检索结果-内蒙古大学图书馆

The effect of emojis on arabic text in sentiment analysis using deep learning

AIP Conference Proceedings 2025年第1期3255卷

作者： Suhad Nasrallah Taraf Ahmed T. Sadiq Informatics Institute for Postgraduate Studies Iraqi Commission for Computers & Informatics Baghdad Iraq Department of computer science College of science University of Technology-Iraq Baghdad Iraq

The emergence of social media has enabled the swift proliferation of explanatory content across various domains, encompassing advertisements, movies, politics, and economics. The growth has been ascertained through the escalation in emotional analysis, encompassing diverse facets. The Arabic review and OMCD big data sets were amalgamated with Twitter data. The textual content was segregated from emojis, and various word embedding techniques were applied, including Spacy (W2V), Fast Text, and Arabic Bidirectional Encoding Representation (AraBERT), resulting in record-high percentages. Convolutional neural networks (CNN), long short-term memory (LSTM), and recurrent neural networks (RNN) were employed in the development of sentiment analysis models. The assessment of model performance was predicated on achieving optimal accuracy, utilizing the voting method to formulate decisions based on weighting. Deep learning (DL) methodologies with the AST (Arabic et al.) dataset resulted in accurate textual content and emoji models. The symbols occupied exact proportions and significantly impacted the final classification. In contrast, for OMCD (Moroccan Offensive Comments Dataset), the text had a more significant impact due to its small number of symbols.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Integrated Grey Wolf Optimizer with Nelder-Mead Method for Workflow Scheduling Problem

An Integrated Grey Wolf Optimizer with Nelder-Mead Method fo...

引用

2020 International Conference on Emerging Technology in Computing, Communication and Electronics, ETCCE 2020

作者： Mohsin, Nuha Sami Alhamdani, Rafah Shihab Al-Dulaimi, Buthainah Fahran Abd Iraqi Commission for Computers Informatics Informatics Institute for Postgraduate Studies Baghdad Iraq University of Information Technology and Communications Smart Cities Dept Baghdad Iraq

ISBN: (纸本)9781665419628

Cloud computing is one of the latest distributed system paradigms that comes with the opportunity of running workflows at reduced costs since it does not require owning any infrastructure Scientific workflows refer to a series of computations that facilitates data analysis in both structured distributed manners. This paper formulated a new mathematical modeling for scientific workflow scheduling (SWS) problem. The formulated optimization problem is considered a multiobjective optimization task where MakeSpan, Cost, Energy, and FlowTime are handled as the objective functions. This study proposes a new hybrid optimization algorithm based on Grey Wolf Optimizer and Nealder Mead Method for solving multi-objective SWS problems. The obtained results based on several workflow templates showed that the proposed algorithm outperformed the well-known Heterogeneous Earliest First Time (HEFT) and Distributed HEFT (DHEFT). Moreover, its performance was better than that of the benchmarking algorithms. © 2020 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Optimization of computer Multimedia Assisted Network Teaching Information Ecosystem

Evaluation and Optimization of Computer Multimedia Assisted ...

引用

Information Technology (ACIT)

作者： Hiba A. Tarish Rosilah Hassan Mustafa Musa Jaber Alaa Q. Raheema Civil Engineering Department University of Technology Baghdad Iraq Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Informatics Institute for Postgraduate Studies (IIPS) Iraqi Commission forComputers and Informatic Baghdad Iraq

At present, the continuous progress in contemporary multimedia innovation on optimization of computer-assisted network teaching with the evaluation of digital learning assets improves students in their cognitive structures by including diverse media aspects that promote learning and memory. The significant challenges in digital multimedia aided information education are corrective maintenance in classroom instructors on the use of audio-visual, poor quality of visuals, and applications that can suddenly lapse into a date. This paper introduces technology in computer Multimedia-assisted Network Teaching based on Big Data (CMNT-BD) network that considerably enhances the accuracy of the interactive development model. BD-based teaching modes can significantly influence student learning, according to parametric studies. In addition to presenting essential knowledge to learners' better-suited forms of learning, it allows for individualized educational experiences. A design technique for a digital learning system is provided in the theoretical analysis of the education platform with the attributes and purposes of the IoT in multimedia technology. This study compares the Internet of Things (IoT) online course on multimedia technologies to a standard online class as a final step. Analytic teaching resources can be effectively connected and communicated using this strategy, resulting in greater integration and a greater connection between the various teaching materials. This conclusion proposes corresponding suggestions to optimize the teaching information ecosystem in the multimedia environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review on lightweight encryption algorithms for IoT devices

