检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Roy, Santanu Singh, Shweta Sahu, Palak Suresh, Ashvath Das, Debashish Computer Science and Engineering Department NIIT University Jaipur India Bangalore India Faculty of Computing Engineering and the Built Environment Birmingham City University United Kingdom

Lung cancer, a severe form of malignant tumor that originates in the tissues of the lungs, can be fatal if not detected in its early stages. It ranks among the top causes of cancer-related mortality worldwide. Detecting lung cancer manually using chest X-Ray image or Computational Tomography (CT) scans image poses significant challenges for radiologists. Hence, there is a need for automatic diagnosis system of lung cancers from radiology images. With the recent emergence of deep learning, particularly through Convolutional Neural Networks (CNNs), the automated detection of lung cancer has become a much simpler task. Nevertheless, numerous researchers have addressed that the performance of conventional CNNs may be hindered due to class imbalance issue, which is prevalent in medical images. In this research work, we have proposed a novel CNN architecture "Multi-Scale Dense Network (MSD-Net)" (trained-from-scratch). The novelties we bring in the proposed model are (I) We introduce novel dense modules in the 4th block and 5th block of the CNN model. We have leveraged 3 depthwise separable convolutional (DWSC) layers, and one 1×1 convolutional layer in each dense module, in order to reduce complexity of the model considerably. (II) Additionally, we have incorporated one skip connection from 3rd block to 5th block and one parallel branch connection from 4th block to Global Average Pooling (GAP) layer. We have utilized dilated convolutional layer (with dilation rate=2) in the last parallel branch in order to extract multi-scale features. Extensive experiments reveal that our proposed model has outperformed latest CNN model ConvNext-Tiny, recent trend Vision Transformer (ViT), Pooling-based ViT (PiT), and other existing models by significant margins. All the codes of these experiments along with its graphs and confusion matrix are provided on a GitHub link: https://***/Singhsshweta/Lung-Cancer-Detection. © 2025, CC BY.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Hierarchal Clustered Based Proactive Caching in NDN-Based Vehicular Network

引用

computer Systems science & engineering 2023年第10期47卷 1185-1208页

作者： Muhammad Yasir Khan Muhammad Adnan Jawaid Iqbal Noor ul Amin Byeong-Hee Roh Jehad Ali Department of Computer Science&Information Technology Hazara University Mansehra21120Pakistan Department of Electronics Engineering Kookmin University Seoul Korea Faculty of Computing Riphah International University Islamabad Pakistan Department of AI Convergence Network Ajou UniversitySuwon16499Korea

An Information-Centric Network(ICN)provides a promising paradigm for the upcoming internet architecture,which will struggle with steady growth in data and changes in *** ICN architectures have been designed,including Named Data Networking(NDN),which is designed around content delivery instead of *** data is the central part of the ***,NDN was developed to get rid of the dependency on IP addresses and provide content *** is one of the major research dimensions for this upcoming internet *** research has been carried out to solve the mobility issues,but it still has problems like handover delay and packet loss ratio during real-time video streaming in the case of consumer and producer *** solve this issue,an efficient hierarchical Cluster Base Proactive Caching for Device Mobility Management(CB-PC-DMM)in NDN Vehicular Networks(NDN-VN)is proposed,through which the consumer receives the contents proactively after handover during the mobility of the *** a consumer moves to the next destination,a handover interest is sent to the connected router,then the router multicasts the consumer’s desired data packet to the next hop of neighboring ***,once the handover process is completed,consumers can easily get the content to the newly connected router.A CB-PCDMM in NDN-VN is proposed that improves the packet delivery ratio and reduces the handover delay aswell as cluster ***,the intra and inter-domain handover handling procedures in CB-PC-DMM for NDN-VN have been *** the validation of our proposed scheme,MATLAB simulations are *** simulation results show that our proposed scheme reduces the handover delay and increases the consumer’s interest satisfaction *** proposed scheme is compared with the existing stateof-the-art schemes,and the total percentage of handover delays is decreased by up to 0.1632%,0.3267%,2.3437%,2.3255%,and 3.7313%at the mobil

