检索结果-内蒙古大学图书馆

10th IEEE International Symposium on Smart Electronic Systems, iSES 2024

作者： Sengupta, Anirban Chaurasia, Rahul Indian Institute of Technology Department of Computer Science and Engineering Indore India Indian Institute of Information Technology Department of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798331533229

This paper presents a novel Swarm Intelligence driven Electronic System-Level (ESL) synthesis-based security methodology for functional Trojan fortification (called 'SWIFT'). Backdoor functional Trojan covertly inserted in the reusable hardware designs is a major concern for ensuring reliability functionality of consumer electronics (CE) systems and also for ensuring consumer trust. Erroneous computed output due to malicious functional Trojan can cause malfunctioning of such reusable IP cores. Therefore, the proposed methodology introduces a framework that integrates triple modular redundancy (TMR) along with a unique multi-vendor allocation that enables the generation of Trojan fortified (resistant) reusable hardware intellectual property (IP) designs capable of countering functional Trojan, if present and producing the correct output. The proposed approach integrates the swarm intelligence-based design space exploration (DSE) process with Trojan fortification design process to optimize any possible design overhead incurred due to TMR design. Results of the experimental evaluation prove that the proposed approach can generate low-cost Trojan fortified IP designs at meagre exploration time and at the expense of nominal overhead compared to prior work (that handle Trojan detection only). Further, the presented approach can handle a several potential vulnerabilities in the DSP design, which shows its robust security strength. © 2024 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Obtaining Crisp Priorities for Triangular and Trapezoidal Fuzzy Judgments

引用

computer Systems science & engineering 2022年第4期41卷 157-170页

作者： Raman Kumar Goyal Jaskirat Singh Nidhi Kalra Anshu Parashar Gagan Singla Sakshi Kaushal Computer Science and Engineering Department Thapar Institute of Engineering and TechnologyPatialaPunjabIndia Computer Science and Engineering University Institute of Engineering and TechnologyPanjab UniversityChandigarhIndia

This paper proposes anoptimal fuzzy-based model for obtaining crisp priorities for Fuzzy-AHP comparison *** judgments cannot be given for real-life situations,as most of these include some level of fuzziness and *** these situations,judgments are represented by the set of fuzzy *** of the fuzzy optimization models derive crisp priorities for judgments repre-sented with Triangular Fuzzy Numbers(TFNs)*** do not work for other types of Triangular Shaped Fuzzy Numbers(TSFNs)and Trapezoidal Fuzzy Numbers(TrFNs).To overcome this problem,a sum of squared error(SSE)based optimization model is *** some other methods,the proposed model derives crisp weights from all of the above-mentioned fuzzy judgments.A fuzzy number is simulated using the Monte Carlo method.A threshold-based constraint is also applied to minimize the deviation from the initial *** Algorithm(GA)is used to solve the optimization *** have also conducted casestudiesto show the proposed approach’s advantages over the *** show that the proposed model outperforms other models to minimize SSE and deviation from initial ***,the proposed model can be applied in various real time scenarios as it can reduce the SSE value upto 29%compared to the existing studies.

关键词： Analytic hierarchy process comparison matrices priority vectors fuzzy judgments triangular fuzzy numbers triangular-shaped fuzzy numbers trapezoidal fuzzy numbers

来源：评论

学校读者我要写书评

暂无评论

Secure Accelerated Computing: High-Level Synthesis Based Hardware Accelerator Design for CNN Applications 10

Secure Accelerated Computing: High-Level Synthesis Based Har...

引用

10th IEEE International Symposium on Smart Electronic Systems, iSES 2024

作者： Chaurasia, Rahul Sengupta, Anirban Indian Institute of Information Technology Department of Computer Science and Engineering Bhopal India Indian Institute of Technology Department of Computer Science and Engineering Indore India

ISBN: (纸本)9798331533229

This paper introduces a novel methodology for designing secure hardware accelerator tailored for convolutional neural network (CNN) applications, leveraging security-aware high-level synthesis (HLS). The methodology outlined offers comprehensive security measures, including hindrance against reverse engineering (RE) and intellectual property (IP) piracy concerns through architectural transformations and embedded biometric palmprint constraints, respectively. Key contributions of this methodology include: i) robust hindrance against RE attack, ii) robust piracy detection with no additional design overhead, iii) definitive proof of IP ownership by achieving significantly lower probability of coincidence (P), indicating lower probability of false positive, and iv) enhanced tamper tolerance (TT) and resilience against brute force attacks compared to recent methodologies. © 2024 IEEE.

