检索结果-内蒙古大学图书馆

International Conference on Semantic computing

作者： Sourabh Vasant Gothe Sushant Dogra Mritunjai Chandra Chandramouli Sanchi Barath Raj Kandur Raja Samsung R&D Institute Bangalore Karnataka India

ISBN: (数字)9781728188997

ISBN: (纸本)9781728189000

As per the analysis by lemongrad, among 1,121 million English speakers globally, there are 743 million nonnative and 378 million native English speakers (7:3 Ratio). With the increasing number of non-native English speakers, there has been a lot of ongoing research on automated Grammatical Error Correction (GEC). Despite the advances in this field, a GEC system for mobile devices with a low model size, quick inference time and high accuracy is a pressing need. Existing solutions for mobile devices are server-based, which poses a potential risk of data privacy to the user. To this end, we propose an on-device hybrid system which consists of various components, such as preprocessor with spell-checker, Deep Neural Network (DNN) model, N-gram language model, rule-corrector for GEC. User's input text is passed through the proposed system sequentially to get the grammatically correct, contextually enhanced and profanity checked output sentence. Our novel system is at par with other available models for mobile devices with inference time of 95ms, module size of 11.6 MB and F 0.5 score of 52.3 on CoNLL-2014 [1] (test).

关键词： Data privacy Semantics computer architecture Pressing Mobile handsets User experience Error correction

来源：评论

学校读者我要写书评

暂无评论

A Nano-Based high-Speed QCA Circuit for Information Security with Image Masking

A Nano-Based High-Speed QCA Circuit for Information Security...

引用

Conference on Information and Knowledge Technology

作者： Saeid Seyedi Hatam Abdoli Department of Computer Engineering Faculty of Engineering Bu-Ali Sina University Hamedan Iran

ISBN: (数字)9798331522254

ISBN: (纸本)9798331522261

A potential method for nanoscale computing, quantum-dot cellular automata (QCA) makes use of the electron tunneling between quantum dots inside a cell as well as the electrostatic interaction between surrounding dots. QCA technology outperforms traditional complementary metal-oxide semiconductor (CMOS) technology in terms of speed, power consumption, security, and space utilization. Due to the importance of security, this article investigates utilizing QCA to generate picture masks and security in these pictures. the mask picture is created by an encoder circuit, which may also be used as a decoder. Even if the secret key is still unknown, the original picture can be retrieved using the mask image. Improving the security characteristics in nano-communication, which uses QCA cells and nanodevices, is essential. Image masking entails encrypting an image using a random key to generate an encrypted picture, also known as a cipher image. After that, the original picture and the cipher image are merged to create a mask image, a hidden information set for users. With the secret key, this mask picture may obtain an image from another cipher image created with the same set of random keys. To ensure security in this paper, the suggested QCA encoder generates the mask picture. the efficacy of these designs was confirmed by using QCADesigner for functional verification. the simulation results show that the suggested solutions not only work well but also much surpass earlier approaches in terms of speed and space consumption. the higher performance of these optimum designs over other circuit designs highlights the potential of QCA technology to improve picture masking and security.

关键词： Ciphers Microprocessors Quantum dots computer architecture Tunneling Nanoscale devices Decoding Security Digital circuits Standards

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Virtualization Security with a Z-Score Based Conjugate Self-Organizing Migration ML Model

Enhancing Cloud Virtualization Security with a Z-Score Based...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Sagar Sidana Sujata Negi thakur Anurag Sinha N Indhumathi Petheru Raj Ahmed Al-Khayyat Vyom Modi Aditya Mishra Anita Kumari Department of computer science and engineering Maharshi Dayanand University Rohtak Haryana India Department of computer science and engineering Graphic Era Hill University India School of Computing and information Science IGNOU New Delhi India Department of Electronics and Communication Engineering Kongu Engineering College Perundurai Erode India Reliance Jio Platforms Ltd Bangalore India Department of computer science and engineering Islamic University Iraq Marwari Education Foundations Group Of Institutions Rajkot India Department of computer science and engineering Applications GLA University Mathura India Department f English Literature RKDF University India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

