检索结果-内蒙古大学图书馆

3rd International Conference on Innovative Practices in technology and Management, ICIPTM 2023

作者： Jayaram, B. Suguna, T. Fairooz, Shaik Arul Selvam, P. Vimal, S. Rmk Engineering College Department of Computer Science and Business Systems Tamil Nadu Kavaraipettai India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Malla Reddy Engineering College Department of Cse -AIML Telangana Secunderabad India Hindusthan College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350336238

Malicious hackers may compromise hundreds or millions of machines with little effort, allowing them to shut down networks, steal sensitive data, and compromise critical infrastructure. Data is stolen and used for malicious purposes by hackers who exploit security flaws in the network. And the sophisticated technology they use, like the bucks they do, are continually feeding them the information they needed, not just once. Moreover, even if Internet firewalls have improved, cybercrime has been on the rise. Then, we have a long way to go before we approach the limit, what with all the different kinds of cloud server devices that can connect to the internet nowadays. It's certain that in the future, little devices, no matter how helpful they are really in our everyday lives, will become the preferred tool of villains. In this research, we offer a novel security technique for protecting sensitive data on cloud servers. This intelligent cloud server was protected from any hacking with the aid of this algorithm. The system's output was measured against those of pre-existing algorithms. More than 96% of inputs are authenticated by the proposed technique, while password cracking operations are reduced by about 3%. The source code security management is improved to 99% and the updating issues for various devices entries is reduced 0.02%, and further the privacy breach is reduced up to 0.32%. Hence the proposed method was more secured from cyber security issues. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Mathematical Model for Cyber-Physical Systems: A Model for Industrial Internet of Things

引用

SN Computer science 2023年第5期4卷 1-7页

作者： Veerachamy, Ramachandran Rao, Ganga Rama Koteswara Arivanantham, Vishnu Priya Kuppusamy, Sangeetha Velayutham, Priya Govindaraj, Rajeshkumar Department of Computer Science and Engineering GITAM School of Computing GITAM Deemed to be University Bengaluru 561203 India Department of Computer Science and Information Technology Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram 520002 India Department of Computational Intelligence School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu Perundurai 638060 India Department of Computer Science and Engineering Paavai Engineering College Tamil Nadu Namakkal 637018 India Department of Information Science and Engineering Bannari Amman Institute of Technology Tamil Nadu Sathyamagalam 638401 India

Proliferated usage of computer devices, smart objects, and electronics significantly impacts the atmosphere, which is inevitable. The existing context has engineered schemes, or Cyber-Physical Systems (CPS), that integrate physical and computation components. The extensive usage of devices has utilized more energy, creating complexity in environmental handling. The problem is improving an automotive function’s reliability, application, or functionality with time and energy constraints. By applying smart technologies, namely Deep Learning (DL) and Machine Learning (ML) in CPS and the Internet of Things (IoT), enduring the utilization of these intensive DL-based approaches has a negative effect on resource utilization. The proposed Energy Efficient Mathematical Model (EEMM) is designed with a mathematical model for IIoT, which guides in solving the drawback of the existing system. The mathematical model integrated CPS-based proposed EEMM has outperformed the existing state-of-art technique. The proposed EEMM attains minimal Energy Consumption (EC) of 521 Jules and the highest reliability rate of 0.987. The proposed EEMM in this research has attained minimal energy usage of 0.987 i for 100 tasks, which is minimal than other existing techniques. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cyber-attacks Energy IIoT IoT Mathematical model Network Smart objects

来源：评论

学校读者我要写书评

暂无评论

A Classification of Face Recognition System Using Faster Region-Based Convolutional Neural Network 2

A Classification of Face Recognition System Using Faster Reg...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Maheswari, M. Alabdeli, Haider Aruna, T.M. Reddy, R. Archana Revathi, R. School of Computing Srm Institue of Science and Technology Department of Computational Intelligence Kattankulathur India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Artificial Intelligence and Machine Learning Bengaluru India School of Computer Science and Engineering Sr University Warangal India Karpagam Academy of Higher Education Department of Computer Science Echanari Coimbatore India

