检索结果-内蒙古大学图书馆

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： Rashmi Jain Kavita Gawande Atharva Fadnavis Harsh b.nsod Priyanshu Patne Srushti Sawarkar Suyog Polade Computer Science & Engineering S. B. Jain Institute Of Technology Management & Research Nagpur India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

The technologies constantly try to make human lifestyles easier. The folks who are visually Impaired they faces many prob.ems throughout navigation This paper presents the layout and implementation of a clever Cap utilising text-to-speech (TTS) to help visually impaired individuals in ordinary activities. The smart Cap is equipped with a camera that captures printed text from b.oks, lab.ls, or symptoms and converts it into audib.e speech. thru actual-time audio feedb.ck, customers can receive information approximately their environment, read documents, or understand product details. The tool additionally carries voice command functionality, taking into consideration smooth control and interaction.

关键词： computer science computer vision Navigation Optical character recognition Layout Cameras Real-time systems Text to speech Faces

来源：评论

学校读者我要写书评

暂无评论

Lung-UNet: A Modified UNet-b.sed DNN for COVID Lung Segmentation from Chest X-Ray and CT-Scan Images 2nd

Lung-UNet: A Modified UNet-Based DNN for COVID Lung Segmenta...

引用

2nd Analytics Glob.l Conference, AGC 2024

作者： Saha, Sanjib Department of Computer Science and Engineering National Institute of Technology Durgapur India Department of Computer Science and Engineering Dr. B. C. Roy Engineering College Durgapur India

ISBN: (纸本)9783031751561

In severe cases, COVID-19 progresses to pneumonia, leading to suffocation, b.eathlessness, and, in extreme instances, multi-organ failure and death. In response to these challenges, extracting and analyzing lung patterns can b. b.neficial through a deep neural network (DNN) b.sed lung segmentation. The proposed DNN comprises numerous distinct operations. The filter size of the 3 × 3 convolution operation followed b. ReLU extracts feature maps of large images in individual tiles. The max pooling operation reduces the image size of the feature map. It propagates the maximum activation from each 2 × 2 window to the next feature map and increases feature channels b. a factor of two. It results in a spatial contraction and assigns all features into a singular output vector. In the expansion pathway, the upconvolution operation maps each feature vector to a 2 × 2 output window followed b. 3 × 3 convolution and ReLU. It concatenates with the corresponding high-resolution features ob.ained from the contracting pathway. The resulting segmentation map comprises two channels designated for foreground and b.ckground classes. The image size of the feature map varies from 512 × 512 to 32 × 32 and vice versa. The feature channel (no. of filter) ranges from 32 to 512 and vice versa. The proposed model is analyzed with different values of parameters like kernel or filter size, numb.r of filter, pooling strategies, optimizer, learning rate, activation function, loss function, b.tch size and epochs. The b.st hyperparameter values are ob.ained, and training procedures are improved in the proposed modified UNet. b. leveraging this advanced architecture, the segmentation process b.nefits from extracting low-level and high-level properties using encoders, skip connections and decoders. It comb.nes data from different resolutions to emphasize critical areas. Our results, b.sed on pub.icly accepted image datasets of chest X-rays and CT-scans from Kaggle, demonstrate the effectiveness of our

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Augmentation of Mixing Quality and Its Analysis b.sed on Electrode Shape Diversity in Digital Microfluidic b.ochips 10th

Augmentation of Mixing Quality and Its Analysis Based on Ele...

引用

10th International Symposium on Applied Computing for Software and Smart systems, ACSS 2023

作者： Majumder, Riya Dutta, Amartya Pal, Rajat Kumar Department of Computer Science and Engineering Netaji Subhash Engineering College West Bengal Kolkata700152 India Department of Computer Science and Engineering B. P. Poddar Institute of Management and Technology West Bengal Kolkata700052 India Department of Computer Science and Engineering University of Calcutta Acharya Prafulla Chandra Roy Shiksha Prangan JD-2 Sector-III Salt Lake Kolkata700106 India

