检索结果-内蒙古大学图书馆

1st International Conference on Emerging Technologies for Dependable Internet of Things, ICETI 2024

作者： Al-Fuhaidi, Belal Farae, Zainab Al-Sorori, Wedad Maqtary, Naseebah Al-Ashmoery, Yahya Al-Fuhaidy, Farouk Al-Taweel, Sadik Faculty of Computing and IT University of Science and Technology Sana’a Yemen Department of IT Al-Razi University Sana’a Yemen Dept. Mathematics & Computer Faculty of Science Sana’a University Sana’a Yemen Department of Electrical Engineering Faculty of Engineering Ibb University Ibb Yemen

ISBN: (纸本)9798331533557

Intrusion detection systems (IDSs) are a necessary principle in WSN security, which can successfully prevent various hackers' and intruders' attempts to hack the network. In this research, we address the problem of achieving high accuracy in detecting intrusions in WSNs due to specific characteristics of WSN data, including the appropriate dataset, the drawbacks of feature selection, and choosing the proper algorithms for the classification process. In this paper, we proposed the anomaly-based IDS model using the DNN algorithm and mutual information (MI) technology to select features. The proposed model has been implemented using the Python language used in the Anaconda platform and relying on the standard NSL-KDD dataset. The experimental results showed the capability of the proposed model to achieve high-performance accuracy in intrusion detection using the DNN algorithm compared to the state-of-the-art. The proposed model outperforms other previous relevant works by 3.65% enhancement in terms of accuracy. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Real Time Intravenous Monitoring and Alert System for Healthcare Management

IoT-Enabled Real Time Intravenous Monitoring and Alert Syste...

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： P Pabitha J Selvakumar Dept. of Computer Technology Anna University MIT Campus Chennai India Dept. of Computer and Science Engineering Sri Ramakrishna Engineering College Coimbatore India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

This paper presents the design and implementation of a Smart-drip Infusion Monitoring System incorporating various sensors and IoT technologies. The system aims to enhance intravenous infusion monitoring by providing precise control and timely alerts during the infusion process. The load cell sensor measures fluid volume, while the air bubble detection sensor detects air bubble status in the intravenous line, ensuring accurate and safe medication delivery. The Arduino Uno coordinates sensor data acquisition, processing, and infusion control, dynamically adjusting the solenoid valve to maintain the prescribed infusion rate. Additionally, the buzzer alerts healthcare providers to critical events such as dose completion or system malfunctions. This integrated approach offers a comprehensive solution for optimizing intravenous therapy, enhancing patient safety, and improving healthcare outcomes.

关键词： Volume measurement Process control Valves Real-time systems Software Sensor systems Sensors Safety Solenoids Monitoring

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor Using CNN and CNN-SVM 3

Detection of Brain Tumor Using CNN and CNN-SVM

引用

3rd International Conference for Emerging Technology, INCET 2022

作者： Duvvuri, Kavya Kanisettypalli, Harshitha Jayan, Sarada Amrita School of Engineering Dept. of Computer Science Engineering Bengaluru India Amrita School of Engineering Dept. of Mathematics Bengaluru India

ISBN: (纸本)9781665494991

Brain tumor is a type of cancerous growth that may occur in the brain. Early diagnosis of the disease is crucial for proper treatment. Diagnosis of brain tumors is usually done using images obtained through magnetic resonance imaging (MRI). MRI images can be classified using a Convolutional Neural Network (CNN), which is a technique in deep learning. It is suitable for classifying large image datasets. Support Vector Machine (SVM) is a technique in machine learning that is predominantly used for classification and in various regression problems. In this paper, we classified brain MRI images using pre-trained models like AlexNet, VGG16, InceptionV3, and ResNet50. Finally, a CNN model and an SVM model are trained with the same dataset. Using the results thus obtained a hybrid CNN-SVM model has been built to get better accuracy and prediction results. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Registered-backoff-time (RBT) based channel access with grouping control for the trigger RAW mode of IEEE 802.11ah IoT Network

引用

computer Networks 2024年 242卷

作者： Huang, Chung-Ming Hsieh, Chia-Han Dept. of Computer Science Information Engineering National Cheng Kung University Tainan Taiwan

This work proposes the Trigger RAW -centric Registered Backoff Time (RBT) -based channel access with the Grouping Control (TRC-RBT-GC) method to tackle the load balance problem in the IEEE 802.11ah network for Internet of Things (IoTs). The main feature of the proposed method is twofold: (1) Each STA generates a RBT value registers it to AP such that AP can schedule STAs to access channel according to STAs’ RBT values. (2) Each RAW consists of a Claiming RAW a Data RAW. Those STAs that only have the uplinked data can deliver their intentions of uplinking data to AP in their respective claiming slot of the Claiming RAW. AP then schedules the STAs that have successfully delivered their intentions of uplinking data based on their RBT values in their respective data slot of the Data Raw. When a data slot of the Data RAW has some remaining time after all of the AP-scheduled STAs have finished their channel access, if there are some STAs failed delivering their intentions of uplinking data to AP, then these STAs can try to access channel in the remaining time of their respective data slot using the regular CSMA/CA scheme based on their RBT values. The simulation results show that the proposed TRC-RBT-GC method can achieve load balance among RAW's slots the system performance can be improved a lot. © 2024 Elsevier B.V.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach to Deal with Cyber Bullying using Machine Learning: A Systematic Review 2

