检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Adarsh, U.K. Bankapur, Aseefhali Pai, Abhilash K. Kartha, V.B. Unnikrishnan, V.K. Department of Atomic and Molecular Physics Manipal Academy of Higher Education Karnataka Manipal576104 India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Background: Plastic Solid Waste (PSW) sorting is a procedure of prodigious importance in the mechanical recycling process of plastics waste. The major limitation of the techniques relying on physical properties of plastics is the delay in analysis and poor accuracy in measurements. The multimodal spectroscopy is proven to be a superlative method in assisting the plastic sorting process due to its analytical prediction with greater confidence. However, it is required to translate this aspect of the spectroscopic techniques into a practical plastic sorting system by combining it with advanced chemometric tools. Results: The indigenously developed Laser Induced Breakdown Spectroscopy (LIBS)-Raman system with single source and single detector gathers the spectral signals in single-shot mode in an accumulated time frame of 20 ms. Out of the combinations of Principal Component Analysis (PCA) and Partial Least Squares (PLS) with Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Partial Least Squares-Discriminant Analysis (PLS-DA) based classifiers, the PLD-DA based model showed the maximum classification accuracy with 95 % based on LIBS data and 100 % based on Raman data. The reliability of the model was assessed using 4-fold cross-validation which showed a sensitivity of 90.28 % and specificity of 98.29 % for predictions based on LIBS data, and 99 % sensitivity and 99.82% specificity for predictions relying on Raman ***: The results show how the combination of multimodal spectroscopy with chemometric analysis enhances the applicability of spectroscopic techniques for plastic sorting. The classification model successfully classified seven types of post-consumer plastic samples based on combined LIBS and Raman data. With the home-built software for automated prediction, the system takes less than a second to predict the plastic type which indeed shows the potential of the method for future industrial applications.

关键词： Spectroscopic analysis

来源：评论

学校读者我要写书评

暂无评论

ShoppingGPT: A GPT-based Product Recommendation Dialogue System 4

ShoppingGPT: A GPT-based Product Recommendation Dialogue Sys...

引用

4th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2023

作者： Yu, Renjie Guan, Yujing Zhan, Yuancheng Guangxi University of XingJian College of Science and Liberal Arts Dept. of Computer and Information Technology Nanning China Guangxi University of Finance and Economics Dept. of School of Big Data and Artificial Intelligence Nanning China Technology of NanNing University NanNing University Dept. Global Institute of Software Nanning China

ISBN: (纸本)9798350324303

This article introduces a shopping recommendation dialogue system called ShoppingGPT, which aims to help people get comprehensive product recommendations based on individual needs and preferences. The system can leverage existing large-scale generative pre-trained models with the ability to communicate and understand human language to provide more detailed and comprehensive product recommendations through multiple conversations with users. By constructing the shopping recommendation dataset and using the large-scale language model fine-tuning methods, we successfully fine-tuned on a large-scale language model and transformed the shopping recommendation task into a sequential labeling task to adapt to our shopping recommendation dialogue system. And we design a specific method for unlabeled prompt, which uses the basic language knowledge of large-scale language models to output product information for unsupervised annotation for product recommendation. In the experiment, we evaluate several existing language model fine-tuning techniques and explore the generalization ability of the ShoppingGPT system on unlabeled samples. We also compared models before and after fine-tuning to see what the models learned from the data. In the discussion section, we provide a detailed analysis of the advantages and limitations of ShoppingGPT and its potential applications in the shopping field. In addition, we explore the potential security challenges that ShoppingGPT can pose and discuss how to address them. Finally, we discussed how to improve ShoppingGPT to make it perform better and more secure. © 2023 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Efficient mode decision in HEVC

Efficient mode decision in HEVC

引用

Artificial Intelligence and data Engineering (AIDE), International Conference on

作者： Gururaj Bijur Ramakrishna M Karunakar A. K Department of Computer Science & Engineering Manipal Institute of Technology MAHE Manipal Udupi Karnataka India Department of Data Science & Computer Applications Manipal Institute of Technology MAHE Manipal Udupi Karnataka India