关键词： High level synthesis

来源：评论

学校读者我要写书评

暂无评论

Adopting Graph Neural Networks to Understand and Reason About Dynamic Driving Scenarios

IEEE Open Journal of Intelligent Transportation Systems

引用

IEEE Open Journal of Intelligent Transportation Systems 2025年 6卷 579-589页

作者： Su, Peng Xiang, Conglei Chen, Dejiu KTH Royal Institute of Technology Faculty of Engineering Design Department Stockholm100 44 Sweden KTH Royal Institute of Technology Electrical Engineering and Computer Science School Stockholm100 44 Sweden

With advances in Deep Neural Networks (DNN), Automated Driving Systems (ADS) enable the vehicle to perceive their surroundings in dynamic driving scenarios and perform behaviors by collecting operational data from sensors such as LiDAR and cameras. Current DNN typically detect objects by analyzing and classifying unstructured data (e.g., image data), providing critical information for ADS planning and decision-making. However, advanced ADS, particularly those required to perform the Dynamic Driving Task (DDT) autonomously, are expected to understand driving scenarios across various Operational Design Domains (ODD). This capability requires the support for a continuous comprehension of driving scenarios according to operational data collected by sensors. This paper presents a framework that adopts Graph Neural Networks (GNN) to describe and reason about dynamic driving scenarios via analyzing graph-based data based on collected sensor inputs. We first construct the graph-based data using a meta-path, which defines various interactions among different traffic participants. Next, we propose a design of GNN to support both the classification of the node types of objects and predicting relationships between objects. As results, the performance of the proposed method shows significant improvements compared to the baseline method. Specifically, the accuracy of node classification increases from 0.77 to 0.85, while that of relationships prediction rises from 0.74 to 0.82. To further utilize graph-based data constructed from dynamic driving scenarios, the proposed framework supports reasoning about operational risks by analyzing the observed nodes and relationships in the graph-based data. As a result, the model achieves a MRR of 0.78 in operational risks reasoning. To evaluate the practicality of the proposed framework in real-world systems, we also conduct a real-time performance evaluation by measuring the average process time and the Worst Case Execution Time (WCET). Com

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Extraction of road using semi-supervised deep learning method 4th

Extraction of road using semi-supervised deep learning metho...

引用

4th International Conference on Computational Methods in science and technology, ICCMST 2024

作者： Mishra, Jalaj Khan, Mohd Jawed Negi, Himanshi Alam, Jitendra Alam, Junaid Singh, Pankaj Pratap Department of Computer Science & Engineering Greater Noida Institute of Technology Greater Noida India Department of Computer Science & Engineering Central Institute of Technology Assam Kokrajhar India

ISBN: (纸本)9781032911571

Detection of road networks using high-resolution aerial or remote sensing imagery constitutes a significant focus within modern research efforts. Currently, deep learning models demonstrate efficiency to a certain degree, they are constrained by a notable reliance on annotated datasets, a practice divergent from optimal methodologies due to the scarcity of extensive, high-quality labeled data. The precision of road prediction is additionally influenced by the latent information embedded within pixels exhibiting diminished confidence values. These pixels play a crucial role in discriminating between road and non-road regions within the images, yet their utilization by deep learning models is suboptimal. To handle these two different issues, opted U-Net as our base model with a sole generator paired with twin dis-criminators and presented this combined setup of U-Net on the Generative Adversarial Network (GAN). At the base of the U-Net architecture, a bottleneck module is incorporated to augment the functionalities of the proposed model. This proposed model attains 98% accuracy on DeepGlobe Road Dataset. Comparative and quantitative assessment demonstrates the enhanced efficiency of our model compared to similar methodologies. © 2025 the Author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Audio Feedback Through Realtime Object Detection Using Yolov5

Audio Feedback Through Realtime Object Detection Using Yolov...

