检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hussain, Zeshan Lam, Barbara D. Acosta-Perez, Fernando A. Riaz, Irbaz Bin Jacobs, Maia Yee, Andrew J. Sontag, David Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology United States Division of Hematology and Oncology Department of Medicine Beth Israel Deaconess Medical Center Division of Clinical Informatics Department of Medicine Beth Israel Deaconess Medical Center Department of Industrial and Systems Engineering University of Wisconsin-Madison United States Division of Hematology and Oncology Department of Medicine Mayo Clinic AZ United States Department of Computer Science McCormick School of Engineering Northwestern University United States Division of Hematology and Oncology Department of Medicine Massachusetts General Hospital United States

Purpose: Evaluate how clinicians approach clinical decision-making when given findings from both randomized controlled trials (RCTs) and machine learning (ML) models. Methods: We designed a clinical decision support system (CDSS) that displays survival curves and adverse event information from a synthetic RCT and ML model for 12 patients with multiple myeloma. We conducted an interventional study in a simulated setting to evaluate how clinicians synthesized the available data to make treatment decisions. Participants were invited to participate in a follow-up interview to discuss their choices in an open-ended format. Results: The cohort contained 32 physicians. When ML model results were concordant with RCT results, physicians had increased confidence in treatment choice compared to when they were given RCT results alone. When ML model results were discordant with RCT results, the majority of physicians followed the ML model recommendation in their treatment selection. Perceived reliability of the ML model was consistently higher after physicians were provided with data on how it was trained and validated. Follow-up interviews revealed four major themes: (1) variability in what variables participants used for decision-making, (2) perceived advantages to an ML model over RCT data, (3) uncertainty around decision-making when the ML model quality was poor, and (4) perception that this type of study is an important thought exercise for clinicians. Conclusion: ML-based CDSSs have the potential to change treatment decisions in cancer management. Meticulous development and validation of these systems as well as clinician training are required before deployment. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

YAQQ: Yet Another Quantum Quantizer - Design Space Exploration of Quantum Gate Sets using Novelty Search

arXiv

引用

arXiv 2024年

作者： Sarkar, Aritra Kundu, Akash Steinberg, Matthew Mishra, Sibasish Fauquenot, Sebastiaan Acharya, Tamal Miszczak, Jaroslaw A. Feld, Sebastian Quantum Intelligence research team Quantum Machine Learning research group Quantum Computing division QuTech Netherlands Department of Quantum & Computer Engineering Delft University of Technology Netherlands Joint Doctoral School Silesian University of Technology Gliwice Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland QTF Centre of Excellence Department of Physics University of Helsinki Finland

The standard model of quantum computation is based on quantum circuits, where the number and quality of the quantum gates composing the circuit influence the runtime and fidelity of the computation. The fidelity of the decomposition of quantum algorithms, represented as unitary matrices, to bounded depth quantum circuits depends strongly on the set of gates available for the decomposition routine. To investigate this dependence, we explore the design space of discrete quantum gate sets and present a software tool for comparative analysis of quantum processing units and control protocols based on their native gates. The evaluation is conditioned on a set of unitary transformations representing target use cases on the quantum processors. The cost function considers three key factors: (i) the statistical distribution of the decomposed circuits’ depth, (ii) the statistical distribution of process fidelities for the approximate decomposition, and (iii) the relative novelty of a gate set compared to other gate sets in terms of the aforementioned properties. The developed software, called YAQQ (Yet Another Quantum Quantizer), enables the discovery of an optimized set of quantum gates through this tunable joint cost function. To identify these gate sets, we use the novelty search algorithm, circuit decomposition techniques (like Solovay-Kitaev, Cartan, and quantum Shannon decomposition), and stochastic optimization to implement YAQQ within the Qiskit quantum simulator environment. YAQQ exploits reachability tradeoffs conceptually derived from quantum algorithmic information theory. Our results demonstrate the pragmatic application of identifying gate sets that are advantageous to popularly used quantum gate sets in representing quantum algorithms. Consequently, we demonstrate pragmatic use cases of YAQQ in comparing transversal logical gate sets in quantum error correction codes, designing optimal quantum instruction sets, and compiling to specific quantum processors. © 202

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Quantum Generative Diffusion Model: A Fully Quantum-Mechanical Model for Generating Quantum State Ensemble

arXiv

引用

arXiv 2024年

作者： Chen, Chuangtao Zhao, Qinglin Zhou, MengChu He, Zhimin Sun, Zhili Situ, Haozhen Faculty of Innovation Engineering Macau University of Science and Technology Macao999078 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States School of Electronic and Information Engineering Foshan University Foshan528000 China Institute of Communication Systems University of Surrey GuildfordGU2 7XH United Kingdom College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China

