检索结果-内蒙古大学图书馆

21st Sound and Music Computing Conference, SMC 2024

作者： Presti, Giorgio Degiorgi, Nicola Fresia, Amedeo Servetti, Antonio Department of Computer Science University of Milan Italy Control and Computer Engineering Department Politecnico di Torino Italy

ISBN: (纸本)9789893520758

This work presents a prototype for the automatic and real-time psychoacoustic frequency masking effect compensation. This tool is intended to handle audio signals with overlapping spectra coming from two different mono or stereo sources in order to emphasise those frequencies of a main source that the second one masks. The goal is achieved using a dynamic equaliser controlled by a function of the differences of the input spectra psychoacoustic models. The tool has been prototyped as a standard Virtual Studio Technology (VST3) plugin and its effectiveness has been tested with a user study carried out in the context of music production. © 2024. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original.

关键词： Psychoacoustic

来源：评论

学校读者我要写书评

暂无评论

Flood Risk Assessment and Interpretation Using Explainable AI 2

Flood Risk Assessment and Interpretation Using Explainable A...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Sharma, Swati Tomar, Vivek Arora, Sangeeta Gupta, Nishant KIET Group of Institutions Delhi - NCR Computer Science & Engineering Department Ghaziabad India University Computer Science & Engineering Department Dehradun India KIET Group of Institutions Delhi-NCR Computer Applications Department Ghaziabad India SET Department of Computer Science & Engineering Sharda University Greater Noida India

ISBN: (纸本)9798350368109

Floods are the unforeseen situations to the society which causes high risk to the society. For proactive action, it is important to identify locations based on past results. It is necessary to take measures before the situation gets worst. For the benefit of society, a novel approach to map flood risk usinga balanced dataset and an Extra Tree Classifier. The Extra Tree Classifier performs better with the Shapely Additive explanation values. It shows improvement towards decision making processes to reduce the causality at the time of floods. The proposed method achieves the accuracy of 93.61% for the estimating flood danger effects on a particular location. In this paper quantitative study was done to handle the challenges to predict the flood danger using the artificial intelligence ethically. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Insights: Leveraging Analytics for Predictive Modeling in Finance 4

Data-Driven Insights: Leveraging Analytics for Predictive Mo...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Purwar, Mitali Deka, Upasana Raj, Himadri Ritu Upes Department of Computer Science & Engineering Dehradun India Noida Institute of Engineering & Technology Department of Computer Science & Engineering Greater Noida India Chandigarh College of Engineering Chandigarh Group of Colleges Department of Computer Science & Engineering Jhanjeri140307 India

ISBN: (纸本)9798350387490

A distinct gap in the most recent business intelligence literature is addressed by this research, which discusses the possibility of radical changes in the market based on the application of predictive analytics. The key goal is to evaluate the impact of the prediction models on ethics, expansiveness, precision and reliability. The evaluation is of a qualitative nature, and topic analysis along with case histories is used to acquire specific, contextualised data. Basic findings indicate that employment of market forecasting skills is enhanced through the use of predictive models since decisions are made much more deliberately. The analysis reveals that these models remain prone to change in a variety of contexts and demonstrates their capacity to deal with large data efficiently. Ethical issues is stressed out, which leads to the conclusion that there should be stricter rules for personal data protection and more openness for procedures to gain the compliance and trust. The conclusions underline the major competitive advantages that, if applied line by line, predictive analytics can offer, calling for more adaptability and sensitivity to the market trends. This report which proposes a 50-50 mix of value creation and integrity does, nonetheless;provide notice of potential ethical issues and data privacy. The guidelines for enhancing the accuracy of the prediction, which complies with the ethical standard are strengthening the information management system and developing novel predictive model technologies. Future research must continue to analyze shifts in predictive analytics understanding new technologies and possible changes in the market. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Multidimensional image morphing-fast image-based rendering of open 3D and VR environments

引用

虚拟现实与智能硬件(中英文) 2025年第2期7卷 155-172页

作者： Simon SEIBT Bastian KUTH Bartosz von Rymon LIPINSKI Thomas CHANG Marc Erich LATOSCHIK Game Tech Laboratory Faculty of Computer ScienceNuremberg Institute of TechnologyNuremberg 90489Germany Department of Electrical Engineering and Computer Science Coburg University of Applied Sciences and ArtsCoburg 96450Germany Human-Computer Interaction Group Institute of Computer ScienceUniversity of WuerzburgWuerzburg 97074Germany

