检索结果-内蒙古大学图书馆

32nd IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2024

作者： Mahanta, Rishabh Kapoor, Hemangee K. Indian Institute of Technology Dept. of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798331539672

Energy harvesting devices are rapidly evolving to rival battery-backed technologies. Batteries have a shorter life- time and need maintenance compared to capacitors. Moreover, the usage of batteries comes with undeniable environmental costs. Distinct challenges have emerged such as performance enhancement, crash consistency of data, energy management, etc. To tackle these challenges we propose DynaCache: A checkpoint-aware reconfigurable cache for Intermittent powered computing systems. It is an intermittent computing architecture consisting of a reconfigurable L1 cache that dynamically trans- forms its write policy to strike a favorable trade-off between per- formance, data consistency, and forward progress of a program. Our proposal achieves a speedup in performance of 1.85x and 1.5x compared to non-volatile write-back cache and volatile write- through cache respectively. It also achieves a 99% reduction in dirty data compared to a volatile write-back cache guaranteeing a near absolute data consistency in a scenario of a power failure. © 2024 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Multiple language Discovery Abuse of Cyberspace with Advanced Transformer Architecture 2

Multiple language Discovery Abuse of Cyberspace with Advance...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Singh, Arvind Tripathi, Abhinandan Buddha Institute of Technology Dept. of Computer Science & Engineering Gorakhpur India

ISBN: (纸本)9798350368109

The number of reported instances of cyber abuse has also increased in tandem with the growth in the quantity of people that are regularly using the internet. Users' online freedom and privacy are jeopardized by such occurrences. Traditionally, the removal of such content from the internet has been accomplished through manual moderation and reporting systems. This strategy has, however, certain drawbacks, such as a reliance on people, longer delays, and less privacy for data. Traditional recurrent sequence models and supervised machine learning have been used in previous attempts to automate this procedure, but they have a tendency to perform badly on non-English material. A versatile solution that can handle multilingual text is urgently needed, given the increasing diversity of consumers using the internet. Moreover, translations frequently lose important context and emotion from content written in vernacular languages. In this work, we offer a generative deep learning based method for the detection of cyber abuse throughout Hindi, English with mixed codes, and Hindi text. The method uses bidirectional transformer-based BERT *** the TRAC-1 standard aggressiveness identification task, the suggested architecture can get extremely positive outcomes on the task leaderboard for English and accomplish cutting-edge performance on the Hindi dataset with mixed codes. The outcomes show that the new strategy is superior to the current ones because they were obtained without the need of numerous models or ensemble-based methods. Effective models that utilize deep learning techniques to analyze multilingual text can process a wider variety of inputs, making them indispensable in combating these types of social ills. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Recognition using Shift In-variant 2-D ConvNet 7

Traffic Sign Recognition using Shift In-variant 2-D ConvNet

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Ramsundar, B. Sudharsan, S. Pravin, A. Sathyabama Institute of Science And Technology Dept of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350359299

This research introduces a novel method for traffic sign identification utilizing a variant 2-D convolutional neural network (CNN) architecture with a shift-invariant operation. Addressing challenges such as variations in size, illumination, occlusions, and perspective, the proposed approach efficiently learns and identifies traffic signs regardless of their location in the input image. The CNN architecture employs common convolutional layers followed by separate shift-invariant convolutional layers for each type of traffic sign, enabling the network to extract both shared and individual traits effectively. Tests conducted on benchmark datasets including the LISA Traffic Sign Dataset (LISA-TSD) and German Traffic Sign Recognition Benchmark (GTSRB) demonstrate superior recognition accuracy compared to state-of-the-art methodologies. The hierarchical design of the proposed model enhances recognisability, making it suitable for intelligent transportation systems. Overall, the study presents a promising variant 2-D CNN model for traffic sign identification with significant potential for real-world applications. © 2024 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2054-2066页

作者： Pfeiffer, Kilian Balaskas, Konstantinos Siozios, Kostas Henkel, Jorg Karlsruhe Institute of Technology Chair for Embedded Systems Karlsruhe76131 Germany University of Patras Department of Computer Engineering and Informatics Patras26504 Greece Aristotle University of Thessaloniki Department of Physics Thessaloniki54124 Greece

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped from the collaborative training. However, dropping devices in FL can degrade training accuracy and introduce bias or unfairness. Several works have tackled this problem on an algorithm level, e.g., by letting constrained devices train a subset of the server neural network (NN) model. However, it has been observed that these techniques are not effective w.r.t. accuracy. Importantly, they make simplistic assumptions about devices’ resources via indirect metrics, such as multiply accumulate (MAC) operations or peak memory requirements. We observe that memory access costs (that are currently not considered in simplistic metrics) have a significant impact on the energy consumption. In this work, for the first time, we consider on-device accelerator design for FL with heterogeneous devices. We utilize compressed arithmetic formats and approximate computing, targeting to satisfy limited energy budgets. Using a hardware-aware energy model, we observe that, contrary to the state of the art’s moderate energy reduction, our technique allows for lowering the energy requirements (by 4× ) while maintaining higher accuracy. © 1982-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Identification of Sugarcane Leaf Diseases and Deficiency Disorders Using Transformers 1

Identification of Sugarcane Leaf Diseases and Deficiency Dis...

