Artificial Intelligence articles list

Artificial Intelligence (AI) has emerged as a disruptive force with the potential to transform various industries, and the field of higher education is no exception. This critical review paper aims to examine the emerging role of AI in Science, Technology, Engineering, and Mathematics (STEM) higher education. The article explores the impact of AI on teaching and learning methodologies, curriculum design, student engagement, assessment practices, and institutional strategies. The review also highlights the potential benefits and challenges associated with integrating AI into STEM education and identifies key areas for future research and development. Overall, this article provides insights into how AI can revolutionize STEM higher education and offers recommendations for harnessing its full potential.

Bharath Kumar

The need for renewable energy sources in addressing global energy demands is growing, especially in Nigeria where electricity demand often exceeds supply. Solar photovoltaic (PV) systems have become a viable solution, with federal universities in Nigeria, as major electricity consumers, recognizing their potential. However, determining the right size of PV systems for individual faculties within these universities is a complex task. This study attempted to simplify this process by introducing an innovative approach to size PV systems in these faculties. The research method used the Extended Kalman Artificial Neural Network (EKF-ANN) and the Crow Search Algorithm (CSA) to enhance the accuracy of PV system sizing. Data was collected on the study site, load demand, weather conditions, system components, and operational control and systems models to establish sizing criteria. The study focused on the optimal size of a solar PV system at the Faculty of Law building, University of Port-Harcourt, and how to improve its accuracy. The results showed that using global solar insolation parameters, EKF-ANN predicted values for global temperature, flock size, and maximal iteration. This optimized system could generate surplus power for effective grid supply. The study found that the optimal size of the series-connected panels for the Faculty of Law building was 96, 83, 73, and 65 units, with corresponding insolation values ranging from 3.737 to 4.368 kW/m2. It was concluded that the combination of CSA and EKF-ANN in solar PV sizing is suitable for achieving optimal outcomes for energy storage and grid supply. Nonetheless, the study recommended additional investigation into real-time and grid-connected solutions to enhance the proposed approach's effectiveness.

FXintegrity Publishing

The domestication of animals and cultivation of crops have been essential to human development throughout history, with the agricultural sector playing a pivotal role. Insufficient nutrition often leads to plant diseases, such as those affecting rice crops, resulting in yield losses of 20-40% of total production. These losses carry significant global economic consequences. Timely disease diagnosis is critical for implementing effective treatments and mitigating financial losses. However, despite technological advancements, rice disease diagnosis primarily depends on manual methods. In this study, we present a novel Self-Attention Network (SANET) based on the ResNet50 architecture, incorporating a kernel attention mechanism for accurate AI-assisted rice disease classification. We employ attention modules to extract contextual dependencies within images, focusing on essential features for disease identification. Using a publicly available rice disease dataset comprising four classes (three disease types and healthy leaves), we conducted cross-validated classification experiments to evaluate our proposed model. The results reveal that the attention-based mechanism effectively guides the Convolutional Neural Network (CNN) in learning valuable features, resulting in accurate image classification and reduced performance variation compared to state-of-the-art methods. Our SANET model achieved a test set accuracy of 98.71%, surpassing current leading models. These findings highlight the potential for widespread AI adoption in agricultural disease diagnosis and management, ultimately enhancing efficiency and effectiveness within the sector.

Mehdhar S. A. M. Al-Gaashani

Tomato is one of the most important vegetables worldwide. It is considered a mainstayof many countries’ economies. However, tomato crops are vulnerable to many diseasesthat lead to reducing or destroying production, and for this reason, early and accuratediagnosis of tomato diseases is very urgent. For this reason, many deep learning modelshave been developed to automate tomato leaf disease classification. Deep learning isfar superior to traditional machine learning with loads of data, but traditional machinelearning may outperform deep learning for limited training data. The authors proposea tomato leaf disease classification method by exploiting transfer learning and featuresconcatenation. The authors extract features using pre-trained kernels (weights) fromMobileNetV2 and NASNetMobile; then, they concatenate and reduce the dimensionalityof these features using kernel principal component analysis. Following that, they feedthese features into a conventional learning algorithm. The experimental results confirmthe effectiveness of concatenated features for boosting the performance of classifiers.The authors have evaluated the three most popular traditional machine learning classifiers,random forest, support vector machine, and multinomial logistic regression; amongthem, multinomial logistic regression achieved the best performance with an averageaccuracy of 97%.