this study presents a new machine learning model for detecting malware in cloud computing settings called Conjugate Self-Organizing Migration (CSOM), which is based on Z-score. Feature vectors are standardized by the model through the use of Z-score normalization, which improves its flexibility with changing data distributions. By merging self-organizing migratory processes with statistical analysis, the CSOM model effectively reduces the threat of growing malware. Using Z-score normalization to guarantee correct representation of changing data, the imaging approach depicts the cloud environment as a dynamic, self-organizing landscape. through conjugate migration techniques, the CSOM model dynamically modifies synaptic weights to minimize false positives and enable the identification of tiny fluctuations in harmful actions. the Z-score-based CSOM model is effective in detecting malware at high accuracy rates in a variety of dynamic cloud environments, as demonstrated by the experimental results. the model demonstrates its flexibility in responding to changing cyberthreats with its strong performance in real-world settings. Finally, with its better accuracy and adaptability, the suggested Z-score-based CSOM model offers a potential approach for cloud computing virus detection. In order to handle the constantly shifting environment of cloud-based cyber threats, further research may examine scalability and more refinement.

关键词： Cloud computing Adaptation models Accuracy Statistical analysis Computational modeling Scalability Vectors Security Virtualization Viruses (medical)

来源：评论

学校读者我要写书评

暂无评论

NetForager: Geographically-Distributed Network performance Monitoring of Web Applications

NetForager: Geographically-Distributed Network Performance M...

引用

IEEE Annual computing and Communication Workshop and Conference (CCWC)

作者： Levent Dane Deniz Gurkan Computer Science University of Houston Houston TX USA Computer Engineering Technology University of Houston Houston TX USA

ISBN: (数字)9781728137834

ISBN: (纸本)9781728137841

Users connect to web applications for various content and services. In addition to the internet for the global user/ customer base, in today's enterprises, most business needs are also served by web applications. the application performance monitoring, testing, and maintenance is a considerable effort when serving customers and business needs. Ensuring a high level of user experience, isolation of network issues from application service performance, and providing a seamless experience independent of the proximity of the end user to the application server are some of the challenges faced in performance assurance efforts. In this respect, a reliable testing and monitoring mechanism for application performance is essential to business continuity. Furthermore, virtualization technologies along with extensive mobility adds tremendous challenge to collection of reliable and isolated data in conducting performance monitoring for any application. In this paper, we present the results of a comprehensive network traffic analysis conducted in a geographically distributed manner for over 15 representative web applications. We report that web applications utilize a wide range of bandwidth capacity due to location of the dynamic content and the time of day that the data may be retrieved. the variations create an inconsistent performance level in their network usage metrics. Our reported metrics such as the duration of complete web data transfer and bandwidth utilization can help enterprises, network engineers, and service providers in fine tuning their services. Our approach does not contain sensitive user information, allows for extensive configuration and customization of the framework, and finally, data capture processes have a built-in sharing mechanism for repeatable network experiments through a data collection description language.

关键词： Data collection Monitoring computer architecture IP networks Containers Servers Measurement

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Cryptocurrency Prices Using Machine Learning Algorithms

Predictive Modeling of Cryptocurrency Prices Using Machine L...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Tanjim Mahmud Tahmina Akter Rishita Chakma Tikle Barua Mohammad Shahadat Hossain Karl Andersson Dept. of Computer Science and Engineering Rangamati Science and Technology University Rangamati Bangladesh Dept. of Computer Science and Engineering Port City International University Chittagong Bangladesh Dept. of Computer Science and Engineering University of Chittagong Chittagong Bangladesh Cybersecurity Laboratory Luleå University of Technology Luleå Sweden

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cryptocurrencies, such as Bitcoin, Binance, Ethereum, FTX, and XRP, are decentralized digital assets known for their volatile nature and potential as investment instruments. Accurate price prediction is crucial for informed investment decisions. this study explores the feasibility of various modeling techniques on diverse data structures and features for predicting the prices of these cryptocurrencies. We utilize daily and high-frequency price data to classify and predict prices using deep learning and machine learning techniques, including LSTM, Bi-LSTM, GRU, linear regression, and SGD regression. Our findings indicate that daily price projections achieve an accuracy of 0.99, outperforming more complex deep learning and machine learning models. Compared to benchmark results, our approach demonstrates superior performance, with the highest scores achieved by the applied statistical methods and advanced algorithms. this research highlights the effectiveness of deep learning and machine learning models in cryptocurrency price forecasting, offering a foundation for further exploration in the field and emphasizing the significance of sample size in predictive modeling.

