检索结果-内蒙古大学图书馆

Iraqi Journal for computer science and Mathematics 2025年第2期6卷 72-81页

作者： AlRababah, Ahmad AbdulQadir Aljahdali, Mohammed Khalid Al jahdali, Abdulrahim Abdulhamid AlGhanmi, Mohammed Saleh Al Barazanchi, Israa Ibraheem Department of Computer Science Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Saudi Arabia College of Engineering University of Warith Al-Anbiyaa Karbala Iraq

Arabic script is exhibited in a cursive style, which is a departure from the norm in many common languages, and the shapes of letters are contingent on their positions within words. The form of the first letter is influenced by the subsequent letter, middle letters are shaped by both preceding and succeeding letters, and the shape of the final letter is determined by the preceding letter. Additionally, certain letters are found to have strikingly similar shapes, making Arabic text recognition a formidable challenge in computer vision. The challenge of detecting and recognizing Arabic handwritten text is addressed in this paper by proposing a novel system that integrates two Deep Learning models without the constraints of a predefined dictionary or language model. Object Detection techniques are employed in the first model to accurately identify lines, words, and punctuation marks, providing a robust foundation for text recognition. In the second model, a powerful recognition system is developed, trained on the IFN/ENIT dataset to predict character sequences from handwritten text images. The architecture is comprised of a convolutional neural network (CNN) with residual connections, followed by a Bi-directional Long Short-Term Memory (BLSTM) layer, and culminates in a fully connected layer. State-of-the-art results in unconstrained Arabic text recognition tasks are achieved by this approach. © 2025 The Author(s).

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Pose invariant non-frontal 2D, 2.5D face detection and recognition technique

引用

International Journal of Information technology (Singapore) 2023年第5期15卷 2603-2611页

作者： Thavani, Shiva Sharma, Sahil Kumar, Vijay Computer Science and Engineering Department Thapar Institute of Engineering and Technology Punjab Patiala India Computer Science and Engineering Department Punjab Engineering College Chandigarh India Information Technology Department Dr. B.R. Ambedkar National Institute of Technology Punjab Jalandhar India

In this paper, the Pose Invariant Identity Recognition (PIIR) technique is proposed. It measures face resemblance using facial landmarks, which are further vigorous to pose disparity. The proposed technique utilizes the concepts of face frontalization and discriminative learning techniques. 3D Morphable Model is used in both techniques for pose invariant. The proposed technique is validated on CAS-PEAL face dataset. Experimental results signify that the proposed technique attains authentication accuracy of 90.24% on face datasets with 30° pan-angle. The proposed technique is further applied on 2.5D face dataset with variant facial positions and expressions. Results reveal that the proposed method can identify the face accurately. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： 2.5D depth-based face recognition Face reconstruction Feature extraction Non-frontal face recognition Pose-invariant identity recognition

来源：评论

学校读者我要写书评

暂无评论

A Mango Disease Prediction for Smart Agiculture using Machine Learning Algorithms 8

A Mango Disease Prediction for Smart Agiculture using Machin...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Lavanya, K. Packialatha, A. Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Chennai Tamilnadu Pallavaram India

ISBN: (纸本)9798350376425

The country's economy relies heavily on agriculture, and the health of the crops is essential to its success. Crop diseases that go undetected can cost the agriculture industry. Thus early detection and identification are crucial. It is possible to avoid crop diseases from destroying the harvest if they are accurately diagnosed and detected. Because healthy and diseased plants appear identical in their early stages, farmers cannot distinguish between the two by watching the crop leaf. India exports vast mangoes, making it an economically and environmentally significant fruit. About 1500 mango species are grown in India, with over 1000 commercial types. There are a lot of diseases that harm mangoes, affecting their look, taste, and economy. The "Prediction of Disease in Mango Fruit Crops"A complex warning system that uses machine learning and IoT. One of the main objectives is to develop a system that can forecast disease outbreaks on mango fruit harvests using historical weather information and crop yield Mango trees in India are plagued by a fungus called Anthracnose, which is the most frequent disease of its kind. Anthracnose, a highly contagious fungus, requires a quick and accurate method of diagnosis. As a result, an in-depth examination of the plants is essential before initiating any control measures. This study examines machine learning(ML) and deep learning (DL) strategies for detecting and classifying mango plant diseases. The performance of ML and DL-based classification models for mango crops and their datasets and feature extraction approachesare examined in this work. Finally, a variety of issues involved in plant disease identification are explored. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

The Role of Machine Learning in Optimizing Industrial Communication Protocols

The Role of Machine Learning in Optimizing Industrial Commun...

