检索结果-内蒙古大学图书馆

Automation and Computation (AUTOCOM), International Conference on

作者： Sanjay Kumar Sonkar Balkar Singh Dept. of Computer Science and Engineering SunRise University Alwar Rajasthan India

In the landscape of rapidly expanding data streams, deriving meaningful insights, particularly frequent itemsets, within massive datasets at a swift pace poses a significant challenge. Addressing this challenge, various methodologies for Frequent Itemset Mining have been proposed, yet they struggle with low support counts and efficiency concerns in handling large datasets. In response, our research introduces Jagged Itemset Counting (JIC) methodologies, aiming to effectively mine Frequent Itemsets from extensive data. The core objective revolves around devising a robust algorithm capable of identifying all Frequent Itemsets, irrespective of database size or the nature of the itemset. Central to this approach is the introduction of a straightforward label representation, GPLN (Geometric Progression Label Number), assigned to each frequent item. Utilizing CGPLN (Cumulative Geometric Progression Label Number), derived from the arithmetic sum of GPLNs within transaction subsets, forms the CGPLN-Label representation for each transaction subset (itemset). Comparative analysis reveals superior performance of JIC over Apriori and Eclat algorithms for small and medium-sized datasets, exhibiting efficiency even at minimal support thresholds. In the realm of Big Data, where FP-Growth and Eclat falter, the proposed technique shines with faster execution times, optimized main memory utilization, and efficient disc memory usage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Traffic Light Control System for Ambulance Using Laser Signals and Raspberry Pi

Automated Traffic Light Control System for Ambulance Using L...

引用

Artificial Intelligence and Data engineering (AIDE), International Conference on

作者： Arun Kumar S Anand Kumar M Robin Rohit Vincent Anusha M S Uttam Upendra Hegde N Nauman Pasha Dept. of Computer Studies Symbiosis Institute of Computer Studies and Research (SICSR) Pune India Dept. of Information Science and Engineering Networks & IoT Lab Presidency University Bangaluru India Dept. of Computer Science and Engineering Networks & IoT Lab Presidency University Bangaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Urban traffic congestion poses a major challenge, particularly for emergency services like ambulances, where delays can have life-threatening consequences. This paper proposes a novel, cost-efficient Automated Traffic Light Control System aimed at prioritizing ambulances at busy intersections, thereby reducing delays and ensuring faster response times. The system utilizes Raspberry Pi Zero 2W, Laser Diodes (KY-008), and Light Dependent Resistors (LDRs) to detect ambulances and dynamically control traffic lights. Unlike traditional systems relying on GPS or RFID technologies, this laser-based approach offers greater precision and affordability through the use of modulated laser signals. Experimental results reveal that this system reduces ambulance response times by 35%. The tests were conducted under simulated urban conditions, highlighting the system's capability to outperform conventional solutions. The simplicity of integration and real-time responsiveness underscore its potential for widespread urban adoption.

关键词： Resistors Semiconductor lasers Traffic control Emergency services Road safety Real-time systems Delays Time factors Traffic congestion Radiofrequency identification

来源：评论

学校读者我要写书评

暂无评论

Energy-Based Controller Design for Decentralized AC Inverter-Base Micro-grids

Energy-Based Controller Design for Decentralized AC Inverter...

引用

Control, Electronics and computer Technology (ICCECT), IEEE International Conference on

作者： Mohsen Bozorgmehrian Samareh Attarsharghi Amin Ramezani Dept. of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran Dept. of Electrical Engineering University of Doha for Science and Technology Doha Qatar

Micro-grids, which utilize photo-voltaic (PV) cells, wind turbines, and batteries, are gaining widespread adoption as a viable solution for renewable and sustainable energy infrastructures. However, ensuring the reliability and stability of these power grids is critical, and several control strategies have been developed to achieve these goals. In this study, we have modeled the decentralized behavior of microgrids using the port-Hamiltonian formulation and a PI controller to control the inverter voltage and output power. To demonstrate the effectiveness of our control method, we have conducted simulations that consider both maximum and worst-case system fluctuations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Transit Entanglement Routing in Quantum Networks: Architecture Design and Optimization

Online Transit Entanglement Routing in Quantum Networks: Arc...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Wan-Ting Ho Shing-Yan Fang Wei-Chia Hsieh Li-Feng Cheni Jian-Jhih Kuo Ming-Jer Tsai Dept. of Computer Science National Tsing Hua University Hsinchu Taiwan Dept. of Computer Science and Information Engineering National Chung Cheng University Chiayi Taiwan

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Quantum networks (QNs) gradually gain significant attention due to their higher security compared with classical networks. Conventional approaches in QN routing often aggregate multiple requests into a batch before determining their routing paths. However, this approach may overlook the limited lifetime of qubits, resulting in critical decoherence. In this paper, we present a new online entanglement routing architecture with an online optimization problem and propose a novel [1, O(log |V|)]-competitive algorithm supporting online requests with admission control, aiming to maximize the number of admitted requests. Finally, extensive simulation results show that our algorithm can outperform the existing approaches by up to 98%.