引用

AIP Conference Proceedings 2024年第1期2885卷

作者： Azhar Sadiq Jafer Khalid A. Hussein Jolan Rokan Naif Computer Science Department College of Education Mustanisiryah University Baghdad Iraq Iraqi Commission for Computers & Informatics/Informatics Institute for Postgraduate Studies Baghdad Iraq

The wireless sensor network (or WSN) is the most recent technology that is going to be the upcoming era of the internet that link various physical objects who connect with each other without required to the human interactions. Even so, security play’s considerable role in network in order to prevent the not data misuses, modification of data, authorized access, etc. The WSN communication could be secured by used a light-weight cryptography, that is the lighter kind of cryptography. About 50’s lightweight cryptography algorithms (basic encryption algorithms) were presented in the recent years with a focus on a certain application, in addition to many other methods have been made by the study for the NIST recent times. To be able to present an alternative view of the WSN security problems and the utilization of lightweight encryption to protect it, this study, a review was presented to review several existing light weight algorithms which could serve this area, along with make comparison among these algorithms relating to performances, implementation, and models of attacks and the protest to these attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compression of speech audio signals using Tap97-wavelet, short DCT, and BZIP2 encoder

引用

AIP Conference Proceedings 2024年第1期3097卷

作者： Zinah Jamal Jabbar Loay E. George Informatics Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq University of Information Technology and Communication Baghdad Iraq

This paper explores the application of a hybrid compression approach using the Tap97-Wavelet transform, Short Discrete Cosine Transform (DCT), and an advanced entropy encoder, specifically the BZIP2 algorithm, to compress speech audio signals. The study aims to investigate the effectiveness and performance of this compression technique in achieving high compression ratios while maintaining acceptable audio quality. This Paper focuses on the control parameters: parameters of quantization step, Sampling rate, the number of passes of the wavelet transform, and the number of blocks in the pre-Discrete Cosine Transform (DCT) stage. These parameters play a crucial role in audio signal processing and compression techniques. Performance evaluation metrics, including compression ratio, peak signal-to-noise ratio (PSNR), Mean Squared Error (MSE) and Mean Absolute Error (MAE) assess the effectiveness and efficiency of this approach, moreover the time of compression was also studied to evaluate the speed of performance in terms of time. The findings of this Paper contribute to the understanding of utilizing hybrid compression approaches for speech audio signals, providing insights into their effectiveness and potential applications in speech processing and transmission systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Swarming for success: Leveraging particle swarm optimization to enhance decision support in data mining

引用

AIP Conference Proceedings 2024年第1期3229卷

作者： Wasnaa Jawad Abbas Al-Bakry Informatics Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Baghdad Iraq University of Information Technology and Communications Baghdad Iraq

Data mining plays a role, in decision support systems by uncovering valuable patterns and knowledge from large datasets. The selection of parameters for data mining algorithms greatly impacts the quality of insights extracted and decision making procedures. Our study introduces a method that leverages Particle Swarm Optimization (PSO) to fine tune parameters for enhancing decision support within the Random Forest algorithm. Taking cues from the way birds flock and fish school the PSO algorithm effectively navigates through the parameter space of the Random Forest algorithm. By integrating PSO with Random Forest we can automatically determine the parameter settings to improve accuracy and efficiency, in data mining tasks thereby enhancing decision making support. Our methods performance across datasets is showcased through experiments and analysis illustrating how PSO can optimize data mining by leveraging Random Forest to enrich decision making processes with insights. This study underscores the potential of PSO and Random Forest, in data mining applications emphasizing their ability to elevate decision making systems and empower both organizations and individuals in their decision making endeavors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recent Techniques of Open Educational Resources

Recent Techniques of Open Educational Resources

引用

2019 Imam Al-Kadhum International Conference for Modern Applications of Information and Communication Technology, MAICT 2019

作者： Abdulameer, Maysaa H. Abdullah, Mahmood Z. Iraqi Commission for Computer and Informatics Informatics Institute for Post-Graduation Studies Baghdad Iraq Al-Mustansiriyah University College of Engineering Baghdad Iraq

The field of learning has a reasonable claim of being a specified example on the way it could be improved or sustained by technology. Operating with technology for the sake of learning, users are expected to be taking longer period of time facing issues, struggling through these issues and in nearly all cases the interaction with technology is one of several effects on the achievement of success. This doesn't mean the fact that Internet and computing have had no sustainable impacts on how users learn and on the options that exist for learners. formal learning field has been experiencing a period of fast changes, and barriers between formal learning and informal one show falling away signs, partly because of changes in accessing information or alternate delivery modes. The impact technology has on pedagogy (structure or way of teaching) is complicated. There are rather few specified researches on how technological potentials and pedagogical responses to those operate to take advantage of life-long learners. In this paper a survey for last designed systems and platforms of e-learning based on open educational resource (OER) via combining evidence from research strands that are based on working in on-line and distant learning under formal settings, and in addition on open and free on-line learning that is typically of less formality. The presented study discusses numerous factors that are related to results of the instruction: the usually unpredictable learner motivations, the paths that those learners take during courses, and signs of success in formal learning and informal learning, based on each of technology and pedagogy. The results of practical activities are given for the sake of widening the access to education with using technology that indicates the fact that open education offers from alternate manners of supporting learners. Those propose an emphasis on design decisions which may be helpful in integrating learning process more thoroughly with how on-line sy