HEVC is the new coding standard aiming to provide better coding efficiency compared to its previous standard. Meantime this increases the computational complexity. In HEVC, there are 35 intra prediction modes, where as in H.264/A VC there were only 9 intra prediction modes. In this paper, we proposed a fast rough mode decision (RMD) algorithm to decrease the computational complexity using up and left reference pixels. The three-stage search method is implemented in RMD algorithm. The results obtained when compared with HM16.18, shows that the proposed algorithm can save 12.78 % to 28.86% of the encoding time with acceptable loss in video quality.

关键词： Degradation Search methods Prediction algorithms data engineering Encoding Quality assessment Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Complex Facial Expression Analysis and Recognition using Deep Networks

Complex Facial Expression Analysis and Recognition using Dee...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Sumana SG Manjula Yerva Shaila S G Srinivas K Vinuth Gowda S Dept. of Computer Applications Dayananda Sagar University Bangalore India Dept. of AIML Sri Siddhartha Institute of Technology Tumkur India Dept of CSE (Data Science) Dayananda Sagar University Bangalore India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Facial expression recognition plays a pivotal role in human-computer interaction. This work focuses on the development of a deep learning-based system for complex facial expression recognition. The methodology involves a comprehensive pipeline starting with the collection of input images utilizing OpenCV. The dataset comprises eight distinct expressions, each portrayed by two men and two women. Image acquisition leverages the 'haarcascade_frontalface_***' for accurate facial detection during expression capture. Subsequently, a preprocessing stage refines the dataset for optimal model training. The core of the work lies in the implementation of a Convolutional Neural Network (CNN). The CNN architecture employs Rectified Linear Unit (ReLU) activation functions for feature extraction and utilizes softmax activation for classification purposes. Through iterative training, the model learns to discern nuanced facial expressions, enabling accurate recognition. This work aims to contribute to the advancement of deep learning-based facial expression recognition systems, potentially enhancing human-computer interaction across various domains.

关键词： Training Human computer interaction Technological innovation Adaptation models Face recognition Refining Predictive models

来源：评论

学校读者我要写书评

暂无评论

Explainable Classification of Macular Degeneration Using Deep Learning

Explainable Classification of Macular Degeneration Using Dee...

引用

IEEE India Conference (INDICON)

作者： Sahil Khose Ankita Ghosh Yogish S. Kamath Neetha I. R. Kuzhuppilly J. R. Harish Kumar Dept. of Information and Communication Technology Manipal Academy of Higher Education Manipal Institute of Technology Manipal India Dept. of Computer Science and Engineering Manipal Academy of Higher Education Manipal Institute of Technology Manipal India Dept. of Ophthalmology Manipal Academy of Higher Education Kasturba Medical College Manipal India Dept. of Electrical and Electronics Engineering Manipal Academy of Higher Education Manipal Institute of Technology Manipal India

Age-related macular degeneration is one of the leading causes of vision loss in individuals. This paper proposes a fundus image-based analysis and automatic grading of AMD using deep learning techniques. We utilize data points from three different datasets and perform augmentation and data sampling to equalise the data distribution. We apply deep learning by proposing EfficientNet-B3 for training a three-class classification model which categorizes the fundus images as having no AMD, mild AMD or severe AMD. The results obtained are evaluated on various metrics and we obtain 93.6% accuracy. We also analyse the trained model by visualising the information learned by it using class activation map algorithms. The accuracy of the proposed method outperforms the majority of the existing methods. The confidence in the proposed model is further increased by the CAM algorithms which indicate that the model predicts the output based on the presence of retinal lesions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fovea Segmentation Using Semi-Supervised Learning

Fovea Segmentation Using Semi-Supervised Learning

引用

IEEE India Conference (INDICON)

