检索结果-内蒙古大学图书馆

2023 International Conference on Smart Systems for Applications in Electrical Sciences, ICSSES 2023

作者： Arunakumari, B.N. Shashidhar, R. Sahana, B. Jagadamba, G. Manjunath, A.S. Roopa, M. Bms Institute of Technology and Management Dept. of Computer Science and Engineering Bengaluru India Jss Science and Technology University Dept. of Electronics & Communication Engineering Mysuru India Rv College of Engineering Dept. of Electronics & Communication Engineering Bengaluru India Siddaganga Institte of Technology Dept. of Information Science and Engineering Tumkuru India Jss Science and Technology University Dept. of Master of Computer Applications Mysuru India Dayananda Sagar College of Engineering Dept. of Electronics & Communication Bengaluru India

ISBN: (纸本)9798350347296

A condensed content-based signature that summarises an audio recording is known as an audio fingerprint. Audio The capability to recognize music regardless of design and without the use of meta-data or watermark embedding has made fingerprinting technologies popular. In. tegrity checking, watermark support, and content-based aural retrieval are additional applications for fingerprinting. The various methods of fingerprinting have been discussed using various justifications and terminologies, such as pattern matching, multimedia information retrieval, or cryptography. It is a distinct and condensed digest created using perceptually important elements of a video. Audio material can be monitored using fingerprinting technologies without requiring embedding of metadata or watermarks. However, audio fingerprinting has extra applications The algorithm is trained using thousands of mini audio speech commands. In order to improve the training efficiency, audio features are extracted during a pre-processing. The accuracy of the developed model is 83.7%. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Stock Price Prediction: A Comprehensive Approach Using Bi-LSTM 4

Deep Learning-Based Stock Price Prediction: A Comprehensive ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Chy, Md. Kalim Amzad Masum, Abdul Kadar Muhammad Alam, Mohammed Shamsul Azad, Md. Abul Kalam Hassan, Md. Maruf Bhuiyan, Touhid International Islamic University Dept. of Computer Science and Engineering Chittagong Bangladesh Daffodil International University Dept. of Software Engineering Dhaka Bangladesh Islamic University of Technology Dept. of Business and Technology Management Gazipur Bangladesh School of It Washington University of Science and Technology VA United States

ISBN: (纸本)9798331529635

This study delves into the prediction of stock prices in the Bangladesh stock market using advanced deep learning frameworks, with a particular focus on the Bidirectional Long Short-Term Memory (Bi-LSTM) model. Traditional statistical models often struggle to effectively capture the complex, non-linear characteristics of financial data, leading to inconsistent results. The Bi-LSTM model, however, addresses this challenge by processing data in both forward and backward sequences, making it particularly suitable for analyzing the intricate dynamics of the Bangladesh stock market. A rigorous feature engineering process is undertaken, incorporating 64 distinct features that include market trends, stock-specific indicators, technical and fundamental variables, as well as crucial macroeconomic factors like gold prices and foreign exchange reserves. The dataset spans historical stock market data from 2012 to 2022, with comprehensive preprocessing steps taken to ensure data quality and consistency. Hyperparameter tuning is executed through a grid search to optimize model performance. The evaluation of the Bi-LSTM model is carried out using metrics such as Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and the R2 score, which demonstrate its enhanced predictive power compared to traditional models. This research contributes to the growing field of deep learning in financial forecasting, offering new perspectives for stock price prediction in emerging markets, while also addressing ethical issues to minimize risks like market manipulation. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Enhancing Graph Representation of the Environment through Local and Cloud Computation

arXiv

引用

arXiv 2023年

作者： Argenziano, Francesco Suriani, Vincenzo Nardi, Daniele Dept. of Computer Control and Management Engineering Sapienza University of Rome Italy

Enriching the robot representation of the operational environment is a challenging task that aims at bridging the gap between low-level sensor readings and high-level semantic understanding. Having a rich representation often requires computationally demanding architectures and pure point cloud based detection systems that struggle when dealing with everyday objects that have to be handled by the robot. To overcome these issues, we propose a graph-based representation that addresses this gap by providing a semantic representation of robot environments from multiple sources. In fact, to acquire information from the environment, the framework combines classical computer vision tools with modern computer vision cloud services, ensuring computational feasibility on onboard hardware. By incorporating an ontology hierarchy with over 800 object classes, the framework achieves cross-domain adaptability, eliminating the need for environment-specific tools. The proposed approach allows us to handle also small objects and integrate them into the semantic representation of the environment. The approach is implemented in the Robot Operating System (ROS) using the RViz visualizer for environment representation. This work is a first step towards the development of a general-purpose framework, to facilitate intuitive interaction and navigation across different domains. © 2023, CC BY.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Further Results on the Structure of Normal Forms of Input-Affine Nonlinear MIMO Systems

Further Results on the Structure of Normal Forms of Input-Af...