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

A new lightweight mechanism for IoT devices protection

引用

AIP Conference Proceedings 2023年第1期3015卷

作者： Rana Fadhel Atiyah Intisar Al-Mejibli Informatics Institute for Postgraduate Studies Iraqi Commission for computer & Informatics Iraq Baghdad Biomedical Informatics College University of Information Technology and Communication Iraq Baghdad

Employing IoT devices presents numerous obstacles, one of which is security as a critical concern in data transfer; hence, the development of adequate security methods for such devices must take into account their limited power, memory, and processor capacities. Consequently, IoT devices require lightweight encryption. This study introduces a lightweight security approach for Internet of Things devices. We created the Speck-Ultra (Speck-U) algorithm, which is a novel and incredibly lightweight encryption system based on the Speck algorithm. Speck-U is based on ECC for the creation of a private key and ECDH for key exchange. A hashing function (HMAC-SHA3) was used to ensure the confidentiality and integrity of transmitted data. The proposal has been utilized in healthcare for testing and validation reasons. The location where the healthcare system was installed depends on the sensors and controllers used to transmit and receive data over the internet. In addition, smartphone and website applications were implemented. Experiments and comparisons demonstrate that Speck-U is more dependable in terms of privacy, security, and integrity than the original Speck. In addition, its encryption, hashing code calculation, and decryption implementation times are superior. The security results were examined and tested using a NIST test suite, with 15 key generation and ciphertext tests passing with flying colors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image classification using a hybrid BiLSTM-CNN for breast cancer

引用

AIP Conference Proceedings 2024年第1期3232卷

作者： Ahmed Abed Maeedi Dalal Abdulmohsin Hammood Shatha Mezher Hasan Informatics Institute for Postgraduate Studies Iraqi Commission for Computers & Informatics Baghdad Iraq Electrical Engineering Technical College Middle Technical University Baghdad Iraq

This research aims to combine BiLSTM and CNN to provide a new model for applications in image classification. A BiLSTM network is a long-term recurrent neural network (RNN) that can recall dependencies. The main potential of BiLSTM, when used in a multi-layer configuration, is to enhance a CNN’s feature extraction capabilities. CNN is able to glean useful information from models that BiLSTM can selectively remember for a long time. The model proposed has performance superior to the standard CNN classifier in image classification. This is due to the data passing through two stages and several layers, the first through BiLSTM and the second through the CNN stage, each of which contains several layers and filters, resulting in high accuracy compared to previous studies. This is because convolutional and recurrent neural networks work together to form the suggested model. This model can be trusted by working great with neural networks for all types of classification tasks. Researchers validated these results by testing our model on a real dataset. The proposed model’s training accuracy is (0.9982), and its testing accuracy is (0.9633), indicating its success and suitability compared to other models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based image Steganalysis

引用

AIP Conference Proceedings 2024年第1期3207卷

作者： Akram Kadhim Mshet Huda Kadhim Tayyeh Information Institute for Postgraduate Studies Iraqi Commission for Computers & Informatics Baghdad Iraq University of Information Technology and Communications Baghdad Iraq

Steganography involves concealing hidden messages inside various types of media, whereas steganalysis is the process of identifying the presence of steganography. Convolutional neural networks (CNN), a type of neural network that outperformed previously proposed machine learning-based methods when introduced, are among the models used for deep learning. While CNN-based methods may yield satisfactory results, they face challenges in terms of classification accuracy and network training stability. The present research introduces a CNN structure to increase hidden data detection and spatial domain image training reliability. The suggested method includes pre-processing, feature extraction, and classification. Evaluation of performance is conducted on datasets Break Our Steganographic System Base (BOSSbase-.01) and Break Our Watermarking System (BOWS2) with three adaptive steganography algorithms. Wavelet Obtained Weights (WOW), Spatial UNIversal WAvelet Relative Distortion (S-UNIWARD), and Highly Undetectable steGO (HUGO) operating at low payload capacities of 0.2 and 0.4 bits per pixel (bpp). The experimental results surpass the accuracy and network stability of prior publications. Training accuracy ranges from 91% to 94%, and testing accuracy ranges from 74.8% to 86.65%.

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：