Mehdhar S. A. M. Al-Gaashani

Colon cancer is the second most common cause of cancer death in women and the third most common cause of cancer death in men. Therefore, early detection of this cancer can lead to lower infection and death rates. In this research, we propose a new lightweight deep learning approach based on a Convolutional Neural Network (CNN) for efficient colon cancer detection. In our method, the input histopathological images are normalized before feeding them into our CNN model, and then colon cancer detection is performed. The efficiency of the proposed system is analyzed with publicly available histopathological images database and compared with the state-of-the-art existing methods for colon cancer detection. The result analysis demonstrates that the proposed deep model for colon cancer detection provides a higher accuracy of 99.50%, which is considered the best accuracy compared with the majority of other deep learning approaches. Because of this high result, the proposed approach is computationally efficient.

Mehdhar S. A. M. Al-Gaashani

Brain tumors (BTs) are deadly diseases that can strike people of every age, all over the world. Every year, thousands of people die of brain tumors. Brain-related diagnoses require caution, and even the smallest error in diagnosis can have negative repercussions. Medical errors in brain tumor diagnosis are common and frequently result in higher patient mortality rates. Magnetic resonance imaging (MRI) is widely used for tumor evaluation and detection. However, MRI generates large amounts of data, making manual segmentation difficult and laborious work, limiting the use of accurate measurements in clinical practice. As a result, automated and dependable segmentation methods are required. Automatic segmentation and early detection of brain tumors are difficult tasks in computer vision due to their high spatial and structural variability. Therefore, early diagnosis or detection and treatment are critical. Various traditional Machine learning (ML) techniques have been used to detect various types of brain tumors. The main issue with these models is that the features were manually extracted. To address the aforementioned insightful issues, this paper presents a hybrid deep transfer learning (GN-AlexNet) model of BT tri-classification (pituitary, meningioma, and glioma). The proposed model combines GoogleNet architecture with the AlexNet model by removing the five layers of GoogleNet and adding ten layers of the AlexNet model, which extracts features and classifies them automatically. On the same CE-MRI dataset, the proposed model was compared to transfer learning techniques (VGG-16, AlexNet, SqeezNet, ResNet, and MobileNet-V2) and ML/DL. The proposed model outperformed the current methods in terms of accuracy and sensitivity (accuracy of 99.51% and sensitivity of 98.90%).

Mehdhar S. A. M. Al-Gaashani

Nuclei segmentation plays an essential role in histology analysis. The nuclei segmentation in histology images is challenging in variable conditions (clinical wild), such as poor staining quality, stain variability, tissue variability, and conditions having higher morphological variability. Recently, some deep learning models have been proposed for nuclei segmentation. However, these models rarely solve the problems mentioned above simultaneously. Most of the information in Hematoxylin and Eosin (H&E) stained histology images is in its channel, and the remaining information is in the spatial domain. We observed that most problems could be solved by considering channel and spatial features simultaneously, e.g., the spatial and channel features provide the solution to the morphological variability and staining variability, respectively. Therefore, we propose a novel spatial-channel attention-based modified UNet architecture with ResNet blocks in encoder layers. The UNet baseline preserves coarse and fine features, thus proving the solution to the tissue variability. The proposed method significantly improves the segmentation performance compared to the state-of-the-art methods on three different benchmark datasets. We demonstrate that the proposed model is generalized for 20 cancer sites, more than any reported literature. The proposed model is less complex than most state-of-the-art models. The impact of the proposed model is that it will help improve further procedures such as nuclei instance segmentation, nuclei classification, and cancer grading.

Ibtihaj Ahmad

In this paper, we propose a deep learning approach for visual recognition of bird species in noisy environments. Bird species recognition has been a challenging task due to the high variation in bird appearances and the presence of noise and clutter in natural environments. Our approach utilizes a deep convolutional neural network (CNN) to learn discriminative features from bird images and classify them into different species. We also incorporate data augmentation techniques to increase the diversity of the training data and improve the robustness of the model. To address the issue of noisy environments, we introduce a novel noise-robust loss function that penalizes the model for incorrect predictions caused by noise. We evaluate our approach on a dataset of bird images collected from diverse environments and compare it with state-of-the-art methods. Our results demonstrate that our approach achieves superior performance in both clean and noisy environments, highlighting the effectiveness of our noise-robust loss function. Our approach has the potential to be applied in real world scenarios for bird species recognition and conservation.

PK Dutta