检索结果-内蒙古大学图书馆

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Tyagi, Kajal Ahlawat, Anil Chaudhary, Himanshi Kiet Group of Institutions Department. of Computer Science and Engineering Ghaziabad Delhi-NCR India

ISBN: (纸本)9798350350357

In the modern day, Internet of Things (IoT) has become critical since it permits seamless integration of physical objects and data-driven communication. IoT improves efficiency, automated processes, and real-time decision-making across the different sectors such as smart cities, transportation, agriculture, healthcare, etc. In IoT, machine learning is essential for advancing security, flexibility, and efficiency. Its real-time anomaly detection improves security by recognizing threats quickly. In this paper, we employed an IoT dataset called NF-ToN-IoT, a NetFlow-based dataset which has nine attack categories. On this dataset, we used SMOTE-ENN, a potent machine learning balancing technique created to solve the issue of class imbalance which provides best results after implementing Machine Learning(ML) models. Preprocessing was done on the dataset to eliminate extraneous or missing values. After that we applied four ML algorithms to classify attacks in NF-ToN-IoT dataset & these are Linear Discriminant Analysis (LDA), Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbors (KNN) classifiers. These algorithms are quite good at identifying patterns and abnormalities in the dataset, which improves the efficiency of attack classification. The framework which we proposed achieved an accuracy rate of 60.6%, 98%, 98.3%, and 99% for LDA, RF, DT, and KNN respectively. Hence, we get the best results from KNN to classify those attacks present in NF-ToN-IoT dataset. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Human Bone Classification System based on Augmented Reality and Deep Learning 10

Human Bone Classification System based on Augmented Reality ...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Bhatla, Shruti Kansal, Vipashi Jain, Upma Nainwal, Ankita Sharma, Garima Graphic Era Hill University Department. of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9789380544472

Recent advancements in education field are completely astounding. In an effort to bring about an effective improvement in the learning experience, the education field has come across several technologies. One such technology is augmented reality (AR). In parallel to this deep learning has also made a number of fields more powerful. Combining these two technologies could enhance the learning experience of students. So, this paper presents a methodology in developing a framework which could classify human bones and render 3D model over the physical space. The TensorFlow model was trained using 100 epochs with 91.04% accuracy. The tflite model was imported into android application software and Unity 3D platform where the framework predicts the classes of images and superimposes it with 3D model and gives accurate results. The possibility deep learning and augmented reality presents for such framework are endless. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Behavior Using a Neutrosophic Deep Learning Model

引用

Neutrosophic Sets and Systems 2025年 76卷 288-310页

作者： Shitaya, Ahmed Mohamed Wahed, Mohamed El Syed Abd El Khalek, Saied Helemy Ismail, Amr Shams, Mahmoud Y. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Computer Science Faculty of computer and information sciences Suez Canal University Egypt Department. of Communication and Computer Engineering Air Defense University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt

We developed an information system using an object-oriented programming language and a distributed database (DDB) consisting of multiple interconnected databases across a computer network, managed by a distributed database management system (DDBMS) for easy access. An intelligent system was designed to assess the difficulty level of preliminary exams and select top-performing advanced students using a Neutrosophic Deep Learning Model. The dataset was randomly split into training (80%) and testing (20%) sets, and the model, trained with the Adam optimizer at a 0.001 learning rate over 50 epochs, incorporated early stopping based on validation loss. This system, implemented at a traditional Egyptian university, achieved a 95% accuracy in predicting student dropout. Student behavior, influenced by personal, environmental, and academic factors, is often evaluated subjectively, leading to inconsistent results. Traditional machine learning approaches struggle with the inherent uncertainty in behavioral data. To address this, we combined neutrosophic theory—a mathematical framework that accounts for truth, falsity, and indeterminacy—with deep learning, which excels at learning complex data relationships, to predict student outcomes such as dropout rates. Evaluating the model on student data, including attendance and grades, showed superior accuracy, achieving a determination coefficient of 0.95, demonstrating the approach's potential for identifying at-risk students and enabling targeted interventions. © 2025, University of New Mexico. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

MushroomDetect: An Investigation into Local Mushroom Classification in Bangladesh Using Transfer Learning 15

