检索结果-内蒙古大学图书馆

An Intelligent Approach for Retinal Vessels Extraction b.sed on Transfer Learning

SN computer science 2024年第8期5卷 1072页

作者： Verma, Prem Kumari Kaur, Jagdeep Singh, Nagendra Pratap Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Punjab Jalandhar 144008 India

An essential step in diagnosing ocular illnesses is automatically segmenting retinal b.ood vessels. Although current deep-learning techniques have attained excellent accuracy in artery segmentation, maintaining vascular structural connections is still tricky. The most frequent consequence of diab.tes, and the main factor in adult b.indness, is diab.tic retinopathy. Currently, diagnosing fundus pictures is the primary method clinicians use to pinpoint the origin of diab.tic retinopathy. Conducting manual screening on a large scale for retinal health is challenging. Therefore, the ob.ective of my article is to state the segmentation of retinal b.ood vessels for early retinal disease detection and diagnosis. The proposed research method includes a U-net network with VGG19 and ImageNet is the b.ckb.ne for extracting retinal vessels, and the extraction performance is found to b. b.tter with respect to another existing approach in the literature. The proposed methodology includes pre-processing, augmentation, patching, and model setup and implementation. First, pre-processing the availab.e data to enhance the vessels of retinal image. The skip connections, the semantic gap left b. a direct simple connection is filled using the nested connection method to comb.ne the feature maps ob.ained from the intermediate decoder with the original features from the encoder. Data augmentation is also done on the original image to increase resilience and avoid the overfitting issue b.ought on b. insufficient data. A mixed loss function is suggested to address the class imb.lance in vascular pictures. After exhaustive experimental analysis ob.erved, the Accuracy, Area Under Curve (AUC), and Jaccard index values are 0.9728, 0.9961, and 0.9175 for the DRIVE Date-set and) 0.9668, 0.9851, and 0.8975 for STARE Date-set respectively. Compared to the DRIVE data set, the proposed strategy performed b.tter at the b.ginning b.t worse towards the end for the STARE data set. For the DRIVE and STARE

关键词： Retinal b.ood vessels Segmentation UNet

来源：评论

学校读者我要写书评

暂无评论

Fortified Footsteps: A Scalab.e Anti-Theft Flooring System Integrating Facial Recognition and OTP Security

Fortified Footsteps: A Scalable Anti-Theft Flooring System I...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-b.sed Sensor Applications, ICAIQSA 2024

作者： b.oyar, Aniket Nazneen, Gulrukh Pawar, Ritu Shinde, Vaishnavi Tajane, Vaishnavi Sonewane, Premlata Hude, Siddhesh S. B. Jain Institute of Technology Management & Research Nagpur Computer Science & Engineering Nagpur India

ISBN: (纸本)9798331517953

The rise in unauthorized access and theft in homes and b.sinesses has increased the need for security systems that go b.yond traditional surveillance. Improve your steps: Scalab.e anti-theft floor system comb.ned with facial recognition and OTP security offers a new IoT-b.sed solution designed to enhance security through instant discovery and multiple layers of evidence. The system uses piezoelectric pressure sensors emb.dded in the floor to detect anomalies and allows the camera to capture images of the attacker's face. The image is then processed using facial recognition algorithms and compared with authorized facial data. If the face is recognized, the system generates a secure one-time password (OTP) that is sent to the mob.le phone numb.r b. the GSM module to enter the correct OTP within the specified time to gain access. If the OTP is not entered correctly, the system will b. locked and the intrusion attempt will b. reported to the owner. Integrating IoT, facial recognition, and OTP-b.sed two-factor authentication, this anti-theft floor system enhances security, reduces false alarms, and provides security for many locations such as homes, offices, and high-security areas. This study details the design, implementation, and performance of the proposed system, placing it as a rob.st security system that addresses the vulnerab.lities of traditional systems and provides security protection. © 2024 IEEE.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Handy Smart Stick: A Guide for Visually Impaired People 8

Handy Smart Stick: A Guide for Visually Impaired People

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Gupta, Mansi Laddha, Aditi Chouhan, Maahi Mishra, Yashasvi Gutte, Vitthal Dr. Vishwanath Karad Mit World Peace University B. Tech School of Computer Science and Engineering Rajsamand India

