检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Harikrishnan, N.B. Jain, Arham Nagaraj, Nithin Department of Computer Science & Information Systems APPCAIR BITS Pilani K K Birla Goa Campus Goa India Department of Computer Science & Information Systems BITS Pilani K K Birla Goa Campus Goa India Consciousness Studies Programme National Institute of Advanced Studies Indian Institute of Science Campus Karnataka Bengaluru India

Decision Tree is a well understood Machine Learning model that is based on minimizing impurities in the internal nodes. The most common impurity measures are Shannon entropy and Gini impurity. These impurity measures are insensitive to the order of training data and hence the final tree obtained is invariant to any permutation of the data. This is a limitation in terms of modeling when there are temporal order dependencies between data instances. In this research, we propose the adoption of Effort-To-Compress (ETC) - a complexity measure, for the first time, as an alternative impurity measure. Unlike Shannon entropy and Gini impurity, structural impurity based on ETC is able to capture order dependencies in the data, thus obtaining potentially different decision trees for different permutations of the same data instances, a concept we term as Permutation Decision Trees (PDT). We then introduce the notion of Permutation Bagging achieved using permutation decision trees without the need for random feature selection and sub-sampling. We conduct a performance comparison between Permutation Decision Trees and classical decision trees across various real-world datasets, including Appendicitis, Breast Cancer Wisconsin, Diabetes Pima Indian, Ionosphere, Iris, Sonar, and Wine. Our findings reveal that PDT demonstrates comparable performance to classical decision trees across most datasets. Remarkably, in certain instances, PDT even slightly surpasses the performance of classical decision trees. In comparing Permutation Bagging with Random Forest, we attain comparable performance to Random Forest models consisting of 50 to 1000 trees, using merely 21 trees. This highlights the efficiency and effectiveness of Permutation Bagging in achieving comparable performance outcomes with significantly fewer trees. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Thermally tunable high Q-factor and low-power silicon resonators using Graphene transparent electrodes

Thermally tunable high Q-factor and low-power silicon resona...

引用

2023 Applied Optics and Photonics China: Laser Technology and Applications;and Optoelectronic Devices and Integration, AOPC 2023

作者： Hong, Qilin Xu, Ping Xu, Wei Zhu, Zhihong College of Advanced Interdisciplinary Studies Hunan Provincial Key Laboratory of Novel Nano Optoelectronic Information Materials and Devices National University of Defense Technology Changsha410073 China Nanhu Laser Laboratory National University of Defense Technology Changsha410073 China Institute for Quantum Information State Key Laboratory of High-Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China

ISBN: (纸本)9781510672246

Tunable and low-power microcavities play a vital role in facilitating the development of large-scale photonic integrated circuits. Among various tuning methods, thermal tuning has gained significant popularity due to its convenience and stability, especially in the fields of optical neural networks and quantum information processing. In recent years, graphene thermal tuning has emerged as a promising technique, offering both tunability and power efficiency by eliminating the need for thick spacers to prevent light absorption. In this study, we propose and fabricate a silicon-based on-chip Fano resonator with graphene nano-heaters. This innovative Fano structure incorporates a scattering block and can be easily manufactured in large quantities. Experimental results demonstrate that the resonator exhibits desirable characteristics, including a high quality factor of approximately 31000 and a low state-switching power consumption of around 1 mW. The temporal responses of the microcavity exhibit satisfactory modulation speed, with a rise time of 9.8 µs and a fall time of 16.6 µs. The findings of this research offer an alternative solution for the future development of large-scale tunable and low-power-consumption optical networks, with potential applications in optical filters and switches. © 2023 SPIE.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment for Nonlinear Cyber-Physical Systems under Stealth Attacks

arXiv

引用

arXiv 2024年

作者： Chen, Guang Sun, Zhicong Ding, Yulong Yang, Shuang-Hua Department of Mechanical and Energy Engineering Southern University of Science and Technology China Department of Civil and Environmental Engineering Hong Kong Polytechnic University Hong Kong Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet SUSTech Shenzhen518055 China Department of Computer Science and Engineering SUSTech Shenzhen518055 China Department of Computer Science University of Reading United Kingdom

