequence of snapshots while guaranteeing a minimum required average achievable rate and a maximum information leakage constraint for each legitimate user. The resource allocation algorithm design is formulated as a non-convex optimization problem, where we account for the imperfect CSI of both the legitimate users and the potential eavesdroppers. To make the problem tractable, we derive a bound for the uncertainty region of the potential eavesdroppers' small-scale fading based on a safe approximation, which facilitates the development of a block coordinate descent-based iterative algorithm for obtaining an efficient suboptimal solution. Simulation results illustrate that the proposed scheme can significantly enhance the physical layer securi

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

AEFNet: Adaptive Scale Feature Based on Elastic-and-Funnel Neural Network for Healthcare Representation

AEFNet: Adaptive Scale Feature Based on Elastic-and-Funnel N...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yang Liu Jialun Wu Yuhua Wei Bing Mao Chen Li Tieliang Gong School of Computer Science and Technology National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an Shaanxi China

ISBN: (纸本)9781665429825

Healthcare Representation learning has been a key element to achieving state-of-the-art performance on healthcare prediction. Recent advances based Electronic Healthcare Records(EHRs) are mostly devoted to extracting temporal progression patterns with temporal model and their variants. Although these works have shown excellent performances in healthcare prediction, the unified temporal pattern may not be suitable for individuals in all healthcare conditions. Moreover, some studies ususally introduce complex Deep Neural Networks models and medical prior knowledge to get compact representation, causing great computational burden. In this paper, we propose a general health care representation model, named AEFNet. We only leverage three simple convolution operations and a set of up and down sampling to ensure performance and model complexity equally, which achieves adaptively extract distinct individual key feature in a light manner. AEFNet can shrink and refine highly suitable scale information adaptively and comletely. Breaking traditional fixed convolution scale or multi-scale, AEFNet achieves scale adaptively to extract the most significant information and context relationship. Finally, We validate our method on the public dataset MIMIC-III, and the evaluation results indicate that our method can significantly outperform other remarkable baseline models.

关键词： Adaptation models Convolution Computational modeling Neural networks MIMICs Medical services Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Novel Antenna Designs for High data Rate Body-Centric Communications in Wearable Devices

Novel Antenna Designs for High Data Rate Body-Centric Commun...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Ishika Soni Manjunatha R V Vijaya Baskar Daljeet Pal Singh Komal Parashar Niranjan Panda Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India School of Sciences Data analytics and Mathematical Sciences JAIN (Deemed to be University) Bangalore Karnataka India Department of Electronics and Communication Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

There is an ever-increasing demand for high data rate communication embedded in wearable devices owing to the exponential growth of smart devices and related technology. The human body is always around, which means that traditional antenna designs will not work well with body-centric communications operations, as signal loss and interference from the presence of the human body must be addressed. This project addresses this limitation by designing new body-centric communications antenna designs for incorporation into wearable devices. Antennas proposed in the literature can use novel techniques that reach high data rates while providing reliable communication links and features like compactness, low power consumption, and multi-band functionalities. The designs are optimized to ensure that the human body has a minimal effect on the signal enhancing performance and stability. The antennas are designed and simulated using advanced simulation tools and validated in the lab. These findings demonstrate the remarkable advantages of high-speed data transmission and link quality compared to traditional antennas. It contributes to developing novel antenna designs that wearable device manufacturers can incorporate into high data rate body-centric communications, enabling dramatically improved performance within tight space constraints. This will make it possible to create next-generation wearable devices with communication functions for applications ranging from healthcare and sports to virtual reality.

