检索结果-内蒙古大学图书馆

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Varshini, Surisetty Hima Varma, Gottimukkala Sarayu Belwal, Meena Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350370249

Telugu, the largest Dravidian language, is one of the Indian languages that is predominantly spoken in Andhra Pradesh, Telangana and a few parts of southern India. The proposed work presents a speech-to-text based recognizer cum parser for some simple sentences in Telugu which are commonly used in day-to-day conversations. The Probabilistic Cocke-Younger-Kasami (P-CYK) algorithm has been employed in order to recognize these simple sentences and generate the corresponding probabilistic parse for these sentences. These parses will be useful in gaining a better understanding about the grammatical structure of a given sentence. At present, there are not many linguistic processing methodologies which are integrated with speech-based inputs for regional languages like Telugu. Hence, an effort has been made in order to efficiently use speech as the form of input and obtain the parse for some basic sentences with the corresponding probability of that parse. The probabilistic parser that has been developed in this work takes speech in Telugu as the input and identifies both grammatically correct and incorrect sentences and produce the probabilistic parse of the grammatically correct sentences. This system was then assessed by making use of the metrics like accuracy score, precision score and recall score. Also, a user interface was developed using Streamlit for the same. © 2024 IEEE.

关键词： accuracy score parser precision score Probabilistic Cocke-Younger-Kasami algorithm probabilistic parse recall score recognizer speech-to-text Streamlit user interface

来源：评论

学校读者我要写书评

暂无评论

Forecasting India's Air Quality: A Machine Learning Approach for Comprehensive Analysis and Prediction 4

Forecasting India's Air Quality: A Machine Learning Approach...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Kothari, Osho Sah, Nabin Kumar Kumar, Konda V S Harshith Nair, Priyanka C Sampath, Nalini Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350349900

With rising industrialization, India confronts increasing difficulties in maintaining air quality regulations. This research proposes a comprehensive analysis and prediction framework based on machine learning approaches for assessing and forecasting the Air Quality Index (AQI) in different place of India. This model takes into account a wide variety of pollutant concentrations that are monitored at regular intervals. This approach, which uses historical data from numerous Indian cities, employs a variety of machine learning methods, including k-Neighbour regression, decision tree regressor, linear regression, and random forest regressor, in addition to support vector regressor. Every model had performed well but the Decision Tree Regression and Random forest has performed best achieving RMSE value as 0.0016 and 0.00095 respectivelly whereas R-Squared value as 0.99 for both the model, indicating strong performance and a substantial progress in air quality prediction. The environmental health risks associated with air pollution have been mitigated by the addition of important knowledge. © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Deep Learning Models for Detection of Diabetic Foot Ulcer using Foot Thermography Images 15

A Comparative Analysis of Deep Learning Models for Detection...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Chowdary, Chava Sriya Ruthwik, Dovala Sai, Kancharla Nitish Rishik, Suthapalli Sampath, Nalini Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Diabetic foot ulcers (DFUs) are a serious consequence for diabetes individuals, frequently resulting in amputation. Early identification is critical in averting such results. This study looks at the effectiveness of deep learning models in recognizing DFUs from foot thermography photos. We evaluate the performance of several deep learning architectures against more contemporary models. The models will be trained and assessed using a publicly accessible foot thermography picture collection that includes both healthy and DFU patients. Each model's performance in DFU identification will be evaluated based on accuracy, precision, recall, and f 1 score. We intend to find the deep learning model with the greatest accuracy,f1 score, and robustness in DFU classification, which would pave the way for a computer-aided diagnostic tool that uses thermography to detect DFU in diabetes patients early. This research shows potential for enhancing patient care and lowering amputation rates. © 2024 IEEE.

关键词： Convolutional Neural Networks (CNNs) Deep learning models Diabetic foot ulcer (DFU) Foot thermography images Transformers

来源：评论

学校读者我要写书评

暂无评论

Leveraging a Custom Multi Modal OCR System for Marksheet Data Extraction 15

Leveraging a Custom Multi Modal OCR System for Marksheet Dat...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Kalra, Bhavvuk D. Suresh, Sreedath Sanjay Adithya, M. Shanmuga Priya, S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350370249

In the current educational landscape, the transition towards digitalization has become crucial. However, the manual entry of data from traditional physical marksheets into digital systems remains a significant bottleneck in the process. Educators often spend significant amount of time and effort entering data into electronic systems, which could be better utilized for more productive *** this paper, we offer a solution to this problem. We propose an automated system that leverages Optical Character Recognition (OCR) Technology to streamline the extraction of essential information from marksheets. We discuss about the Dataset, preprocessing on the input image, Multi Modal OCR system Structure and other implementation details. We conclude the paper by a comparative study of our Multi Modal OCR system with other Commercially available OCRs like EasyOCR, PaddleOCR and PyTesseract. © 2024 IEEE.