Classical diffusion models have shown superior generative results. Exploring them in the quantum domain can advance the field of quantum generative learning. This work introduces Quantum Generative Diffusion Model (QGDM) as their simple and elegant quantum counterpart. Through a non-unitary forward process, any target quantum state can be transformed into a completely mixed state that has the highest entropy and maximum uncertainty about the system. A trainable backward process is used to recover the former from the latter. The design requirements for its backward process includes non-unitarity and small parameter count. We introduce partial trace operations to enforce non-unitary and reduce the number of trainable parameters by using a parameter-sharing strategy and incorporating temporal information as an input in the backward process. We present QGDM’s resource-efficient version to reduce auxiliary qubits while preserving generative capabilities. QGDM exhibits faster convergence than Quantum Generative Adversarial Network (QGAN) because its adopted convex-based optimization can result in better convergence. The results of comparing it with QGAN demonstrate its effectiveness in generating both pure and mixed quantum states. It can achieve 53.02% higher fidelity in mixed-state generation than QGAN. The results highlight its great potential to tackle challenging quantum generation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Optical Imaging Incorporated Non-Destructive Morphological Boundary Detection of Fruit Disorders: A Pilot Study

High-Resolution Optical Imaging Incorporated Non-Destructive...

引用

Advancements in Computing (ICAC), International Conference on

作者： Nethmi Tharushi Hakmana Nipun Shantha Kahatapitiya Sasmitha Weerasinghe Deshan Kalupahana Bhagya Nathali Silva Naresh Kumar ravichandran Daewoon Seong Sangyeob Han Seung Yeol Lee Hee-Young June Mansik Jeon Jeehyun Kim Udaya Wijenayake Ruchire Eranga Wijesinghe Department of Mechanical Engineering Faculty of Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Engineering Faculty of Engineering University of Sri Jayewardenepura Nugegoda Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Center for Excellence in Informatics Electronics & Transmission (CIET) Sri Lanka Institute of Information Technology Malabe Sri Lanka Center for Scientific Instrumentation Korea Basic Science Institute Daejeon Republic of Korea School of Electronic and Electrical Engineering College of IT Engineering Kyungpook National University Daegu Republic of Korea ICT Convergence Research Center Kyungpook National University Daegu Republic of Korea Department of Plant Medicine Kyungpook National University Daegu Republic of Korea Institute of Plant Medicine Kyungpook National University Daegu Republic of Korea Department of Electrical and Electronic Engineering Faculty of Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

Plant diseases caused by various pathogens, such as fungi, bacteria, and viruses, lead to significant reductions in crop yield and quality. Early detection of these diseases is critical for preventing their spread and optimizing crop yield. Traditional methods of disease detection, while effective, often involve invasive or time-consuming procedures that may not provide real-time insights. This study investigates the use of Swept-Source Optical Coherence Tomography (SS-OCT) for non-destructive, high-resolution imaging to identify morphological abnormalities in fruit specimens affected by diseases. The research focuses on differentiating healthy regions, healthy boundaries, infected boundaries, and fully infected regions in apples. Using a 1310 nm center wavelength laser, the SS-OCT system captured detailed cross-sectional images of fruit tissue, revealing microstructural changes associated with disease progression. A qualitative assessment of the two-dimensional (2D) OCT images highlighted distinct layers in healthy tissues, noticeable structural deformities, and the merging of microstructural layers in the boundary and infected regions. Quantitative depth-profile analysis of axial-direction A-scan profiles further demonstrated the reduction and merging of intensity peaks correlating with tissue abnormalities in infected fruit specimens. These findings underscore the potential of SS-OCT as an effective tool for early disease detection in agricultural products, providing a means for timely intervention and optimized postharvest management.

关键词： Plant diseases Pathogens Statistical analysis Two-dimensional displays Merging High-resolution imaging Optical imaging Real-time systems Crop yield Diseases

来源：评论

学校读者我要写书评

暂无评论

An Early Warning System to Predict Earthquakes based on WT-ARIMA-ANN Model

An Early Warning System to Predict Earthquakes based on WT-A...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： Uppara raghu Babu Shrinwantu raha Mujtaba Ali Khan C. Yamini R. Jayadurga Gourav Kalra Department of Civil Engineering Srinivasa Ramanujan Institute of Technology Andhra Pradesh India Department of Geography Bhairab Ganguly College Belgharia Kolkata India Department of Computer Science College of Computing and Informatics University of North Carolina Charlotte Department of Mathematics PSNA College of Engineering and Technology Dindigul Tamil Nadu India Department of MBA Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Mechanical Engineering Maharishi Markandeshwar (Deemed to be University) Mullana India

