检索结果-内蒙古大学图书馆

14th International Conference on Measurement, MEASUREMENT 2023

作者： Ghosh, Anupam Bhattacharjee, Madhurima Kathpalia, Aditi Brunovsky, Martin Palus, Milan Institute of Computer Science of the Czech Academy of Sciences Department of Complex Systems Prague Czech Republic National Institute of Mental Health Clinical Research Programme Klecany Czech Republic

ISBN: (纸本)9788097262976

In this paper, we infer the direction of information transfer between interacting subsystems using a cross-dependence index derived from the phase dynamics of coupled subsystems. First, we apply this method to unidirectionally coupled Rössler oscillators. This index always has a higher value along the direction of coupling than that opposite to the coupling. Finally, we employ this method in analysis of EEG signals. The aim of this analysis is to identify the direction of information transfer in the brain in patients suffering from depression and quantify its changes during the treatment process. © 2023 Institute of Measurement science, Slovak Academy o.

关键词： Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Pattern Discovery in an EEG Database of Depression Patients: Preliminary Results 14

Pattern Discovery in an EEG Database of Depression Patients:...

引用

14th International Conference on Measurement, MEASUREMENT 2023

作者： Hlavackova-Schindler, Katerina Pacher, Christina Plant, Claudia Lazarenko, Mykola Palus, Milan Hlinka, Jaroslav Kathpalia, Aditi Brunovsky, Martin University of Vienna Data Mining and Machine Learning Research Group Faculty of Computer Science Vienna Austria Czech Academy of Sciences Institute of Computer Science Department of Complex Systems Prague Czech Republic National Institute of Mental Health Clinical Research Programme Klecany Czech Republic

ISBN: (纸本)9788097262976

The ability to predict response to medication treatment of depressed patients, either early in the course of therapy or before treatment even begins can avoid trials of ineffective therapy and save patients from prolonged intervals of suffering. Symptom alleviation requires 4-6 weeks after starting current antidepressive medication. Based on the data basis of the patients and their EEG before and on the 7th day of treatment we apply data mining, causal discovery and machine learning approaches to discover interactive patterns between patient's brain regions to separate the treatment responders from non-responders. In this paper we report the preliminary results of our international project "Learning Synchronization Patterns in Multivariate Neural Signals for Prediction of Response to Antidepressants"ongoing at the University of Vienna, the Czech Academy of sciences and the National Institute of Mental Health in the Czech Republic. © 2023 Institute of Measurement science, Slovak Academy o.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Boosting Operating Theatre Utilisation Gains in Master Surgery Scheduling via Enhanced Genetic Algorithm with Naïve Seeds 18

Boosting Operating Theatre Utilisation Gains in Master Surge...

引用

18th IEEE International Conference on computer science and Information Technologies, CSIT 2023

作者： Dovhaniuk, Oleksii Reidy, Grace Dineen, Charlie Redmond, Paul Corrigan, Mark Tabirca, Sabin University College Cork School of Computer Science Cork Ireland South South West Hospital Group Ireland Transforming Theatre Programme Cork Ireland Royal College of Surgeons in Ireland Transforming Theatre Programme Dublin Ireland University College Cork Department of Surgery Cork Ireland

ISBN: (纸本)9798350360462

This paper starts a series of research works dedicated to developing a practical and robust scheduling system for hospitals with operating capacities. The current goal is to ensure that a genetic algorithm can generate valuable solutions for operating theatre scheduling problems and optimise simple-to-implement schedules. Operating theatre is the most costly resource in hospitals, requiring highly coordinated action from caregivers to satisfy patient's needs and, at the same time, minimise idle time and overruns. Therefore, any tool that helps organise and structure patient flow saves time, money and effort both for a healthcare recipient and hospital administration. The work overviews existing medical resource scheduling methods and emphasises the advantages and disadvantages of some of the approaches. Based on the existing methods, the genetic algorithm with some unique features and enhancing strategies is presented. The algorithm experiments and tuning are performed on real-hospital records. The results show the advantage of the proposed genetic algorithm over manual and naïve scheduling approaches, proving the value of the genetic algorithm for scheduling operating theatres. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

K- Nearest Neighbour-Based Chronic Kidney Disease Prediction System: A Case of Toxic Metals in Urine

K- Nearest Neighbour-Based Chronic Kidney Disease Prediction...

引用

science, Engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Adebusola Tope-Oke Bukola Badeji-Ajisafe Abiodun Oguntimilehin Martin Victor Inyang Opani Aweh Oluwatoyin Abiola Department of Mathematical and Physical Sciences (Computer Science Programme) Afe Babalola University Ado-Ekiti Nigeria