关键词： Character Isolation CNN Data Extraction Digits Handwritten Letters Marksheets Multi Modal Neural Network Optical Character Recognition (OCR) Preprocessing Region of Interest Template Image Text Recognition

来源：评论

学校读者我要写书评

暂无评论

YoloV8-Powered Surveillance: Safeguarding Crops from Wildlife and Fire Hazards 15

YoloV8-Powered Surveillance: Safeguarding Crops from Wildlif...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Nishanth, K. Pranav, Shri S. Jayasuriyaa, E. Lalithamani, N. Prasand, Ajey M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798350370249

Agriculture is the backbone of India's economy. However, the farmers are facing crop damage due to wild animals encounter and fire. The study has mainly intended to provide a solution for the prevention of wildlife encounters into agricultural field and fire using Object Detection. This study mainly focuses on detection of fire and four distinct animals: Elephant, Wild Boar, Deer and Cow. The dataset contains 7000 images with annotated five categories of Object. We trained five YOLOv8 models (nano - YOLOv8n, small - YOLOv8s, medium - YOLOv8m, large - YOLOv8l, extra-large – YOLOv8x) on our dataset. Raspberry Pi equipped with a Camera captures video of the crop field and applies Yolov8 (Object Detection Algorithm) to detect fire and wildlife encounters and plays some loud noises to deter wild animals. The Farmer is notified with a photograph of Farm and class name of the animal detection made through a Telegram Bot. The trained medium YOLOv8m model has attained a mAP of 92.2%, proving its efficacy in identifying fire and wild animals. By integrating this device across farm field, real-time automated monitoring and alerts can be provided to farmers, minimizing crop losses. © 2024 IEEE.

关键词： Fire hazards

来源：评论

学校读者我要写书评

暂无评论

Enhancing Village Ranking: Leveraging Cluster Analysis and Machine Learning 5

Enhancing Village Ranking: Leveraging Cluster Analysis and M...

引用

5th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2024

作者： Karthikeya, Moturi Madhan, S. Sha, Akhbar Megha, R. Dhanush Krishna, R. Gopakumar, G. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

The research presented in this paper addresses the critical challenge of ranking Indian villages based on their potential for socioeconomic growth, inspired by the objectives of the Shyam Prasad Mukerji Rurban Mission (SPMRM). Leveraging a novel algorithm known as ClusterRank, an extension of the PageRank algorithm, we endeavor to provide a timely, efficient, and accurate solution for village ranking. The ClusterRank algorithm, an extension of the well-known PageRank algorithm, serves as the cornerstone of our approach. It excels in its ability to efficiently and accurately rank villages, outperforming alternative ranking methods. Notably, our findings reveal the superior convergence speed of the ClusterRank algorithm, affirming its capacity to produce rapid results. To assess the efficacy of ClusterRank, we employ a range of statistical ranking coefficients, including the Spearman, Kendall, and Point Biserial correlation coefficients. Our analysis demonstrates a strong positive correlation, with a Spearman correlation coefficient of 0.89, between the rankings generated by ClusterRank and the ground truth rankings provided by SPMRM. This correlation underscores the effectiveness of ClusterRank in identifying villages with high growth potential and highlights its alignment with the objectives of the SPMRM. This research presents a compelling case for the adoption of the ClusterRank algorithm by SPMRM as a valuable tool in the identification of rural areas poised for rurban development. Such adoption not only promises substantial time and resource savings but also directs the focus of SPMRM towards the implementation of targeted interventions and initiatives to uplift rural communities. Moreover, our supplementary analyses using Kendall and Point Biserial correlation coefficients further validate the robustness of the ClusterRank algorithm. © 2024 The Authors. Published by Elsevier B.V.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Integrative Day Trading Stock Trend Prediction using Web Scraping and Sentiment Analysis 9

Integrative Day Trading Stock Trend Prediction using Web Scr...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Chennupati, Anjali Prahas, Bhamidipati Ghali, Bharadwaj Aaditya Venugopalan, Manju Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