引用

Social and Sustainable Innovations in technology and engineering (SASI-ITE), International Conference on

作者： P. Nagamani V. Venkata Anusha Md. Shabeena B. Srimivas Raja T. Niteesh Kumar G. Durga Prasad Department of Computer Science and Engineering Godavari Institute of Engineering & Technology (A) Department of Electronics and Communications Engineering Godavari Institute of Engineering & Technology(A)

ISBN: (数字)9798350360790

ISBN: (纸本)9798350360806

Abstract-This study offers a novel approach that combines Google Text-to-Speech (GTTS) with YOLOv5 (You Only Look One) object identification to improve accessibility for those with visual impairments. By using object detection and sound recognition to provide real-time information about their surroundings, the suggested system empowers blind individuals. Leveraging its efficiency and speed, the YOLOv5 model is used to reliably identify and categorize items inside the user’s surroundings. To improve situational awareness, sound recognition algorithms are integrated in tandem to recognize and analyse auditory signals, such as alerts, sirens, or other significant noises. Detected items are translated into intelligible spoken descriptions using GTTS to fill in the visual information gap and provide an aural comprehension of the environment. The realtime operation of the system guarantees the prompt and pertinent dissemination of information. Extensive testing with visually impaired participants is used to assess the efficacy of the proposed solution, with a focus on user input and system response. The results show how the system can greatly enhance the quality of life for those who are visually impaired by providing them with a thorough and intuitive grasp of their surroundings.

关键词： YOLO Visualization Technological innovation Visual impairment Real-time systems Text to speech Reliability

来源：评论

学校读者我要写书评

暂无评论

Smart City: Practice of Artificial Intelligence, Robotics and Internet of Things

Smart City: Practice of Artificial Intelligence, Robotics an...

引用

2024 International Conference on Computational Intelligence and Computing Applications, ICCICA 2024

作者： Gupta, Suresh Chand Kumar, Deepak Parkash, Ved Bindra, Sandeep Singh Panipat Institute Of Engineering And Technology Department Of Computer Science & Engineering Haryana Panipat India State Institute Of Engineering And Technology Department Of Computer Engineering Haryana Nilokheri India

ISBN: (纸本)9798350306446

The discussion about smart cities under review about for a long while in established researchers, enterprises, and cultural gatherings, and various audits on the point are available. The term "smart city"alludes to new businesses using data and correspondence advancements alongside the capacities and conditions of metropolitan areas. Discussing about smart city thoughts and analyses towards certifiable acknowledgment, while empowering the mentioned attributes, is a momentum contest. The further empowering of broad smart city facilities and their combination need financially and monetarily solid executions. This will enhance the demands on the designing, sending, activity, upkeep, and development of smart cities. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

An Initial Risk Assessment for Multimodal with LSTM-Based Trust Evaluation Framework for Autonomous Vehicle Security

引用

SN computer science 2025年第2期6卷 1-15页

作者： Renjith, P.N. Balasubramani, S. Ramesh, K. Patnala, Eswar School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

This research aims to develop a new approach to increase the safety and reliability of Autonomous Vehicle (AV) through the proposed risk assessment framework, supported by the trust evaluation approach derived from a machine learning algorithm. This work proposes a comprehensive risk assessment model with real-time sensor data, Vehicle-to-Vehicle (V2V), key communication reliability, environmental cognition, and Improved Long Short-Term Memory (I-LSTM). This framework is multidimensional compared to most conventional models, focusing primarily on assessing individual threat factors. Here, the machine learning portion is designed to evaluate and predict trust by quickly processing vast amounts of information from sensors, signals, and prior operation history. Such an approach to trust assessment enables the system to continuously evaluate the dependability of automated vehicle operation and identify threats to security with improved accuracy. The effectiveness of the performance of this method is substantiated by a number of stand-alone and live scenarios, where the model's performance is higher in perceiving possible risks, avoiding threats, and enhancing safety than the conventional approaches. The findings suggest that the safety regulations of the AVs will be improved by using a multi-dimensional risk assessment model and integrating the I-LSTM trust rating with 95.5% accuracy, 96.7% risk identification, and 180 ms response time. This will cause AV and its surrounding environment to be accepted by the public and used on the roads. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Autonomous vehicles LSTM model Machine learning Risk assessment Trust evaluation