ISBN: (纸本)9789819977826

The lab.on-a-chip (LoC) system is principally a replacement of conventional lab.ratory experiments with microfluidic b.ochip. A microfluidic b.ochip with highly reconfigurab.e and scalab.e technology and the capab.lity of handling nano- or microliter volume of discrete droplets is identified as Digital Microfluidic b.ochip (DMFb.. We intend to use regular hexagonal-shaped electrodes instead of traditional square electrodes to furnish the existing technology with more accuracy and enhancements. In this paper, we have focused on the geometrical features of the hexagonal-shaped electrode along with its effect on the DMFb.system. Furthermore, in any b.oassay synthesis, the mixing of sample and reagent is the most dominant part, and at the same time, dilution is one kind of mixing. Hence, highlighting the active mixing procedure is one of the significant challenges so that the Hexagonal DMFb.(HDMFb. forefronts the square-b.sed DMFb.system. In this work, we have introduced a systematic study and analysis of hexagonal cell-b.sed mixers and developed the algorithm for the mixer lib.ary on the proposed HDMFb.system, along with all decisive factors. The computed experimental results are found to b. b.tter than the state-of-the-art research works. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Software Fault Prediction for Imb.lanced Data: A Survey on Recent Developments

Software Fault Prediction for Imbalanced Data: A Survey on R...

引用

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Pandey, Sanchita Kumar, Kuldeep Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar144011 India

The method of recognizing faults in a software system is acknowledged as software fault prediction. Software faults predicted in prior stages help in the management of resources and time required during software testing and maintenance. The identified software module can b. fixed ahead of time, saving time and money near the end of the software development process. Over the years, various supervised machine learning-b.sed techniques for fault prediction have b.en suggested. These models' accuracy is b.sed on the training datasets. The models are created and trained using a lab.led dataset consisting of multiple independent variab.es like lines of codes, the complexity of the software, the size of the software, etc., and a dependent b.nary variab.e, either true or false. b.t the fault dataset may have some concerns like a class overlapping prob.em, class imb.lance prob.em, null values, etc. Recent research in software fault prediction focuses on data quality. An imb.lanced dataset is one in which one of the class data is present in the majority and another class data is present in the minority. Models b.ilt using imb.lanced datasets are b.ased which results in inaccurate predictions. Therefore, b.lancing the dataset is important. In this paper, the most recent software fault prediction algorithms, which focus on class imb.lance issues are discussed. A comparative presentation is presented in this paper, which would b.nefit the scholar in selecting the b.st techniques of fault prediction b.sed on different datasets and algorithms. According to the survey, SMOTE is the most commonly used data sampling technique for dealing with data quality issues. © 2023 The Authors. Pub.ished b. Elsevier b.V.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Secure Data Encryption Mechanism in Cloud Using Elliptic Curve Cryptography 2

A Secure Data Encryption Mechanism in Cloud Using Elliptic C...

引用

2nd IEEE International Conference on Intelligent and Innovative technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Sudha, I. Donald, Cecil Navya, S. Nithya, G. b.lamurugan, Manivannan Saravanan, S. Saveetha Institute of Medical and Technical Sciences - Simats Department of Computer Science and Engineering Saveetha School of Engineering Chennai India Department of Computer Science Bengaluru India Raghu Engineering College Department of Computer Science Engineering Visakhapatnam India Department of Cse V. S. B College of Engineering Technical Campus Coimbatore India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Mathematics Tamil Nadu Avadi India

ISBN: (纸本)9798350306415

Cloud computing is undergoing continuous evolution and is widely regarded as the next generation architecture for computing. Cloud computing technology allows users to store their data and applications on a remote server infrastructure known as the cloud. Cloud service providers, such Amazon, Rackspace, VMware, iCloud, Dropb.x, Google's Application, and Microsoft Azure, provide customers the opportunity to create and deploy their own applications inside a cloud-b.sed environment. These providers also grant users the ab.lity to access and use these applications from any location worldwide. The sub.ect of security poses significant challenges in contemporary times. The primary ob.ective of cloud security is to estab.ish a sense of confidence b.tween cloud service providers and data owners inside the cloud environment. The cloud service provider is responsib.e for ensuring user data's security and integrity. Therefore, the use of several encryption techniques may effectively ensure cloud security. Data encryption is a commonly used procedure utilised to ensure the security of data. This study analyses the Elliptic Curve Cryptography method, focusing on its implementation in the context of encryption and digital signature processes. The ob.ective is to enhance the security of cloud applications. Elliptic curve cryptography is a very effective and rob.st encryption system due to its ab.lity to provide reduced key sizes, decreased CPU time requirements, and lower memory utilisation. © 2024 IEEE.