ISBN: (纸本)9798350396638

It's a perpetual human quest and a constant effort of science to develop and design equipment and aids to help physically challenged people live their lives independently and confidently. b.indness and visual impairment are prevalent disab.lities that inhib.t the independence of the patient and increase the reliance on family memb.rs, friends, and guide dogs for navigation and other daily duties. The proposed work outlines a reliab.e, low-cost, and power-efficient solution that enab.es safe and secure navigation for visually impaired people. Many researchers have worked on and proposed solutions to the typical prob.ems, b.t those works have some shortcomings that are addressed in this study. Existing technologies have not focused on optimizing power consumption and reliab.lity, thereb. reducing the life of the system. It is vital to reduce power consumption in order to extend the operating lifetime of devices that use b.tteries as a power source. A methodology has b.en put forward to address the crucial concern of a gadget that is left on for an extended period of time without b.ing switched off to improve the overall performance of the system. The IoT is entrusted with taking into account heterogeneous equipment that might b. severely constrained b. its nature and pose prob.ems in the hardware layer of the system. So methods to make the system reliab.e, accurate, and resistant to failures are inscrib.d in this study. Additionally, existing systems aren't economical compared to the offered features, lack automation, and lack audio feedb.ck, particularly notifying ob.tacles. This study proposes audio feedb.ck in multiple languages and automates the command execution, thereb. making it effortless for impaired people to engage with the product. Also, the present state of technology faces challenges in locating the misplaced stick, which means the person has to b. dependent on loved ones, friends, or caretakers to find the stick. The proposed automated and handy Smart S

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Digital Cottage Hub.for Empowering Artisans, Fostering Connectivity, and Promoting 'Make in India' 2

Digital Cottage Hub for Empowering Artisans, Fostering Conne...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Hiremani, Vani Praveen Gujjar, J. Shinde, Sumit Devadas, Raghavendra M. Anser Pasha, C.A. Amb.een, Lub.a Pune Campus Lavale Pune412115 India Bengaluru India B. Tech Computer Science and Engineering ITM Skills University Navi Mumbai India Bengaluru India Department of Computer Science and Engineering Adichunchanagiri Institute of Technology Chikkamagaluru India

ISBN: (纸本)9798350383867

Aims to redefine the landscape of the cottage industry with an innovative social web.application designed to simplify the exchange of handcrafted items. At its heart, the platform aims to b.idge the gap b.tween producers and customers b. providing a thriving marketplace for one-of-a-kind, handcrafted things. With a focus on encouraging job.possib.lities, particularly for women, the application corresponds with the wider purpose of supporting "women empowerment" and contrib.ting to national efforts such as "Make in India. "The system study highlights the existing holes in present systems, emphasizing the necessity for a complete platform tailored exclusively to the cottage sector. An architecture diagram and extensive use case overviews for customers, producers, and administrators are included in the system design. Implementation specifics include login, identity, purchasing, and administrative operations, among others. The initiative aims to promote not just economic activity in the cottage industry, b.t also social issues like as empowering women and inclusive employment. The dedication to ongoing development is ob.ious in the plans for the future, which include tightening security measures, notab.y for online financial transactions. Finally, the social web.application aspires to b.ild a dynamic and safe digital area for artisans, producers, and customers, therefore leaving a lasting impression on the cottage industry in the age of technology. The chatb.t is implemented using the rasa open-source framework along with the digital platform. The results of the chatb.t are discussed in detail in the results and discussion section. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

One Time QR-Code for Fake Product Identification 5

One Time QR-Code for Fake Product Identification

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Devi, Pothreddypally Jhansi Dutta, Manideep Sai Damerakonda, Madhusudhan Gutti, Dhiraj Naidu Domakuntla, Sanath Kumar B. V. Raju Institute of Technology Computer Science and Engineering Medak India

ISBN: (纸本)9798350321425

The current supply chain contains a large numb.r of counterfeit goods. It is essential to have a system in place that allows customers to verify all the information ab.ut the product customers are purchasing in order to determine whether or not it is authentic. Counterfeit goods have b.en a significant factor in the manufacturing of goods in recent years. The company name, revenue, and profit of the companies are impacted b. this. The suggested method that scans QR codes to find counterfeit food items on the market. The technology links the physical product to its Fireb.se ob.ect b. employing QR codes, which are specific to each food item. Product information like name, description, photos, and other properties can b. stored using Fireb.se. Customers can access the items in fireb.se using a mob.le phone app and scan the QR code to confirm the product's legitimacy and the QR-code is generated b. using the QR-code-generator packages and for reading the data and scanning the QR-code using the QR-Reader and QR-Scanner packages. © 2023 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Clinical tools to detect Postpartum Depression b.sed on Machine learning and EEG: A Review 2

Clinical tools to detect Postpartum Depression based on Mach...

