检索结果-内蒙古大学图书馆

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Jogi, Shwetha Shilpa, B.K. Samyaktha, G.A. Akshatha, Y. Poornima, A.S. Department of Computer Science and Engineering Siddaganga Institute of Technology Tumakuru India

One of the important medical tests to evaluate overall human health condition is the Complete Blood Cell Count (CBC). Traditionally these blood cells were counted manually by visual inspection or by using the haemocytometer along with some chemical compounds and other scientific equipment’s which is a tedious task and more time consuming. To avoid this problem, the proposed work here is the machine learning approach of automatic identification and counting of blood cells (RBC’s, WBC’s and Platelets) using ‘You Only Look Once’ in short YOLO object detection and classification algorithm to automatically identify and count the blood cells from the blood smear images. This YOLO framework will be trained the modified Blood Cell Count Data set (BCCD) of blood smear images to automatically identify and count the RBC’s, WBC’s and Platelets from the blood smear images. Thus, overall, the computer aided system of counting and detection enables to count the blood cells just in less than a second and this can be useful in the practical applications. We choose YOLO framework which is about three times faster than Faster RCNN with VGG-16 architecture. YOLO uses a single neural network to predict bounding boxes and class probabilities directly from the full image in one evaluation. We retrain YOLO framework to automatically identify and count RBCs, WBCs, and platelets from blood smear images. In order to improve the counting accuracy, a verification method has been developed to avoid repeated counting by the framework. © Grenze Scientific Society, 2023.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Novel Intent Detection and Active Learning Based Classification 37

Novel Intent Detection and Active Learning Based Classificat...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Mullick, Ankan Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India

ISBN: (纸本)9781577358800

Novel intent class detection is an important problem in real world scenario for conversational agents for continuous interaction. Several research works have been done to detect novel intents in a mono-lingual (primarily English) texts and images. But, current systems lack an end-to-end universal framework to detect novel intents across various different languages with less human annotation effort for mis-classified and system rejected samples. This paper proposes NIDAL (Novel Intent Detection and Active Learning based classification), a semi-supervised framework to detect novel intents while reducing human annotation cost. Empirical results on various benchmark datasets demonstrate that this system outperforms the baseline methods by more than 10% margin for accuracy and macro-F1. The system achieves this while maintaining overall annotation cost to be just ∼ 6-10% of the unlabeled data available to the system. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Mitr - Face Emotion Recognition Based Adaptive E- Learning Platform 9

Mitr - Face Emotion Recognition Based Adaptive E- Learning P...

引用

9th IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2023

作者： Sheejamol, P.T. Chetan Teja, G.V.S. Balaram, Battini Rao, Putta Suman Chacko, Anu National Institute of Technology Department of Computer Science and Engineering Calicut India

ISBN: (纸本)9798350319651

Assistive technology (AT) for improving the learning experience for differently abled students has received greater focus after COVID as it was revealed that traditional e-learning applications cannot be effectively used by them. Children with learning difficulties usually suffer from a lower attention span. In the physical scenario, a therapist actively engages the student by changing the activities so as to help them focus. In this paper, we propose an e-learning platform that personalizes the learning experience for children with difficulties by regulating their emotions. The tool uses facial emotion recognition to gauge the interest of the student and plans the learning pathway so as to help him relax and be more engaged. A proof of concept, Mitr meaning friend in Hindi, was developed to check the feasibility of the idea. Mitr is a baseline version, and it proves that the use of Artificial Intelligence (AI) in Assistive technology can improve personalization and effectiveness for people. © 2023 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Popular Word Embeddings and Deep Learning Methods for Tweets Classification 5

Comparative Study of Popular Word Embeddings and Deep Learni...

引用

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Sethumadhavan, Praneeth Alluru, Kavya School of Computer Science & Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350305449

This study aims to find the best deep learning models and word embedding methods that can be used for the classification of tweets as positive or negative. Data was preprocessed and lemmatized and then tokenization of tweets was done to be made suitable for training. Four different word embedding methods Word2Vec, GloVe, FastText, and SpaCy were used as embedding layers for deep learning models. Six different neural networks, simple NN, CNN, LSTM, GRU, Bi-LSTM, and BiGRU, were trained and tested. Bi-LSTM along with Word2Vec word embedding layer produced the highest accuracy of 84.28%. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Detection of Canine Parvovirus using ELM and Support Vector Machine Algorithm from Blood Tests

Detection of Canine Parvovirus using ELM and Support Vector ...