关键词： Vehicular network named data networking caching hierarchical architecture

来源：评论

学校读者我要写书评

暂无评论

Intelligent Online Shopping using ML-based Product Comparison Engine

Intelligent Online Shopping using ML-based Product Compariso...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： K Harikirshnan. R Nagavigneshwar. R Vignesh. R. Santhosh R. Reshma Department of Computer Science and Engineering Faculty of Engineering Karpagam Academy of Higher Education Coimbatore Tamil Nadu India

A relatively recent technique for gathering data online is known as scraping. The automated process involves the exploration of e-commerce websites and obtaining certain data, such as pricing, reviews, quality features, etc. Sentiment analysis of product attributes on e-commerce platforms, such as pricing, reviews, quality, etc., can substantially increase user satisfaction in the e-commerce industry. It continues to be difficult to envision precise sentiment analysis. This research work summarizes the product comparison website that implements intelligent web scraping. The website has a processing model that uses the Machine Learning (ML)-based product comparison engine. The simulation analysis for model training and testing uses the GitHub dataset and the Support Vector Machine (SVM) algorithm. The SVM classifies the product from various websites based on the rank value, assigned based on the selected features of the product. The proposed model is compared with other ML algorithms such as Decision Tree, Naïve Bayes, and Random Forest. The comparative analysis shows that the SVM algorithm can classify the best products with the highest accuracy ratio of 94.71%over other algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study of Cryptographic Primitives in the context of Blockchain's Data Integrity and Privacy 11

A Study of Cryptographic Primitives in the context of Blockc...

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Singh, Ramveer Pooja Agarwal, Ambuj Kumar Naaz, Rohaila Kumar, Raj Vijay, Richa Greater Noida Institute of Professional Studies Greater Noida India School of Engineering and Technology Ct University Ludhiana India School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India Teerthanker Mahaveer University Faculty of Engineering and Computing Sciences Moradabad India Department of Computer Applications Faridabad India

ISBN: (纸本)9781665487320

In Today's World, Blockchain is a promising Technology in all areas;things have also been drastically changed after COVID-19;challenges surfaced for implementing blockchain technology in the context of its computational complexity and security. After invention of it in 2008, cryptocurrency applications, i.e., Bitcoin it also getting introduced in Different applications. One of the Major Building blocks of Blockchain is Cryptography techniques. This paper discusses Cryptographic primitives used in different phases of Blockchain implementation and the challenges of implementing these cryptographic primitives. Bitcoin uses Cryptographic primitives to generate public-private key pairs and mining, while Ethereum uses Elliptic curve cryptography to create public-private keys and digital signatures. This paper divided uses of cryptographic primitives into three categories used in Blockchains, i.e., key generation Hashes, signature generation hashes, and proof hashes. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Proposal of high attenuating external magnetic field chamber for biological experiments

Proposal of high attenuating external magnetic field chamber...

引用

International Conference on Computational Problems of Electrical engineering (CPEE)

作者： Marek Bajtoš Robert Cichorowski Roman Radil Ladislav Janoušek Department of Electromagnetic and Biomedical Engineering Faculty of Electrical Engineering and Informational Technology Žilina Slovakia Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

ISBN: (数字)9798331506643

ISBN: (纸本)9798331506650

This work presents the design, construction, and validation of a chamber for magnetic field attenuation. Needs of magnetic background controlling during experiments focused on behavior of biological samples exposed to various levels of the low frequency time-varying magnetic field set the motivation for this work. The solution is proposed with regard to the correct cultivation conditions of microbiological samples. The chosen methodology is established on the means of numerical modeling and simulations, as well as 3D printing techniques. The design process incorporates computer-aided design (CAD) software for the chamber proposal, subsequent printing via a 3D printer, followed by the construction of an attenuating chamber using mu-metal foil. The validation process involves measurements of magnetic flux density within the chamber, and comparison thereof with numerical simulations performed via CST Design Studio. All the solution steps resulted in a valid and effective magnetic field attenuation chamber, suitable for use in laboratory conditions.