ISBN: (纸本)9798350373110

In recent times, face recognition is a kind of biometric authentication which is widely used for security purpose in many areas like image processing, pattern recognition. However, recognizing the human face was very difficult as the poses in the input images vary, various conditions of light, brightness, expressions, ages. To overcome from it, a proposed method was introduced in this paper known as Faster Region-based Convolutional Neural Network (RCNN). The main advantage of using the proposed method is it will minimize the training process time as it consisting of two fully connected layers namely classifier and regression layer. Initially, the proposed method was implemented on ORL database consisting of 40 classes, then the images in the database undergoes image resizing and enhancing in the preprocessing stage. Where, Image resizing id done to reduce images size so that every image is same in size that will minimize the processing time and image enhancing was done to adjust the brightness of the image. In further, for extracting the features from preprocessed images, CNN is used, so that extracted features are given to the classification stage to detect the face of human or not. In detecting the faces, proposed Faster RCNN achieved high accuracy of 98.64% when compared with other existing methods like IFC, EFRA and VGG16. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-Platform Multimodal Frogeye Leaf Spot Recognition and Classification: Advancing with Cutting-Edge CNN Technologies and Transfer Learning in Diverse Plant Species 7

Cross-Platform Multimodal Frogeye Leaf Spot Recognition and ...

引用

7th International Conference on Circuit Power and computing Technologies, ICCPCT 2024

作者： Mohan, G. Usharani, R. Tomar, Vatsala Arthi, A. Kuriyal, Suniti Kumar Yuvaraj, K.P. K.S.Rangasamy College of Technology Department of Mathematics Tamil Nadu India SRM Institute of Science and Technology School of Computing Department of Computational Intelligence Faculty of Engineering and Technology Chennai India IIMT University School of Life Science & Technology Department of Botany UP Meerut India Karpagam College of Engineering Department of Information Technology Coimbatore India Pt.L.M.S.Sridev Suman Uttarakhand University Campus Department of Botany Rishikesh India Sri Krishna College of Engineering and Technology Department of Mechanical Engineering Coimbatore India

ISBN: (纸本)9798350372816

Frogeye Leaf Spot, a common agricultural disease, poses a significant threat to crop yields. Using multimodal data from different platforms successfully has been a hurdle for existing research in leaf spot detection. Using cutting-edge convolutional neural network (CNN) and transfer learning techniques, this research presents a Cross-Platform Multimodal Recognition system to solve this issue. With a recall of 0.88, F1-score of 0.90, accuracy of 0.91, and precision of 0.92, the suggested method demonstrates exceptional performance. Our accuracy is 6% higher, F1-score is 8% higher, and recall is 9% higher than the preceding state-of-the-art, according to comparisons with previous studies. Improved Frogeye Leaf Spot detection on many platforms is a direct result of our method's success in combining picture and sensor data. This study improves farmers' ability to identify diseases and provides a solid answer for precision agriculture. Our Cross-Platform Multimodal Recognition system has shown to be effective in enhancing agricultural disease recognition, and the shown advances highlight its potential influence on crop management tactics. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Projective Exploration on Individual Stress Levels using Machine Learning 2

Projective Exploration on Individual Stress Levels using Mac...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Nagendra Prabhu, S. Singh, Amarjeet Bhavya, B. Sreeja, K. Bhargavi, P. Srm Institute of Science Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai603203 India New Horizon College of Engineering Department of Computer Science and Engineering Department Bangalore India

ISBN: (纸本)9781665400527

Recently, Stress Prediction in every individual based on their profile and behaviour is a challenging task in the current sector. Current system is a manual process where it is difficult to identify the stress in the college students or employees. There is no automation for any stress prediction. System uses machine learning algorithms or AI algorithms to find out the stress levels, these technologies are used for application development. The purpose of this project is to reduce stress in students and employees. Computer science has come a long way in the last few years. It is massive and multifaceted. It has been used in a variety of applications to meet the basic needs of human society. In the field of healthcare, machine learning has made significant progress. Stress is a deadly disease that kills a large number of people worldwide. How machine learning techniques can assist in reducing the risk of stress prediction, is examined in this study. © 2022 IEEE.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

Is it Nemo or Dory? Fast and accurate object detection for IoT and edge devices 21

Is it Nemo or Dory? Fast and accurate object detection for I...