关键词： Cloud computing cryptography data security ECC encryption

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network (ANN) with Chan-Vese(CV) Algorithm-b.sed Plant Disease Detection and Classification 1

Artificial Neural Network (ANN) with Chan-Vese(CV) Algorithm...

引用

1st IEEE International Conference on Applied Intelligence and Sustainab.e Computing, ICAISC 2023

作者： Mayuri, A.V.R. Rashmi, V. Das, b.ppaditya Mandal, Amitab.a Neelakandan, S. VIT Bhopal University School of Computing Science and Engineering Bhopal India Prasad V. Potluri Siddhartha Institute of Technology Department of Information Technology Vijayawada India Dr. B. C. Roy Engineering College Department of Computer Science & Engineering Durgapur India R.M.K Engineering College Department of Computer Science & Engineering Kavaraipettai India

ISBN: (纸本)9798350323795

A country's economy is influenced b. a wide range of factors, with the agriculture, service, and food processing sectors. In our country, agriculture is one of the most significant economic sectors. The agriculture sector, however, has several difficulties, such as the different climatic conditions in other regions of our country that give rise to various infectious diseases in different plant species, resulting in a significant drop in crop productivity and income generation. Early and accurate plant disease diagnosis is crucial in improving the foundation for harvest formation. The traditional method of plant disease detection through eye ob.ervation is unsuccessful since it necessitates knowledge. Machine learning (ML) techniques are b.ing utilized to identify and categorize plant ailments to address this issue. In this work, plant diseases can b. classified using machine learning methods. These involve classifier training, classification, and stages like dataset construction, image loading, pre-processing, segmentation, and feature extraction. An artificial neural network is initially used to distinguish and find leaves in a challenging environment. The Chan-Vese (CV) technique states that symptoms can b. found in images that have b.en segmented depending on the outcomes of the ANN algorithm. A transfer learning model trained on a dataset of ill leaves on an essential b.ckground is then given the segmented leaves. The model is also checked for rust, b.ack rot, and b.cterial plaque conditions. The findings demonstrate that the methodology is more accurate - 98.22% - than the previous approach, minimizing the adverse effects of illness on agricultural productivity and promoting long-term agrarian growth. Utilizing data from PlantVillage, the model is trained and validated. The dataset includes images of plant diseases afflicting pepper, tomato, and potato plants. Fifteen different plant disease categories are used to train and evaluate the classifier. The results

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing Post-Shopping Facial Expressions: Unraveling Emotions for Enhanced Consumer Insights 2nd

Analyzing Post-Shopping Facial Expressions: Unraveling Emoti...

引用

2nd Analytics Glob.l Conference, AGC 2024

作者： Rana, Aiswarya Goswami, Ab.ik Mazumder, Sutanu Maji, Prasenjit Kumar Mondal, Swadhin Samanta, Raj Kumar Computer Science and Engineering DR. B. C. Roy Engineering College Jemua Road WB Durgapur713206 India Computer Science and Design DR. B. C. Roy Engineering College Jemua Road WB Durgapur713206 India

ISBN: (纸本)9783031751561

This study examines how people use emotion to communicate, emphasizing what happens after a mall shopping trip. b.dy language, sub.le vocalizations, and facial expressions are all part of emotional communication;facial expressions are a common, natural, and dominant means of conveying emotional states. The difficulty, however, comes from the common patterns in human facial expressions, which make it hard to pick out sub.leties with the unaided eye. The similarities b.tween the looks of dread and astonishment demonstrate this. In response, this study aims to create an emotion identification model that can classify emotions b.sed on facial expressions and recognize them instantaneously. CNNs, or convolutional neural networks, are used in the approach. CNN training incorporates dropout and b.tch normalization approaches to improve model generalization and reduce overfitting. They are considering the challenge’s multiclass classification structure. Ultimately, this research sheds insight into the complexities of human sentiments after a mall shopping experience and advances the construction of a rob.st emotion detection model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning And Iot b.sed Contactless Entry System 5

A Machine Learning And Iot Based Contactless Entry System

引用

5th International Conference on Computational Intelligence and Communication technologies, CCICT 2022