Stealth attacks pose potential risks to cyber-physical systems because they are difficult to detect. Assessing the risk of systems under stealth attacks remains an open challenge, especially in nonlinear systems. To comprehensively quantify these risks, we propose a framework that considers both the reachability of a system and the risk distribution of a scenario. We propose an algorithm to approximate the reachability of a nonlinear system under stealth attacks with a union of standard sets. Meanwhile, we present a method to construct a risk field to formally describe the risk distribution in a given scenario. The intersection relationships of system reachability and risk regions in the risk field indicate that attackers can cause corresponding risks without being detected. Based on this, we introduce a metric to dynamically quantify the risk. Compared to traditional methods, our framework predicts the risk value in an explainable way and provides early warnings for safety control. We demonstrate the effectiveness of our framework through a case study of an automated warehouse. Copyright © 2024, The Authors. All rights reserved.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Design of AED Based Drone to Deliver the Medical Kit on an Emergency Basis

Design of AED Based Drone to Deliver the Medical Kit on an E...

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： P. Nagarani Mohd Wazih Ahmad R Shalini Pavitar Parkash Singh Department of Emerging Technologies CVR College of Engineering Hyderabad India Department of Computer Science and Engineering hri Ram Murti Smarak college of Engineering and Technology Bareilly India Department of BCA & IT School of computing sciences Vels Institute of Science Technology and Advanced Studies Chennai India Department of Management Lovely Professional University Phagwara India

Access to reliable modes of transportation is essential. Postal delivery to multi-million-dollar freight transports, practically everything is linked to its connections. Wheeled motor vehicles and manned aeroplanes are now the only options for transporting medical supplies at times of urgent need, which may be expensive, time-consuming, and often impossible if the emergency site is far. Drones are a game-changer in the medical industry because they can transfer vital supplies like blood and medical equipment. Unfortunately, given the state of the art, the drone's battery life is a constraint that may slow down the delivery process. This article details the research into the mechanisms designed for drones to increase their battery life and efficiently deliver first aid supplies. The drone's system safely delivers and drops medical supplies, reducing the drone's takeoffs and landings. The primary goal of this research is to develop a device that can safely transport medical equipment to its destination and then carefully unload it there. Results showed the system could safely transport and deploy first aid supplies during flight and landing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing HIV Drug Resistance Prediction Using Bidirectional LSTM Neural Networks

引用

Procedia computer science 2025年 258卷 2888-2898页

作者： Poojitha D Tanmay Darak Ushnish Samaddar Vasavi C S Karthikeyan B Divya B. Korlepara Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham 560035 India Department of Artificial Intelligence Amrita School of Artificial Intelligence Bengaluru Amrita Vishwa Vidyapeetham 560035 India Department of Embedded Technology School of Electronics Engineering Vellore Institute of Technology Vellore 632014 India Divison of Physics School of Advanced Sciences Vellore Institute of Technology Chennai 600127 India

One major obstacle that humanity faces today is the ability of viruses to develop resistance to antibiotics or other drugs used in treating the diseases. In the current study, we utilise a specifically developed Bidirectional Long Short-Term Memory (LSTM) neural network to identify HIV drug resistant strains in an effort to help clinicians identify the most appropriate treatment options so that the development new resistant strains is prevented as much as is possible. By incorporating the Bidirectional LSTM model, temporal dependency analysis is improved and deepened in both forward and backward directions, improving the model’s performance and interpretability. The accuracy of the model is measured by MAE and R² where the result from MAE is 16.151 of PI (Protease Inhibitors), 14.703 of NRTI (Nucleoside Reverse Transcriptase Inhibitors) and 18.815 of NNRTI (Non-Nucleoside Reverse Transcriptase Inhibitors) while result from R² is 0.914 of PI, 0.942 of NRTI and 0.885 of NNRTI. Consequently, these results suggest the custom model may be useful to refine drug resistance predictions to progress the accuracy of HIV treatment.