引用

Proceedings of the 11th International Conference on the Internet of Things

作者： Sudhanshu Agarwal Richard Vuduc College of Computing Georgia Institute of Technology United States School of Computational Science and Engineering Georgia Institute of Technology United States

ISBN: (纸本)9781450385664

Current state-of-the-art object detection neural networks, such as YOLO and SSD, are trained and developed on server-class GPUs. These neural networks do not scale down well to resource-constrained devices, with both accuracy and precision taking a significant hit at the expense of speed. This is particularly concerning as object detection algorithms are often used for low-powered devices, such as surveillance and smart-home cameras, where accuracy is critical. Therefore, these devices generally tend to forward data to servers for processing, which adds network latency. In other cases, algorithms developed for these devices shrink neural networks to reduce computation at the expense of accuracy, which is often not acceptable. We create an alternative object detection scheme for static-camera systems such as those used in surveillance and smart-home settings. Our model does not require positions of objects in training data, enabling us to retain only the relevant parts of a video frame for training data and reduce data storage cost while preserving privacy of other subjects in the video. When evaluated on static-camera video feeds using an NVIDIA Jetson Nano (a hybrid Arm and GPU IoT embedded device platform), our method increases throughput compared to Tiny YOLOv3. Further, it takes half of the time that Tiny YOLOv3 takes when run on OpenCV’s CUDA-optimized DNN framework per frame while having high accuracy of bounding box prediction and classification. The lessons learned from this work also suggest other strategies for tailoring the deployment of deep learning algorithms at the edge.

关键词： Background Modeling Object Detection Edge computing Parallel computing

来源：评论

学校读者我要写书评

暂无评论

Improving Time-Series Classification Accuracy Based on Temporal Feature Representation Learning Using CRU-LSTM Autoencoder 5

Improving Time-Series Classification Accuracy Based on Tempo...

引用

5th IEEE International Conference on Cognitive Machine Intelligence, CogMI 2023

作者： Kim, Dohee Sim, Sunghyun Yoon, Bori Liu, Ling Bae, Hyerim Pusan National University Major in Industrial Data Science & Engineering Dept. Industrial Engineering Busan Korea Republic of Dong-Eui University Dept. Industrial Management & Big Data Engineering Busan Korea Republic of College of Computing Georgia Institute of Technology Georgia United States

ISBN: (纸本)9798350323832

Time-series data consists of a sequence of observations recorded in chronological order, where the data changes over time. This type of data exhibits various characteristics, such as temporal volatility, trends, and seasonality. Recently, a new layer structure called Correlation Recurrent Units (CRU) has been proposed to capture not only temporal variability but also trends and seasonality in time-series data. In this study, we propose an end-to-end model that utilizes a CRU autoencoder to learn temporal feature representations and address time-series classification problems simultaneously. To validate the performance of our proposed model, we conducted comparative experiments using 30 time-series classification datasets from six different types. The experimental results showed that the proposed model outperformed the baseline models in 20 out of the 30 time-series datasets. This indicates that the proposed approach effectively captures various temporal features in time-series data and improves the performance of time-series classification tasks. © 2023 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Routing in Underwater Wireless Sensor Networks Through Cluster-Dragonfly Optimization 3

Energy-Efficient Routing in Underwater Wireless Sensor Netwo...

引用

3rd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Anitha, D. Husain, Saif O. Velpula, Srikanth Rajani, N. Dineshkumar, R. School Of Computing Srm Institute Of Science And Technology Department Of Computational Intelligence Tamilnadu Kattankulathur India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Sr University Department Of Electrical And Electronics Engineering Warangal India Nitte Meenakshi Institute Of Technology Dept.of Ece Bengaluru India Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Saveetha University Department Of Electronics And Communication Engineering Chennai India

