检索结果-内蒙古大学图书馆

Electrical Power engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Suresh Kumar Pemmada Janmenjoy Nayak H S Behera Subhashree Mohapatra Department of Computer Science and Engineering Aditya Institute of Technology and Management (AITAM) Tekkali India Department of Computer Science Mahara ja Sriram Chandra Bhanja Deo University Baripada Odisha India Dept. of Information Technology Veer Surendra Sai University of Technology Burla Odisha India Department of Computer Science and Engineering SOA University Bhubaneswar Odisha India

ISBN: (纸本)9781665478403

Just-in-time defect prediction (JITDP) is a technique for predicting if a code change is defective. JITDP ensures software quality throughout the design phase and requires developers to check and resolve defects on time. Several recent studies have proposed using JITDP to detect changes that potentially create defects at check-in time. JITDP techniques utilize change metrics obtained from software repositories to forecast defect-inducing changes. In this research, we presented Bootstrap aggregation to detect changes that potentially create defects at check-in time by employing the publicly accessible change metrics dataset Mozilla. The proposed method has been compared to several machine learning techniques to verify the proposed approach's performance. The findings reveal that the proposed approach beat all comparable machine learning methods in various classification measures. In addition to the proposed approach, the decision tree and k nearest neighbor algorithms performed well.

关键词： Measurement Power engineering Codes Machine learning algorithms Software quality Prediction algorithms Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Neural Network based Student Grade Prediction Model

Neural Network based Student Grade Prediction Model

引用

Machine Learning, computer Systems and Security (MLCSS), International Conference on

作者： Yagyanath Rimal Vijay Singh Rathore Sakuntala Pageni Debabrata Samanta Marimuthu Karuppiah Debabrata Singh Pokhara University Gandaki Nepal Department of Computer Science IIS (Deemed to be University) Jaipur India Department of Department of Education Tribhuvan University PNC Kaski Nepal Department of Computer Science CHRIST (Deemed to be University) Bangalore India Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi-NCR Campus Ghaziabad India Department of CA SOA University Bhubaneswar India

Student final grade GPA is the collective efforts of their previous and ongoing efforts of each semester examination may predict accurately using the neural network which receives the input weight of each matrix element of variables to next neuron. The GPA prediction based on regular class performance and previous grades with background variables were found much significant. This research tries to explore the model comparison and evaluate student grade prediction using various neural network models. The single-layer half i.e., successful student model predicts 90 total accuracies than the single layer with five hidden layer neurons (88.5 percent). The multi-layer with two hidden layers (7,3) is 84 percent accuracy is less than one percent accuracy than multilayer with three hidden layers. Similarly, the multilayered with four hidden layered 25,12,7,3 model predicts the least accuracy (77 percent accuracy) for student grade. Similarly, the passed student prediction model has less accuracy than both students' 86 percent.

关键词： Training Computational modeling Neurons Predictive models Nonhomogeneous media Numerical models computer security

来源：评论

学校读者我要写书评

暂无评论

Editorial

Studies in Big Data

引用

Studies in Big Data 2020年 64卷 v-vii页

作者： Patnaik, Srikanta Department of Computer Science and Engineering SOA University Odisha Bhubaneswar India

来源：评论

学校读者我要写书评

暂无评论

Editorial

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and Computing 2020年 1060卷 v-vi页

作者： Patnaik, Srikanta Department of Computer Science and Engineering SOA University BhubaneswarOdisha India

来源：评论

学校读者我要写书评

暂无评论

Role of social media marketing on consumer purchase behaviour: A critical analysis 1

Role of social media marketing on consumer purchase behaviou...

