17 July 2023 in International Journal of Information technology and Computer Engineering
The integration of artificial intelligence into the realm of education has emerged as a consequence of using information and communication technologies as effective instruments to enhance the process of teaching and learning. In November 2022, an AI-driven chatbot known as ChatGPT was introduced. This chatbot possesses the capability to produce coherent and informative responses akin to those generated by humans in response to user inputs. ChatGPT demonstrates its adaptability as a potential facilitator of open education by providing assistance, guidance, and feedback to self-directed learners; thereby amplifying their motivation and involvement. The aim of this paper is to conduct a comprehensive analysis of the aforementioned aspects and delve into the prospective application of ChatGPT within educational frameworks. More precisely, its objectives encompass advocating integration of ChatGPT in educational contexts and furnishing educators with a repertoire of methodologies and approaches to guarantee the prudent and efficacious incorporation of ChatGPT in pedagogical or research endeavors. Through these efforts, the paper strives to foster a heightened and well-informed discourse about the utilization of ChatGPT within the scope of education. The paper outlines the essential strategies and methodologies that should be concurrently utilized when incorporating the services of ChatGPT in educational settings.
1 January 2019 in Passer Journal of Basic and Applied Sciences
The global spread of Covid-19 has enhanced the adoption of virtual education and the use of technology in order to reduce the risk of contagion. Recently, the academics have turn out to be more technology-orientated and the educational establishments continue to seek opportunities in order to adopt an environment where all researchers could have access to high-quality scientific resources at anytime and anywhere in the world. Cloud computing is a model, which provides the users with services and application software on-demand, using the Internet. While the use of cloud computing applications is growing, there are ongoing research challenges related to guaranteeing security, privacy and the integration of the cloud applications. To the extent of our knowledge, the present study is the first from this type to thoroughly present the impacts of the COVID-19 pandemic on cloud computing environment in higher education institutions in Iraqi universities. This study will critically analysis the views of the faculty staff and researchers in Iraqi universities on cloud computing. It also tries to take a quick look at how Iraqi university staff responded to the epidemic in terms of research activities. The results shows that about 99% of the respondents considered the cloud applications to have great role in encouraging the research works in their institutes. Concerning the benefits of cloud services, the availability and saving cost were selected as most important factors that encouraging the adoption of cloud services. On the other hand, issues related to performance, lack of user control were selected as major problems in applying cloud services in Iraqi institutions Finally, it can be concluding that reducing the risks of the security, authorization, control and providing better performance of cloud services can enhance the use of cloud applications by researchers at Iraqi universities.
4 February 2023 in Advances in Multimedia
A trustworthy and secure identity verification system is in great demand nowadays. The automatic recognition of the 3D middle finger knuckle is a new biometric identifier that could offer a precise, practical, and efficient alternative for personal identification. According to earlier studies, deep learning algorithms could be used for biometric identification. However, the accuracy of the current 3D middle finger knuckle recognition model is relatively low. Motivated by this fact, in this study, seven deep learning neural networks have been modified and trained to identify 3D middle finger knuckle patterns using transfer learning. Using the Hong Kong Polytechnic Universitys 3D knuckle image dataset, an extensive experiment was performed. Two sessions of data from different camera lenses were used to assess the performance of the suggested deep learning model. The results show that the InceptionV3 method significantly enhanced the recognition of 3D middle finger knuckle patterns with 99.07 accuracy, followed by Xception, NasNetMobile, and DenseNet201 (97.35, 92.92, and 92.59, respectively), which is superior to the current middle finger knuckle recognition model. This accurate, fast, and automatic middle finger knuckle identification will help to be implemented in real-time and small-scale settings like offices, schools, or personal devices like laptops and smartphones, where training is simple.
1 June 2025 in Diyala Journal of Engineering Sciences
ATAbas Nariman Sidiq Tilako
Abas Nariman Sidiq Tilako
SASarwer Jamal Al-Bajalan
Alzheimer's disease (AD) is one of the common neurodegenerative disorders presenting with progressive cognitive decline and synaptic impairment. The need for accurate and accessible diagnostic methods is especially pressing in resource-limited regions. This study presents the first open electroencephalography (EEG) dataset for Alzheimer's Disease (AD) in Iraq, recording electrophysiological activity in four stages of cognition, namely, Healthy, Mild, Moderate, and Severe. The dataset comprised recordings from 53 participants and was recorded using a 40-channel EEG device based on the 10-20 electrode placement standard. Considering this EEG dataset, advanced preprocessing, such as the removal of artifacts, Independent Component Analysis (ICA), and Automatic Subspace Reconstruction (ASR), was performed to ensure high signal quality suitable for all state-of-the-art Machine Learning (ML) and Deep Learning (DL) analyses. Benchmark classification was conducted with a wide variety of ML and DL models, including Random Forest (RF), Gradient Boosting methods, Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), and Long Short-Term Memory networks (LSTMs), showing promising results-a maximum of 96.85% by Random Forest within ML techniques and a maximum of 96.05% by DNNs in DL techniques. This dataset fills a critical gap in regional AD research and moves toward developing low-cost, noninvasive diagnostic tools. Future work may be performed on more extended and more diverse datasets with more sophisticated multimodal approaches for improving AD diagnosis and early intervention. The dataset can be downloaded from https://shorturl.at/Z0b8D.
27 August 2017 in Kurdistan Journal of Applied Research
The existence of Massive datasets that are generated in many applications provides various opportunities and challenges. Especially, scalable mining of such large-scale datasets is a challenging issue that attracted some recent research. In the present study, the main focus is to analyse the classification techniques using WEKA machine learning workbench. Moreover, a large-scale dataset was used. This dataset comes from the protein structure prediction field. It has already been partitioned into training and test sets using the ten-fold cross-validation methodology. In this experiment, nine different methods have been tested. As a result, it became obvious that it is not applicable to test more than one classifier from the (tree) family in the same experiment. On the other hand, using (NaiveBayes) Classifier with the default properties of the attribute selection filter has a great time consuming. Finally, varying the parameters of the attribute selections should be prioritized for more accurate results.