A devastating earthquake is one of the Earth’s most destructive natural disasters. Real-time seismic monitoring facilities can evolve into Earthquake Early Warning (EEW) systems with the help of modern technology, property damage, reducing the number of casualties, and economic losses. The proposed EEW system’s goal is to supply a precise damage assessment just before an earthquake hits a certain area. The proposed method involves preprocessing, feature extraction, and model training. It is recommended to preprocess the data by first filtering it and then reformatting it. Filtering is essential for getting rid of irrelevant or noisy information. In feature extraction, the Principal Component Analysis (PCA) provides a useful perspective on the data by establishing a new coordinate system, and it also offers a method for reducing the data’s dimensionality. Once the features have been obtained, the models are trained with WT-ARIMA-ANN. The proposed method outperforms two widely used alternatives, ARIMA and ANN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disentangling Prosody Representations with Unsupervised Speech Reconstruction

arXiv

引用

arXiv 2022年

作者： Qu, Leyuan Li, Taihao Weber, Cornelius Pekarek-Rosin, Theresa Ren, Fuji Wermter, Stefan The Institute of Artificial Intelligence Zhejiang Lab Hangzhou China The Department of Informatics University of Hamburg Hamburg Germany The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in Automatic Speech Recognition (ASR) and speaker verification tasks respectively. However, it is still an open challenging research question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for supervised training schemes to achieve robust large-scale and speaker-independent ASR. The aim of this paper is to address the disentanglement of emotional prosody from speech based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed speech reconstruction model Prosody2Vec: (1) a unit encoder that transforms speech signals into discrete units for semantic content, (2) a pretrained speaker verification model to generate speaker identity embeddings, and (3) a trainable prosody encoder to learn prosody representations. We first pretrain the Prosody2Vec representations on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks. Both objective (weighted and unweighted accuracies) and subjective (mean opinion score) evaluations on the EVC task suggest that Prosody2Vec effectively captures general prosodic features that can be smoothly transferred to other emotional speech. In addition, our SER experiments on the IEMOCAP dataset reveal that the prosody features learned by Prosody2Vec are complementary and beneficial for the performance of widely used speech pretraining models and surpass the state-of-the-art methods when combining Prosody2Vec with HuBERT representations. Some audio samples can be found on our demo website1 Copyright © 2022, The Authors. All righ

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

RL-MADP: Reinforcement Learning-based Misdirection Attack Prevention Technique for WSN 16

RL-MADP: Reinforcement Learning-based Misdirection Attack Pr...

引用

16th IEEE International Wireless Communications and Mobile Computing Conference, IWCMC 2020

作者： Mustafa, Iqra Aslam, Shahzad Aslam, Sheraz Qureshi, Muhammad Bilal Ashraf, Nouman Mohsin, Syed Muhammad Mustafa, Hasnain Department of Computing Cork Ireland Computer Engineering and Informatics Cyprus University of Technology Department of Electrical Engineering Limassol Cyprus Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Department of Computer Science Islamabad Pakistan Waterford Institute of Technology Ireland Institute of Southern Punjab Department Od Statistics and Mathematics Multan Pakistan Comsats University Islamabad Department of Computer Science Pakistan

ISBN: (纸本)9781728131290

Wireless Sensor Networks (WSNs) provide noteworthy advantages over conventional methods for various real-time applications, i.e., healthcare, temperature sensing, smart homes, homeland security, and environmental monitoring. However, limited resources, short life-time network constraints, and security vulnerabilities are the challenging issues in the era of WSNs. Besides, WSNs performance is susceptible to network anomalies, particularly to misdirection attacks. The above-mentioned issues pose our attentions to produce a security-aware application. In this work, therefore, we present a Reinforcement Learning (RL) algorithm for Misdirection Attack Detection and Prevention (RL-MADP) in WSNs. In our proposed approach, other than the flat architecture configuration for WSN, Markov Decision Process (MDP) from RL is considered. Where, each sensor node is fully aware of its environment. It is an online method and incurs minimal computation cost, and performs load-balancing with higher residual energy to prolong the network lifetime. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Abstraction engineering

arXiv

引用

arXiv 2024年

作者： Bencomo, Nelly Cabot, Jordi Chechik, Marsha Cheng, Betty H.C. Combemale, Benoit Wąsowski, Andrzej Zschaler, Steffen Durham University Computer Science Durham Durham United Kingdom Luxembourg Institute of Science and Technology University of Luxembourg Esch-sur-Alzette Luxembourg University of Toronto Department of Computer Science TorontoON Canada Michigan State University Department of Computer Science and Engineering 428 S. Shaw Lane 4115 Engineering Building East LansingMI48824 United States University of Rennes IRISA and Inria Campus de Beaulieu Rennes35042 France IT University of Copenhagen Department of Computer Science Rued Langgaards Vej 7 Copenhagen2300 Denmark King’s College London Department of Informatics Bush House 30 Aldwych LondonWC2B 4BG United Kingdom