引用

2024 International Conference on Advances in Computing Research on science engineering and technology, ACROSET 2024

作者： Kharbas, Vikas Kumar Mahesh, T.R. Upadhyay, Satish Vivekananda Global University Department of Computer Science & Application Jaipur India Faculty of Engineering and Technology Department of Computer Science Engineering Bangalore India Atlas SkillTech University Department of UGDX Mumbai India

ISBN: (纸本)9798350388800

Due to the complexity and urgency of information exchange in modern companies, optimizing communication protocols in the workplace is essential. Using methods from machine learning, this research takes a fresh tack toward optimizing the performance of communication protocols. The suggested approach integrates Reinforcement Learning (RL), Convolutional Neural Networks (CNNs), and Genetic Algorithms (GAs) to provide a self-optimizing system with dynamic behavior. The RL feature facilitates this protocol's flexibility in the face of dynamic network circumstances by providing rapid feedback. CNNs are used for real-time anomaly detection to improve safety and dependability. GAs methodically explores combinations of protocol parameters to determine the optimal collection that matches specified performance criteria. The recommended technique was compared to the usual methodology using a variety of efficiency and reliability measures. The findings demonstrate that the proposed approach frequently outperforms the state-of-the-art methods in a broad range of commercial settings with regards to efficiency, dependability, and adaptability. Understanding how to enhance industrial communication protocols is crucial in the age of Industry 4.0 and the IIoT. The recommended solution offers an autonomous, adaptable, and secure tool for boosting communication in dynamic production situations. © 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

Synergizing Futures: Precision Career Mapping with Llama 2 and AI Fine-Tuning for Personalized Path Prediction and Guided Navigation

Synergizing Futures: Precision Career Mapping with Llama 2 a...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Singh, Anuradha Sharma, Himanshu Jindal, Kanika Chaudhary, Ankur Noida Institute Of Engineering And Technology Department Of Computer Science And Engineering Greater Noida India Noida Institute Of Engineering And Technology Department Of Electronics And Communication Engineering Greater Noida India

ISBN: (纸本)9798350366846

These days, a lot of students struggle in how to choose the career. As they progress through their studies, students must recognize their abilities and assess their areas of interest to determine the most appropriate job for them. With the aid of this approach, today's youngsters will be able to determine which career route will yield the best outcomes in the long run if they choose the suggested vocation. This will assist in raising the student's performance and spark their interest to keep them concentrated on their desired job. This system is based on an exam that students must complete;based on their responses, it will produce a summary of the test results. The primary goal of this system is to give a summary of the artificial intelligence methods that we employed to forecast the student's performance. This structure likewise be emphasizing how we are identifying characteristics in student data by employing prediction systems. For educators, educational institutions, and students alike, using this system has proven to be advantageous. In this paper we have used various technologies like Flutter, Llama-2 generative A.I. model, Firebase and UI/UX design tools. Our experimental results of proposed system reduce the career searching effort by 80% when tested for Lyman people. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Framework for Automatic Sarcasm Detection Using Proposed Tensor-DNN-50 Algorithm 4th

A Real-Time Framework for Automatic Sarcasm Detection Using ...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Murthy, Jamuna S. Siddesh, G.M. Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru India

ISBN: (纸本)9789819726103

Social media platforms such as Twitter, Facebook, and Instagram are vast repositories of trending global news. They generate an enormous amount of data, offering a valuable resource for both academic researchers and IT marketing teams. These data can be harnessed for various insights and applications. A prominent and pressing research area within this data is the detection of sarcasm and fake news. The internet is rife with misleading and false information, often causing widespread confusion. Current research primarily categorizes news as either real or fake, using machine learning algorithms. However, this binary approach struggles with news that is partially true yet contains elements that could be deemed fake. To address this issue, our work introduces a real-time framework for sarcasm detection, utilizing an innovative deep learning technique called Tensor-DNN-50 for multiclass classification. The TDNN-50 model not only classifies news articles based on authenticity but also quantifies the level of sarcasm within them. Comparative analysis against leading techniques like SVM, att-RNN, and EANN demonstrates the superiority of our proposed algorithm. It achieves an impressive accuracy of 96.4% for two-class classification, 94.32% for four-class classification, and an astonishing 99.1% for seven-class classification. These results underscore the potential of our Tensor-DNN-50 Model in effectively addressing the intricate challenges of sarcasm detection and news classification with unparalleled accuracy across multiple classes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Building a neural speech recognizer for quranic recitations

引用

International Journal of Speech technology 2023年第4期26卷 1131-1151页

作者： Al-Issa, Suhad Al-Ayyoub, Mahmoud Al-Khaleel, Osama Elmitwally, Nouh Department of Computer Engineering Jordan University of Science and Technology Irbid22110 Jordan Department of Computer Science Jordan University of Science and Technology Irbid22110 Jordan School of Computing and Digital Technology Birmingham City University BirminghamB4 7XG United Kingdom Department of Computer Science Faculty of Computers and Artificial Intelligence Cairo University Giza12613 Egypt