作者： Ankita Ghosh Sahil Khose Yogish S. Kamath Neetha I. R. Kuzhuppilly J. R. Harish Kumar Dept. of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Dept. of Ophthalmology Kasturba Medical College Manipal Academy of Higher Education Manipal India Dept. of Electrical and Electronics Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

Despite the accessibility of retinal fundus images in recent years, fovea segmentation is an exacting task due to the insufficiency of labelled data. In this paper, we propose a deep learning pipeline which utilizes unlabelled data alongside labelled data for the segmentation of fovea. We train 484 labelled images using the Deeplabv3+ architecture and deploy EfficientNet-B3 as the encoder in the framework. Additionally, we introduce semi-supervised learning in our pipeline and train 1200 unlabelled images by generating their pseudo labels. We evaluate our results on the Jaccard index, Dice score, sensitivity, specificity and accuracy. Our Dice score of 82.43% and Jaccard index of 70.52% surpasses the existing methods. We obtain 91.74% sensitivity, 99.75% specificity and 99.57% accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian Belief Network Analysis for SPAD System in Railways

Bayesian Belief Network Analysis for SPAD System in Railways

引用

Multimedia Processing, Communication & Information technology (MPCIT), International Conference on

作者： Manjunath Sargur Krishnamurthy Bommisetty Rahul Chandrahas Reddy Bondala M Vishnu Vardhan Reddy Magha Raghul G Ambika B J JP Morgan & Chase Co. Houston Texas USA Dept. of AI&ML BMS Institute of Technology and Management Bengaluru Dept. of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Karnataka

ISBN: (数字)9798350375466

ISBN: (纸本)9798350375473

Even with a powerful network of signaling and warning systems in the country, there have been many examples of trains crossing the red signal due to various factors, even today. These occurrences, known as Signal Passed At Danger (SPAD) events, could potentially result in severe consequences such as train derailments, train collisions, infrastructure collisions, and other dangerous events. Traditionally, these events have been analyzed using the Fault Tree Analysis (FTA) approach Bayesian Network (BN) is considered to be a better model to represent this situation when it comes to handling complexity. Bayesian Network allows for integration and includes systematic knowledge about the system, which helps to get a very flexible concise, and simple graphed representation. This study demonstrates applications of Bayesian Belief Networks (BBN) analysing and enlightening the Signal Passed at Danger (SPAD) system in railway processes. Execution of BBN offers more dynamic and flexible models compared to outmoded Fault Tree Analysis (FTA), struggling with complexity. BBN efficiently catches the inter dependencies between factors that are contributing to SPAD events, such as signal conditions, human errors, and mechanical issues. Over simulations and probability calculations using OpenMarkov software, Study revealed key intuitions, such as identifying highly risk apparatuses within SPAD system. The outcomes include enhanced risk calculation accuracy and recommendations for improving signal systems and safety protocols. These conclusions contribute to a safer and reliable railway structure, highlighting the success of BBN for complex, safety critical systems in real world applications.

关键词： Analytical models Systematics Rail transportation Software Bayes methods Safety Complexity theory Software reliability Single-photon avalanche diodes Fault trees

来源：评论

学校读者我要写书评

暂无评论

Code Smell Detection using Hybrid Machine Learning Algorithms 5

Code Smell Detection using Hybrid Machine Learning Algorithm...