关键词： Deep learning Machine learning algorithms Accuracy Statistical analysis Computational modeling Linear regression Predictive models Prediction algorithms Long short term memory Investment

来源：评论

学校读者我要写书评

暂无评论

Parallel information theory based construction of gene regulatory networks 08

引用

Proceedings of the 15th international conference on high performance computing

作者： Jaroslaw Zola Maneesha Aluru Srinivas Aluru Department of Electrical and Computer Engineering Iowa State University Ames IA Department of Genetics Cellular and Developmental Biology Iowa State University Ames IA

ISBN: (纸本)9783540898931

We present a parallel method for construction of gene regulatorynetworks from large-scale gene expression data. Our method integratesmutual information, data processing inequality and statisticaltesting to detect significant dependencies between genes, and efficientlyexploits parallelism inherent in such computations. We present a novelmethod to carry out permutation testing for assessing statistical significancewhile reducing its computational complexity by a factor of Θ(n2),where n is the number of genes. Using both synthetic and known regulatorynetworks, we show that our method produces networks of qualitysimilar to ARACNE, a widely used mutual information based *** present a parallelization of the algorithm that, for the first time, allowsconstruction of whole genome networks from thousands of microarrayexperiments using rigorous mutual information based *** report the construction of a 15,147 gene network of the plant Arabidopsisthaliana from 2,996 microarray experiments on a 2,048-CPUBlue Gene/L in 45 minutes, thus addressing a grand challenge problemin the NSF Arabidopsis 2010 initiative.

关键词： gene networks mutual information parallel computational biology systems biology

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Synth-to-Real Depth Estimation: From Synthetic Street Scenes to Real-World Data

Zero-Shot Synth-to-Real Depth Estimation: From Synthetic Str...

引用

Brazilian symposium on computer Graphics and Image Processing (SIBGRAPI)

作者： Luís Gustavo Lorgus Decker Jose Luis Flores Campana Marcos Roberto e Souza Helena de Almeida Maia Helio Pedrini Institute of Computing University of Campinas Campinas SP Brazil

ISBN: (数字)9798350376036

ISBN: (纸本)9798350376043

this paper introduces a novel method for estimating depth maps from single images using a convolutional neural network (CNN) architecture. Our approach leverages synthetically generated data that simulates front views from autonomous vehicles. the model employs a ConvNeXt encoder and a U-Net-based decoder, achieving effective depth estimation performance. A scale- and shift-invariant loss function is utilized during training to enhance generalization capabilities. the proposed model demonstrates strong results on real-world datasets without requiring fine-tuning, highlighting the effective transfer of information from synthetic to real-world data. Additionally, we show that high-quality data significantly improves performance compared to larger, low-quality datasets.

关键词： Training Graphics Sensitivity Filtering Data integrity Estimation Feature extraction Data models Convolutional neural networks Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Improving Connectivity of IoT-Enabled Networks through Big Data Analytics

Improving Connectivity of IoT-Enabled Networks Through Big D...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： K S Kiran Sumanta Sen Sunil Sharma School of Engineering and Technology JAIN (Deemed to be University) Bangalore Karnataka India Department of Pharmacy ARKA JAIN University Jamshedpur Jharkhand India Department of Computer Science & Application Vivekananda Global University Jaipur India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

the net of things (IoT) has quick grow to be the backbone of many corporations, taking into account real-time statistics collection and automatic tasks. However, the connectivity of these IoT-enabled networks can become without difficulty congested when huge amounts of data are generated in a brief time frame. To be able to hold a high stage of overall performance, big facts analytics can be used to research the massive volumes of generated statistics, provide insights and locate anomalies to improve community connectivity. Massive statistics analytics will permit higher records processing and evaluation competencies, become aware of regions of improvement and optimize network operations. Additionally, predictive analytics techniques can be used to forecast upcoming community congestion and take movement that could enhance network performance in real time. this, but, requires green facts collection, garage and control gear to ensure that the big records analytics answer is effective and efficient. this paper investigates how massive records analytics may be used to improve the connectivity of IoT-enabled networks through leveraging the energy of predictive analytics.

