检索结果-内蒙古大学图书馆

2021 International Conference on Intelligent technologies, CONIT 2021

作者： Sreedevi, M. Manasa, Garikapati Apurva, Idupulapati Koneru Lakshmaiah Education FoundationVaddeswaram Dept of Computer Science and Engineering Andhra Pradesh India Koneru Lakshmaiah Education Foundation Vaddeswaram Jonnalagadda Mohana and Reddem Pravallika Final Year B.Tech CSE Andhra Pradesh India

ISBN: (纸本)9781728185835

To enhance the capability of the learning model in this research paper we have developed a hybrid feature selection method. To defeat the curse of dimensionality, to speed up the classification process, and to get more accurate results a hybrid feature selection model is developed which is a combination of multiple filter methods and a wrapper method. In this model, we employed two sets of Filter Methods-basic filter methods, a correlation filter method and two Statistical Ranking filter methods (ANOVA and ROC-AUC) to generate two different subsets of important features, and a Wrapper method (Recursive Feature Elimination with Cross-Validation) is applied on the combined subset to generate a final subset of important features for better prediction results. Five machine learning algorithms-Logistic Regression (LR), Decision Tree, Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbour are used to evaluate the classification accuracy. The proposed hybrid method is applied over four low and four microarray datasets. Outputs are compared to find out which algorithm works best with the proposed model as the results diverge with the machine learning algorithm. Precision, Sensitivity, and Specificity are calculated for each outcome and they demonstrate that the suggested method improved the accuracy of the algorithms. © 2021 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A Recommendation System for Crop Prediction Under Diverse Weather Conditions

A Recommendation System for Crop Prediction Under Diverse We...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： P ShunmugaLakshmi V Ram Kishore Pillai Pratham Ramachandran S Santhi S Kalaiselvi B.Tech Information Technology National Engineering College Kovilpatti Tamil Nadu Dept. of Information Technology National Engineering College Kovilpatti Tamil Nadu Dept. of Computer Science and Engineering National Engineering College Kovilpatti Tamil Nadu

In order to develop strategic initiatives in agricultural belonging for trading protocol and tripling countrymen earnings, early and accurate agricultural output estimation is pivotal in computable and commercial decision at the territory plane. Crop production forecasting, which is done to foresee a greater crop output, is the impressive difficulty in the agronomic division. To help farmers increase agricultural yield, this study has collected and evaluated data on N, P, K, temperature, humidity, ph, rainfall and soil_moisture. The superior values of this work are to recommend the crop to cultivate, suggest the appropriate fertilizers to use and predict the disease of a crop. A python environment is used to perform initial preprocessing on the data. KNN classification is used for developing the recommendation system. The link between the count, nutrients, temperature, humidity, pH, rainfall, and crop, are visualized using bar graphs and scatter plots. The tensor and torch were used to forecast crop disease and also to suggest appropriate fertilizer based on the data. The application was developed using Python Flask. This Classification was compared with other algorithms such as SVM, DT , RF and K-means.

关键词： Support vector machines Temperature sensors Linear regression Crops Humidity Prediction algorithms Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of ResNet, EfficientNet, and MobileNetV2 for Detecting Skin Conditions in Deep Learning Models

Comparative Analysis of ResNet, EfficientNet, and MobileNetV...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： M. Rajkumar Shreenath Raghunath Siriyala Ananya Sharma D. Naga Sujith Kumar Department of Smart Computing School of Information Technology & Engineering Vellore Institute of Technology VIT University Vellore Campus Tamil Nadu India B.Tech-Information Technology School of Computer Science Engineering and Information Systems (SCORE) Vellore Institute of Technology VIT University Vellore Campus Tamil Nadu India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

Comparing the effectiveness of Skin Condition Detection using ResNet, EfficientNet and MobileNetV2 deep learning models. The 3 skin conditions that have been considered are Acrochordon, Lichenoid Keratosis and Vascular Lesions. The ResNet Model, EfficientNet Model and MobileNetV2 Model have been assessed against one another. ResNet and EfficientNet both predicted the skin condition with an accuracy of 92.1875% which is greater than MobileNetV2, which predicted the skin condition with 90.625% accuracy. Through this research, it has been concluded that ResNet and EfficientNet are significantly better than MobileNetV2 in terms of training models to accurately detect skin conditions.