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

Loss of renal function is a symptom of chronic kidney disease (CKD). Numerous lives are lost each year as a result of the disease, which frequently has symptoms that are not obvious. Since kidney disease is a progressive condition, it spreads quickly and eventually causes a decline in kidney function. Using factors like age, bacteria, diabetes mellitus, and white blood cell count to name a few, previous studies predicted kidney illness, but they did not incorporate toxic metals in urine. Using machine learning methods, CKD may be predicted with a high degree of accuracy in medical investigations. Thus, this study uses three of the supervised classification methods learning algorithms, which include, Decision tree, Random Forest, and K Nearest Neighbor (KNN) algorithms for the prediction of CKD. A raw dataset of hazardous metals in urine that was gathered from two Nigerian hospitals was used to analyze the performance of the algorithms' predictions. Copper (Cu), Zinc (Zn), Iron (Fe), Lead (Pb), Magnesium (Mg), Chromium (Cr), Cadmium (Cd), and Selenium (Se) are some of these metals. Based on how accurate the results were, a performance analysis was carried out. According to the comparison of the algorithms, the KNN method, which has the highest accuracy, is ideal for predicting chronic renal disease. This work created a system to predict CKD along five classifications using the KNN algorithm.

关键词： Accuracy Machine learning algorithms Nearest neighbor methods Lead Prediction algorithms Chronic kidney disease Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Deep Learning Models in Alzheimer’s Disease Diagnosis

引用

Procedia computer science 2025年 258卷 2352-2361页

作者： Leena Arya Yogesh Kumar Sharma Smitha Nayak Janaki Sivakumar Assistant Professor Computing Department Muscat College Oman Associate Professor Programme leader Computer security and forensics Department of Computer Science and Creative Technologies Global College of Engineering and Technology Muscat Oman

Alzheimer’s Disease (AD) is an ever-evolving neurodegenerative confusion that influences the neurons of the mind in a manner that hinders the patients’ ability to solve problems and remember issues and that requires timely and proper identification to enable appropriate management and treatment. Based on MRI medical images, deep learning models have become one of the most effective approaches for analyzing the signs of the early stages of AD. This research, therefore, carries out a comparative analysis of five deep learning models such as Convolutional Neural Networks (CNNs) like AlexNet, VGGNet, and ResNet, as well as Long Short-Term Memory (LSTM) networks and 3D Convolutional Neural Networks (3D-CNNs) in the finding of Alzheimer’s Sickness from medical imaging data. Each model’s arrangement parameters, for example, layer configurations, learning rate, batch size, optimizer, number of epochs, loss function, applying techniques for regularization, activation functions, and the input dimensions, using pre-trained weights, were carefully initialized to yield a proper comparison between the models. Diagnostic performances were evaluated utilizing precision, responsiveness(recall), specificity, and region under the receiver operating characteristic curve (AUC-ROC). ResNet outperformed other profound learning models in diagnosing Alzheimer’s Disease from MRI scans with a precision of 0.91 and AUC-ROC of 0.95. At the same time, VGGNet, AlexNet, LSTM, and 3D-CNNs demonstrated varying strengths and limitations in balancing accuracy, computational efficiency, and feature extraction.

关键词： Artificial Intelligence (AI) Cognitive Impairment Data Augmentation Diagnosis Accuracy Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Sinkhole Attack on RPL in Static, Mobile, and Hybrid Network Environment

Comprehensive Analysis of Sinkhole Attack on RPL in Static, ...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Faisal Ali Garba Oluwakemi Oduwole Kabiru Ibrahim Kunya Shazali Abbas Ibrahim Sikirat Kehinde Aina Department of Computer Science Education Sa’Adatu Rimi University of Education Kano Nigeria Computer Science Programme National Mathematical Center Kwali-Sheda Abuja Nigeria Department of Computer Science Federal University Gashua Yobe Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The Routing Protocol for Low-Power and Lossy Networks (RPL) is extensively utilized in Internet of Things (IoT) environments due to its efficiency in managing constrained devices. However, it is especially prone to Sinkhole attacks, when rogue nodes post bogus routing metrics, contributing to large interruptions in network performance. These attacks degrade packet delivery, introduce delays, and drain energy, especially in dynamic networks. While several studies have explored the repercussions of Sinkhole attacks in static networks, little emphasis has been devoted to how these attacks influence mobile and hybrid network environments, where node movement and diverse topologies offer extra obstacles. Understanding the comparative repercussions of Sinkhole attacks in different contexts is crucial for building appropriate security tactics. This study gives a detailed simulation-based analysis utilizing Contiki 3.0 and the Cooja simulator to analyze the impact of Sinkhole attacks on static, mobile, and hybrid networks. Simulations were done with varied node densities (10, 20, and 30 nodes) and different percentages of malicious nodes (10%, 20%, and 30%). Performance parameters such as Packet Delivery Ratio (PDR), Average End-to-End Delay (AE2ED), overhead packets, energy consumption, and throughput were measured across all circumstances. The results reveal that mobile networks are the most vulnerable to Sinkhole attacks, with considerable losses in PDR and increases in energy usage and delay. Static networks offer more stable performance but are prone to long-term degradation when malicious nodes remain established. Hybrid networks demonstrate various consequences, with static attackers generating limited damage and mobile attackers spreading disturbance across the network. These results underline the necessity for individualized security solutions based on the unique network environment. Static networks demand rapid detection and isolation procedures, whereas mobile an

关键词： Performance evaluation Energy consumption Network topology Throughput Routing Routing protocols Delays Topology Security Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Structured multi-track accompaniment arrangement via style prior modelling 24

Structured multi-track accompaniment arrangement via style p...