引用

5th International Conference on Inventive Research in Computing applications, ICIRCA 2023

作者： Mahalakshmi, D. Kasinathan, Prabakaran Elangovan, D. Rohith Bhat, C. Balamurugan, M. Sivakumar, S. Panimalar Engineering College Dept. of Information Technology India School of Computing Veltech Rangarajan Dr. Sagunthula R & D Institute of Science and Technology Dept. of Cse India Panimalar Engineering College Dept. of Cse India Chennai India Sri Sairam Engineering College Affiliated to Anna University Dept. of Cse India Lakshmi Bangaru Arts and Science College Dept. of Computer Applications melmaruvathur India

ISBN: (纸本)9798350321425

Code smells frequently leads to the discovery of decreased code quality, drains on application resources, or even critical security vulnerabilities embedded within the application's code. While code smells may not always indicate a particularly serious problem, it do often lead to the discovery of these issues. Software's structural characteristics lead to a design issue that makes it challenging to manage and maintain code refactoring. The goal of the current research is to create methods for identifying code smells. The machine learning algorithm is a reliable method for individualized smell detection, but there aren't many studies on how well it works for different developers. In this proposed work used two different deep learning algorithms and five different machine learning ensembles to detect suspicious code. Investigation of the data class, God class, Feature-envy, and Long-method datasets revealed that each contained various levels of code smells. Although there is room for improvement, the outcomes of prior publications' applications of machine learning and stacking ensemble learning methods to this dataset were satisfactory. A class balancing method (SMOTE) was implemented to address the problem of class imbalance within the datasets. While the Feature- envy dataset with the selected dozen metrics produced the lowest accuracy (91.45%) for the Max voting method, the Long-method dataset with the various chosen metrics produced the highest accuracy (100%) for all five methods. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

HealthPredictor: Accurate Health Insights at Your Fingertips

HealthPredictor: Accurate Health Insights at Your Fingertips

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Mahantesh M. Sajjan Nausheen Ammanagi Laxmi Pujari Vishwanath S Kamatar Meenaz Belavatgi Dept. of Master of Computer Applications K.L.E. Institute of Technology Hubballi India Dept. of Computer Science and Engineering K.L.E. Institute of Technology Hubballi India

ISBN: (数字)9798350364569

ISBN: (纸本)9798350364576

The "HealthPredictor: Accurate Health Insights at Your Fingertips" system transforms healthcare by predicting diseases based on user symptoms. Utilizing advanced machine learning models such as Decision Tree, SVM, Random Forest, and Logistic Regression, it assesses the likelihood of various illnesses. The system compares symptoms to a comprehensive dataset to provide accurate predictions, aiding in early detection. Users can consult with specialist doctors through an integrated chat feature, ensuring quick access to medical advice. By continuously learning from historical data, the system enhances its predictive capabilities, identifying new health patterns and trends. This proactive approach empowers users with timely information and personalized consultations, leading to better health outcomes.

关键词： Support vector machines Accuracy Medical services Transforms Prediction algorithms Real-time systems Reliability Medical diagnostic imaging Regression tree analysis Random forests

来源：评论

学校读者我要写书评

暂无评论

A Family of Probabilistic Triple-bit Encryptions for Secure Cloud applications 2

A Family of Probabilistic Triple-bit Encryptions for Secure ...

引用

2nd International Conference on Secure Cyber Computing and Communications, ICSCCC 2021

作者： Bhat, Radhakrishna Manipal Academy of Higher Education Manipal Institute of Technology Dept. of Computer Science and Engineering Karnataka Manipal576104 India

ISBN: (纸本)9781665444156

In order to strengthen secure cloud storage and retrieval, we propose a new family of triple-bit encryption switching protocols which can encrypt any plaintext m ∈ {0, 1}n and generate the ciphertexts of $\frac{{2n}}{3}\cdot\log N$ size where k=log N, N is the RSA composite, n ∈ and is a multiple of an integer 3. The proposed protocols support encryption switching (i.e., switching from homomorphic setting to non-malleability). The semantic security of all the proposed protocols is guaranteed under standard quadratic residuosity assumption and the non-malleability is guaranteed under resilient to adaptive chosen ciphertext attack. The proposed scheme can encrypt a binary string of any length with any probability distribution and also provide the optional tamper evidence. Finally, a tamper-proof secure information retrieval method over the untrusted cloud has been presented. © 2021 IEEE.

关键词： Semantics

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：