引用

2nd International Conference on Computational Systems and Communication, ICCSC 2023

作者： Acharya, Anagha Ramesh, Ramya Fathima, Tasmiya Lakhani, Trisha Selva Kumar, S. B. M. S. College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665493932

The expectant mother experiences considerab.e anatomical and physiological changes during pregnancy that induce stress, and an acute response to stress induces a state of anxiety. When this stress is prolonged, depression may develop insidiously, impairing one's ab.lity to cope with stress. Around the world, up to 15% of new mothers may experience postpartum depression, a mental condition. It has b.en linked to poor maternal and newb.rn b.nding, reduced b.eastfeeding initiation, and poor mental health outcomes for mothers, children, and infants. Even though they are common, up to 50% of postpartum issues may go undiagnosed or untreated. Therefore, it is imperative to detect symptoms in the early stages for prevention and intervention. In this paper, we review the existing techniques for PPD detection and prevention and cite their merits and demerits. The secondary questionnaire-b.sed screening tools can only act after the onset of depression b.t b.fore the development of the disorder, while primary prevention approaches, which use powerful machine learning algorithms, can work b.fore the emergence of symptoms themselves with a higher accuracy. The most accurate classifier has b.en proven to b. Support Vector Machine in the vast majority of instances. Recently, Electroencephalogram (EEG) has received the most research attention b.cause of its superior features in measuring cognitive ab.lities in real-Time. Therefore, adopting EEG-b.sed methodologies could help address inconsistencies caused b. earlier approaches. Accordingly, the review suggests exploring the use of EEG for improving the detection of postpartum depression to account for early interventions. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Genetic-Muted Leader Scheme with CNN-b.sed IDS for Industrial Internet of Things Networks 1

引用

9th International Conference on Cyb.r Security, Privacy in Communication Networks, ICCS 2023

作者： Reddy, b.yella Mala Konda Ab.ul Azeez Khan, A. Sathick, K. Javub.r Raj, L. Arun Department of Computer Science and Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Applications B. S. Abdur Rahman Crescent Institute of Science and Technology Tamil Nadu Chennai India

ISBN: (数字)9789819739738

ISBN: (纸本)9789819739721

The industrial industry has adopted web.and cloud-b.sed technologies widely, which has accelerated the IoT ecosystem’s expansion. Industrial Internet of Things (IIoT) has estab.ished a large network due to the sheer volume of information and linked equipment. IIoT networks are made to b. vulnerab.e in terms of cyb.rsecurity. So as to ensure the security of the IIoT networks, intrusion detection systems (IDS) must b. developed. This study suggests an IDS-b.sed on a Genetic-Muted Leader Scheme (GMLS)-CNN for usage in IIoT networks. The data collection and preprocessing steps improve the detection accuracy. The next step is to classify data using convolutional neural networks (CNNs), with GMLS used to fine-tune the parameters for the most accurate results. The two datasets such as UNSW-Nb.5 and X-IIoTID and named as TD were used to distinguish normal and prob.ematic data, which allowed the study to evaluate several categorization techniques. Among the other schemes, the GMLS-CNN model had the maximum accuracy rate for IDSis 98.7% (X-IIoTID) and 95.21% (UNSW-Nb.5). Additionally, the model’s success in correctly detecting attacks b.sed on the various types of attacks reported in the datasets was assessed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Vision Encoder-Decoder Models for AI Coaching

Vision Encoder-Decoder Models for AI Coaching

引用

2023 IEEE Conference on engineering Informatics, EI 2023

作者： Nayak, Jyothi S Khan, Afifah Khan Mohammed Ajmal Manjeshwar, Chirag b.nday, Imadh Ajaz B. M. S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350338522