引用

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

作者： Jingwei Zhao Gus Xia Ziyu Wang Ye Wang Institute of Data Science NUS and Integrative Sciences and Engineering Programme NUS Graduate School Machine Learning Department MBZUAI and Computer Science Department NYU Shanghai Computer Science Department NYU Shanghai and Machine Learning Department MBZUAI School of Computing NUS and Institute of Data Science NUS and Integrative Sciences and Engineering Programme NUS Graduate School

ISBN: (纸本)9798331314385

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel system that leverages prior modelling over disentangled style factors to address these challenges. Our method presents a two-stage process: initially, a piano arrangement is derived from the lead sheet by retrieving piano texture styles; subsequently, a multi-track orchestration is generated by infusing orchestral function styles into the piano arrangement. Our key design is the use of vector quantization and a unique multi-stream Transformer to model the long-term flow of the orchestration style, which enables flexible, controllable, and structured music generation. Experiments show that by factorizing the arrangement task into interpretable sub-stages, our approach enhances generative capacity while improving efficiency. Additionally, our system supports a variety of music genres and provides style control at different composition hierarchies. We further show that our system achieves superior coherence, structure, and overall arrangement quality compared to existing baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VR-Fi: Positioning and Recognizing Hand Gestures via VR-embedded Wi-Fi Sensing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Hongbo Li, Xin Li, Jiachun Zhu, Haojin Luo, Jun Collaborative InitiativeInterdisciplinary Graduate Programme 639798 Singapore College of Computing and Data Science 639798 Singapore Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

Accurate gesture-based interactions are crucial for enhancing the immersive experience in VR (virtual reality) systems;they in turn necessitate gesture positioning and recognition in physical world. However, existing VR gesture recognition methods are predominantly vision-based, incurring high computational demands and raising privacy concerns. Meanwhile, Wi-Fi-based gesture recognition methods, deemed as promising complement to vision-based ones, typically lack gesture positioning capabilities. To this end, we propose VR-Fi, a gesture positioning and recognition system leveraging VR(-headset)-embedded Wi-Fi. To position gestures across different areas, VR-Fi innovates in a frequency-hopping bandwidth expansion (FHBE) technique to improve spatial resolution for locating a target. Additionally, VR-Fi innovates in neural models to process the FHBE-enhanced Wi-Fi CSI (channel state information) and enable the multi-task requirements of the joint positioning and recognition of hand gestures. Extensive experimental results demonstrate that VR-Fi achieves a positioning accuracy of 94.47%, a recognition accuracy of 92.13%, and a joint accuracy of 89.47%. © 2002-2012 IEEE.

关键词： Frequency hopping

来源：评论

学校读者我要写书评

暂无评论

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders 41

Purify Unlearnable Examples via Rate-Constrained Variational...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Yi Wang, Yufei Xia, Song Yang, Wenhan Lu, Shijian Tan, Yap-Peng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Computer Science and Engineering Nanyang Technological University Singapore

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (D-VAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://***/yuyi-sd/D-VAE. Copyright 2024 by the author(s)

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Exploring the impact of stratification on the dynamics of bioconvective thixotropic fluid conveying tiny particles and Cattaneo-Christov model:Thermal storage system application

引用

Propulsion and Power Research 2024年第3期13卷 416-432页

作者： T.Oreyeni M.D.Shamshuddin A.M.Obalalu A.Saeed Nehad Ali Shah Department of Physical Sciences Mathematics Programme UnitPrecious Cornerstone UniversityIbadanNigeria Department of Computer Science and Artificial Intelligence(Mathematics) SR UniversityWarangalTelangana State 506371India Department of Mathematics Augustine University Ilara EpeLagosNigeria Center of Excellence in Theoretical and Computational Science(TaCS-CoE) Faculty of ScienceKing Mongkut’s University of Technology Thonburi(KMUTT)126 Pracha Uthit Rd.BangModThung KhruBangkok 10140Thailand Department of Mathematics and Statistics College of ScienceImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh 11623Saudi Arabia

Stratified thermal storage promotes energy sustainability by storing excess energy during times of low demand for later use making it possible to integrate renewable energy sources like solar and *** communication discusses the significance of triple stratifica-tion using the Cattaneo-Christov model in the bioconvectiveflow of thixotropicfluid coexisting with nanoparticles and gyrotactic *** Cattaneo-Christov heat and massflux is incorporated into thefluid model allowing more accurate prediction of heat and mass phenomena in thefluid *** governing partial differential equations that describefluidflow are parametrized to yield an ordinary differential equation system by adopting suitable *** series solutions are obtained by applying the homotopy analysis method(HAM).The effects of relevant parameters on the various profiles are revealed and accurately *** is observed that amplified thermal stratification lowers the temperature of ***,Brownian motion is used to illustrate the random movement of small particles suspended in liquids,and it is envisioned that the concentration distribution is significantly influenced by the Brownian motion of nanoparticles.

关键词： Cattaneo-Christov model Stratification Bioconvection Nanofluid

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：