检索结果-内蒙古大学图书馆

International Conference on Computing and networking Technology (ICCNT)

作者： Rahul Ravikumar M V Sujith Kumaar Shirish Krishna M Jayasurkanth Vr Yasshwanth Sanjay Kishore Saravanan Senthil Kumar Thangavel S Thangeswari K Somasundaram Selvanayaki Kolandapalayam Shanmugam Center for Computational Engineering &Networking Amrita Vishwa Vidyapeetham Amrita School of Artificial Intelligence Coimbatore India Department of Aerospace Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Department of Plant Pathology Tamilnadu Agricultural University Coimbatore India Department of Mathematics Amrita School of Physical Sciences Coimbatore India Department of Mathematics and Computer Science Ashland University Ohio USA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Traditional systems for crop disease detection often rely on manual inspection methods, which are time-consuming, labor-intensive, and prone to human error. In this context, the necessity of using transfer learning becomes apparent as it allows for leveraging pre-existing knowledge from large datasets to improve the performance of models trained on smaller, domain-specific datasets. IoT has also played a significant role in our automation process. Transfer learning leveraging MobilenetV2 is particularly beneficial for this problem of detecting Pokkah Boeng disease in sugarcane crops, as it enables the adaptation of pretrained models, such as MobileNetV2, to accurately identify Pokkah Boeng disease even with limited set of data. LIME is employed to provide transparent explanations for the model’s predictions, enhancing its interpretability and facilitating informed decision-making in agricultural management. By combining transfer learning with xAI and aerial drone technology, having add-ons of IoT and facilitating a comprehensive comparative study, PokkahScan offers a comprehensive solution for timely disease detection and crop management in sugarcane farming.

关键词： Adaptation models Explainable AI Transfer learning Crops Manuals Predictive models Inspection Diseases Drones Farming

来源：评论

学校读者我要写书评

暂无评论

Detection of Hate Speech Text in Hindi-English Code-mixed Data

引用

Procedia Computer Science 2020年 171卷 737-744页

作者： K Sreelakshmi B Premjith K.P. Soman Center for Computational Engineering & Networking (CEN) Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India

Social media sites like Twitter, Facebook, being user-friendly and a free source, provide opportunities to people to air their voice. People, irrespective of the age group, use these sites to share every moment of their life making these sites flooded with data. Apart from these commendable features, these sites have down side as well. Due to lack of restrictions set by these sites for its users to express their views as they like, anybody can make adverse and unrealistic comments in abusive language against anybody with an ulterior motive to tarnish one’s image and status in the society. So it became a huge responsibility for the Government and these sites to identify this hate content before it disseminates to mass. Automatic hate speech detection faces quite a lot of challenges due to the non-standard variations in spelling and grammar. Especially for a country like India with huge multilingual and bilingual population, this hate content would be in code-mixed form which makes the task demanding. So our paper projects a machine learning model to detect hate speech in Hindi-English code-mixed social media text. The methodology makes use of Facebook’s pre-trained word embedding library, fastText to represent 10000 data samples collected from different sources as hate and non-hate. The performance of the proposed methodology is compared with word2vec and doc2vec features and it is observed that fastText features gave better feature representation with Support Vector Machine (SVM)-Radial Basis Funcrion (RBF) classifier. The paper also provides an insight to the researchers working in the field of code-mixed data that character level features provide best result for code-mixed data.

关键词： Code-mixed Support Vector Machine fastText Hate speech Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

Emotion Detection in Hinglish(Hindi+English) Code-Mixed Social Media Text

引用

Procedia Computer Science 2020年 171卷 1346-1352页

作者： T Tulasi Sasidhar Premjith B Soman K P Center for Computational Engineering and Networking (CEN) Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India

Human communication is often embedded with emotion and it can be expressed via different mediums like vocal interaction, texts, non-verbal communication like facial expressions and gestures. Even though textual communication is a more common way of interaction the rapid utilization of social media has taken it to another level. Social media open an easy way for people to express their emotions. So people around the world utilize this opportunity and express themselves in social media platforms through texts over various subjects. People make use of these platforms to exhibit their like or dislike towards something, how they felt about a situation, their reaction to a government decision and so on. Hence, understanding the emotion expressed in such social media texts has a significant number of applications emphasizing the need to detect it. The human brain is quite intelligent to sense such kind of emotion associated with a text but for a machine to gain such perception is quite difficult. In Natural Language Processing, emotion recognition and classification is a commonly researched task where a model can detect these type of emotions. It is quite challenging when it comes to Indian Languages due to the lack of data, as well as being a multilingual society people tend to use code-mixed pattern in social media. The lack of annotated corpus in the Hindi-English code-mixed domain and unavailability of the standard model to classify, left this area of research still an exploring region. In this paper, to analyze such data, we created a dataset of 12000 Hindi-English code-mixed texts collected from various sources and annotated them with emotions Happy, Sad and Anger. In our work, a pretrained bilingual model is used to generate feature vectors and deep neural networks are employed as classification models. It is observed that with the selected features, CNN-BiLSTM gave better performance compared to other experimented models with 83.21% classification accuracy.