An Efficient Approach to Deal with Cyber Bullying using Mach...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Naveen Kumar, M.R. Vishwachetan, D. Mushtaq Ahmed, D.M. Dayananda, K.J. Manasa, K.J. Nanda, K.V. Vidyavardhaka College of Engineering Information Science and Engineering Mysuru India Ramaiah Institute of Technology Information Science and Engineering Bengaluru India Gsss Ssfgc Dept. of Computer Application Mysuru India MUSoE Dept. of Aiml Manasagangothri Mysuru India Sri Siddhartha Institute of Technology Compter Application Tumkur India

ISBN: (纸本)9798350328202

The prominence of social media platforms like Facebook, WhatsApp, and Instagram have given rise to Cyber crime, notably in the form of Cyber bullying. This unique manifestation of harassment involves individuals exploiting social networks to engage in harmful behaviors such as posting toxic comments or sharing embarrassing content, often causing severe reputation damage to victims, particularly among teenagers. This Paper gives a comprehensive survey of technical approach to tackle this escalating issue, employing advanced machine learning algorithms such as Support Vector Machines (SVM), Convolution Neural Networks (CNN), and J48. The objective is to review models capable of accurately detecting Cyber bullying, thereby contributing to the creation of robust systems that promote a safer online environment, focusing on safeguarding vulnerable demographics like teenagers and also possible future direction. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Forecasting Classification Model for Traffic Analysis using Machine Learning Techniques

An Intelligent Forecasting Classification Model for Traffic ...

引用

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

作者： Bodla Kishor Rajesh Tiwari Raj Kumar Patra Latika Pinjakar Mahesh Singh Dept. of Computer Science and Engineering CMR Engineering College Hyderabad India Dept. of Computer Science and Engineering CMR Technical Campus Hyderabad India Dept. of Computer Science and Engineering Symbiosis Institute of Technology Nagpur India Dept. of EEE Shri Shankaracharya Technical Campus Bhilai Durg India

In addition to taking care of the normal citizens, Road Traffic protection is also one of the main issue for corporations governing the transportation. We use data mining techniques to get the hidden matter from the database. The applications of Data mining is there in various fields such as fraud detection, marketing and many more. Many countries were affected due to many decisions that were taken by the governments one such issue is globalization. This has brought some drastically changes in the intake level and the financial related activities and this has given a boost to transportation department. Understanding the importance of the street protection the authorities are putting effort to know the reasons behind the street accidents. The increase in the street injuries made it difficult to determine the limitations of the street injuries. This paper explains the street injuries frequency from analysing the database. This work is about 95% efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bi-LSTM-RF based Hybrid Deep Learning Approach to Identify Level of Depression from Bengali Facebook Status

Bi-LSTM-RF based Hybrid Deep Learning Approach to Identify L...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Steve Austin Shah Nawaz Haider Rajib Shil Nisrat Sharmin Lija Kazi Rifah Noor Dept. of Computer Science & Engineering University of Science and Technology Chittagong Chittagong Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Depression is a worldwide epidemic and is of special concern due to its impact on mental health and the need for comprehensive studies for better detection and treatment. As the severity of depression grows among the Bengali population, yet the identification is relatively uncommon in this wider community, it appears to be in high demand. In our research, an efficient deep hybrid learning is instituted to identify levels of depression in Bangla text. We gathered 3000 Bengali Facebook posts for our dataset labeled for three levels of depression, mild, moderate, and severe. A bidirectional Long Short-Term Memory (bi-LSTM) architecture and a Random Forest classifier have been applied. We followed some pre-processing steps for these texts, which involved cleaning, correcting mistakes, removing stop words, segmentation, and embedding the text using Word2Vec to turn the text into vectors. The bi-LSTM model performed at an accuracy of 90.5% but this was improved to 93.67% when combined with Random Forest by using Softmax generated class scores as features. The aspects of our proposed hybrid bi-LSTM-RF techniques suggest that it could be more precise and effective for depression detection in the less researched Bangla language. These results provide insight into the application of deep learning with classical classifiers for sentiment classification in the mental health field and enhancing the treatment of depression by early detection.