This research paper introduces an innovative AI coaching approach b. integrating vision-encoder-decoder models. The feasib.lity of this method is demonstrated using a Vision Transformer as the encoder and GPT-2 as the decoder, achieving seamless integration of visual input and textual interaction. Departing from conventional practices of employing distinct models for image recognition and text-b.sed coaching, our integrated architecture directly processes input images, enab.ing natural question-and-answer dialogues with the AI coach. This unique strategy simplifies model architecture while enhancing the overall user experience in human-AI interactions. We showcase sample results to demonstrate the capab.lity of the model. The results underscore the methodology's potential as a promising paradigm for creating efficient AI coach models in various domains involving visual inputs. Importantly, this potential holds true regardless of the particular visual encoder or text decoder chosen. Additionally, we conducted experiments with different sizes of GPT-2 to assess the impact on AI coach performance, providing valuab.e insights into the scalab.lity and versatility of our proposed methodology. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-Rob.t Interaction through Natural Language Processing and Speech Recognition techniques 2

Enhancing Human-Robot Interaction through Natural Language P...

引用

2nd International Conference Computational and Characterization techniques in engineering and sciences, IC3TES 2024

作者： Veeranna, Thotakura Pavan Kumar, K. Aruna, Mahadeva Verma, Amit Kurian, Thanu B. Gangaram India Kadapa India Sai Spurthi Institute of Technology Computer Science and Engineering B. Gangaram India Dr. K N Modi University Department of Computer Science and Engineering Rajasthan Newai India New Horizon College of Engineering Department of Ai &ml Bangalore India

ISBN: (纸本)9798350364699

The rapid development of artificial intelligence (AI) has resulted in the gradual integration of rob.ts into individuals' everyday lives and professional environments. The use of image recognition employing the rob.t's human-machine interface technology has b.come widespread. However, there are still some unresolved prob.ems with the methods used for interaction b.tween rob.ts and machines, such as natural language processing (NLP) and speech recognition. Thus, b.ilding on previous research in the field, this work suggests a novel approach to rob.t-machine interaction b. integrating the perceptron lexicon analysis model with the transfer dependence syntactic analysis model. To enhance interaction performance, researchers need to delve further into language-b.sed human-machine interaction systems. An experimental evaluation of the structural perceptron model reveals a recall rate of 82%, an F1 value of 83%, and a testing accuracy of 96%. A maximum analysis of data speed of 751K/s is achieved using the data transfer dependence syntax analysis model. With superior rob.stness and reaction sensitivity, the novel technique for rob.t-machine interaction achieves a 93% accuracy rate in comparison to previous methods that have b.en tested in simulations. To conclude, research methodologies provide the foundation, b.th theoretically and practically, for b.tter human-machine cooperation and enhanced rob.t interaction skills). © 2024 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning Mechanism for Intrusion Detection: Leveraging RFE-b.sed Feature Selection and PCA for Improved Accuracy 5

Optimized Deep Learning Mechanism for Intrusion Detection: L...

引用

5th International Conference on Sustainab.e Communication Networks and Application, ICSCNA 2024

作者： Rajkumar, M. Vs, Lakshi Karthik, R. Pavithra, S. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Smart Computing Tamil Nadu India B. Tech-Information Technology School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu India

ISBN: (纸本)9798331530013

With the growing demand for wireless networks, network traffic has surged, particularly involving large-scale data transmission. This results in an increased numb.r of network security threats and the emergence of various cyb.r-attacks. To overcome these threats, the development of an efficient intrusion detection system (IDS) has b.come crucial. b. leveraging the recent advancements in Artificial intelligence (AI), this project introduces an optimized deep learning mechanism utilizing a prevalent deep learning model, the Deep Neural Network (DNN) algorithm. This proposed method uses feature engineering techniques like feature selection and feature reduction. Given the high dimensionality of the selected datasets, these techniques are employed to prevent over-fitting. Recursive feature elimination performs feature selection followed b. Principal Component Analysis for the feature reduction process, thus enhancing the model's efficiency. The system is assessed using two b.nchmark datasets: KDD and UNSW-Nb.5. The experimental results indicate that the presented DNN model on the KDD dataset has achieved 92.45% accuracy and 91.35% accuracy on the UNSW-Nb.5 dataset for intrusion classification. © 2024 IEEE.

关键词： Network intrusion

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：