关键词： Code-Mixed Text Emotion Detection ID-Convolution Neural Network Word2Vec Long Short-Term Memory

来源：评论

学校读者我要写书评

暂无评论

Towards identifying most important leads for ECG classification. A Data driven approach employing Deep Learning

引用

Procedia Computer Science 2020年 171卷 602-608页

作者： Sujadevi VG Soman K.P. Center for Computational Engineering & Networking (CEN) Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India

Electrocardiogram (ECG) is a vital tool to determine the structure and function of the heart. Automated classification of the ECG data helps in earlier diagnosis before the doctor could personally investigate. Most of the cardiac diseases are life threatening universally. In an effort towards accurate detection of cardiac disease by automated identification, several dataset has been released [Physionet]. Deep learning requires massive amount of dataset to be able to provide best results, hence we chose to use the dataset from The China Physiological Signal Challenge 2018, that contains 12 lead ECG recordings from 6877 subjects with eight major cardiac anomalies. To improve the detection / prediction of the Electrophysiology anomalies, a data driven approach was employed. computational Experiment was performed with novel architecture and approach using Deep Neural Network (DNN) that has resulted in relatively very high accuracy of 99.01%. A minimal set of ECG leads to get maximum accuracy was identified.

关键词： Electrocardiogram Electrophysiology Convolutional Neural Network Bidirectional Long Short-Term Memory Networks Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Assessment of watershed areas of western and eastern ghats using geospatial techniques 8

Assessment of watershed areas of western and eastern ghats u...

引用

8th IEEE International Conference on Communication and Signal Processing, ICCSP 2019

作者： Sathish Kumar, B. Geetha, P. Soman, K.P. Center for Computational Engineering and Networking Amrita School of Engineering Coimbatore India

ISBN: (纸本)9781538675953

Water is more essential for all living organisms in this world. The amount of rainfall in the forest is reducing rapidly while the need has increased. During summer the water shortage rises acutely in the forest areas. The dried up water bodies in and around the forest region drive the animals into the human habituated areas in search of water. The physical layout of the area upstream from a specified outlet point is called as watershed or basin. If management of watershed is not done properly then there will be depletion of other natural resources based on this watershed. In this case GIS can be used to analyze the watersheds around the forest and to check the availability of water inside the forest. The result of the analysis of this collected forest areas will be useful to find areas where the water is available in forest. Thus the main objective is to locate artificial ponds in forests. © 2019 IEEE.

关键词： Watersheds

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Intelligent Named Entity Recognition of Cyber Security 5th

Deep Learning Approach for Intelligent Named Entity Recognit...

引用

5th International Symposium on Signal Processing and Intelligent Recognition Systems, SIRS 2019

作者： Simran, K. Sriram, S. Vinayakumar, R. Soman, K.P. Center for Computational Engineering and Networking Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India Division of Biomedical Informatics Cincinnati Children’s Hospital Medical Centre CincinnatiOH United States

ISBN: (纸本)9789811548277

In recent years, the amount of Cyber Security data generated in the form of unstructured texts, for example, social media resources, blogs, articles, and so on has exceptionally increased. Named Entity Recognition (NER) is an initial step towards converting this unstructured data into structured data which can be used by a lot of applications. The existing methods on NER for Cyber Security data are based on rules and linguistic characteristics. A Deep Learning (DL) based approach embedded with Conditional Random Fields (CRFs) is proposed in this paper. Several DL architectures are evaluated to find the most optimal architecture. The combination of Bidirectional Gated Recurrent Unit (Bi-GRU), Convolutional Neural Network (CNN), and CRF performed better compared to various other DL frameworks on a publicly available benchmark dataset. This may be due to the reason that the bidirectional structures preserve the features related to the future and previous words in a sequence. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Effect of Annotation and Loss Function on Epiphyte Identification using Conditional Generative Adversarial Network

Effect of Annotation and Loss Function on Epiphyte Identific...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： S. Aswin V.V. Sajithvariyar Ramesh Sivanpillai V. Sowmya Gregory K Brown A. Shashank K. P. Soman Center for Computational Engineering and Networking Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India Wyoming GIS Center University of Wyoming Laramie WY USA University of Wyoming Laramie WY USA

ISBN: (数字)9781728157917

ISBN: (纸本)9781728157924

The deep neural networks are capable of processing large amounts of data for image processing applications like classification, segmentation and identification etc. Conditional- Generative Adversarial Network (C-GAN) is an example of Deep Learning (DL)-based image processing algorithm that is used widely for identifying targets in images. In a Deep Learning based image processing application the quality of the input image plays an important role. The quality and variations within the dataset helps the neural network filters to derive the best features for the classification and identification of the target in the image. Many deep learning approaches will have a preprocessing pipeline which improves the quality of the input training data. The objective of this study was to evaluate the effect of preprocessing methods to improve C-GAN's ability to detect epiphytes in images acquired by Unmanned Aerial Vehicles (UAVs). These methods include 1) trimming the training images to include mostly the target plant, 2) generating annotation images with a thresholding technique, and 3) incorporating binary cross entropy loss function. Results obtained from this study shows that the percent occupancy of input images and annotation method plays an important role in identifying the target plant.