引用

2023 International Conference on computer, Electronics and Electrical engineering and their Applications, IC2E3 2023

作者： Kole, Silica Kuppili, Venkatanareshbabu National Institute of Technology Department of Computer Science and Engineering Goa India

ISBN: (纸本)9798350338003

Canine parvovirus is a widespread disease affecting dogs, particularly young puppies. Most frequently, a fecal ELISA test is used to detect this virus. This test does not guarantee the presence of the virus in the dog and costs between 3500 and 4000 RS (INR). Generally, Veterinary doctors conduct blood tests of the affected dogs and then recommend the fecal ELISA test since different parameters of blood tests also cannot accurately predict the presence of Parvovirus. In this paper, a novel method of Parvovirus detection is proposed based on the blood chemistry report of the dog. This method uses a Semi-supervised Support Vector Machine (SSVM) based model to detect the virus using the blood chemistry parameters of the animal with labeled and unlabeled data. © 2023 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Hate Speech Detection in Assamese

Transformer-Based Hate Speech Detection in Assamese

引用

2023 IEEE Guwahati Subsection Conference, GCON 2023

作者： Ghosh, Koyel Sonowal, Debarshi Basumatary, Abhilash Gogoi, Bidisha Senapati, Apurbalal Central Institute of Technology Computer Science and Engineering Assam Kokrajhar India

ISBN: (纸本)9798350337785

Hate speech or hate content detection in a text is one of the emerging research in Natural Language Processing. Over several years, the popularity of social media has sky-rocketed, where anyone can share their feelings, desire, anger, etc. Sometimes, these posts include offensive information that hurts others, intentionally or unconsciously. Depending on the forum's visibility, such posts instantly spread over millions of people, which may lead to violence. In these circumstances, it is an essential task to identify whether the comment is hateful. In the Indian language context, this task presents greater complexity due to its multilingual nature and limited availability of resources. This situation motivated us to analyze hate speech in the Assamese language. The paper's contribution is in two aspects: firstly, it involves the development of a tagged dataset in Assamese comprising 4,000 sentences;secondly, by fine-tuning the mBERT-cased (bert-base-multilingual-cased) and the Bangla-BERT (sagorsarker/bangla-bert-base) model using the Assamese data to detect instances of hate speech effectively. Based on what we know, it is one of the pioneering attempts at detecting hate speech in the Assamese language. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Genetic-Chicken Swarm Algorithm for Minimizing Energy in Wireless Sensor Network

引用

computer Systems science & engineering 2023年第2期44卷 1451-1466页

作者： A.Jameer Basha S.Aswini S.Aarthini Yunyoung Nam Mohamed Abouhawwash Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032India Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of ComputationalMathematics Science and Engineering(CMSE) Michigan State University East LansingMI48824USA.

Wireless Sensor Network(WSN)technology is the real-time applica-tion that is growing rapidly as the result of smart *** power is one of the most signiﬁcant resources in *** enhancing a power factor,the clustering techniques are *** the forward of data in WSN,more power is *** the existing system,it works with Load Balanced Cluster-ing Method(LBCM)and provides the lifespan of the network with scalability and *** the existing system,it does not deal with end-to-end delay and deliv-ery of *** overcoming these issues in WSN,the proposed Genetic Algo-rithm based on Chicken Swarm Optimization(GA-CSO)with Load Balanced Clustering Method(LBCM)is *** Algorithm generates chromosomes in an arbitrary method then the chromosomes values are calculated using Fitness *** Swarm Optimization(CSO)helps to solve the complex opti-mization ***,it consists of chickens,hens,and *** divides the chicken into *** Balanced Clustering Method(LBCM)maintains the energy during communication among the sensor nodes and also it balances the load in the *** proposed GA-CSO with LBCM improves the life-span of the ***,it minimizes the energy consumption and also bal-ances the load over the *** proposed method outperforms by using the following metrics such as energy efﬁciency,ratio of packet delivery,throughput of the network,lifetime of the sensor ***,the evaluation result shows the energy efﬁciency that has achieved 83.56%and the delivery ratio of the packet has reached 99.12%.Also,it has attained linear standard deviation and reduced the end-to-end delay as 97.32 ms.