引用

1st International Conference on Applied Machine Learning, ICAML 2019

作者： Satpathy, Smitarani Patnaik, Srikanta Department of Computer Science and Engg. SOA University Bhubaneswar India Department of Computer Science and Engineering SOA University Bhubaneswar India

ISBN: (纸本)9781728139081

For sharing and expressing opinions, an individual can use the virtual space in the web and Social media is a platform for such things;where discuss on certain issues, comments on different facts and comparing things with others. On the other hand, consumer marketing and brand management are connected with it and create much more complexity in this global, quickly growing technology-world. Also it influences consumer purchasing behavior and purchasing attitude. Currently, social media like facebook, youtube, etc., has gained remarkable attention in the last decade. Social media has become so important in affecting purchasing behavior of prospective customers that the companies have their own social site to handle to provide customers information they require and found it easily. The major focus on this paper is to describe the potential benefits associated with the application of machine learning techniques. Adopting a Neuro-Fuzzy system that, under uncertainty, has the capacity to process information towards better choices linked to virtual retail system parameter. Focus is on the particular field like business, education, society and youth how it affects society in a broad way. © 2019 IEEE.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

Analysis of learning approaches for machine translation systems 1

Analysis of learning approaches for machine translation syst...

引用

1st International Conference on Applied Machine Learning, ICAML 2019

作者： Satpathy, Subhashree Mishra, Smita Prava Nayak, Ajit Kumar Computer Science and Engineering SOA Deemed to be University Bhubaneswar India Computer Science and Information Technology SOA Deemed to be University Bhubaneswar India

ISBN: (纸本)9781728139081

Machine Translation(MT) is a part of Natural Language Processing(NLP). It is the method of translating Source Language(SL) text into Target Language(TL). The gap between computer programmer and linguist can be resolved with this system. The problems like lexical ambiguity, part of speech tagging, syntactic and structural ambiguity, synonym etc will arise while developing such systems. To develop a proper bilingual machine translation system for two natural languages is a challenging and demanding task for researchers. It is required to analyze the information as well as technology behind every natural language translation. This work represents the various approaches with current trends of machine translation system. In recent trends various machine learning approaches have been developed to tackle the above said problems. Most recently neural machine translation attain very good result by using different deep neural network techniques and machine learning algorithms. © 2019 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Carbon dots encapsulated in (YGd)2O3:Eu3+ nanophosphors for thermal sensing, advanced forensic and information security applications

引用

Materials Today Sustainability 2024年 26卷

作者： Chandana, M.R. Radha Krushna, B.R. Navya, N. Sharma, S.C. Malleshappa, J. Kar, Bikash George, Augustine Krithika, C. Amudha, P. Manjunatha, K. Yun Wu, Sheng Madhavi, K. Nagabhushana, H. Department of Physics University College of Science Tumkur University Tumkur572103 India Prof. C.N.R. Rao Centre for Advanced Materials Tumkur University Tumkur572103 India Honorary Professor of Law and Forensic Materials Jain University Bangalore562112 India Department of Dermatology IMS and SUM Hospital SOA University Odissa 751003 India Department of Computer Science Kristu Jayanti College Autonomous Bengaluru560077 India Department of Oral Medicine and Radiology Meenakshi Ammal Dental College Meenakshi Academy of Higher Education and Research Chennai600095 India Department of Computer Science and Engineering Avinashilingam Institute for Homescience and Higher Education for Women Coimbatore641108 India Department of Physics National Dong Hwa University Hualien97401 Taiwan Department of Physics Maharani Science College for Women Palace Road Banglore560001 India

The outstanding optical characteristics of carbon dots (CDs) make them an extremely promising class of multifunctional nanomaterials based on carbon. The incorporation of hydrothermally prepared Aloe vera carbon dots (AVCDs) into europium doped yttrium gadolinium ((YGd)2O3:Eu3+) mixed oxide nanophosphors ((YGO):Eu3+ NPs) synthesized through the solution combustion (SC) method. The resulting (YGO):Eu3+@AVCDs nanocomposite (NCs) demonstrates a broad excitation band, with the intense peak at ∼395 nm, aligning with the emission wavelength (350–420 nm) of n-UV LED chips. Notably, the (YGO):Eu3+@AVCDs (5 wt %) NCs exhibits a 4 fold increase in photoluminescence (PL) intensity compared to (YGO):7Eu3+, attributed to the fluorescence resonance energy transfer (FRET) between AVCDs and Eu3+ ions. Remarkably, even at an elevated temperature of 423 K, the thermal stability of (YGO):Eu3+@AVCDs (5 wt %) remains exceptional, retaining 88.31 % of its initial luminescence intensity. The internal quantum efficiency (IQE) is measured at a notable 74.16 %, while the optimized composite achieves a remarkable color purity of 99.59 %. Latent fingerprints (LFPs) are effectively developed on different surfaces using the optimized NCs via a simple powder dusting technique, and these fingerprints (FPs) revealed under 365 nm UV light. The study also examines various pore parameter namely size, shape, number, position, type, and inter-distance. Moreover, a transparent anti-counterfeiting (AC) ink is fabricated using optimized NCs providing effective AC features through its red emission under 365 nm UV light. This study not only offers solutions for overcoming the self-quenching effect of CDs but also underscores the potential applications in white light emitting diodes (w-LEDs), latent fingerprints, lip prints (LPs), and anti-counterfeiting. © 2024