引用

1st International Conference on Pioneering Developments in computer Science and Digital Technologies, IC2SDT 2024

作者： Sarkar, Subhasish Kumar, Gautam National Institute of Technology Dept. of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350365016

Early identification of plant diseases and nutrient deficiencies is crucial for ensuring healthy food production, especially for crops like sugarcane, which contribute significantly to our food supply. Farmers often struggle to differentiate between diseases and deficiencies due to similar symptoms. To overcome such challenges, this study leverages the application of transformers to classify whether the given input is suffering from disease or deficiency. For this purpose, two transformers, i.e., Vision Transformer (ViT) and Swin Transformer is trained on the dataset having leaves of sugarcane. The performance of the model is calculated in terms of precision, recall, accuracy and F-score. From the results, it is found that the Vision transformer with an accuracy of 99.6% can classify diseases and deficiencies more accurately compared to the 99.2% accuracy for Swin transformer. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Agritech Harmony: Real-time ESP32 Automation and Cloud Computing for Socially-Informed Crop Suggestions 5

Agritech Harmony: Real-time ESP32 Automation and Cloud Compu...

引用

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Bawadkar, Vishal Verma, Aman Pawar, Aditya Phatale, Utkarsh Sadaphule, Prashant Dept. of Computer Engineering AISSMS Institute of Information Technology Pune India

ISBN: (纸本)9798350361155

Accurately predicting long-term crop yield trends remains a crucial challenge in optimizing agricultural practices and ensuring food security. This paper proposes a novel framework that merges real-time data acquired from Internet of Things (IoT) sensors with a Bi-directional LSTM model with an attention mechanism to achieve this objective. This architecture extracts insights from historical and future environmental conditions and prioritizes critical factors influencing yield through attention weighting. The framework incorporates an ESP32-managed sensor network measuring humidity, temperature, moisture, rainfall, and NPK levels, providing a continuous stream of real-time field data. Evaluation of real-world datasets demonstrates the framework's superiority over traditional methods, yielding significantly higher prediction accuracy and exposing key drivers of yield fluctuations through attention analysis. An accessible API facilitates seamless integration with farm management systems, empowering farmers with data-driven decision-making capabilities. This paper highlights the transformative potential of integrating deep learning, real-time IoT data, and APIs for revolutionizing agriculture, paving the way for a more sustainable and resilient agricultural futur. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Task Scheduling in Cloud Environments using Dynamic Velocity-Adaptive Particle Swarm Optimization

Multi-Objective Task Scheduling in Cloud Environments using ...

引用

2024 OPJU International technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Kumar, Ravi Vardhan, Manu Natinal Institute of Technology Dept. of Computer Science and Engineering Raipur India

ISBN: (纸本)9798350373783

In the realm of cloud computing, tackling the multi-objective task scheduling problem means finding the best way to assign tasks to virtual machines, taking into account conflicting goals like minimizing execution time, load balance and cost. This intricate task demands smart algorithms to strike a balance between these competing objectives, ensuring the most efficient use of resources and meeting user expectations in the cloud. Different optimization techniques, such as Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO), have been explored to handle this challenge and optimize task scheduling in the cloud environment. In classical PSO, particles can move at varying speeds in each iteration. In this study, we apply Velocity Stagnation Particle Swarm Optimization (VSPSO) variants where velocity stagnation applied during particles movement. This approach provides particles with a third movement option, enabling them to maintain the same velocity as in the previous iteration. VSPSO has a greater capacity to balance the exploration and exploitation. VSPSO adjusts the initial term of the PSO velocity equation to prevent premature convergence. Furthermore, the population of VSPSO is split into two swarms to ensure *** the inherent capabilities of PSO, VSPSO algorithm dynamically updates particle velocities to attain 5-6% total execution time 6-10% reduced cost and optimal balance load. Through meticulous comparisons with other algorithms, including Genetic Algorithm and Ant Colony Optimization, this study scrutinizes the effectiveness of our enhanced PSO approach. The overarching goal is to push the boundaries of multi-objective task scheduling in cloud computing by attaining minimal execution time, reduce cost and optimal balance load on each virtual machines. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture Inventory Management System Using Machine Learning Algorithms 1