关键词： Bidirectional LSTM neural networks resistant strains genetic sequences bioinformatics Protease Inhibitors Nucleoside Reverse Transcriptase Inhibitors Non-Nucleoside Reverse Transcriptase Inhibitors

来源：评论

学校读者我要写书评

暂无评论

Optimal Area-Sensitive Bounds for Polytope Approximation

arXiv

引用

arXiv 2023年

作者： Arya, Sunil da Fonseca, Guilherme D. Mount, David M. Department of Computer Science and Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Aix-Marseille Université LIS Marseille France Department of Computer Science Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States

Approximating convex bodies is a fundamental question in geometry and has a wide variety of applications. Given a convex body K of diameter ∆ in d for fixed d, the objective is to minimize the number of vertices (alternatively, the number of facets) of an approximating polytope for a given Hausdorff error Ε. The best known uniform bound, due to Dudley (1974), shows that O((∆/Ε)(d-1)/2) facets suffice. While this bound is optimal in the case of a Euclidean ball, it is far from optimal for "skinny" convex bodies. A natural way to characterize a convex object's skinniness is in terms of its relationship to the Euclidean ball. Given a convex body K, define its surface diameter ∆d-1 to be the diameter of a Euclidean ball of the same surface area as K. It follows from generalizations of the isoperimetric inequality that ∆ ≽ ∆d-1. We show that, under the assumption that the width of the body in any direction is at least Ε, it is possible to approximate a convex body using O((∆d-1/Ε)(d-1)/2) facets. This bound is never worse than the previous bound and may be significantly better for skinny bodies. The bound is tight, in the sense that for any value of ∆d-1, there exist convex bodies that, up to constant factors, require this many facets. The improvement arises from a novel approach to sampling points on the boundary of a convex body. We employ a classical concept from convexity, called Macbeath regions. We demonstrate that Macbeath regions in K and K's polar behave much like polar pairs. We then apply known results on the Mahler volume to bound their number. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning applications and techniques in healthcare domain: A review

引用

AIP Conference Proceedings 2024年第1期2802卷

作者： R. Mary Sheeba R. Parameswari Department of Computer Science School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Chennai India

Machine Learning (ML) / Deep Learning (DL) has been applied in the development of the healthcare domain in recent years due to its increased potential and performance. It provides better support to clinicians and patients in various aspects, such as automating medical billing, clinical decision support, disease diagnosis, etc. It also plays a vital role in pattern recognition, online recommendation, finance, robotics, information security, etc. It can learn and realize the pattern from the healthcare records and gives better predictions about the disease. The goal of this review paper is to provide an overview of: (i) Machine Learning concepts; (ii) Machine Learning applications, techniques and its purpose in the healthcare domain; (iii) challenges and issues in maintaining health records; and (iv) finally, it helps to minimize the research gap with best decision support system using Machine Learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anonymous Distributed Localisation via Spatial Population Protocols

arXiv

引用

arXiv 2024年

作者： Gąsieniec, Leszek Kuszner, Lukasz Latif, Ehsan Parasuraman, Ramviyas Spirakis, Paul Stachowiak, Grzegorz Department of Computer Science University of Liverpool United Kingdom Institute of Informatics Physics and Informatics University of Gdańsk Poland AI4STEM Education Center Department of Mathematics Science and Social Studies Education University of Georgia AthensGA United States School of Computing University of Georgia AthensGA United States Institute of Computer Science University of Wroclaw Poland

In the distributed localization problem (DLP), n anonymous robots (agents) A0, . . . ,An-1 begin at arbitrary positions p0, . . . , pn-1 ∈ S, where S is a Euclidean space. Initially, each agent Ai operates within its own coordinate system in S, which may be inconsistent with those of other agents. The primary goal in DLP is for agents to reach a consensus on a unified coordinate system that accurately reflects the relative positions of all points, p0, . . . , pn-1, in S. Extensive research on DLP has primarily focused on the feasibility and complexity of achieving consensus when agents have limited access to inter-agent distances, often due to missing or imprecise data. In this paper, however, we examine a minimalist, computationally efficient model of distributed computing in which agents have access to all pairwise distances, if needed. Specifically, we introduce a novel variant of population protocols, referred to as the spatial population protocols model. In this variant each agent can memorise one or a fixed number of coordinates, and when agents Ai and Aj interact, they can not only exchange their current knowledge but also either determine the distance dij between them in S (distance query model) or obtain the vector -→vij spanning points pi and pj (vector query model). We examine three DLP scenarios, proposing and analysing several types of distributed localisation protocols, including: 1. Self-stabilising localisation protocol with distance queriesWe propose and analyse self-stabilising localisation protocol based on pairwise distance adjustment. We also discuss several hard instances in this scenario, and suggest possible improvements for the considered protocol, 2. Leader-based localisation protocol with distance queries We propose and analyse several leaderbased protocols which stabilise in o(n) parallel time. These protocols rely on efficient solution to multi-contact epidemic, an extension of one-way epidemic in population protocols, and 3. Self-stabil

