检索结果-内蒙古大学图书馆

Machine learning approach to enhance performance of suspicious activity detection system

AIP Conference Proceedings 2023年第1期2587卷

作者： Shahanawaj Ahamad B. Bhaskara Rao K. Srikanth V. P. Hara Gopal Pritika Mehra Malik Bader Alazzam College of Computer Science and Engineering University of Hail Hail City Saudi Arabia Dept. of Computer Science and Engineering RGM College of Engineering and Technology Nandyal Kurnool Andhra Pradesh India Dept. of Computer Science and Engineering G Pulla Reddy Engineering College Kurnool Andhra Pradesh India Research Scholar Dept. of Computer Science Guru Nanak Dev University Amritsar Punjab India Faculty of Computer Science and Informatics Amman Arab University Amman Jordan

Deep learning algorithms are a subset of the machine learning algorithms, which aim at finding several layers of distributed representations. Recently, many deep learning methods have been suggested to tackle conventional artificial intelligence issues. Machine learning is an important component of artificial intelligence, which is used to build algorithms based on the data trends and historical connections between data. Machine learning is utilized in many areas such as bioinformatics, intrusion detection, Information retrieval, game playing, marketing, virus detection, picture de-convolution and so on. Image processing and deep learning methods are linked to machine learning system to identify the fire, unauthentic vehicle and person in this study. More over gadgets such as AC, LED and other electronic equipment have been controlled in suggested system. The suggested model is offering scalable machine learning based solution to control electrical equipment remotely gives protection against fire and un authentic person. The purpose of deep learning is to build intelligent trained network that should be competent to track fire and unauthentic items in organization. The aim of study is to consider research connected to machine learning, deep learning and image processing and analyzing the limits of earlier works. Proposed work includes linked machine learning model to collect the signal and forecast and detect on the basis of trained neural network. The presentation of prediction on web page linked to web interface has been created. Simulation guarantees the improvement of performance of model using user specified trained neural network and conducts the comparative analysis of performance. Capturing is made frame by frame in form of picture and captured information are preprocessed to minimize size of graphics then the pattern in frame is identified using deep learning method. Here pre-trained set is utilized to track recurrence of specific event. The combination of

关键词：

来源：评论

学校读者我要写书评

暂无评论

New design of efficient non-linear stream key generator

引用

AIP Conference Proceedings 2023年第1期2834卷

作者： Saif Ahmed Shaker Ayad Ghazi Nasir Faez Hassan Ali Iraqi Commission for Computer and Informatics/Informatics Institute for Postgraduate Studies Baghdad Iraq Ministry of Education Baghdad Iraq Mustansiriyah University College of Science Math. Dept. Baghdad Iraq

In this paper we will design a new key generator (KG) depends on the LFSR unit and chaotic map. The designed KG can be used for many purposes, like cryptography and steganography. The suggested KG is called Efficient Stream KG which proves its efficiency when passes all the tests of the basic efficiency criteria (periodicity, linear complexity, correlation immunity, and randomness). In this work we suggest three different samples of output binary keys with different lengths, the tests results are arranged in many tables to describe the pass decisions for the designed KG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HPTMT parallel operators for high performance data science & data engineering

arXiv

引用

arXiv 2021年

作者： Abeykoon, Vibhatha Kamburugamuve, Supun Widanage, Chathura Perera, Niranda Uyar, Ahmet Kanewala, Thejaka Amila Von Laszewski, Gregor Fox, Geoffrey Luddy School of Informatics Computing and Engineering BloomingtonIN47408 United States Biocomplexity Institute Initiative and Computer Science Dept. University of Virginia Indiana University Alumni IN47408 United States

Data-intensive applications are becoming commonplace in all science disciplines. They are comprised of a rich set of sub-domains such as data engineering, deep learning, and machine learning. These applications are built around efficient data abstractions and operators that suit the applications of different domains. Often lack of a clear definition of data structures and operators in the field has led to other implementations that do not work well together. The HPTMT architecture that we proposed recently, identifies a set of data structures, operators, and an execution model for creating rich data applications that links all aspects of data engineering and data science together efficiently. This paper elaborates and illustrates this architecture using an end-to-end application with deep learning and data engineering parts working together. © 2021, CC BY.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

An Efficient Localization for Indoor Environment using Classification Algorithms

An Efficient Localization for Indoor Environment using Class...