引用

IEEE Conference on Decision and control

作者： Alberto Isidori Dept. of Computer Control and Management Engineering University “Sapienza” Rome Italy

In a recent paper it has been shown that the existence, for a MIMO nonlinear system, of normal forms with a special structure that proves to be useful in the design of feedback laws is implied by an assumption introduced a long time ago by Hirschorn in his work on systems invertibility. In this paper, we provide an alternative viewpoint and prove that a necessary and sufficient condition for the existence of such kind of normal forms can be identified in a special feature of the so-called maximal controlled invariant distribution algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A/B Testing and Audience Creation for Effective Digital Marketing: Evidences from Facebook Analytics 6

A/B Testing and Audience Creation for Effective Digital Mark...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Singh, Nripendra Jaiswal, Anand Singh, Prakhar Sharma, Dilip Kr. PennWest University Dept. of Management and Marketing Clarion United States New Delhi Institute of Management Dept. of Operations and Scm Delhi India PennWest University Computer Information Science Department Clarion United States GLA University Dept. of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350346961

Digital marketers use a number of strategies, including custom audiences, lookalike audiences, ad creative, and A/B testing, to organize and enhance how they present advertisements to consumers. The purpose of this research is to show an effective method and process for running advertisements on Facebook more efficiently. The study has taken a case study of a company- Great Deal Tires and analyzed the Facebook analytics data and insights with A/B testing and audience creation approach to assess the digital marketing impact. The study has implemented three test strategies for designing and placing Facebook ads for Great Deal Tires in order to assess the marketing impact. In the first test, a custom audience was chosen, and an identical Facebook video ad's impact was evaluated based on the duration of the ad. In the second test, A/B testing was used to test Facebook ads, and the results of the tests were compared across three different audience groups to determine how well the ads performed. The third test evaluated on the audience conversion in the terms of subscribing to the Page, in which three different ads were shown to three distinct audience groups in order to compare the effects of the various ads on the diverse audiences. The study's findings provided important information about Facebook ad placement, its effects on various audience segments, and digital marketing strategies to increase audience outreach. The study is important in demonstrating that Facebook advertisements are an effective marketing medium and a digital marketer can achieve good outreach with a modest investment of funds.. © 2023 IEEE.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

Study of the Process of Porous Materials Impregnation Using the Example of Leather Tanning 18

Study of the Process of Porous Materials Impregnation Using ...

引用

18th International Scientific and Technical Conference on Dynamics of Systems, Mechanisms and Machines, Dynamics 2024

作者： Damdinova, T.Ts. Radnaeva, V.D. Dept. Engineering and Computer Graphics Dept. Leather and Fur Technology. Water Resources and Commodity Research of Non-Food Goods East Siberia State University of Technology and Management Ulan-Ude Russia

ISBN: (纸本)9798331509019

The paper presents the results of the study of the process of porous materials impregnation from the point of view of percolation theory. Diffusion front, diffusion front shell, percolation cluster are determined using developed application. Processing of digital images obtained during the study of the porous object impregnation is used. This allowed obtaining the necessary quantitative characteristics of the diffusion front, percolation clusters and percolation shell. Quantitative characteristics were analyzed and kinetic curves of the impregnation process were constructed on the example of leather tanning process. As a result, the main stages of the impregnation process of the tanning composition: accumulation, percolation and distribution have been revealed. The methodology of the impregnation process study and the method of its visualization have been developed and applied to the processes of leather tanning. The universality of this development will allow applying them to the study processes in other porous materials, and in modeling and creation of new materials. © 2024 IEEE.

关键词： Leather

来源：评论

学校读者我要写书评

暂无评论

Detection of Multi-Class Multi-Label Ophthalmological Diseases in Retinal Fundus Images Using Machine Learning

Detection of Multi-Class Multi-Label Ophthalmological Diseas...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Karule, P.T. Bhele, Sujata B. Palsodkar, Prasanna Agarkar, Poonam T. Hajare, Hirendra R. Patil, Prashant R. Yeshwantrao Chavan College of Engineering Dept. of Electronics Engineering M.S Nagpur India Government College of Engineering Dept. of Electronics & Telecommunication Engineering M.S Nagpur India Ballarpur Institute of Technology Dept. of Computer Science and Engineering M.S Chandrapur India Smt. Radhikatai Pandav College of Engineering Dept. of Management Studies M. S Nagpur India

ISBN: (纸本)9798350319019

Multi-disease diagnosis of fundus image is a great challenge even though sophisticated computer-aided tools are available and ophthalmologist experience is to par. Clinical tests capture abnormalities and anatomical structures for various diagnoses of the retinal image. The proposed work uses RFMiD (Retinal Fundus Multi-Disease Image Dataset) to classify ocular diseases using an efficient feature extraction framework and machine learning. The framework considers 8-12 diverse ophthalmological diseases from 3200 dataset images labeled with the help of two senior medical (retinal) experts. Experimental evaluation of the dataset using Random forest classified up to 10 diseases with an accuracy of 100% while 96.75% was obtained when 12 diseases were considered without augmenting the dataset images. The evaluation successfully determined the retinal infection due to fine-grained variability, appearance, and closeness in the presence of several lesions. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Ophthalmic Diagnostics: CNNs in Cataract Detection 2