Smart Agriculture Inventory Management System Using Machine ...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Kanyal, Hoshiyar Singh Jain, Harshit Tyagi, Harsh Yadav, Satyarth Prakash ABES Institute of Technology Ghaziabad Dept. of Computer Science and Engineering India

ISBN: (纸本)9798350353648

In the agricultural sector, smallholder farmers in India face significant challenges with post-harvest losses, fluctuating market prices, and unsustainable practices. This research proposes a mobile-based application designed specifically for farmers in region of India, focusing on specific crops. To reduce agricultural waste, the app features an optimal storage location based on crop type. To improve farmer income, the app includes a crop recommendation module that integrates historical yield data, weather forecasts, soil characteristics, and real-time market prices. Machine learning models, validated with field data, suggest high-yield, profitable crops and optimal sales timing. A market information hub provides real-time mandi prices and demand forecasts. With a user-friendly interface and visual explanations, the app addresses the technological constraints of smallholder farmers. This research aims to reduce agricultural waste, improve farmer income, and promote sustainable agriculture practices. © 2024 IEEE.

关键词： Agricultural economics

来源：评论

学校读者我要写书评

暂无评论

OpenVAS vs the Rest: Unveiling the Competitive Edge in Vulnerability Scanners 3

OpenVAS vs the Rest: Unveiling the Competitive Edge in Vulne...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Sharma, Mayank Desai, Divyanshu Arun, Aditya Ranganathan Priya, L. Rajagopalan, Narendran National Institute of Technology Dept. of Computer Science and Engineering Puducherry India

ISBN: (纸本)9798350381931

In an increasingly interconnected and digital world, robust vulnerability management is paramount to safeguarding critical information assets and maintaining the integrity of network infrastructures. This paper explores into the heart of vulnerability assessment by presenting a comprehensive analysis of OpenVAS, an open-source vulnerability scanning tool, and its distinct advantages over other competing solutions. OpenVAS has emerged as a standout contender in the realm of vulnerability scanners, owing to its unique features, exceptional performance, and a commitment to open-source principles. Our study begins by providing an overview of the vulnerability management landscape, highlighting the importance of timely and accurate vulnerability assessment. Key advantages examined in this paper include OpenVAS's extensive coverage of vulnerability databases, ease of customization, scalability, and its robust community support. Moreover, its open-source nature ensures transparency and flexibility, making it an attractive choice for both small businesses and large enterprises. This paper aims to serve as a valuable resource for cybersecurity practitioners, IT professionals, and decision-makers seeking a thorough understanding of vulnerability assessment tools. By shedding light on OpenVAS's unparalleled strengths, it provides insights that empower organizations to make informed choices for their cybersecurity posture. In an era where cyber threats evolve rapidly, OpenVAS emerges as the beacon of proactive vulnerability management, offering distinct advantages that redefine the standards for the industry. As cybersecurity assumes an increasingly critical role in the digital age, this paper underscores the significance of choosing a tool that not only detects vulnerabilities but also empowers organizations to address them effectively. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Augmenting Sentiments into Chat-GPT Using FacialEmotion Recognition 10

Augmenting Sentiments into Chat-GPT Using FacialEmotion Reco...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Iyer, Aditya A. Vojjala, Saipranav Andrew, J. Manipal Institute of Technology Dept. of Computer Science and Engineering Manipal India

ISBN: (纸本)9798350384369

This research initiative addresses the task of enhancing Chat Generative Pre-trained Transformer's (ChatGPT's) conversational capabilities by integrating the comprehension and response to user emotions conveyed through facial expressions. The central challenge lies in refining the AI system's proficiency to tailor responses according to users' detected emotional states. In this pursuit, our study adopts a comprehensive approach, aiming to seamlessly incorporate emotional intelligence into AI-driven interactions. To achieve this objective, the methodology involves integrating real-time sentiment analysis based on facial expressions into the ChatGPT framework. This is carried out through the utilization of a deep convolutional neural network (DCNN) architecture, designed to recognize and interpret various emotions exhibited in facial expressions. The primary goal is to enable ChatGPT to dynamically adjust its responses, fostering a more empathetic and contextually relevant interaction with users. In terms of evaluation metrics for facial expression recog- nition, our assessment employs a confusion matrix to quantify the model's performance across different emotional categories. Additionally, a heuristic approach is implemented, wherein the sum total probability of each detected emotion is calculated over the duration the user enters the prompt. These evaluation methodologies aim to provide a comprehensive understanding of the model's accuracy and effectiveness in discerning and responding to user emotions. Overall, this research contributes to the ongoing endeavor of imbuing AI systems with emotional intelligence, paving the way for more nuanced and human-like interactions. © 2024 IEEE.

关键词： Chatbots

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：