引用

2020 International Conference on Computational science and Computational Intelligence, CSCI 2020

作者： Mulahuwaish, Aos Towne, Wyatt Ghafoor, Kayhan Zrar Maghdid, Halgurd S. Saginaw Valley State University Dept. of Computer Science and Information Systems Michigan United States Salahaddin University-Erbil Dep. of Software Engineering and Informatics Iraq Koya University Faculty of Engineering Dept. of Software Engineering Kurdistan Region-F.R. Iraq

ISBN: (纸本)9781728176246

The positioning accuracy of various kinds of devices is often calculated by using Wi-Fi fingerprints as a data source of Received Signal Strength (RSS). Through different matching algorithms, these RSS values are related to corresponding positioning coordinates for positioning estimation. In this paper, we compare two well known Machine Learning (ML) structures for calculating positioning accuracy: Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) and a Decision Tree (DT). Both matching algorithms run through a series of datasets in two parts. In the first part, the datasets contain raw, non-normalized RSS values. In the second part, the RSS values are all normalized to remove noise in the datasets. After extensive testing and simulations, the tests showed that as long as RSS values are first normalized, a Decision Tree offers better average positioning accuracy. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Steganography using Mode-Based Least Significant Bit (MBLSB) Method 4

Steganography using Mode-Based Least Significant Bit (MBLSB)...

引用

4th International Conference on informatics and Computing, ICIC 2019

作者： Wong, Ng Poi Hardy Megawan, Sunario Andri STMIK Mikroskil Dept. of Computer Science Medan Indonesia Dept. of Informatics Management STMIK Mikroskil Medan Indonesia

ISBN: (纸本)9781728122076

In the Least Significant Bit (LSB) method of steganography, inserting bits into the cover image is generally done using the blue channel while ignoring the red and green channels as the human eye is relatively insensitive to blue color as such making it easier to hide the secret bits. However this approach is also easier to be detected and therefore attacked as one can discover the secret bits by observing the size distribution in each channel of the cover image. Our work introduces a simple method that insert the secret bits into cover image based on mode value of the bits of all channels, as such the insertion is evenly distributed based on the cover image size and is harder to be detected or attacked. Our proposed MBLSB approach divides the cover image into several insertion blocks, of which each pixel value will be taken from all pixels in each channel. Finally a XOR gate is applied to the secret bit and the retrieved pixel value to get the mode value for the purpose of determining the insertion bit value. The resulting stego-image quality are evaluated using PSNR with value above 60 dB (no apparent noise) and MSE with value below 1.0 while the average success rate of secret data extraction in the event of a color noise attack is 66.45%. © 2019 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Stabilization with Zero Location Constraints for Delay-Based Non-collocated Vibration Suppression ⁎

引用

IFAC-PapersOnLine 2021年第18期54卷 121-126页

作者： Haik Silm Wim Michiels Tomáš Vyhlídal Departement of Computer Science KU Leuven Celestijnenlaan 200A 3001 Leuven Belgium Dept. Instrumentation and Control Engineering Faculty of Mechanical Engineering and Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6 Czechia

A generally applicable design of non-collocated vibration absorption by a delayed resonator is proposed. It is grounded in the direct assignment of imaginary axis zeros of the transfer function between the periodic disturbance force and the target. We show that these transmission zeros are characterized as eigenvalues of a delay differential-algebraic system. Furthermore, a stabilizing local controller is added to the setup in order to widen the range of admissible vibration frequencies. These design requirements are translated into an optimization problem of the spectral abscissa function subjected to zero location constraints. The presented approach and algorithm are validated by a simulation on a three body lumped mass-spring system.