关键词： Deep learning Annotations Pipelines Neural networks Training data Generative adversarial networks Unmanned aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

DCNN-IDS: Deep Convolutional Neural Network Based Intrusion Detection System 4th

DCNN-IDS: Deep Convolutional Neural Network Based Intrusion ...

引用

4th International Conference on computational Intelligence, Cyber Security, and computational Models, ICC3 2019

作者： Sriram, S. Shashank, A. Vinayakumar, R. Soman, K.P. Center for Computational Engineering and Networking Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India Division of Biomedical Informatics Cincinnati Children’s Hospital Medical Centre CincinnatiOH United States

ISBN: (纸本)9789811596995

In the present era, cyberspace is growing tremendously and the intrusion detection system (IDS) plays a key role in it to ensure information security. The IDS, which works in network and host level, should be capable of identifying various malicious attacks. The job of network-based IDS is to differentiate between normal and malicious traffic data and raise an alert in case of an attack. Apart from the traditional signature and anomaly-based approaches, many researchers have employed various deep learning (DL) techniques for detecting intrusion as DL models are capable of extracting salient features automatically from the input data. The application of deep convolutional neural network (DCNN), which is utilized quite often for solving research problems in image processing and vision fields, is not explored much for IDS. In this paper, a DCNN architecture for IDS which is trained on KDDCUP 99 data set is proposed. This work also shows that the DCNN-IDS model performs superior when compared with other existing works. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Towards Evaluating the Robustness of Deep Intrusion Detection Models in Adversarial Environment 1

引用

7th International Symposium on Security in Computing and Communications, SSCC 2019

作者： Sriram, S. Simran, K. Vinayakumar, R. Akarsh, S. Soman, K.P. Center for Computational Engineering and Networking Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India Division of Biomedical Informatics Cincinnati Children’s Hospital Medical Centre CincinnatiOH United States

ISBN: (数字)9789811548253

ISBN: (纸本)9789811548246

Network Intrusion Detection System (NIDS) is a method that is utilized to categorize network traffic as malicious or normal. Anomaly-based method and signature-based method are the traditional approaches used for network intrusion detection. The signature-based approach can only detect familiar attacks whereas the anomaly-based approach shows promising results in detecting new unknown attacks. Machine Learning (ML) based approaches have been studied in the past for anomaly-based NIDS. In recent years, the Deep Learning (DL) algorithms have been widely utilized for intrusion detection due to its capability to obtain optimal feature representation automatically. Even though DL based approaches improves the accuracy of the detection tremendously, they are prone to adversarial attacks. The attackers can trick the model to wrongly classify the adversarial samples into a particular target class. In this paper, the performance analysis of several ML and DL models are carried out for intrusion detection in both adversarial and non-adversarial environment. The models are trained on the NSLKDD dataset which contains a total of 148,517 data points. The robustness of several models against adversarial samples is studied. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Addressing Sanitation and Health challenges in rural India through socio-technological interventions: A Case Study in Odisha 9

Addressing Sanitation and Health challenges in rural India t...

引用

9th Edition of IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2021

作者： Rengaraj, Vineeth Simmon, Ajay Vikash, S. Zel, Rosy Adhikari, Hemantha Sherpa, Pemba Geetha, P. Cornet, Souresh Amrita Vishwa Vidyapeetham Department of Civil Engineering Coimbatore India Amrita Vishwa Vidyapeetham Department of Mechanical Engineering Coimbatore India Amrita Vishwa Vidyapeetham Department of Electronics and Communications Engineering Coimbatore India University At Buffalo Community For Global Health Equity BuffaloNY United States Center For Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India Amrita School For Sustainable Development Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9781665432405

The Government of India's Swachh Bharat Mission has augmented access to sanitation in rural India. Despite notable progress, many communities still practice Open Defecation (OD). This paper reports on a 2-year study of a tribal village, in the state of Odisha, India, where the challenge of open defecation (OD) was supervened from a socio-technical aspect. It aimed at understanding the reasons for the prevalence of OD in rural India. It focused on how this challenge could be solved using appropriate technology. The methodology adopted Human centered Design and Co-Design to directly engage with the local population and gain a first-hand familiarity of their living experience. This project determined that longer commitment using a bottom-up participatory and user-centered approach was key in bringing about a higher social impact. In-depth interaction with the community made it possible to understand that the problem actually was the lack of water in the community, that led to sanitation related challenges. In collaboration with the community, a water filtration and distribution system was designed to finally address both the water and sanitation challenges of the community. © 2021 IEEE.

关键词： Rural areas

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：