Background In recent years,the demand for interactive photorealistic three-dimensional(3D)environments has increased in various fields,including architecture,engineering,and ***,achieving a balance between the quality and efficiency of high-performance 3D applications and virtual reality(VR)remains *** This study addresses this issue by revisiting and extending view interpolation for image-based rendering(IBR),which enables the exploration of spacious open environments in 3D and ***,we introduce multimorphing,a novel rendering method based on the spatial data structure of 2D image patches,called the image *** this approach,novel views can be rendered with up to six degrees of freedom using only a sparse set of *** rendering process does not require 3D reconstruction of the geometry or per-pixel depth information,and all relevant data for the output are extracted from the local morphing cells of the image *** detection of parallax image regions during preprocessing reduces rendering artifacts by extrapolating image patches from adjacent cells in *** addition,a GPU-based solution was presented to resolve exposure inconsistencies within a dataset,enabling seamless transitions of brightness when moving between areas with varying light *** Experiments on multiple real-world and synthetic scenes demonstrate that the presented method achieves high"VR-compatible"frame rates,even on mid-range and legacy hardware,*** achieving adequate visual quality even for sparse datasets,it outperforms other IBR and current neural rendering *** Using the correspondence-based decomposition of input images into morphing cells of 2D image patches,multidimensional image morphing provides high-performance novel view generation,supporting open 3D and VR ***,the handling of morphing artifacts in the parallax image regions remains a topic for future resea

关键词： computer graphics 3D real-time rendering computer vision Image morphing Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Supervised Machine Learning in Cardiology: A Predictive Model for Heart Disease 11

Supervised Machine Learning in Cardiology: A Predictive Mode...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Mall, Anamika Singh, Ankita Bansal, Ayush Gupta, Hriday Kumar Kiet Group of Institutions Department of Computer Science and Engineering UP Ghaziabad India

ISBN: (纸本)9798350350357

One of the worst diseases in the world, heart disease takes a great toll on lives every year. In order to treat this potentially fatal illness, a tool or gadget must be practical, accurate, and dependable. This will allow for prompt detection or prediction, which will lead to efficient treatment and a decline in death rates. The heart is the most important organ in the human body, second only to the brain, and it is vital to the circulation of blood to all organs. A swift and accurate diagnostic method is imperative to mitigate the high mortality associated with cardiac disorders. Predicting the incidence of these disorders holds paramount importance in the medical domain. In the contemporary era, machine learning techniques prove invaluable for predicting and automating the interpretation of extensive and intricate datasets in various fields, including medicine. This research introduces a statistical model for heart disease, aiding medical examiners and cardiac practitioners in forecasting based on fundamental aspects of a patient's health history. The model, constructed using a Decision Tree, achieves an impressive accuracy of approximately 97%. The crucial functions of machine learning, data analytics, and data mining highlight how important these technologies are to improving the diagnosis and treatment of cardiac disorders. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

ELCD-NSC2: a novel early lung cancer detection and non-small cell classification framework

引用

Neural Computing and Applications 2024年第24期36卷 15149-15164页

作者： Helaly, Hadeer A. Badawy, Mahmoud El-Gendy, Eman M. Haikal, Amira Y. Electrical Engineering Department Faculty of Engineering Damietta University Damietta Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Department of Computer Science and Informatics Taibah University Medina Saudi Arabia

The survival rate of lung cancer relies significantly on how far the disease has spread when it is detected, how it reacts to the treatment, the patient’s overall health, and other factors. Therefore, the earlier the lung cancer diagnosis, the higher the survival rate. For radiologists, recognizing malignant lung nodules from computed tomography (CT) scans is a challenging and time-consuming process. As a result, computer-aided diagnosis (CAD) systems have been suggested to alleviate these burdens. Deep-learning approaches have demonstrated remarkable results in recent years, surpassing traditional methods in different fields. Researchers are currently experimenting with several deep-learning strategies to increase the effectiveness of CAD systems in lung cancer detection with CT. This work proposes a deep-learning framework for detecting and diagnosing lung cancer. The proposed framework used recent deep-learning techniques in all its layers. The autoencoder technique structure is tuned and used in the preprocessing stage to denoise and reconstruct the medical lung cancer dataset. Besides, it depends on the transfer learning pre-trained models to make multi-classification among different lung cancer cases such as benign, adenocarcinoma, and squamous cell carcinoma. The proposed model provides high performance while recognizing and differentiating between two types of datasets, including biopsy and CT scans. The Cancer Imaging Archive and Kaggle datasets are utilized to train and test the proposed model. The empirical results show that the proposed framework performs well according to various performance metrics. According to accuracy, precision, recall, F1-score, and AUC metrics, it achieves 99.60, 99.61, 99.62, 99.70, and 99.75%, respectively. Also, it depicts 0.0028, 0.0026, and 0.0507 in mean absolute error, mean squared error, and root mean square error metrics. Furthermore, it helps physicians effectively diagnose lung cancer in its early stages and allows spe

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Optimizing Storage for Energy Conservation in Tracking Wireless Sensor Network Objects

引用

computer Systems science & engineering 2023年第5期45卷 1211-1231页

作者： Vineet Sharma Mohammad Zubair Khan Shivani Batra Abdullah Alsaeedi Prakash Srivastava Department of Computer Science and Engineering KIET Group of InstitutionsDelhi-NCRGhaziabad201206India Department of Computer Science and Information Taibah UniversityMedina42353Saudi Arabia Department of Computer Science Taibah UniversityMedina42353Saudi Arabia Department of Computer Science and Engineering Graphic Era(Deemed to be University)Dehradun248002India