关键词： Vibration control Delayed resonator Transmission zeros Stability Spectral method

来源：评论

学校读者我要写书评

暂无评论

Parallelization of Global Sequence Alignment on Graphics Processing Unit

Parallelization of Global Sequence Alignment on Graphics Pro...

引用

2020 IEEE International Conference on Communications, Computing, Cybersecurity, and informatics, CCCI 2020

作者： Kalare, Kailash W. Obaidat, Mohammad S. Tembhurne, Jitendra V. Meshram, Chandrashekhar Hsiao, Kuei-Fang PDPM IIITDM Dept. of Computer Science and Engg. Jabaplur India College of Computing and Informatics University of Sharjah United Arab Emirates Indian Institute of Information Tech. Dept. of Computer Science and Engg. Nagpur India Jayawanti Haksar Government Post Graduation College College of Chhindwara University Department of Post Graduation Studies and Research in Mathematics Betul M.P460001 India College of Computing and Informatics University of Sharjah Departmnet of Information Systems United Arab Emirates

ISBN: (纸本)9781728120355

In this paper, we propose a work distribution strategy to implement DNA global sequence alignment (GSA). The proposed strategy is implemented on Compute Unified Device Architecture (CUDA) for large biological sequences. The main objective of this work is to minimize the execution time required for DNA global alignment of large biological sequences. The proposed approach covers both the memory optimizations and minimization of execution time. We considered the biological sequences of different size to fit into the global memory under CUDA. The efficient use of global memory and memory optimization dominate the results of execution time. The results demonstrate the significant higher speedup using CUDA. © 2020 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Topological modes observed in Si photonics SSH integrated circuit

Topological modes observed in Si photonics SSH integrated ci...

引用

2022 Conference on Lasers and Electro-Optics Pacific Rim, CLEO/PR 2022

作者： Nakamura, R. Nakama, T. Balčytis, A. Ozawa, T. Ota, Y. Iwamoto, S. Ito, H. Baba, T. Dept of Electrical & Computer Eng. Yokohama National Univ. 79-5 Tokiwadai Hodogaya-ku Yokohama240-8501 Japan School of Engineering RMIT University MelbourneVIC3000 Australia Advanced Institute for Materials Research Tohoku Univ. Sendai980-8577 Japan Dept. of Applied Physics and Physico-Informatics Keio Univ. 3-14-1 Hiyoshi Kohoku-ku Yokohama223-8522 Japan Research Center for Advanced Science and Technology The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo153-8904 Japan

We fabricated a sophisticated Si photonic integrated circuit for investigating topological photonics SSH model. In the selective excitation and observation of SSH coupled microrings, we observed the wavefunctions of e... 详细信息

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Identification of molecular signatures and pathways common to blood cells and brain tissue based RNA-Seq datasets of bipolar disorder: Insights from comprehensive bioinformatics approach

引用

informatics in Medicine Unlocked 2022年 29卷

作者： Islam, A.M. Humyra Rahman, Md Habibur Bristy, Sadia Afrin Andalib, K.M. Salim Khan, Umama Awal, Md Abdul Hossain, Md Shahadat Moni, Mohammad Ali Bioinformatics and Biomedical Research Network of Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering Islamic University Kushtia 7003 Bangladesh Electronics and Communication Engineering Discipline Khulna University Khulna 9208 Bangladesh Department of Quantitative Sciences International University of Business Agriculture and Technology Dhaka 1230 Bangladesh Dept. of Computer Science and Engineering Pabna University of Science and Technology Bangladesh School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St Lucia QLD 4072 Australia