关键词： Performance evaluation Training Design methodology Transmitting antennas Clothing Virtual reality Stability analysis Reliability Wearable devices Antennas

来源：评论

学校读者我要写书评

暂无评论

DARWIN 1.5: Large Language Models as Materials science Adapted Learners

arXiv

引用

arXiv 2024年

作者： Xie, Tong Wan, Yuwei Liu, Yixuan Zeng, Yuchen Wang, Shaozhou Zhang, Wenjie Grazian, Clara Kit, Chunyu Ouyang, Wanli Zhou, Dongzhan Hoex, Bram School of Photovoltaic and Renewable Energy Engineering University of New South Wales KensingtonNSW Australia GreenDynamics SydneyNSW Australia Department of Linguistics and Translation City University of Hong Kong Hong Kong Department of Computer Science University of Wisconsin-Madison MadisonWI United States Shanghai Artificial Intelligence Laboratory Shanghai China School of Computer Science and Engineering University of New South Wales KensingtonNSW Australia School of Mathematics and Statistics University of Sydney CamperdownNSW Australia DARE ARC Training Centre in Data Analytics for Resources and Environments CamperdownNSW Australia

Materials discovery and design aim to find compositions and structures with desirable properties over highly complex and diverse physical spaces. Traditional solutions, such as high-throughput simulations or machine learning, often rely on complex descriptors, which hinder generalizability and transferability across different material systems. Moreover, These descriptors may inadequately represent macro-scale material properties, which are influenced by structural imperfections and compositional variations in real-world samples, thus limiting their practical applicability. To address these challenges, we propose DARWIN 1.5, the largest open-source large language model tailored for materials science. By leveraging natural language as input, DARWIN eliminates the need for task-specific descriptors and enables a flexible, unified approach to material property prediction and discovery. Our approach integrates 6M material domains papers and 21 experimental datasets from 49,256 materials across modalities while enabling cross-task knowledge transfer. The enhanced model achieves up to 59.1% improvement in prediction accuracy over the base LLaMA-7B architecture and outperforms SOTA machine learning approaches across 8 materials design tasks. These results establish LLMs as a promising foundation for developing versatile and scalable models in materials science. © 2024, CC BY.

关键词： Materials properties

来源：评论

学校读者我要写书评

暂无评论

Automation Through Machine Learning: Reinvigorating Cyber Security

Automation Through Machine Learning: Reinvigorating Cyber Se...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Jayashree V. Bagade Sukhvinder Singh Dari Rekha Dhivrani Santosh Chowhan G. Ravivarman V Janakiraman Department of Information Technology Vishwakarma Institute of Technology Pune india Symbiosis Law School Nagpur Symbiosis International Pune India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Data Analytics and Mathematical Sciences Jain (Deemed to be University) Bangalore Karnataka India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cyber security is predicated heavily on manual efforts to fight malicious assaults, but such processes are increasingly turning into overwhelmed by means of the quantity of threats - a hassle worsened in the course of the global COVID-19 pandemic. This has highlighted the importance of leveraging device studying (ML) to automate cyber protection methods. In this article, we speak how ML may be used to optimize the detection, prevention, and remediations of malicious assaults in an extensive kind of applications and offerings. We discover the various procedures being evolved that may assist make the identity of threats greater accurate and greater effortlessly to be had. We additionally recollect the capacity challenges associated with the software of ML strategies, along with the potential for unfair bias in opposition to positive instructions of customers, and become aware of methods for addressing those issues. Our end emphasizes the significance of leveraging ML in order to enable automation in cyber safety, as well as to make sure the detection of state-of-the-art new threats.

关键词： Automation Pandemics Prevention and mitigation Manuals Machine learning Turning Software Security Protection computer crime

来源：评论

学校读者我要写书评

暂无评论

Leveraging CNN-Transformer Hybrid Architecture for Accurate Breast Tumor Segmentation in Mammograms 8

Leveraging CNN-Transformer Hybrid Architecture for Accurate ...