The amount of needed control messages in wireless sensor networks(WSN)is affected by the storage strategy of detected *** broadcasting superfluous control messages consumes excess energy,the network lifespan can be extended if the quantity of control messages is *** this study,an optimized storage technique having low control overhead for tracking the objects in WSN is *** basic concept is to retain observed events in internal memory and preserve the relationship between sensed information and sensor nodes using a novel inexpensive data structure entitled Ordered Binary Linked List(OBLL).Whenever an object passes over the sensor area,the recognizing sensor can immediately produce an OBLL along the object’s *** retrieve the entire information,the OBLL can be traversed with logarithmic complexity which is much less than the traversing complexity of existing linked list *** evaluation and simulations were carried out to ensure that the suggested technique minimizes the number of messages and thus saving energy and extending the network life.

关键词： Energy conservation linked list object tracking wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Interactive Agent Foundation Model: A Meta-Learning Strategy 3

Interactive Agent Foundation Model: A Meta-Learning Strategy

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Dwivedi, Mani Dwivedi, Anuj Kr. KIET Group of Institutions Delhi-NCR Department of Computer Science and Engineering Ghaziabad India Galgotias College of Engineering and Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798331523893

Artificial intelligence (AI) systems are evolving from static, task-specific models to dynamic, agent-based systems that perform well in a variety of scenarios. We present an Interactive Agent Foundation Model using a novel multi-task agent training methodology that includes many pretraining techniques such as language modelling, visual masked autoencoders, and next-action prediction. This framework's adaptability and versatility have been shown in the robotics, gaming AI, and healthcare sectors, yielding results that are pertinent to the situation. Effective multimodal and multitask learning is made possible by utilizing a variety of data sources, such as textual information, gaming data, robotics sequences, and large-scale video datasets. Our method offers a viable way forward for creating adaptable, proactive, multimodal systems. © 2025 IEEE.

关键词： Robot learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Algorithm for Handwritten Document Enhancement

引用

computers, Materials & Continua 2024年第3期78卷 3763-3786页

作者： Shu-Chuan Chu Xiaomeng Yang Li Zhang Václav Snášel Jeng-Shyang Pan College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China School of Information and Control Engineering Qingdao University of TechnologyQingdao266520China Faculty of Electrical Engineering and Computer Science VŠB-TU OstravaOstrava70080Czech Republic Department of Information Management Chaoyang University of TechnologyTaichung41349Taiwan

The Gannet Optimization Algorithm (GOA) and the Whale Optimization Algorithm (WOA) demonstrate strong performance;however, there remains room for improvement in convergence and practical applications. This study introduces a hybrid optimization algorithm, named the adaptive inertia weight whale optimization algorithm and gannet optimization algorithm (AIWGOA), which addresses challenges in enhancing handwritten documents. The hybrid strategy integrates the strengths of both algorithms, significantly enhancing their capabilities, whereas the adaptive parameter strategy mitigates the need for manual parameter setting. By amalgamating the hybrid strategy and parameter-adaptive approach, the Gannet Optimization Algorithm was refined to yield the AIWGOA. Through a performance analysis of the CEC2013 benchmark, the AIWGOA demonstrates notable advantages across various metrics. Subsequently, an evaluation index was employed to assess the enhanced handwritten documents and images, affirming the superior practical application of the AIWGOA compared with other algorithms.

关键词： Metaheuristic algorithm gannet optimization algorithm hybrid algorithm handwritten document enhancement

来源：评论

学校读者我要写书评

暂无评论

Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes 38

Achieving Near-Optimal Convergence for Distributed Minimax O...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Huang, Yan Li, Xiang Shen, Yipeng He, Niao Xu, Jinming College of Control Science and Engineering Zhejiang University China Department of Computer Science ETH Zurich Switzerland

In this paper, we show that applying adaptive methods directly to distributed minimax problems can result in non-convergence due to inconsistency in locally computed adaptive stepsizes. To address this challenge, we propose D-AdaST, a Distributed Adaptive minimax method with Stepsize Tracking. The key strategy is to employ an adaptive stepsize tracking protocol involving the transmission of two extra (scalar) variables. This protocol ensures the consistency among stepsizes of nodes, eliminating the steady-state error due to the lack of coordination of stepsizes among nodes that commonly exists in vanilla distributed adaptive methods, and thus guarantees exact convergence. For nonconvex-strongly-concave distributed minimax problems, we characterize the specific transient times that ensure timescale separation of stepsizes and quasi-independence of networks, leading to a near-optimal convergence rate of Õ (ϵ-(4+δ)) for any small δ > 0, matching that of the centralized counterpart. To our best knowledge, D-AdaST is the first distributed adaptive method achieving near-optimal convergence without knowing any problem-dependent parameters for nonconvex minimax problems. Extensive experiments are conducted to validate our theoretical results. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：