In the digital era, data is pivotal across disciplines like business, marketing, engineering, and social sciences. This research proposes a new method of acquiring intraday stock data from the National Stock Exchangeand sentiment-laden news articles, via the web-scrapping technology. Spark's distributed computing framework that provides powerful processing capabilities has been employed to perform sentiment analysis and quantify sentiment scores for the chosen stock over the past month. Concurrently, the XGBoost algorithm processes the historical stock data to predict future values along with the cross-validation process. With the integration between the XGBoostpredictions and the sentiment score, this model offers stock recommendations to the user to either buy or sell a certain stock. The proposed model performance is evaluated for future value predictionsbased on the average RMSE score reported as *** extremely systematic take reaches across financial prediction, natural language processing, and machine learning to supply recommendations for investors. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Aural Signatures: Audio Fingerprinting Techniques for Real-Time Audio Recognition 3

Aural Signatures: Audio Fingerprinting Techniques for Real-T...

引用

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Sharan Nripesh Reddy, B. Sai Venkat, B. Manohar, I. Abhishek, S. Anjali, T. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798350396157

Audio fingerprinting is an essential technique for copyright protection and music recognition. The capacity to accurately categorize audio content and spot possible copyright violations is vital for musicians, content creators, and streaming services. With its valuable solutions for copyright protection, content monitoring, and music recommendation, this study has significant implications for the music industry. In the research, the research focused on developing robust audio fingerprinting methods for precise audio content recognition. These tactics have shown to be remarkably accurate and quite effective. The approach is based on the use of strong hashing techniques and the extraction of various audio aspects. Long Short-Term Memory (LSTM) along with SVM, KNN, and CNN were employed in the research. Notably, LSTM outperformed other models, showcasing an outstanding accuracy rate of 93 %. The results hold particular promise for massive music platforms and instantaneous content matching. The proposed methods have demonstrated the effectiveness of these strategies in identifying audio material, even under challenging conditions. © 2024 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

Suraksha: Advanced SOS Android App with Intelligent Spam Alert Management and Collaborative Decision-Making 15

Suraksha: Advanced SOS Android App with Intelligent Spam Ale...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Padmavathi, A. Shashini, V. Ryan, J. Collin Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

Safety is first and foremost in the current busy life, and smartphones give a helping hand in protecting. This paper has presented an Android app, Suraksha, which enhances personal safety during emergencies. This app ensures that assistance is sought immediately, whereas traditional ways require one to call a person or send the person a message or even unlock the phone, which may not happen when in distress. The nature of shrugs allows the app to differentiate a safe situation and a red alert. Through distress shrugs, the app sends the user's location and the user's defined message to the pre-registered ones. Suraksha app depends on humans to judge the alerts and all the information involved, which creates a bundle of evidence that will be sufficient. It is designed with a Machine Learning model, which studies the user's learned things and the emergency type to understand its effectiveness. © 2024 IEEE.

关键词： Android Convulated neural networking Gesture GPS Isolation Forest Machine learning Registered Contacts Transmission protocols

来源：评论

学校读者我要写书评

暂无评论

A Self-Adapting and Efficient Dandelion Algorithm and Its Application to Feature Selection for Credit Card Fraud Detection

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 377-390页

作者： Honghao Zhu MengChu Zhou Yu Xie Aiiad Albeshri IEEE School of Computer and Information Engineering Bengbu UniversityBengbu 233030China School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China Helen and John C.Hartmann the Department of Electrical and Computer EngineeringNew Jersey Institute of TechnologyNewark NJ 07102 USA College of Information Engineering Shanghai Maritime UniversityShanghai 201306China Department of Computer Science King Abdulaziz UniversityJeddah 21481Saudi Arabia

A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all optimization problems. A self-adapting and efficient dandelion algorithm is proposed in this work to lower the number of DA's parameters and simplify DA's structure. Only the normal sowing operator is retained;while the other operators are discarded. An adaptive seeding radius strategy is designed for the core dandelion. The results show that the proposed algorithm achieves better performance on the standard test functions with less time consumption than its competitive peers. In addition, the proposed algorithm is applied to feature selection for credit card fraud detection(CCFD), and the results indicate that it can obtain higher classification and detection performance than the-state-of-the-art methods.

关键词： Credit card fraud detection(CCFD) dandelion algorithm(DA) feature selection normal sowing operator

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：