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Exploring Convolution Neural Networks for Image Classification in Medical Imaging

Exploring Convolution Neural Networks for Image Classificati...

引用

Intelligent and Innovative Technologies in computing, Electrical and Electronics (IITCEE), International Conference

作者： Vishwa Priya V Padmini Chattu K. Sivasankari Dnyaneshwar Tukaram Pisal Bantupalli Renuka Sai D. Suganthi Department of CS Vels Institute Science Technology and Advanced Studies Chennai Tamilnadu India ACE Engineering College Department of ECE Sri Sai Ram Institute Of Technology Chennai Tamilnadu India SVPMs Institute of Management Malegaon Baramati Pune Maharashtra India Computer Science and Engineering Raghu Engineering College Visakhapatnam Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Thandalam Chennai

Modern healthcare relies on medical imaging to diagnose and cure diseases. Convolution Neural Networks (CNNs) have excelled at image categorization, and their use in medical imaging could change illness diagnosis. This study examines CNN's medical picture categorization performance. This study used X-rays, CT scans, MRIs, and histopathology slides. Traditional CNNs, transfer learning models, and bespoke networks were constructed and trained. The training data included lung ailments, cancer detection, bone fractures, and neurological disorders. Our investigations showed that CNNs can extract complex characteristics from medical photos, improving classification accuracy. Transfer learning, where pre-trained models were fine-tuned on medical data, performed well with 94.8% accuracy. We used cutting-edge data augmentation and attention strategies to improve model generalization and interpretability. In addition to high classification accuracy, we studied model explainability using gradient-based methods and visualization to highlight medical picture regions of relevance that influenced model predictions. Building trust with medical practitioners and understanding deep learning model decision-making requires interpretability. In clinical settings, CNN deployment raises ethical and practical issues such as data privacy, model robustness, and regulatory compliance. According to our research, CNNs may increase medical picture classification accuracy and speed. X-rays had the best accuracy at 95.2%, followed by CT scans at 92.7% and MRIs at 94.1%. Histopathological slides exhibited 88.6% accuracy; however, this shows that CNNs can diagnose diseases from microscopic images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Holographic-Pattern Based Multi-User Beam Training in RHS-Aided Hybrid Near-Field and Far-Field Communications

arXiv

引用

arXiv 2024年

作者： Zhang, Shupei Di, Boya Kaushik, Aryan Eldar, Yonina C. State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing China The Department of Computing & Mathematics Manchester Metropolitan University United Kingdom The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Reconfigurable holographic surfaces (RHSs) have been suggested as an energy-efficient solution for extremely large-scale arrays. By controlling the amplitude of RHS elements, high-gain directional holographic patterns can be achieved. However, the complexity of acquiring real-time channel state information (CSI) for beamforming is exceedingly high, particularly in large-scale RHS-assisted communications, where users may distribute in the near-field region of RHS. This paper proposes a one-shot multi-user beam training scheme in large-scale RHS-assisted systems applicable to both near and far fields. The proposed beam training scheme comprises two phases: angle search and distance search, both conducted simultaneously for all users. For the angle search, an RHS angular codebook is designed based on holographic principles so that each codeword covers multiple angles in both near-field and far-field regions, enabling simultaneous angular search for all users. For the distance search, we construct the distance-adaptive codewords covering all candidate angles of users in a real-time way by leveraging the additivity of holographic patterns, which is different from the traditional phase array case. Simulation results demonstrate that the proposed scheme achieves higher system throughput compared to traditional beam training schemes. The beam training accuracy approaches the upper bound of exhaustive search at a significantly reduced overhead. Copyright © 2024, The Authors. All rights reserved.

关键词： Beamforming

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：