关键词： Solid modeling Time-frequency analysis Design automation Three-dimensional displays Computational modeling Attenuation Three-dimensional printing Numerical models Magnetic fields Proposals

来源：评论

学校读者我要写书评

暂无评论

Design Principles for Data-Driven Decision Evaluation

引用

Procedia computer science 2024年 239卷 563-574页

作者： Nada Elgendy Tero Päivärinta Ahmed Elragal Karoliina Hannula Kaisa Puolitaival M3S Faculty of Information Technology and Electrical Engineering University of Oulu Finland Department of Computer Science Electrical and Space Engineering Luleå University of Technology Sweden Antell Oulu Finland

Human-machine collaboration has potentially led to higher quality and more informed data-driven decisions. However, evaluating these decisions is necessary to measure the benefits, as well as enable experiential learning and posterior rationalization of the results and consequences. Nevertheless, the multiplicity of human-machine collaboration modes, as well as the multi-faceted nature of data-driven decisions complicates evaluation, and evaluation solutions are lacking both in research and in practice. This is further reflected in the complexity of incorporating evaluation in the design of such data-driven decision making systems, since developers are left without theoretically grounded and practically feasible principles to guide implementation. In this paper, we propose a set of five design principles, explicated from theory and practice, for systems implementing data-driven decision evaluation as the output of design science research cycles. The design principles are: 1) multi-faceted evaluation criteria, 2) unified viewpoint, 3) collaborative rationality, 4) processual ex-post evaluation, and 5) adaptive feedback and learning loops. They are further contextualized in the case of AI-enabled menu design at Antell, an innovative pioneer in the restaurant business in Finland, and consequently evaluated by the development managers of the project. Accordingly, the design principles contribute to the knowledge base on metahuman systems and data-driven decision evaluation, by concretizing existing normative concepts into prescriptive knowledge, also guiding future research and generalizing towards a design theory. Furthermore, they provide implementable statements for designing and developing such systems in practice and can be used as a checklist to compare and evaluate existing systems.

关键词： data-driven decision making human-machine collaboration ex-post evaluation collaborative rationality design principles

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Optimization Approaches for Dissolved Oxygen Prediction in River Systems

Machine Learning and Optimization Approaches for Dissolved O...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hazem Alnajjar Nadia Al-Rousan Douaa Al-Rouan Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AlBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan School of Civil Engineering Universiti Sains Malaysia Nibong Tebal Pulau Pinang MALAYSIA

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This study aims to combine optimization algorithms of feature selection and machine learning models for DO prediction at a water monitoring station. The dataset consisted of water quality indicators from three stations, whose DO was the target variable at the third station. This study used seven optimization algorithms to select the most relevant features. The selected features were then used along with ten machine-learning models for building predictive models. Several models were evaluated based on R 2 , MAE, and MSE metrics. Hence, Gradient Boosting and Random Forest models yielded better prediction results. The results showed high accuracy, reflected by the values of R 2 , which were 0.987 and 0.922 for the training data and 0.769 and 0.745 for the test data, respectively. The findings underscore the effectiveness of combining feature selection with optimized machine learning models for accurate DO prediction, which is essential for monitoring water quality.

关键词： Machine learning algorithms Biological system modeling Water quality Predictive models Prediction algorithms Feature extraction Rivers Water monitoring Optimization Random forests

来源：评论

学校读者我要写书评

暂无评论

Cloud based Weather Station using IoT Technology to Track the Air Parameters

Cloud based Weather Station using IoT Technology to Track th...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： S. Jayanthi E. Srividhya N. Ramshanka Srinivasan T R P. B. Edwin Prabhakar Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.D. Engineering College Chennai Tamil Nadu India Department of Computer Engineering Faculty of Electrical and Computer Engineering Jimma Institute of Technology Jimma University Jimma Ethiopia Department of Computer Science Engineering New Prince Shri Bhavani College of Engineering & Technology Chennai Tamil Nadu India

