检索结果-内蒙古大学图书馆

7th International Conference on advanced computing and Intelligent Engineering, ICACIE 2022

作者： Singh, Shashi Pal Kumar, Ajai Pundir, Kanishka AAIG Center for Development of Advanced Computing Pune India Banasthali Vidyapith Rajasthan Banasthali India

ISBN: (纸本)9789819950140

This study describes how to develop a machine learning system for the translation of Indian languages (Hindi, Gujarati, and Punjabi) using a form of deep neural network (DNN). We are employing a form of RNN called long short-term memory (LSTM). The state-of-the-art algorithm for sequential data is recurrent neural networks (RNNs). This research work pertaining to RNN-based translation of Indian Languages involved experimenting with nmt models (unidirectional nmt and bidirectional) and their hyperparams to devise results important from real-world perspective. We employed the neural machine translation (NMT) model to get the best results. Unlike the standard phrase-based translation system, which consists of many small sub-components that are tweaked independently, this approach allows a single system to be trained directly on the source and target text and attempts at neural machine translation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Carving of bitmap files from digital evidences by contiguous file filtering

Carving of bitmap files from digital evidences by contiguous...

引用

International Conference on Security in Computer Networks and Distributed Systems, SNDS 2012

作者： Chelliah, Balan Vidyadharan, Divya S. Shabana, P. Thomas, K.L. Center for Development of Advanced Computing Trivandrum Ministry of Communications and Information Technology Government of India India

ISBN: (纸本)9783642341342

An evidence file is a bit-stream copy of any digital storage media or a hard disk partition. Retrieving files from these evidence files without the intervention of file system is quite challenging as the storage locations where file contents are stored are unknown or the contents of files are unavailable in contiguous storage locations. In addition to this, portion of some of the deleted files might have been overwritten by new files. In this paper, we propose a method to carve bitmap files from evidence files by making use of the presence of slack area in the evidence file. The contiguous file filtering technique proposed in this paper makes the carving of fragmented files easier. © 2012 Springer-Verlag.

关键词： Hard disk storage

来源：评论

学校读者我要写书评

暂无评论

A multilayer deep learning framework for auto-content tagging 5th

A multilayer deep learning framework for auto-content taggin...

引用

5th International Conference on advanced Machine Learning Technologies and Applications, AMLTA 2020

作者： Jain, Shikha Jain, Ajit Kumar Singh, Shashi Pal Banasthali Vidyapith BanasthaliRajasthan India AAI Center for Development of Advanced Computing Pune India

ISBN: (纸本)9789811533822

With the rapid and recent development of Internet of things (IoT), Bigdata, the most fundamental challenge is to explore the large volume of data from heterogeneous data sources (logs, audio, video, reports, news, social media, etc.). The tools and techniques that are being used in successful transforming of structured data into business intelligence simply do not work when it comes to unstructured data. An estimated 80% of data held by firms today are unstructured. We have powerful computations tools such as graphics processor units (GPUs) for complex calculations and Hadoop, spark for Bigdata management still technology is lacking in complete utilization of available data. Deep learning is a powerful tool to resolve the issues related to data, such as automatic extraction of complex data and representation of large volume unsupervised and uncategorized raw data. But extracted data do not have any standard format. In the survey of Bigdata mining system and IoT systems, it has been found that a layer is needed in Bigdata mining framework that can work on structured, unstructured and semi-structured data and can integrate the complete raw data. The proposed framework is a multilayer deep learning model that performed the clustering of unstructured huge text data followed by classification layer, CNN, to extract features and classify the raw data clusters in parallel manner. Conversion of unstructured data in standard format by automates content tagging helps decision-making systems to easily identify the related data and increase the data utilization. © Springer Nature Singapore Pte Ltd 2021.

关键词： Multilayers

来源：评论

学校读者我要写书评

暂无评论

Loop partitioning for distributed memory multiprocessors as unimodular transformations 91

Loop partitioning for distributed memory multiprocessors as ...

引用

5th ACM International Conference on Supercomputing

作者： Kulkarni, D. Kumar, K.G. Basu, A. Paularj, A. Center for Development of Advanced Computing 2/1 Brunton Road Bangalore 560 025 India

ISBN: (纸本)0897914341

In this paper, we present a unimodular loop transformation called rotation as a simple, systematic and uniform method for partitioning the iteration spaces of doubly nested loops for execution on distributed memory multiprocessors. We define three parameters which could be used to choose an optimal rotation. These parameters are the parallelism factor, the load imbalance and the volume of communication. We present algebraic expressions for these parameters and discuss their relative significance in choosing a combined metric. © 1991 ACM.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DNN Machine Translation for Indian Languages

DNN Machine Translation for Indian Languages

引用

International Conference on Sustainable Technology and advanced computing in Electrical Engineering, ICSTACE 2021

作者： Singh, Shashi Pal Kumar, Ajai Singh, Lenali Angra, Tanya Center for Development of Advanced Computing AAIG Pune India Banasthali Vidyapith Rajasthan Banasthali India

ISBN: (纸本)9789811943638

For developing and using various features provided by the internet by all the sections of the society, it is important to make the technology accessible irrespective of the language. So, the translation between the languages becomes important criterion. Previously, the machine translation has been used to translate between different languages, which eased the communication between people from different linguistic backgrounds. But in the last couple of years, the advancement and enhancement of Deep Neural Network (DNN) allowed us to rewrite our approach for machine translation completely. This paper discusses the process and the methodology to build the Machine translation system using Deep Neural Network (DNN) for translation between different Indian languages, using the combination of two ideas, i.e., Recurrent Neural Networks and Encoding. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Defeasible reasoning with conceptual graphs 91

Defeasible reasoning with conceptual graphs

引用

1991 ACM Computer Science Conference

作者： Kalathur, S. Center for Development of Advanced Computing 2/1 Brunton Road Bangalore India - 560 025

No abstract available.