Enhancing Ophthalmic Diagnostics: CNNs in Cataract Detection

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Solanki, Kartik Singh, Shaurya Pratap Yadav, Aman Sharma, Vikrant Awasthi, Shashank Vats, Satvik Graphic Era Hill University Dept. of Computer Science Uttarakhand Dehradun India G.L. Bajaj Institute of Management Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350371055

Cataracts have been one of the most prevalent eye disorders, which often can cause significant visual impairment due to the clouding of the eye's lens. This condition can worsen in future, often leading to severe vision problems and even blindness. Consequently, detecting cataracts is paramount in mitigating the associated risks and preventing the onset of blindness. Throughout the years there has been quite good progress in leveraging cutting-edge technology, especially due to machine learning, to improve the perfection and efficacy of cataract detection. Convolutional Neural Networks (CNNs) have made an appearance as a commanding implement for computerized the systematization of eye images in the context of cataract identification. Proposed research was more concerned with fine-tune the process of cataract identification, aiming to increase the accuracy while minimizing the data loss. To accomplish this, we conducted a series of experiments, with a key focus on manipulating a critical parameter: the number of training epochs. The proposed research revealed a compelling relationship between the number of training epochs and the accuracy and loss of data in CNN. As we delved into a spectrum of epoch values, a clear pattern emerged: the higher the number of epochs, the more refined and potent the model became. In this research, a significant milestone was reached when utilizing a generous number of 90 epochs, resulting in an impressive accuracy rate of 97.37%. © 2024 IEEE.

关键词： Cataract detection Convolutional Neural Network (CNNs) Deep learning efficacy Eye disorders Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Learning on the Edge: Online Learning with Stochastic Feedback Graphs 36

Learning on the Edge: Online Learning with Stochastic Feedba...

引用

36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Esposito, Emmanuel van der Hoeven, Dirk Fusco, Federico Cesa-Bianchi, Nicolò Dept. of Computer Science Università degli Studi di Milano Italy Istituto Italiano di Tecnologia Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy

ISBN: (纸本)9781713871088

The framework of feedback graphs is a generalization of sequential decision-making with bandit or full information feedback. In this work, we study an extension where the directed feedback graph is stochastic, following a distribution similar to the classical Erdős-Rényi model. Specifically, in each round every edge in the graph is either realized or not with a distinct probability for each edge. We prove nearly optimal regret bounds of order (Equation presented) (ignoring logarithmic factors), where αΕ and δΕ are graph-theoretic quantities measured on the support of the stochastic feedback graph G with edge probabilities thresholded at Ε. Our result, which holds without any preliminary knowledge about G, requires the learner to observe only the realized out-neighborhood of the chosen action. When the learner is allowed to observe the realization of the entire graph (but only the losses in the out-neighborhood of the chosen action), we derive a more efficient algorithm featuring a dependence on weighted versions of the independence and weak domination numbers that exhibits improved bounds for some special cases. © 2022 Neural information processing systems foundation. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Differential Co-expression Network Analysis to Investigate Sexual Dimorphism in Colon Cancer

Differential Co-expression Network Analysis to Investigate S...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Alfano, Caterina Farina, Lorenzo Petti, Manuela Sapienza University of Rome PhD Program in Network Oncology and Precision Medicine Rome Italy Sapienza University of Rome PhD Program in Network Oncology and Precision Medicine Dept. of Computer Control and Management Engineering Rome Italy Sapienza University of Rome Dept. of Computer Control and Management Engineering Rome Italy

ISBN: (纸本)9781665468190

Colorectal cancer is the third most diagnosed cancer in the world, but it has a higher mortality rate in men compared to women. However, we are not close to understanding how and why sex influences the outcome of the disease. This study focuses on mRNA expression profiles of colon cancer patients to look for molecular differences in the development of colon cancer between men and women. We used paired expression data (i.e., data collected in pairs of normal and cancer cells, by taking samples from the same individual), we identified differentially expressed genes (cancer vs normal) and computed co-expression and differential co-expression gene networks (men vs women). Doing so, we inferred the main changes and alterations happening in cancer tissues, and specifically how these changes were different among men and women. We found that the co-expression networks of women and men affected by colon cancer are quite different and we reported the genes that show the most differences in this comparison, checking if they could also be associated to sexual dimorphism or sexual hormones. Among these genes we found a interesting presence of genes associated to the Wnt signaling pathway which has been found to be regulated by estrogen and whose activation is strongly linked with colon cancer. © 2022 IEEE.

关键词： Diseases

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：