检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Balavaseekaran, I. Dileep, Ambili Sabitha, Sai Hindustan Institute Of Technology And Science Dept Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

Daily lives have been made much easier with the invasion of IoT devices in many fields such as health care, education, smart homes, agriculture, etc. Nowadays these devices are prone to many cyber attacks that exist currently and require impregnable security. The most common attacks that happen on an IoT device are DoS and DDoS. The methodology considered in this research employs machine learning algorithms and PCA (Principal Component Analysis) to classify the type of DDoS and DoS attacks that occur on IoT devices. The research also includes the implementation of genetic algorithm in evolutionary feature selection to optimize the features used in the classification process. This research work employs six supervised machine-learning algorithms such as K-Nearest Neighbor (KNN), Decision Tree, Naive Bayes, Neural Network, Random Forest, and Boosted Tree, to classify the different types of attacks that may occur in the Internet of Things (IoT) devices and a comparative analysis on these algorithms are performed. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

DynaCache: A Checkpoint Aware Reconfigurable Cache for Intermittently Powered Computing Systems 32

DynaCache: A Checkpoint Aware Reconfigurable Cache for Inter...

引用

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

Comparative Analysis of Machine Learning Methods in Climate Data Extraction and Forecasting

Comparative Analysis of Machine Learning Methods in Climate ...

引用

2025 International Conference on Emerging Technologies for Intelligent Systems, ETIS 2025

作者： Khajgiwale, Parth Ajit Naveen, Atul Jethani, Nishtha Shitole, Ajitkumar International Institute of Information Technology Dept. of Computer Engineering Hinjewadi Pune India

ISBN: (纸本)9798331507541

Climate forecasting plays a critical role in understanding and mitigating the impacts of climate change. Advances in machine learning (ML) have significantly enhanced the accuracy of climate projections, particularly when dealing with large and complex datasets derived from regional climate models (RCMs) and global climate models (GCMs). This study investigates the application of various ML techniques for predicting precipitation based on temperature data extracted from climate datasets. We evaluate a range of regression models, including linear models and advanced ensemble methods such as Gradient Boosting and XGBoost, along with deep learning approaches like Convolutional Neural Networks (CNNs). Through a rigorous evaluation of these models, we focus on their performance as measured by Mean Squared Error (MSE) to identify the most effective techniques for capturing the intricate relationships within climate data. By analyzing existing studies and performance metrics, we aim to provide insights into the capabilities and limitations of these ML models in improving climate predictions. Furthermore, this research highlights the need for incorporating additional climate variables and optimizing model configurations to enhance predictive accuracy in climate forecasting. © 2025 IEEE.

关键词： Convolutional neural networks

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

Cross-Layer Distributed Attack Detection Model for the IoT

引用

International Journal of Ambient Computing and Intelligence 2022年第1期13卷 1-17页

作者： Ahmed, Hassan I. Nasr, Abdurrahman A. Abdel-Mageid, Salah M. Aslan, Heba K. Informatics Department Electronics Research Institute Cairo Egypt Computer Engineering Faculty of Engineering Al-Azhar University Cairo Egypt Computer Engineering Department College of Computer Science and Engineering Taibah University Saudi Arabia Center of Informatics Science Faculty of Information Technology and Computer Science Nile University Egypt

The security of IoT that is based on layered approaches has shortcomings such as the redundancy, inflexibility, and inefficiently of security solutions. There are many harmful attacks in IoT networks such as DoS and DDoS attacks, which can compromise the IoT architecture in all layers. Consequently, cross layer approach is proposed as an effective and practical security defending mechanism. Cross-layer distributed attack detection model (CLDAD) is proposed to enhance security solutions for IoT environments. CLDAD presents a general detection method of DDoS in sensing layer, network layer, and application layer. CLDAD is based on big data analytics techniques, which enable the detection process to be performed in a distributed way, so the model can detect DDoS attacks in any layer on-the-fly and the model support the scalability of the IoT environment. CLDAD is tested based on three datasets, namely artificial jamming attack dataset, BoT-IoT dataset, and BoT-IoT-based HTTP. The results showed that the proposed model is efficient in detecting attacks in the three layers of the IoT. Copyright © 2022, IGI Global.

关键词： Big data

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

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

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

Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous Racing 12

Parallel Neural Computing for Scene Understanding from LiDAR...

引用

12th International Conference on Intelligent Systems and Embedded Design, ISED 2024

作者： Sah, Suwesh Prasad Chinara, Suchismita National Institute of Technology Dept. Computer Science and Engineering Rourkela India

ISBN: (纸本)9798331522612

Autonomous driving in high-speed racing, as opposed to urban environments, presents significant challenges in scene understanding due to rapid changes in the track environment. Traditional sequential network approaches may struggle to meet the real-time knowledge and decision-making demands of an autonomous agent covering large displacements in a short time. This paper proposes a novel baseline architecture for developing sophisticated models capable of true hardware-enabled parallelism, achieving neural processing speeds that mirror the agent's high velocity. The proposed model (Parallel Perception Network (PPN)) consists of two independent neural networks, segmentation and reconstruction networks, running parallelly on separate accelerated hardware. The model takes raw 3D point cloud data from the LiDAR sensor as input and converts it into a 2D Bird's Eye View Map on both devices. Each network independently extracts its input features along space and time dimensions and produces outputs parallelly. The proposed method's model is trained on a system with two NVIDIA T4 GPUs, using a combination of loss functions, including edge preservation, and demonstrates a 2x speedup in model inference time compared to a sequential configuration. Implementation is available at: github/ParallelPerceptionNetwork. Learned parameters of the trained networks are provided at: huggingface/ParallelPercentionNetwork. © 2024 IEEE.

关键词： Deep learning

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

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：