ISBN: (纸本)9798350318609

In this paper, develop a power control scheme for underwater wireless sensor networks that takes into account the impact of communication ranges on network performance, including energy utilization and delay overhead. The primary objective of our scheme is to assign a differentiated optimal communication radius for each sensor node, enhancing overall network efficiency. The proposed method utilizes energy-aware Cluster-Dragonfly Optimization (CDFO), but it might face challenges in handling large-scale optimization, and the scalability of the algorithm may be limited when dealing with high-dimensional or complex optimization. Although the proposed CDFO method exhibits high performance compared to existing methods, such as Self-Adaptive Glow Worm Swarm Optimization (SA-GWO), Improved Coyote Optimization Algorithm (ICOA), Hybrid Cat Cheetah Optimization algorithm (HCCOA), and Chaotic Search-and-Rescue Optimization (CSRO), it may still face challenges in terms of handling large-scale optimization. Nevertheless, the proposed CDFO yields impressive results, achieving a Packet Delivery Ratio (PDR) of 99%, Packet Loss Ratio (PLR) of 4%, Energy Consumption of 9%, and Alive Node count of 330. These outcomes outperform existing methods in the context of Underwater WSN. © 2024 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

AI based Chatbots using Deep Neural Networks in Education 2

AI based Chatbots using Deep Neural Networks in Education

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Chempavathy., B. Prabhu, S. Nagendra Varshitha, D.R. Vinita Lokeswari, Yaratapalli New Horizon College of Engineering Department of Cse Bengaluru India Srm Institute of Science Technology Kattankulathur School of Computing Department of Computational Intelligence Chennai603203 India

ISBN: (纸本)9781665400527

The present era of technology had a tremendous influence on society. With the advancements in the artificial intelligence and machine learning domains, machines are trying to impersonate humans. Chabot's are gaining popularity in this aspect and have changed the patterns of conversations between humans and computers. With the creation of these virtual assistants, the conversational services have been improvised. Basically, a Chabot is a software program programmed to interact with humans using artificial intelligence in messaging platforms. Nowadays, Chabot's are not just restricted to one field, they can be used in numerous fields in different forms. The Chabot introduced in this paper mainly concerns itself with college activities. college campuses are vast in the area. If a particular person has a query about which he wants to inquire, the individual would have to shuttle from here and there in order to gather the information for the query. So, the main intention of this research is to develop a college friendly chatterbot sooner or later, servicing the scholars. The tools used are artificial intelligence, such as natural language input and deep learning methods like deep neural networks. This uses LSTM, an extension of RNN, in order to process the user input. It trains the Chabot using these techniques and gives a response. All the data of the Chabot, which is the input given by the human, will be stored in a database and the data will be saved every time a query is asked for future use. © 2022 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

Quantum Teleportation and EntanglementBased Quantum Blind Signature Protocol for Quantum Secure Communication in Security Service Bases 23

Quantum Teleportation and EntanglementBased Quantum Blind Si...

引用

Proceedings of the 5th International Conference on Information Management & Machine Intelligence

作者： Sumathy G Suresh A Udendhran R Maheshwari A Arun Prasath Selvaraj Department of Computational Intelligence SRM Institute of Science and Technology India Networking and Communications SRM Institute of Science and Technology India Department of Computational Intelligence SRM IST India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology India

ISBN: (纸本)9798400709418

Quantum teleportation and entanglement-based quantum blind signature protocol were promising new technologies for secure communication between security service bases. They were secure against a variety of attacks, including eavesdropping, signatory disavowal, verifier denial, and forgery. The protocol worked by using quantum entanglement to create a shared secret state between the security service bases. This shared secret state was then used to generate a quantum signature for each message sent between the bases. The signature was then verified by the receiving base using the shared secret state. Compared to classical blind signature schemes, the main advantages of the quantum entanglement-based quantum blind signature protocol were its information-theoretic security and reduced complexity and noise. However, this protocol also faced some challenges, such as preparing and storing entangled states, performing quantum operations and measurements, and ensuring the trustworthiness of the third party. Despite these challenges, the quantum entanglement-based quantum blind signature protocol was a promising new technology for secure communication between security service like military bases. It had the potential to revolutionize the way that military bases communicated with each other, making it possible to send secure messages without revealing the content or identity of the messages.

关键词：

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：