关键词： Deep learning Training Analytical models Accuracy Quantization (signal) Green communications Skin Reliability Lesions Tuning

来源：评论

学校读者我要写书评

暂无评论

Monitoring state of mind using Natural Language Processing

Monitoring state of mind using Natural Language Processing

引用

International Conference on Advances in Computing, Communication and Control (ICAC3)

作者： Vemula Sai Saketh Srinivas Khatravath Yashvanth Kumar Guntupalli B.Tech Computer Science PES University Bangalore India M.Tech Electronics and Electrical Communication IIT Kharagpur Kharagpur India

ISBN: (纸本)9781665426350

State of mind is essential in every person’s life to keep their life stable, calm and peaceful. The key factors that contribute towards them are mood, emotion and thoughts. Monitoring them is key to a person's overall development and allows family and friends to support them to a greater extent. One aspect of getting a report on this is using the words being typed by the person on their computer or mobile, browser history, songs and movies played. This paper proposes a sentiment analysis system where information about mood and thoughts are conveyed by means of natural language processing. These logs captured during each time session are classified to gain insights about the person. This reduces the likelihood of any drastic decisions taken by the person and provides a better means of conveying the information and maintaining communication between them and their relations.

关键词： Sentiment analysis Mood Motion pictures browsers History Monitoring

来源：评论

学校读者我要写书评

暂无评论

Cloud-based fault prediction using IoT in office automation for improvisation of the health of employees

Cloud-based fault prediction using IoT in office automation ...

引用

Advance Computing and Innovative technologies in Engineering (ICACITE), International Conference on

作者： Nakul Shahdadpuri Somanchi Hari Krishna SathiJyothirmaye Reddy C. Ganesh Kirti Agarwal Sourabh bhattacharya IPG Programme {(B.Tech + M.Tech (It)} IIITM Gwalior Department of Business Management Vignana Bharathi Institute of Technology Malkajigiri Telangana Department of Management Marwadi University Rajkot Gujarat Computer and Communication Engineering Sri Eshwar College of Engineering Anna University Chennai ITERC College Delhi (NCR) India Department of Management and Social Science Haldia Institute of Technology West Bengal

Modern technology is the best thing to be used in every commercial sector. The devices are well equipped to understand the problems of the users. The offices are now been maintained by technology the devices for daily monitoring even the electrical appliances are been monitored and maintained by technology. In previous times the best method of this work is to make it via cloud computing, but now as technology has evolved and evolved new adding devices are making system malfunction. The fault of cloud computing needs to be identified, So the best method is to automate the office with the introduction of IoT. it is a platform equipped with all the facilities for monitoring and maintaining the devices inside the office, even the working capacity of employees is also measured via this method. The study is showing the effectiveness of the IoT to identify the faults of cloud computing related to maintaining the working method of the office. The data collected for this study is secondary data like articles, books, journals and many more. Then gathered data is analyzed by qualitative data analysis. The results are quite positive about the use of it to automate the office and its working procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face Spoof Detection Using Gray Level Co-Occurrence Matrix and Discrete Wavelet Transform Feature Extractor

Face Spoof Detection Using Gray Level Co-Occurrence Matrix a...

引用

International Conference on Computing sciences (ICCS)

作者： Amal Mathew Kaushik Daiv Polkumpally Rohan Goud Piyush Talreja Sai Sanjana Reddy Vatte B.tech Computer Science Ms Ramaiah University of Applied Sciences Bangalore Karnataka India B.E. Computer Science MIT College of Engineering Pune Maharashtra India B.E Computer Science Chaitanya Bharathi Institute of Technology Hyderabad India B.E Computer Science Maharashtra Institute of Technology Pune Maharashtra India

ISBN: (纸本)9781665494465

Face identification using ML (machine learning) is well-known. Attendance structures may benefit from this method. Using this method, you may achieve the desired area, as well as beneficial attributes and a dataset, by preparing two sets of data again for test and training phases. To distinguish between a testing set and a test sets, a photograph is used as a testing set. An ensemble classification method is used to sort the test images into categories like “identified” and “unidentified.” This model can't provide reliable findings since it simply divides data into two categories. The development of GLCM was motivated by the need to use texture properties to identify faces. The existence of the query picture is noted once face detection has taken place. In simulation findings, the new model outperforms the baseline models in terms of accuracy. Keywords—Ensemble classifier, GLCM, Face Spoof, SVM, DWT

关键词： Training Image segmentation Face recognition Training data Machine learning Transforms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Crop Analysis and Seed Marketing using Regression and Association Rules of India

Crop Analysis and Seed Marketing using Regression and Associ...

引用

Emerging Trends in Information technology and Engineering (ic-ETITE), Conference on

作者： Vivank Sharma Mansi Shukla Ritika Mandal B.Tech (Information Technology) Vellore Institute of Technology Vellore India B.Tech (Computer Science) Vellore Institute of Technology Vellore India

ISBN: (数字)9781728141428

ISBN: (纸本)9781728141435

The agriculture plays a crucial and vital role in the country's Economy. A major population of any country across the globe depends on agriculture for survival. Many times resources are wasted when the farmers are not able to correctly predict the crop to be grown due to lack of information. We have tried to build a model that predicts the type of crop that can be cultivated in a given land on the basis of climatic conditions. Therefore, the crop with maximum production probability for a given area of land can be cultivated and thus in this way, the resources and hard work of the farmers would be optimized and will give better results. This model would also help in effective seed marketing as the predictive analysis of the suitable crop would help the suppliers supply the suitable crop seed in enough quantity to the farmers which would benefit the suppliers as well as the farmers.