ISBN: (纸本)0897913825

No abstract available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data mining: Consumer behavior analysis 3

Data mining: Consumer behavior analysis

引用

3rd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2018

作者： Singh, Shashi Pal Kumar, Ajai Yadav, Neetu Awasthi, Rachna Aaig Center for Development of Advanced Computing Pune India Banasthali Vidyapith Banasthali Rajasthan India

ISBN: (纸本)9781538624401

The whole world is overloaded via innumerable data like scientific data, financial data, mathematical data, geographic data, employment data, and other various kinds of data. Manually analyzing or summarizing this data is impractical, the reason behind this is incredible increment in data in this generation of information and network distribution. Objective of Data mining is to extract the required information, instruction, and pattern from a huge quantity of information and data by the help of multiple tools and techniques. Therefore, it is very essential to select significant techniques to mine the database, because of the several other varieties of data in data base and every data has their individual mining techniques. In this research paper we are going to analyze the consumer behavior, that can help us not only in the retailer market/industry but we can use it in the medical, online shopping etc. Here we are talking about consumer behavior analysis, so we are taking market industry data. Data mining techniques are most conventional and sufficient technique for behavior analysis. Main target of this paper is to recognize behavior of a consumer, his/her psychological condition, consumer's decision making during purchase and then finding how much suitable methods of data mining are applied to enhance the conventional method. Here association rules are deployed to mine out required rules for customer applied in purchased data in retailers shop or organization. After that the required rule can be used for further required filed line online shopping, medical field etc. © 2018 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Collusion-Proof Result Inference in Crowdsourcing

引用

Journal of Computer Science & Technology 2018年第2期33卷 351-365页

作者： Peng-Peng Chen Hai-Long Sun Yi-Li Fang Jin-Peng Huai State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing 100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing 100191 China

In traditional crowdsourcing, workers are expected to provide independent answers to tasks so as to ensure the diversity of answers. However, recent studies show that the crowd is not a collection of independent workers, but instead that workers communicate and collaborate with each other. To pursue more rewards with little effort, some workers may collude to provide repeated answers, which will damage the quality of the aggregated results. Nonetheless, there are few efforts considering the negative impact of collusion on result inference in crowdsourcing. In this paper, we are specially concerned with the Collusion-Proof result inference problem for general crowdsourcing tasks in public platforms. To that end, we design a metric, the worker performance change rate, to identify the colluded answers by computing the difference of the mean worker performance before and after removing the repeated answers. Then we incorporate the collusion detection result into existing result inference methods to guarantee the quality of the aggregated results even with the occurrence of collusion behaviors. With real-world and synthetic datasets, we conducted an extensive set of evaluations of our approach. The experimental results demonstrate the superiority of our approach in comparison with the state-of-the-art methods.

关键词： crowdsourcing quality control collusion collaborative crowdsourcing result inference

来源：评论

学校读者我要写书评

暂无评论

ALDIMS - A language for programming distributed memory multiprocessors 6

ALDIMS - A language for programming distributed memory multi...

引用

6th Distributed Memory computing Conference, DMCC 1991

作者： Kumar, K.G. Kulkarni, D. Basu, A. Paulraj, A. Center for Development of Advanced Computing 2/1 Brunton Road Bangalore560 025 India

ISBN: (纸本)0818622903

In this paper we present ALDIMS, a language that combines the expressibility of general functional (MIMD) parallelism with compact expressibility of data (SPMD) parallelism. It uses distributed data structures for specifying data partitions and single assignment variables as abstract means of inter-process communication. Constructs for unstructured parallelism and process placement specifications make general MIMD parallelism expressible. We describe the issues of implementing process invocation and communication primitive generation. We also discuss source level parallelization and optimization issues and strategies. © 1991 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid POS classification using long short term memory 3

Hybrid POS classification using long short term memory

引用

3rd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2018

作者： Singh, Shashi Pal Kumar, Ajai Lohan, Anu Chaudhary, Jigyasa Daksh, Pragya Aaig Center for Development of Advanced Computing Pune India Banasthali Vidyapith Banasthali Rajasthan India

ISBN: (纸本)9781538624401

A Part of Speech classifier is an important tool that is used to develop many NLP tasks. In this paper we described Deep Neural Network based architecture, that given a sentence, outputs a part-of-speech tag sequence. For Part of Speech classification, we trained a LSTM network by semi-supervised learning. We further applied a probabilistic approach to improve Part of Speech prediction of the LSTM network. Word2vec deep learning tool is used for learning high-quality distributed vector representations of words that capture a large number of precise word relationships. By using a small amount of labeled dataset of words and applying cosine similarity we assign Part of Speech tags to words. If some words don't show nearness to any word in labeled dataset, then we apply probabilistic approach for classification of unclassified words of input sentence. This hybrid neural Part of Speech classifier is evaluated over a corpus of 1000 sentences having a total of 7, 400 words;part of speech classification system achieved the accuracy of 94.71 %. © 2018 IEEE.

关键词： Long short-term memory

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：