关键词： Deep learning Accuracy Social networking (online) Soft sensors Mental health Depression Transformers Vectors Real-time systems Random forests

来源：评论

学校读者我要写书评

暂无评论

Boosted Hybrid Privacy Preserving Data Mining (BHPPDM) Technique to Increase Privacy and Accuracy 3

Boosted Hybrid Privacy Preserving Data Mining (BHPPDM) Techn...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Prasanthi, Kundeti Naga Chandra Sekhara Rao, M.V.P. Pallapothu, Seshu Babu Lakireddy Balireddy College of Engineering Department of Computer Science and Engineering Mylavaram India Rvr and Jc College of Engineering Dept. of Cse Chowdavaram India Kakaraprthi Bhavanarayana College Dept. of Mathematics Vijayawada India

ISBN: (纸本)9781665462167

In the current scenario, large volumes of data are generated by different organizations. Data Mining (DM) applications provide suitable patterns that lead to business growth, improved health care and improved services to users etc. The Humongous data volumes may also contain some confidential information about individuals. So, this data may be exploited for identity theft, identity disclosure etc. In this situation, data mining methodologies that provide confidentiality are useful. Though Privacy-Preserving Data Mining (PPDM) methodologies like randomization, perturbation, anonymization etc., provide privacy, but when applied individually, they are ineffective. Henceforth, this article proposes a combination of these techniques called Boosted Hybrid Privacy Preserving Data Mining (BHPPDM). The proposed technique provides more privacy of data than the current methodologies whilst providing better classification accuracy as demonstrated by investigational results. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automatic Evaluation Systems for Descriptive Answers Using BERT: Addressing Context and Coherence Challenges

Enhancing Automatic Evaluation Systems for Descriptive Answe...

引用

International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES)

作者： Sagarika Dash Dhawaleswara Rao CH Rudra Kalyan Nayak M.V.B.T. Santhi Dept. of Computer Science Engineering Centurion Univrsity of Technology and Management Odisha India Dept. of Computer Science Engineering VIT Bhopal Univrsity Sehore Madhya Pradesh India Dept. of Computer Science Engineering Koneru Lakshmalah Education Foundation Vaddeswaram Andhra Pradesh India

ISBN: (数字)9798331506452

ISBN: (纸本)9798331506469

This study explores the application of advanced Natural Language Processing (NLP) techniques, specifically leveraging BERT-based models, for evaluating semantic similarity between text inputs. The methodology involves preprocessing text through tokenization, stemming, and sentence chunking, followed by the generation of sentence embeddings using the ‘bert-base-nli-mean-tokens’ model. The model, fine-tuned on Natural Language Inference (NLI) tasks, captures deep contextual relationships, enhancing the ability to compute text similarity through cosine similarity of high-dimensional embeddings. The evaluation used datasets from Semantic Textual Similarity (STS) benchmarks, combined with educational text samples. Key metrics such as Pearson correlation, Spearman correlation, and Root Mean Squared Error (RMSE) were employed to assess the model's performance in predicting similarity scores between text pairs. Results demonstrate that the model achieves a Pearson correlation of 0.53, indicating moderate agreement with human-annotated scores, while the Spearman correlation score of 0.26 highlights a weaker monotonic relationship. An RMSE of 0.12 further suggests low prediction error, supporting the model's efficacy in identifying similarities between text pairs. These findings underscore the potential of BERT-based models in applications like automated essay grading, paraphrase detection, and content-based recommendation systems, where accurate assessment of text similarity is critical

关键词： Measurement Correlation Accuracy Computational modeling Semantics Predictive models Signal processing Transformers Tokenization Context modeling

来源：评论

学校读者我要写书评

暂无评论

Beyond Copy Paste: Plagiarism Detection using Machine Learning

Beyond Copy Paste: Plagiarism Detection using Machine Learni...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Akula Vasuteja Alavalapalli Vasanth Reddy A. Pravin Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Since plagiarism is a major problem in both academic and professional settings, it is crucial to create effective plagiarism detection methods. Accuracy evaluation for classical models such as SVM, Naive Bayes, and Random Forests usually involves cross-validation, where the dataset is split into training and testing folds, and the accuracy for each fold is then computed. These techniques lack the neural network-like loss functions, but they can still be used to analyze model performance by charting accuracy against the number of folds. But in CNNs and RNNs, training entails updating a loss function over epochs through iterative optimization; for classification problems, this is usually categorical cross-entropy. The values of the loss function are monitored during training, and the convergence of the model is shown by graphing them against the number of epochs. Accuracy metrics are calculated in parallel for the training and validation stages, and the model's classification accuracy throughout successive epochs is displayed in graphs. The plagiarism detector provides users with a complete report that highlights plagiarized portions together with their original sources which results in 97.99% of accuracy in order to aid educators, researchers, and other professionals in preventing plagiarism.

关键词： Training Support vector machines Plagiarism Computational modeling Writing Reliability Organizational aspects

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：