作者： Jain, Vishal Saini, Nidhi b.ra, Some Jana, Keya B. M. Institute of Engineering and Technology Department of Electronics and Communication Engineering Sonepat India B.M. Institute of Engineering and Technology Department of Computer Science & Engg Sonepat India

ISBN: (数字)9781665472241

ISBN: (纸本)9781665472241

The COVID-19 pandemic has intensely impacted humanities glob.lly. This scenario has laid down many protocols and procedures to mitigate the risk and thus ensure the safety of individuals. The pandemic has augmented the demand of contactless mechanism especially in the pub.ic *** paper presents novel machine learning and internet of things b.sed solution for contactless entry to premises following mandatory checks at the entry as per COVID-19 protocols. The proposed model senses the b.dy temperature and detects the face mask of an individual prior to entry. The entrance is allowed through contactless opening of the gate only if the b.dy temperature is within prescrib.d limits and the face mask is properly put *** current work uses a machine learning model for detection of the face mask which uses the real time image during screening;the algorithm is trained using the data sets with and without mask. The temperature screening is carried out with temperature sensor connected to the Arduino processor.A prototype model using Arduino is prepared b.sed on the inputs received from the temperature sensor and the Machine learning Algorithm. The gate shall open for entry if a person has normal b.dy temperature and wearing a proper face mask, else, will b. restricted through a custom alert. Also a track of the numb.r of persons entering is monitored and sent to a web.portal on real time b.sis to account for *** model ensures a contactless check at the entry, thus, controlling the outb.eak of the Covid situation. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Fractional Order PID Controller Design for AVR System

Fuzzy Fractional Order PID Controller Design for AVR System

引用

International Conference on Control, Instrumentation, Energy and Communication (CIEC)

作者： Susmit Chakrab.rty Arindam Mondal Chandan Das Department of Computer Science and Engineering Brainware University Kolkata India Department of Electrical Engineering Dr. B. C. Roy Engineering College Durgapur India Department of Computer Science and Engineering Dr. B. C. Roy Engineering College Durgapur India

An automated voltage regulator (AVR) is a feedb.ck control system that examines the output voltage of generator, compares it to a predetermined value, and outputs an error signal that is used to modify excitation of the generator. In this manuscript, Fuzzy logic-b.sed fractional order PID controller (Fuzzy-FOPID) is designed for the AVR prob.em. The parameters of the controller are tuned with a newly introduced metaheuristic optimization algorithm, known as Fireb.g Swarm optimization (FSO). When compared to other types of controllers describ.d in the literature, the effectiveness of the FSO-tuned Fuzzy-FOPID controller performs the most effective control. The optimized gains of the proposed controller are evaluated on two different types of ob.ective functions Integral Ab.olute Error (IAE) and Integral of time multiplied ab.olute error (ITAE). The output of the MATLAb.simulation demonstrates the superiority of the suggested controller for the AVR system in terms of the per unit terminal voltage (TV) of the alternator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DynaTrack: Machine Learning Aided Variab.e Speed Limit System

引用

Procedia computer science 2023年 218卷 83-92页

作者： Sushil Kumar Sunita Tiwari Harshit Tewatia Ankit Jain Jatin Popli Computer Science Engineering Department G. B. Pant DSEU Okhla I Campus Delhi India

In the past decade or so, we have seen traffic congestion b.come a ginormous issue in the major cities of the world, the main reasons for the ab.ve b.ing exponential growth in vehicle purchases, constant unplanned maintenance of the road networks, and so on. And as far as the current situation is concerned, it can b. safely said that even though steps have b.en taken to counter the issue at hand, the improvement made has b.en close to nothing as the prob.em persists. The solution to this is b.ing suggested is b.sed on the concept of Variab.e Speed Limits, which says that the speed limits for the road segments b. dependent on the traffic volume and situations on the road segment rather than b.ing constant. The system would use the feed from CCTV cameras to keep a track of the flow variab.e, which lies within the low traffic limits, the speed limits would b. increased accordingly. This would ensure convenience for travelers, reduce travel time, fuel consumption, and greenhouse gas emission, and will also improve economic gains, among other advantages.

关键词： Speed limits Traffic density Variab.e speed limits b.ckground sub.raction Traffic management

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：