The Internet of Things (IoT) technology is a viable alternative for monitoring meteorological data in a specific area and making the data accessible from anywhere in the world. This is based on the idea that IoT technology connects electronic sensors to the public internet. Data from the embedded system can be accessed via the internet from anywhere in the world. In some regions, it may be impossible to examine and monitor vital weather parameters utilizing wires and analog devices during some weather threats. This research proposes a comprehensive approach for monitoring the weather conditions in a particular region and making the information accessible in other parts of the globe using a system described in this study. The IoT is the underlying technology that enables this. It is a highly developed and effective method for connecting things to the internet and bringing the whole internet of things together in a network. This research work has developed an IoT-based forecast concerning sustainable development using an embedded system that can report weather status such as air pressure, heating rate, moisture, air quality, illuminance, and so on in real time. The measurement data has been given as an input to Thingspeak's server for processing and assessment.

关键词： Temperature measurement Temperature sensors Embedded systems Moisture Pollution measurement Internet of Things Servers

来源：评论

学校读者我要写书评

暂无评论

Robotrolley: Customer Following Trolley (CFT)

Robotrolley: Customer Following Trolley (CFT)

引用

International Conference on Open Source Systems and Technologies (ICOSST)

作者： Aneeqa Ramzan Rafay Mustafa Zerish Rehman Saira Suleman Maria Noor Rehana Bibi Department of Electrical Engineering NUTECH Islamabad Pakistan Faculty of Computer Science and Engineering GIKI Topi Swabi Pakistan

Due to inconvenience and time wasting factor in traditional trolleys employed in shopping malls, markets and shopping complexes etc, we have come up with the novel solution named as RoboTrolley i.e. an intelligent customer following trolley (CFT) that will follow the customer while maintaining a suitable distance. The CFT strikes an optimal equilibrium between automation and personalized experience through this harmonious fusion of technology and human-centric design and redefines the shopping experience. This design has been achieved by integrating contemporary technology into the establishing framework of customer-oriented traditional shopping in order to enhance efficiency and convenience throughout shopping. This intelligent CFT operates on one ultrasonic and two IR sensors for distance and motion detection of customer respectively, L298 motor driver module for 4 DC geared motors and Arduino UNO as micro-controller in the design to bring paradigm shift in retail dynamics. Percentage performance and speed in meter per second versus distance in centimeter has been observed for our CFT i.e. between 5 cm to 45 cm. This CFT range is selected after testing the workable ultrasonic sensor’s range with a safety margin so no other person can disturb the detection of actual customer by coming in between. More than 90 percent performance has been observed on a particular distance of 35cm and 45cm between customer and our proposed CFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review On the Techniques Used for Detection of Fabric Defects Using AI

Review On the Techniques Used for Detection of Fabric Defect...

引用

Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS), International Conference on

作者： Isheeta Batra S A Hari Prasad K S Arvind Department of Computer Science and Engineering Faculty of Engineering & Technology JAIN (Deemed-to-be UNIVERSITY) Karnataka India Department of Electronics and Communication Engineering Faculty of Engineering & Technology JAIN (Deemed-to-be UNIVERSITY) Karnataka India

The garment industry is the second-most polluting industry after oil. These mass-produced clothes if rejected are dumped and have an enormous impact on the environment. Therefore, to save the cost post production it is important to identify any sorts of defects pre-production when clothes are in a textile form, so that in case the fabric lacks somewhere in quality it can always be replaced, saving all the time and cost. This detection is possible using techniques like segmentation, or on the basis of texture or by using deep learning algorithms each having its own advantages and disadvantages to efficiently identify the defects in textile fabric. This paper is a comprehensive study of these three techniques and comparison made on basis of brief analysis which say that the deep learning technique is the best of the three for detection of defects keeping in contrast the type of research and developing technologies.

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：