This work is an effort towards building Neural Speech Recognizers system for Quranic recitations that can be effectively used by anyone regardless of their gender and age. Despite having a lot of recitations available online, most of them are recorded by professional male adult reciters, which means that an ASR system trained on such datasets would not work for female/child reciters. We address this gap by adopting a benchmark dataset of audio records of Quranic recitations that consists of recitations by both genders from different ages. Using this dataset, we build several speaker-independent NSR systems based on the DeepSpeech model and use word error rate (WER) for evaluating them. The goal is to show how an NSR system trained and tuned on a dataset of a certain gender would perform on a test set from the other gender. Unfortunately, the number of female recitations in our dataset is rather small while the number of male recitations is much larger. In the first set of experiments, we avoid the imbalance issue between the two genders and down-sample the male part to match the female part. For this small subset of our dataset, the results are interesting with 0.968 WER when the system is trained on male recitations and tested on female recitations. The same system gives 0.406 WER when tested on male recitations. On the other hand, training the system on female recitations and testing it on male recitation gives 0.966 WER while testing it on female recitations gives 0.608 WER. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Hybrid Technique for Constructing Footprint Extraction System from Satellite Imaginary 2

Hybrid Technique for Constructing Footprint Extraction Syste...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Raghavendran, N. Menaga, P. Prabu, V. Vignesh Manimaran, V. Robinson, Y. Harold Ramanan, K. Francis Xavier Engineering College Department of Computer Science and Engineering Tamil Nadu Tirunelveli India Rajalakshmi Engineering College Department Of Computer Science & Business Systems Tamil Nadu Chennai India Bannari Amman Institute of Technology Department of Civil Engineering Tamil Nadu India National Engineering College Department of Information Technology Tamil Nadu Kovilpatti India NPR College of Engineering and Technology Natham Department of Computer Science and Engineering Tamil Nadu Dindigul India

ISBN: (纸本)9798350365269

The building extraction of the footprint from the satellite imagination has been a research problem that needs to be solved efficiently. The hybrid semantic segmentation framework is used to increase the footprint extraction system as the Inria Aerial Image Labeling Dataset is involved in improving the extraction of the footprint, the proposed technique is framed with the CGAN model and Mask RCNN for utilizing the instance segmentation which manages the data augmentation and semantic segmentation process. The performance evaluation shows that the proposed technique has an improved F1 score and accuracy as the effect of every functionality for the footprint extraction has been analyzed subsequently. © 2024 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Execution of CNN-Based Sanguine Data Transmission with LSB-SS and PVD-SS

引用

computer Systems science & engineering 2023年第8期46卷 1707-1721页

作者： Alaknanda S.Patil G.Sundari Arun Kumar Sivaraman Department of Electronics and Communication Sathyabama Institute of Science and TechnologyChennaiTamil Nadu600119India School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India

The intact data transmission to the authentic user is becoming crucial at every moment in the current ***;is a technique for concealing the hidden message in any cover media such as image,video;and audio to increase the protection of *** resilience and imperceptibility are improved by choosing an appropriate embedding *** paper gives a novel system to immerse the secret information in different videos with different *** audio and video steganography with novel amalgamations are implemented to immerse the confidential auditory information and the authentic user’s face image.A hidden message is first included in the audio from the multimedia file;using LSB *** Stego-video is created in the second stage by merging the authorized user’s face into the frame of the video;by using PVD ***-audio is linked again with the stego-video in the third *** incorporated perspective techniques(LSB-SS and PVD-SS algorithms)with more significant data immersing capacity,good robustness and imperceptibility are proposed in this research *** spread spectrum approach is used to increase the complexity of secret data *** different video files are tested with different voice files with the results such as PSNR,SSIM,RMSE and MSE as 52.3,0.9963,0.0024 and 0.0000059,respectively.

关键词： Audio steganography data hiding information security pixel value differencing

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection Using Xception Model

Brain Tumor Detection Using Xception Model

引用

2024 International Conference on Advances in Computing Research on science engineering and technology, ACROSET 2024

作者： Philip, Joshwa Joy Rani, Ruchi Kumar, Sumit School of Computer Engineering and Technology Dr Vishwanath Karad Mit World Peace University Department of Computer Science and Engineering Pune India School of Computer Engineering and Technology Dr Vishwanath Karad Mit World Peace University Department of Computer Engineering and Technology Pune India Department of Electronics and Telecommunication Maharashtra Pune India

ISBN: (纸本)9798350388800

Numerous morphological and histological characteristics of brain tumors make diagnosis and treatment very challenging. Traditional diagnosis methods often depend on the analysis of medical images, which can lead to unclear conclusions and errors. In recent years, machine learning (ML) and deep learning techniques (DL) have shown great scope in improving the detection and classification of brain tumors. These methods extract the features and classify medical imaging data, such as MRI, CT, and PET scans. Convolutional and recurrent neural networks give better performance even though there are challenges in the dataset. In the proposed work, Xception architecture is used which is a type of convolution neural network. This model is pretrained on the ImageNet dataset. The proposed model achieves 99.90% accuracy in brain tumor detection. © 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

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：