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

SCMC: Smart city measurement and control process for data security with data mining algorithms

引用

Measurement: Sensors 2024年 31卷

作者： Selvarajan, Shitharth Manoharan, Hariprasath Goel, Sonali Akili, Chiranjeevi Prakash Murugesan, S. Joshi, Vaishali School of Built Environment Engineering and Computing Leeds Beckett University Leeds LS1 3HE United Kingdom Department of Electronics and Communication Engineering Panimalar Engineering College Poonamallee Tamil Nadu Chennai 600123 India Department of Electrical Engineering ITERSOA Deemed to be University Odisha Bhubaneswar India Software Engineer US Technology International Pvt Ltd India Department of Computer Science and Engineering R.M.D Engineering College Kavaraipettai 601206 India School of CSIT Symbiosis University of Applied Sciences Indore India

In this paper the importance of monitoring smart city with integration of sensors and Internet of Things (IoT) is discussed with establishment of node control process. To describe the feature of smart cities time measurements are considered with one hop distance between various nodes. Hence the system model is established for various parameters that are integrated with K-means algorithm for clustering and C4.5 for classification. As a result of combining the dual algorithms with system model it is possible to establish a secured state for each data with proper response factor. The major significance of proposed method is to introduce node point where all increasing queues in smart cities are controlled due to the information that is achieved from every data points. Moreover the improvement in projected model can be observed with four scenarios where security at every data point plays an important role at an increased level of 84%. In addition to security the amount of stable points is increased with reduction in disparities for about 2% thereby every applications in smart cities are monitored in a precise way. © 2023 The Authors

关键词： Measurement and control Security Sensors Smart city

来源：评论

学校读者我要写书评

暂无评论

Pedestrian detection using ResNet-101 based Mask R-CNN

引用

AIP Conference Proceedings 2023年第1期2705卷

作者： Sonal Sahu Satya Prakash Sahu Deepak Kumar Dewangan Department of Information Technology National Institute of Technology Raipur India Department of Computer Science and Engineering ITER SOA University Bhubaneswar India

Pedestrian detection is the most important process of any intelligent surveillance or advanced autonomous vehicle system. Autonomous vehicles observe the surroundings using camera, lidar, radar or sensor to detect the pedestrian from a certain distance so that vehicle can take the appropriate action. There are many frameworks that have been proposed by the researcher in the past years to make a better pedestrian detection model. The enhancement in the deep learning detection process becomes more accurate, but still, it is lacking in terms of accuracy and computational speed. To resolve this problem we are introducing a new deep learning model that uses the advantage of two most popular deep learning algorithms to detect the pedestrian more accurately in less time. In this paper we are using ResNet101 as a backbone of Mask R-CNN. Use of ResNet-101 here to extract the feature map as well as it overcomes the vanishing gradient and exploding gradient problem because of skipping connection features. Mask RCNN does masking on objects after classification to provide better visibility. The main aim of this model is to reduce the computational cost and increase the accuracy without affecting the robustness of the system. Based on the experimental result on the INRIA dataset the accuracy is reported 98.9% to 100% of the proposed model with 3.57% error rate that is less than the human error rate. We hope this model will get more improvement in the future to deal with the upcoming challenges in autonomous vehicles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial

Proceedings - 2020 4th Annual International Conference on Da...

引用

Proceedings - 2020 4th Annual International Conference on Data science and Business Analytics, ICDSBA 2020 2020年 xx页

作者： Patnaik, Srikanta International Relation and Publication Department of Computer Science and Engineering SOA University Bhubaneswar India

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：