关键词： performance evaluation Gears Scalability Big Data Real-time systems User experience Safety Reliability Internet of things Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Design and optimisation of an efficient HDF5 I/O Kernel for massive parallel fluid flow simulations

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2017年第24期29卷 e4165.1-e4165.12页

作者： Ertl, Christoph Frisch, Jerome Mundani, Ralf-Peter Tech Univ Munich Computat Engn Munich Germany Rhein Westfal TH Aachen Inst Energy Efficiency & Sustainable Bldg E3D Aachen Germany

More and more massive parallel codes running on several hundreds of thousands of cores are entering the computational science and engineering domain, allowing high-fidelity computations on up to trillions of unknowns for very detailed analyses of the underlying problems. Such runs typically produce gigabytes of data, hindering both efficient storage and (interactive) data exploration. Advanced approaches based on inherently distributed data formats such as hierarchical data format version 5 become necessary here to avoid long latencies when storing the data and to support fast (random) access when retrieving the data for visual processing. this paper shows considerations and implementation aspects of an I/O kernel based on hierarchical data format version 5 that supports fast checkpointing, restarting, and selective visualisation using a single shared output file for an existing computational fluid dynamics framework. this functionality is achieved by including the framework's hierarchical data structure in the file, which also opens the door for additional steering functionality. Finally, the performance of the kernel's write routines are presented. Bandwidths close to the theoretical peak on modern supercomputing clusters were achieved by avoiding file-locking and using collective buffering.

关键词： computational fluid dynamics computational steering HDF5 high-performance computing I/O

来源：评论

学校读者我要写书评

暂无评论

Generic high-Speed Design with Low-Area Implementations of Statistical Operations Based on an FPGA Device

Generic High-Speed Design with Low-Area Implementations of S...

引用

International symposium on Symbolic and Numeric Algorithms for Scientific computing (SYNASC)

作者： Mouhamad Chehaitly Jorge Querol Praveen Vummadisetty Symeon Chatzinotas SnT University of Luxembourg Luxembourg

ISBN: (数字)9798331532833

ISBN: (纸本)9798331532840

Artificial Intelligence has emerged as a transformative technology, revolutionizing numerous industries by enabling advanced automation, predictive analytics, and decision-making capabilities. For that Artificial Intelligence overruns many domains like telecommunication, smart manufacturing industry, autonomous machines, Automated Disease Diagnosis in Medical Imaging, defense, and others. On the other hand, the hardware implementation of Artificial Intelligence comes with certain challenges and constraints, especially in a critical area, which leverages machine learning algorithms and real-time data analysis to optimize production processes and improve overall efficiency. Statistical operations play a crucial role in various machine learning algorithms to understand, process data, or make predictions to optimize models. So, in this work, we developed a high-speed and low-area design and implemented statistical operations for image or signal processing using an FPGA Device. To enhance the performance, we develop different hardware architectures based on different levels of parallelism to process the statistical operations to compute the Mean, Variance, and RMS (Root Mean Square). these generic architectures work in parallel/pipeline architectures with and without memory. the proposed architectures implement an FPGA target (Intel/Altera Agilex 7: AGMH039R47A2E1V) using Altera Quartus prime pro edition version 23.4 and achieve an ultra-high throughput with low-area consumption compared to the state-of-art methods. For 480×640 image size, the mean calculation architecture involves 1498 logic registers, 1912 slice LUT, and just 29kbits memory and it operates at a maximum frequency of 406.5MHz. Additionally, for an 8×8 image size, we need 33 clock cycles to achieve the mean calculation and 33+1 clock cycles to complete the variance calculation, compared to other approaches that require more than 64 clock cycles.

关键词： Industries Machine learning algorithms computer architecture throughput Hardware Real-time systems Artificial intelligence Root mean square Field programmable gate arrays Clocks

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：