来源：评论

学校读者我要写书评

暂无评论

DeepRice: A deep learning and deep feature based classification of Rice leaf disease subtypes

引用

Artificial Intelligence in Agriculture 2024年第1期11卷 34-49页

作者： P.Isaac Ritharson Kumudha Raimond X.Anitha Mary Jennifer Eunice Robert Andrew J Department of CSE Karunya Institute of Technology and Sciences CoimbatoreTamilnaduIndia Department of Robotics Engineering Karunya Institute of Technology and SciencesCoimbatoreIndia Department of Mechatronics Engineering Manipal Institute of TechnologyManipal Academy of Higher EducationManipalKarnataka 576104India Department of Computer Science and Engineering Manipal Institute of TechnologyManipal Academy of Higher EducationManipalKarnataka 576104India

Rice stands as a crucial staple food globally,with its enduring sustainability hinging on the prompt detection of rice leaf ***,efficiently detecting diseases when they have already occurred holds paramount importance for solving the cost of manual visual identification and chemical *** the recent past,the identification of leaf pathologies in crops predominantly relies on manual methods using specialized equipment,which proves to be time-consuming and *** study offers a remedy by harnessing Deep Learning(DL)and transfer learning techniques to accurately identify and classify rice leaf diseases.A comprehensive dataset comprising 5932 self-generated images of rice leaves was assembled along with the benchmark datasets,categorized into 9 classes irrespective of the extent of disease spread across the *** classes encompass diverse states including healthy leaves,mild and severe blight,mild and severe tungro,mild and severe blast,as well as mild and severe brown *** meticulous manual labelling and dataset segmentation,which was validated by horticulture experts,data augmentation strategies were implemented to amplify the number of *** datasets were subjected to evaluation using the proposed tailored Convolutional Neural Networks *** performance are scrutinized in conjunction with alternative transfer learning approaches like VGG16,Xception,ResNet50,DenseNet121,Inception ResnetV2,and Inception *** effectiveness of the proposed custom VGG16 model was gauged by its capacity to generalize to unseen images,yielding an exceptional accuracy of 99.94%,surpassing the benchmarks set by existing state-of-the-art ***,the layer wise feature extraction is also visualized as the interpretable AI.

关键词： Rice leaf disease Deep learning CNN Crop yield Agriculture Food security

来源：评论

学校读者我要写书评

暂无评论

Enhanced Textual Image Classification with Ensemble Learning of MobileNetV2 and ResNet50

Enhanced Textual Image Classification with Ensemble Learning...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in technology, IC-SIT 2024

作者： Tripathy, Sasmita Pattanaik, Satya Ranjan Rabindranath, Mohanty Hitesh Dash, Ratnakar Centurion University of Technology and Management Department of Computer Science and Engineering Bhubaneswar India Gandhi Institute for Technology Department of Computer Science and Engineering Bhubaneswar India National Institute of Technology Rourkela Department of Computer Science and Engineering Rourkela India

ISBN: (纸本)9798350369175

Textual image classification is crucial in various applications, such as document digitization and automatic language identification. Although ensemble learning has been increasingly utilized to improve the accuracy of deep learning models, the optimal approaches for this task are still under-explored. This research evaluates the effectiveness of ensemble learning techniques for textual image classification, focusing on combining Convolutional Neural Networks (CNNs) like MobileNetV2 and ResNet50. The dataset used in this study includes images in multiple languages, adding complexity to the classification task. By leveraging ensemble learning, we enhanced the performance of these models, achieving an accuracy of 77%, surpassing the individual CNN models. These findings suggest that ensemble learning can significantly boost the effectiveness of deep learning models in textual image classification tasks. © 2024 IEEE.

关键词： Contrastive Learning

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：