关键词： Energy efﬁciency sensor nodes chicken swarm optimization load balanced clustering method wireless sensor network cluster heads load-balancing ﬁtness function

来源：评论

学校读者我要写书评

暂无评论

Gene Selection Using Multi-Objective Optimization for Disease Classification 5

Gene Selection Using Multi-Objective Optimization for Diseas...

引用

5th IEEE PhD Colloquium on Emerging Domain Innovation and technology for Society, PhD EDITS 2023

作者： Mishra, Debasmita Sinha, Nidhi Cmr Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350316278

The expression levels of thousands of genes in two sample cells are compared using micro array technology. It is possible to make key medical diagnoses, treat a specific disease, track the progression of the disease, and predict how the disease will respond to therapy using those sample cells, depending on their diverse sources. We must choose the most valuable genes from among the thousands of genes present in the microarray because not all of them are helpful in categorizing a particular condition. Our method of gene selection involves two stages. Thousands of genes are reduced to a few hundred (N=100) by utilizing a parametric technique in stage 1, and in stage 2, the collected genes chosen in stage 1 are going through a process of multi-objective genetic algorithm (MOGA), employing Pareto GA (Genetic Algorithm). A smaller fraction of the top-ranked genes chosen in stage 2 is taken into consideration classifying the disease to find with the highest accuracy. © 2023 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Dependency analysis of various factors and ML models related to Fertilizer Recommendation 3

Dependency analysis of various factors and ML models related...

引用

3rd International Conference on Secure Cyber Computing and Communications, ICSCCC 2023

作者： Vaishnavi, S. Shanmugam, Nandikaa Kiran, Galla Priyadharshini, A.Saraswathi School of Computer Science and Engineering Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350300710

Adopting the same fertilizer gives minimum yield to the farmers as soil properties have changed drastically due to the change in environmental condition. In literature, different algorithmic analysis has been carried out to predict the fertilizer considering various factors, however, there is a gap in identifying every possible factor relevant to fertilizer recommendation. Hence, in our proposed work, we have utilized various soil and environmental factors like Nitrogen, Phosphorus and Potassium values, humidity, rainfall, weather condition and performed a dependency analysis of these factors to give a more accurate fertilizer prediction so as to enhance the crop yield. Algorithms such as Random Forest, Decision Tree, Support Vector Machine (SVM), Naïve Bayes (NB) and Logistic Regression (LR) have been explored to study the suitability of these algorithms in fertilizer prediction. The presented algorithms are compared based on the performance metrics such as accuracy, F1 score, Recall and precision. It is found that, among other algorithms, SVM performed better with maximum accuracy of 97% when all the factors are taken into account. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Approaches towards Fake News Detection using Machine Learning and Deep Learning 10

Approaches towards Fake News Detection using Machine Learnin...

引用

10th International Conference on Signal Processing and Integrated Networks, SPIN 2023

作者： Kumar, Nitish Kar, Nirmalya National Institute of Technology Agartala Department of Computer Science and Engineering India

ISBN: (纸本)9781665490993

Fake news evolving around us for a very long time. The gradual growth of social media platforms has provided us with an easily accessible and publishable news platform in front of the audience that news may be true or False. The spreading of fake news increased as compared to ancient times. Nowadays Fake news detection become a tough challenge for Both Natural language processing(NLP) and Machine Learning (ML) experts. For detecting fake news fact-checking is also very important. In this paper, we focus on the analysis of recently published papers in this domain and the analysis of different techniques for detecting fake news. Through this survey, we will get inside knowledge of the detection process of fake news using different natural language processing, machine learning, and Deep Learning Techniques. © 2023 IEEE.

关键词： Support vector machines

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：