Bipolar disorder (BD), also referred to as manic depression, is a mental illness marked by significant mood fluctuations as well as changes in sleep, energy, thinking, and behavior. About 1% of the world's population is affected by BD. In the United States, roughly 3% of people are thought to be impacted at some point in their lives;female and male percentages appear to be similar. The most prevalent age for the onset of symptoms is 20 years old;early-onset is connected with a worse prognosis. The primary molecular markers for identification and therapeutic target screening have now become a worldwide concern. We looked at gene expression data from brain tissue (RNA-seq) in this work. Transcriptomic analysis of GSE53239 and GSE81396 was implemented to figure out the DEGs. Gene ontology and Kyoto Encyclopedia of Genes and Genomes analyses were used to perform functional annotation and pathway enrichment analysis of DEGs, respectively. In addition, a protein-protein interaction network was built to find hub proteins (HSPA1A, GNL1, FOSL1, DDX39B, BAG3, ARHGAP11A, MDC1, PRRC2A, VPS52, and DHX16). Subsequently, TFs-DEGs interaction, miRNAs-DEGs interaction, and correlated diseases were also identified. In the brain tissues of BD patients, we discovered possible new linkages between pathogenic processes. Beryllium sulfate exhibited the most negative correlation and ability to reverse BD. As a result, this research provides molecular biomarkers at the RNA and protein levels that may aid in the better understanding of molecular processes, as well as potential pharmacological targets and therapies for the treatment of BD patients. © 2022 The Authors

关键词： Bioinformatics Bipolar disorder Gene ontology Genes Hub protein Pathways

来源：评论

学校读者我要写书评

暂无评论

Numerical analysis of unsteady free convection under the combined influence of inclined magnetohydrodynamic and exothermic chemical reaction in an enclosure filled with nanofluid

引用

International Journal of Thermofluids 2024年 23卷

作者： Alaydamee, Hussein H. Alomari, Mohammed Azeez Al-Salami, Qusay H. Alyousuf, Farah Q.A. Alqurashi, Faris Flayyih, Mujtaba A. Department of Chemical Engineering University of Al-Qadisiyah College of Engineering Al-Qadisiyah58002 Iraq Department of Mechanical Engineering University of Al-Qadisiyah Ad-Diwaniyah58001 Iraq College of Engineering University of Warith Al-Anbiyaa Karbala Iraq Department of Business Administration College of Administrative and Financial Sciences Cihan University-Erbil Iraq Department of Computer Network College of Engineering and Computer Science Lebanese French University Erbil Kurdistan Region Iraq Mechanical Engineering Dept. College of Engineering University of Bisha Bisha Saudi Arabia Biomedical Engineering Department College of Engineering and Technologies Al-Mustaqbal University Hillah Iraq

Unsteady study of the natural convection of aluminum oxide-water nanofluid within a trapezoidal geometry containing a circular cylinder located at its center. Finite Element method has been considered for the numerical analysis. The proposed investigation handled the impact of Rayleigh number (103–105), chemical reaction parameter (0–4), aluminum oxide nanoparticles volume fraction (0–0.06), magnetic field (0–63) and its inclination angle (0°–90°), and circular obstacle diameter (0.3–0.7) effects on time-dependent natural convection of Al2O3–H2O nanofluid. On the other hand, the value of Prandtl number has kept constant at (Pr = 6.2). Since the nanofluid mobility at φ = 0.02, Ha = 3, and Fk = 1 significantly improved, the heat transfer rate achieved its maximum intensity at Ra = 105. Research also reveals a little effect on heat transfer by increasing the fraction of nanoparticles. Additionally, as Ha intensifies from 0 to 63, a final change in the mean Nusselt number of 28.65 % is displayed. Finally, as the magnetic field angle of rotation is diminished, more enhancement in heat transmission is achieved. This research provides insights into the intricate relationship between natural convection and exothermic reaction under the influences of various conditions. This can illustrate the flow and thermal behaviors of nanofluid in such non-uniform shapes in many engineering applications. © 2024

关键词： Natural convection

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：