关键词： Simulation Data security Aggregates Qubit Decision making Focusing Routing Quantum networks Global communication Optimization

来源：评论

学校读者我要写书评

暂无评论

Deepfake Image Detection using Deep Learning

Deepfake Image Detection using Deep Learning

引用

Artificial Intelligence and Data engineering (AIDE), International Conference on

作者： Arun Kumar S Anand Kumar M Robin Rohit Vincent Uttam Upendra Hegde Anusha M S N Nauman Pasha Dept. of Computer Studies Symbiosis Institute of Computer Studies and Research (SICSR) Pune India Dept. of Information Science and Engineering Bio-Intelligence Lab Presidency University Bangaluru India Dept. of Computer Science and Engineering Bio-Intelligence Lab Presidency University Bangaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Deepfake images are generated by modifying existing visuals and are frequently exploited in harmful ways. When executed proficiently, these images can be almost indistinguishable from authentic ones. The increasing development of deep learning techniques has largely fueled the increase in deepfake content. While numerous techniques are available for creating deepfake images, the most commonly employed are GANs and autoencoders. This paper presents a way to make deepfake detection more accurate by using a combination of the YOLOv8 model and a Recurrent Neural Network (RNN). YOLOv8 extracts spatial details from the images, while the RNN identifies temporal patterns and subtle irregularities across image frames, signaling potential manipulation. This methodology presents an efficient solution for identifying deepfake images and reducing their misuse.

关键词： YOLO Deep learning Deepfakes Adaptation models Analytical models Visualization Recurrent neural networks Accuracy Computational modeling Faces

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Image Processing Technique for Early Lung Cancer Prediction

A Deep Learning Based Image Processing Technique for Early L...

引用

Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), ASU International Conference in

作者： Nowshin Tasnim Kazi Rifah Noor Mursalina Islam Mohammad Nurul Huda Iqbal H Sarker Dept. of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong Bangladesh Dept. of Computer Science & Engineering United International University Dhaka Bangladesh Edith Cowan University Perth WA Australia

Lung cancer is the primary cause of cancer mor-tality all over the world due to the increase of tobacco consumption, and industrialization in developing nations. As the early-stage diagnosis can reduce the mortality rate significantly, early detection with the availability of high-tech Medical facilities is highly necessary. In this research, we used deep learning (DL) methods initially on patient's 1190 CT scan images from the Kaggle IQ-OTH lung cancer dataset, and after significant image preprocessing steps we found augmented images including normal, malignant, and benign cases to identify high-risk in-dividuals to detect lung cancer and also predict the malignancy and thus, taking early actions to prevent long-term consequences. A thorough performance comparison between several classifiers, including the conventional CNN, Resnet50, and InceptionV3, has been presented. Here, affine transformation, gaussian noise, and other rigorous image preprocessing techniques are used. The contribution obtained a 98% validation accuracy while reducing the model's complexity with the previous preprocessing stage. The comparison method shows that the suggested preprocessing method yields a higher F1 score value of 97%, validating our suggested methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Know Your Enemy To Save Cloud Energy: Energy-Performance Characterization of Machine Learning Serving

Know Your Enemy To Save Cloud Energy: Energy-Performance Cha...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Junyeol Yu Jongseok Kim Euiseong Seo Dept. of Computer Science and Engineering Sungkyunkwan University