MushroomDetect: An Investigation into Local Mushroom Classif...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Adhikari, Bornita Hossain, Md. Mikail Akter, Sumaia Ahamed, Md. Sazzadur Daffodil International University Department. of Computer Science and Engineering Dhaka Bangladesh Bangladesh Agricultural University Department. of Agricultural Chemistry Mmensingh Bangladesh Daffodil International University Department. of software Engineering Dhaka Bangladesh

ISBN: (纸本)9798350370249

When it comes to achieving food security, one of the main obstacles is ensuring that the diet includes high-quality foods. The development of scientific technologies has made manual local identification completely impractical because it takes so long and is so imprecise. To address this problem Using a machine vision-based approach to swiftly identify the most popular and farmed mushrooms from photos raises the accuracy level to our desired level. Pictures of our chosen species were carefully clicked to compile the dataset. We carefully selected new circumstances for seven varieties of selected mushrooms, including 'Ear mushroom,' 'Golden Oyster,' 'Milky Mushroom,' 'Oyster mushroom(Po2),' 'Oyster mushroom(Po10),' 'Pink Oyster,' and 'Reishi Mushroom,' to generate a bespoke dataset. We collected the 500 basic photographs and divided them into 7 groups. To get a position where training a dataset will be simple, we sought to increase the amount of raw dataset with augmentation. InceptionV3, InceptionResNetV2, and DenseNet201 were the transfer learning models employed in the initial stage. After putting DenseNet201 into practice, we received the intended outcome. All of these models provide us with a respectable level of accuracy, but after training DenseNet201, we were able to reach an accuracy of 96.72%. Accidental mushroom identification may also be possible in this study. © 2024 IEEE.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

Securing Images: Cryptographic Approach in Big Data Scenario 15

Securing Images: Cryptographic Approach in Big Data Scenario

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Shah, Kriti Priya Sah, Subodh Narayan Kothari, Osho Vishwas, H.N. Amrita Vishwa Vidyapeetham Amrita School of Computing Department. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Digital Image as a form of data is a critical component of the digital age. Therefore, Image Encryption and Decryption is one of the important aspect for modern communication. Image security for such digital images remain one of the important questions to be answered [14][15]. Among all the advanced Encryption and Decryption algorithm, Advanced Encryption Standard (AES) and Chaotic Map Algorithm remains the prominent approaches for image security through advanced encryption and decryption approaches. This Study undertakes these two algorithm for encryption and decryption approaches for image. AES on one hand is considered for its strong security and consistent performance whereas Chaotic Map is considered for its dynamics for encryption. In a Big Data scenario, performance efficiency, scalability, and robustness of these algorithms are critical factors due to the large volumes of image data involved. Further statistical analysis including Entropy, Mean Squared Error (MSE), Correlation Coefficient, Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) are considered for both the algorithms. Additionally both the algorithms are further evaluated on the basis of encryption and decryption time and key sensitivity for the security reasons. © 2024 IEEE.

关键词： AES (Advanced Encryption Standard) Big Data Chaotic map-based encryption Image decryption Image encryption Image Security Statistical Analysis

来源：评论

学校读者我要写书评

暂无评论

Predicting BPL Match Winners: An Empirical Study Using Machine Learning Approach 14

Predicting BPL Match Winners: An Empirical Study Using Machi...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Adhikari, Bornita Ahamed, Md. Sazzadur Daffodil International University Department. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350335095

With the evolution of computer science, every company is implementing the newest technologies to survive in market with better decision-making capabilities, better communication and customer satisfaction. The only means of fulfilling all these criteria's is to perform data analysis that is more accurate and pure. In cricket, where no one can guess which team will win until the last ball of the last over, machine learning can help by predicting the results of the games. Match outcome prediction models have a lot of financial incentive because cricket is a multi-billion-dollar industry. The goal of this study is to identify the most accurate machine learning model that can accurately predict the winner given the data from the Bangladesh Premier League. For this analysis five ML models XGBoost, Gradient Boosting, KNN, Decision Tree, Random Forest has been tested for the purpose of model building despite that our proposed model is XGBoost. To get access to BPL dataset web scrapping has been done, the dataset contains 15 columns and 3239 values and 8 team was available in each season from 2018 to 2023. We use cutting-edge machine learning techniques based on the use of numerous models, feature selection, and data separation techniques. Finally, by structuring every line of action, the forecast accuracy is attained. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning and Deep Learning based Approach to Generate a Speech Emotion Recognition System 18