Modern software-based systems operate under rapidly changing conditions and face ever-increasing uncertainty. In response, systems are increasingly adaptive and reliant on artificial-intelligence methods. In addition to the ubiquity of software with respect to users and application areas (e.g., transportation, smart grids, medicine, etc.), these high-impact software systems necessarily draw from many disciplines for foundational principles, domain expertise, and workflows. Recent progress with lowering the barrier to entry for coding has led to a broader community of developers, who are not necessarily software engineers. As such, the field of software engineering needs to adapt accordingly and offer new methods to systematically develop high-quality software systems by a broad range of experts and non-experts. This paper looks at these new challenges and proposes to address them through the lens of Abstraction. Abstraction is already used across many disciplines involved in software development—from the time-honored classical deductive reasoning and formal modeling to the inductive reasoning employed by modern data science. The software engineering of the future requires Abstraction engineering—a systematic approach to abstraction across the inductive and deductive spaces. We discuss the foundations of Abstraction engineering, identify key challenges, highlight the research questions that help address these challenges, and create a roadmap for future research. © 2024, CC BY.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Mqtt Routing Optimizing Based Intrusion Detection for Internet of Things Using Hybrid Machine Learning

Mqtt Routing Optimizing Based Intrusion Detection for Intern...

引用

Decision Aid Sciences and Application (DASA), International Conference on

作者： Haider K. Hoomod Mohammad Alaa Al-Hamami Aqeel Kamil Kadhim Qutaiba Humadi Mohammed Jolan Rokan Niaf College of Education Mustansiriyah University Baghdad Iraq Department of Management Information Systems Applied Science University Manama Kingdom of Bahrain Computer Techniques Engineering Department Imam Al-Kadhim College Baghdad Iraq College of Nursing University of Baghdad Baghdad Iraq Informatics Institute for Postgraduate Studies University of Information Technology and Communications Baghdad Iraq

ISBN: (数字)9798350369106

ISBN: (纸本)9798350369113

With the advent of the Internet of Things, a world was born in which everything could be uniquely identified and monitored, tracked, and managed by computer programs. Items can self-configure using a predefined communication protocol. Other software programs can be linked to operate together using Message Queue Telemetry Transport Protocol (MQTT) or MQSeries components. Business integration software and middleware are common terms for this category of applications. With its suggested lightweight, easy-to-implement, and lowbandwidth system for billions of smart items, the MQTT protocol offers a wide range of potential applications, including home automation. In order to enhance the power savings in MQservice routing, we presented an intelligent assistant for optimizing routing model. For Internet of Things (IoT) purposes, it introduces an optimal routing model based on optimized hybrid machine learning-based anomaly detection (OHMLA). In order to extend the reach of a network, the offered approach allows Internet of Things devices to make efficient use of energy. To further enhance Intrusion Detection identification and get optimum network selection routes, the moth Salp Swarm technique (SSA) technique is used for the optimized hyperparameters. The model is capable of accurately detecting attacks that result in network congestion, causing delays in connection response and data transfer in IoT network.

关键词： Transport protocols Network intrusion detection Machine learning Routing Data transfer Data models Delays Classification algorithms Internet of Things Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Medical Neurological Image Fusion using Wavelet Pooled Edge Preserving Autoencoder

arXiv

引用

arXiv 2023年

作者： Das, Manisha Gupta, Deep radeva, Petia Bakde, Ashwini M. The Department of Electronics and Comm. Engineering Visvesvaraya National Institute of Technology Nagpur40010 India The Departament de Mathematics and Informatics Universitat de Barcelona Barcelona08007 Spain The Computer Vision Center Cerdanyola08193 Spain The Department of Radio-Diagnosis All India Institute of Medical Sciences Nagpur441108 India

Medical image fusion integrates the complementary diagnostic information of the source image modalities for improved visualization and analysis of underlying anomalies. Recently, deep learning-based models have excelled the conventional fusion methods by executing feature extraction, feature selection, and feature fusion tasks, simultaneously. However, most of the existing convolutional neural network (CNN) architectures use conventional pooling or strided convolutional strategies to downsample the feature maps. It causes the blurring or loss of important diagnostic information and edge details available in the source images and dilutes the efficacy of the feature extraction process. Therefore, this paper presents an end-to-end unsupervised fusion model for multimodal medical images based on an edge-preserving dense autoencoder network. In the proposed model, feature extraction is improved by using wavelet decomposition-based attention pooling of feature maps. This helps in preserving the fine edge detail information present in both the source images and enhances the visual perception of fused images. Further, the proposed model is trained on a variety of medical image pairs which helps in capturing the intensity distributions of the source images and preserves the diagnostic information effectively. Substantial experiments are conducted which demonstrate that the proposed method provides improved visual and quantitative results as compared to the other state-of-the-art fusion methods. © 2023, CC BY.

关键词： Feature extraction

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：