The proportion of machine learning (ML) inference in modern cloud workloads is rapidly increasing, and graphic processing units (GPUs) are the most preferred computational accelerators for it. The massively parallel computing capability of GPUs is well-suited to the inference workloads but consumes more power than conventional CPUs. Therefore, GPU servers contribute significantly to the total power consumption of a data center. However, despite their heavy power consumption, GPU power management in cloud-scale has not yet been actively researched. In this paper, we reveal three findings about energy efficiency of ML inference clusters in the cloud. ❶ GPUs of different architectures have comparative advantages in energy efficiency to each other for a set of ML models. ❷ The energy efficiency of a GPU set may significantly vary depending on the number of active GPUs and their clock frequencies even when producing the same level of throughput. ❸ The service level objective(SLO)-blind dynamic voltage and frequency scaling (DVFS) driver of commercial GPUs maintain an immoderately high clock frequency. Based on these implications, we propose a hierarchical GPU resource management approach for cloud-scale inference services. The proposed approach consists of energy-aware cluster allocation, intra-cluster node scaling, intra-node GPU scaling and GPU clock scaling schemes considering the inference service architecture hierarchy. We evaluated our approach with its prototype implementation and cloud-scale simulation. The evaluation with real-world traces showed that the proposed schemes can save up to 28.3% of the cloud-scale energy consumption when serving five ML models with 105 servers having three different kinds of GPUs.

关键词： Energy consumption Power demand Graphics processing units Prototypes computer architecture Machine learning Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Monolithically Integrated High-Order Vernier Filters and Tuning Circuits for Electronic-Photonic Quantum System-on-Chip

Monolithically Integrated High-Order Vernier Filters and Tun...

引用

CLEO: science and Innovations, S and I 2022

作者： Cabanillas, J.M. Fargas Kramnik, D. Wang, I. Buchbinder, S. Ramesh, A. Kumar, P. Stojanović, V. Khilo, Anatol Popović, M.A. Department of Electrical and Computer Engineering Photonics Center Boston University BostonMA02215 United States Department of Electrical Engineering and Computer Science UC Berkeley BerkeleyCA94720 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States

We demonstrate a monolithically integrated 6th-order filter, w ith h eater driver circuits implemented alongside photonics in a zero-change 45 nm CMOS platform, achieving 80 dB on-chip pump power suppression. © O... 详细信息

ISBN: (纸本)9781557528209

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Analysing Breast Cancer Classification Using Explainable Artificial Intelligence

Analysing Breast Cancer Classification Using Explainable Art...

引用

Annual Information Technology, Electromechanical engineering and Microelectronics Conference (IEMECON)

作者： Kazi Fardeen Harshadeep Bhaduri Soham Hazra Praloy Mondal Sarbajit Manna Tapas Si Dept. of Computer Science & Electronics Ramakrishna Mission Vidyamandira Howrah West Bengal India Dept. of Computer Science & Engineering University of Engineering & Management Jaipur Rajasthan India

ISBN: (数字)9798350387315

ISBN: (纸本)9798350387322

Worldwide, breast cancer is becoming the most serious illness that affects women. It is believed that early diagnosis and treatment of breast cancer can increase survival rates and decrease the need for surgery. Machine Learning model is very reliant on features for their proper training. However, understanding how a prediction is being affected by specific features is very important for a model’s interpretation. Understanding what features support a prediction is important as it provides some transparency to the inner workings of the model. Gaussian Naive Bayes (GNB), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) are used to classify the breast cancer data, and accuracy, sensitivity, specificity, false-positive rate, precision, F 1 -score, and Geometric-Mean (GM) are used for the performance assessment. Furthermore, Multi-Criteria Decision Making (MCDM) is used to evaluate overall performance assessment based on the aforementioned performance measures and DT is found to be best among all the classifiers. Finally, an Explainable AI model namely LIME is used to interpret the predicted outcomes and impact of the different features of the data on the model’s prediction.

关键词： Support vector machines Radio frequency Analytical models Accuracy Explainable AI Predictive models Nearest neighbor methods Breast cancer Data models MCDM

来源：评论

学校读者我要写书评

暂无评论

Slax: A Composable JAX Library for Rapid and Flexible Prototyping of Spiking Neural Networks

arXiv

引用

arXiv 2024年

作者： Summe, Thomas M. Joshi, Siddharth Dept. of Computer Science and Engineering University of Notre Dame United States

Recent advances to algorithms for training spiking neural networks (SNNs) often leverage their unique dynamics. While backpropagation through time (BPTT) with surrogate gradients dominate the field, a rich landscape of alternatives can situate algorithms across various points in the performance, bio-plausibility, and complexity landscape. Evaluating and comparing algorithms is currently a cumbersome and error-prone process, requiring them to be repeatedly re-implemented. We introduce Slax, a JAX-based library designed to accelerate SNN algorithm design, compatible with the broader JAX and Flax ecosystem. Slax provides optimized implementations of diverse training algorithms, allowing direct performance comparison. Its toolkit includes methods to visualize and debug algorithms through loss landscapes, gradient similarities, and other metrics of model behavior during training. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine 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：