A Machine Learning and Deep Learning based Approach to Gener...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Sumera Vaidehi, K. Nisha, Qamar Stanley College of Engineering and Technology for Women Department of Artificial Intelligence & Data Science and Computer Engineering Hyderabad India Stanley College of Engineering and Technology for Women Department. of Computer Science Engineering Hyderabad India

ISBN: (纸本)9789380544519

The most common and general medium via which we humans convey or communicate our thoughts, emotions, feelings or ideas artlessly is by speech or articulation. Blending of this artless way of speech with the technological advancements of AI, has given rise to the importance of building emotion recognition systems from speech today. Even more, the speech/articulation emotion recognition system presented here is also to contribute in and facilitate various emerging applications of today like, in detecting persons' physiological state (as in lie detectors), also be used in forensics, medicine. The proposed work identifies/associates an appropriate label/emotion for the respective emotion from speech presented in the form of an audio file (.wav format). About 4240 audio samples are taken. 1440, 2800 samples from RAVDESS and TESS datasets are considered respectively. After this process of Data collection, features are separately extracted for each audio dataset mentioned above. Energy, pitch, ZCR, co-efficient of Mel frequency ceptrum (MFCC) are some of the features considered in this study. Furthermore, clubbing and merging of 2 datasets is performed resulting in a total of 4240 rows and 24 columns (features/characteristics including 1class label) of audio samples. The resulting 4240 samples of feature dataset is split/bifurcated into training and testing set by considering 3 different possibilities/instances viz;60%-40% ratio, 70%-30% ratio, 80%-30% ratio. The models namely CNN, Random forest and Support Vector Machine are trained to classify the dataset into 8 different emotions (neutral, calm, happy, sad, angry, fearful, disgust, surprise). An attempt to implement the models using two very essential disciplines of AI i.e. Machine Learning and Deep Learning is made here. The accuracy or results are depicted by generating confusion matrices on test data for CNN, RF and SVM models (Each model is trained and test across 3 different ratios viz;60%-40%, 70%-30%, 80%-20%). C

关键词： Classification CNN Confusion matrices Extraction of features MFCC RF Speech/articulation Emotion Recognition SVM

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging Information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Identification of Tomato Flu using Deep Learning 10

A Novel Approach for Identification of Tomato Flu using Deep...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Mittal, Kanak Sharma, Garima Tripathi, Vikas Nainwal, Ankita Pandey, Priyank Graphic Era Deemed to Be University Department. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9789380544472

The study proposes a novel deep learning-based model for early and accurate detection of the Tomato Flu virus, also known as tomato fever, which has recently emerged in children under the age of five in the Indian state of Kerala. The model utilizes a deep learning method to classify skin pictures and check whether a person is suffering from the virus or not, with an accuracy of 100% and a validation loss of 0.2463. Additionally, an API is developed for easy integration into various web/app frameworks. The authors highlight the importance of careful management of rare viral diseases, especially in the context of the ongoing COVID-19 pandemic. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

A Cost Effective IoT-based Solution for Biometric Security Systems in Blood Banks 10

A Cost Effective IoT-based Solution for Biometric Security S...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Gupta, Shagun Agarwal, Shruti Sharma, Garima Agarwal, Piyush Graphic Era Deemed to Be University Department. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9789380544472

We have always been concerned about outsiders breaking into our homes, offices, and, in particular, hospital blood banks. Blood samples from people with uncommon blood types are stored in a blood bank. Any adjustments or modifications can possibly endanger people's lives. As a result, security is critical. The Internet of Things (loT) paradigm seeks to solve this security issue as cheaply as possible. This research proposes a low-cost fingerprint door lock system that can store 137 fingerprints at once. The loT model includes two phases: the enrolment phase, in which fingerprints are enrolled, and the verification phase, in which the person accessing the blood bank must authenticate their fingerprint. This is one of the cheapest and finest ways to safeguard blood banks against intruders, and it may be simply implemented by various government entities and non-profit groups that serve society. It has a 98% accuracy rate. The system uses lights and a buzzer to approve or disapprove people. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Internet of things

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：