关键词： regression elimination association marketing Telemarketing Farmers (2004) Regression (Psychology) crops Avian Crop agriculture Association (Psychology) Association rules elimination Seeds Globe Land

来源：评论

学校读者我要写书评

暂无评论

SD-measure: a social distancing detector

arXiv

引用

arXiv 2020年

作者： Gupta, Savyasachi Kapil, Rudraksh Kanahasabai, Goutham Joshi, Shreyas Srinivas Joshi, Aniruddha Srinivas B.Tech Department of Computer Science and Engineering National Institute of Technology Warangal Telangana506004 India

The practice of social distancing is imperative to curbing the spread of contagious diseases and has been globally adopted as a non-pharmaceutical prevention measure during the COVID-19 pandemic. This work proposes a novel framework named SD-Measure for detecting social distancing from video footages. The proposed framework leverages the Mask R-CNN deep neural network to detect people in a video frame. To consistently identify whether social distancing is practiced during the interaction between people, a centroid tracking algorithm is utilised to track the subjects over the course of the footage. With the aid of authentic algorithms for approximating the distance of people from the camera and between themselves, we determine whether the social distancing guidelines are being adhered to. The framework attained a high accuracy value in conjunction with a low false alarm rate when tested on Custom Video Footage Dataset (CVFD) and Custom Personal Images Dataset (CPID), where it manifested its effectiveness in determining whether social distancing guidelines were practiced. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

VLSI implementation using fully connected neural networks for energy consumption over neurons

引用

SUSTAINAbLE ENERGY techNOLOGIES AND ASSESSMENTS 2022年第PartA期52卷

作者： Mehbodniya, Abolfazl Kumar, Ravi Mohanty, Sachi Nandan Geetha, A. bedi, Pradeep Tripathi, Rohit [a]Department of Electronics and Communications Engineering Kuwait College of Science and Technology (KCST) Doha Area 7th Ring Road Kuwait [b]Department of Electronics and Communication Engineering Jaypee University of Engineering and Technology Guna Madhya Pradesh India [c]Department of ECE Saveetha School of Engineering SIMATS Thadalam Chennai - 602105 Tamil Nadu India [d]Department of Computer Science & Engineering Vardhaman College of Engineering (Autonomous) Hyderabad India [e]B.Tech Department of ECE Indian Institute of Space Science and Technology Thiruvananthapuram 695547 Kerala India [f]Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu 603203 India

Increasingly, the capacity of artificial neural networks to identify and express top-level concepts in sets of data has become quite significant. Deep learning models like fully connected layer machine learning have demonstrated outstanding results in range of identification and verification applications. It's technology deployments suffered as from complexity and huge silicone areas with energy consumption. Memory accesses, the bulk from which happens in fully connected systems, comprise the energy usage of machine learning. It has many of the depths of neural network. Throughout this work, researchers suggest densely connected networks by demonstrating that there is indeed a drop in the number of links inside fully connected systems of up to 90% enhancing the quality of three popular sets of data. To decrease the memory needs have suggested low-connected grid networks, researchers present perhaps an effective hardware implementation based on the linear response registers. In comparison to the traditional design of fully connected layer neural network models, the suggested design could save up to 90 percent of storage. Findings of execution further reveal that artificial neurons of suggested weak network connections have a power consumption decrease up to 84 percent compared to one single atom of fully connected layer machine learning.

关键词： Neural Network Deep learning Energy consumption VLSI

来源：评论

学校读者我要写书评

暂无评论

Twitter Sentiments Analysis Using Machine Learninig Methods

Twitter Sentiments Analysis Using Machine Learninig Methods

引用

Emerging technology (INCET), International Conference for

作者： Lokesh Mandloi Ruchi Patel B.Tech Computer Science and Engineering Meidcaps University Indore India Dept. Computer Science and Engineering Medicaps University Indore India

ISBN: (数字)9781728162218

ISBN: (纸本)9781728162225

Analysis of sentiments is the method of deciding whether the sentiments in the text is positive, negative or neutral. It is also known as material polarity or mining of opinions. The growth and advancement in social media platforms engaged a huge number of users. Social media platform like twitter where users can post their tweets in 280 characters. because of the limited number of characters in tweets, it becomes easy for the sentiment analysis. On Twitter 550 millions of tweets are posted daily. Twitter also represents all age group people and also a fair representation of gender. Therefore, the sentiment analysis of twitter data becomes somewhat general sentiments of society. In this paper, we will compare various Machine Learning methods like the Naïve bayes Classification method, Support Vector Machine Classification Method and Maximum Entropy Classification method. We will see how sentiments analysis is done by this classification algorithm and what is the accuracy and precision in these cases.

关键词： Sentiment analysis Twitter Machine learning Feature extraction Support vector machines Entropy

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：