引用

8th International Women in data science Conference at Prince Sultan University, WiDS-PSU 2025

作者： Ali, Mudassar Tahir, Muhammad Zeeshan Mariam, Iqra Nawaz, Khadija Mahmood, Tariq Chelloug, Samia Allaoua College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Zhejiang University Department of Computer Science and Technology Hangzhou310027 China School of Electronics and Information Engineering Liaoning University of Technology Jinzhou121000 China University of Education Faculty of Information Sciences Vehari61100 Pakistan Artificial Intelligence and Data Analytics Lab Ccis Psu SA Riyadh Saudi Arabia Ccis Pnu Department of Information Technology SA Riyadh11671 Saudi Arabia

ISBN: (纸本)9798331520922

Breast cancer detection through mammograms is very crucial for early diagnosis, and tumor segmentation is an important step in treatment planning. This paper proposes a novel approach by combining CNNs with transformers, which we call the Hybrid CNN + Transformer model, for the task of breast tumor segmentation. It leverages the strengths of CNN s in local feature extraction to capture fine details, such as tumor boundaries, and combines them with transformers that model long-range dependencies and contextual relationships across images for the exact delineation of tumor regions in complex tissue structures. Our methodology will be tested on the high-quality mammog-raphy dataset annotated with both benign and malignant lesions, the so-called INbreast dataset. Herein, the CNN backbone-first for instance, ResNet or EfficientNet-extracts the input mammo-gram hierarchically;features are fed into a transformer layer in order to capture global dependencies, after which the final segmentation mask is generated by using a U-Net style decoder for a pixel-wise tumor classification. The segmentation accuracies of our models demonstrated the significant improvement achieved in tumor segmentation, using Hybrid CNN + Transformer when compared with tra-ditional CNN-based models on challenging tumor boundaries and complex tissue patterns. An accurate, robust, completely automatic method for tumor segmentation will thus enable improved diagnostic feasibility on clinical grounds. Furthermore, the combination of learning at both local and global features improved generalizability to previously unseen mammogram images and therefore strengthened clinical applicability. © 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

Investigating The Role of Deep Learning Technology in Health Care System

Investigating The Role of Deep Learning Technology in Health...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Girija Rani Karetla Tarigoppula V. S. Sriram Kapil Joshi Mehul Gor Shivaji Bothe Shruti Bhatia School of Computer Data and Mathematical Sciences Western Sydney University Australia Department of CSE NSRIT Visakhapatnam A.P. Uttaranchal Institute of Technology Uttaranchal University Department of PIET Parul University Department of IT& Business Analytics Sri Balaji University Pune (SBUP) Department of Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand

A major obstacle to the transformation of health care is the ability to extract information and useful insights from complex, high-dimensional, and varied biological data. Modern biomedical research has seen the emergence of a number of new data sources, some of which are complicated, diverse, poorly documented, and typically unstructured, such as digital health records, neuroimaging, -omics, sensor data, and text. Prior to building predictive or classification models on top of the features, conventional data mining and computational science, complex data and insufficient domain expertise, there are several problems on both phases. New efficient paradigms for creating end-to-end learning approaches from complex information are provided by the most recent deep learning technology advancements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-task Financial Forecasting

arXiv

引用

arXiv 2022年

作者： Yang, Linyi Li, Jiazheng Dong, Ruihai Zhang, Yue Smyth, Barry Westlake Institute for Advanced Study Westlake University China School of Engineering Westlake University China The Insight Centre for Data Analytics University College Dublin Ireland Department of Computer Science University of Warwick United Kingdom

Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasting may entail. Traditionally, financial forecasting has heavily relied on quantitative indicators and metrics derived from structured financial statements. Earnings conference call data, including text and audio, is an important source of unstructured data that has been used for various prediction tasks using deep earning and related approaches. However, current deep learning-based methods are limited in the way that they deal with numeric data;numbers are typically treated as plain-text tokens without taking advantage of their underlying numeric structure. This paper describes a numeric-oriented hierarchical transformer model (NumHTML) to predict stock returns, and financial risk using multimodal aligned earnings calls data by taking advantage of the different categories of numbers (monetary, temporal, percentages etc.) and their magnitude. We present the results of a comprehensive evaluation of NumHTML against several state-of-the-art baselines using a real-world publicly available dataset. The results indicate that NumHTML significantly outperforms the current state-of-the-art across a variety of evaluation metrics and that it has the potential to offer significant financial gains in a practical trading context. © 2022, CC BY-NC-ND.

关键词： Investments

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：