IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Low-speed scalar control of induction motor by fuzzy logic
Get PDFEfforts have continually been directed toward optimizing processes in various fields, and the application in induction motors is no exception. Scalar control V/f offers a straightforward method to regulate the speed of a three-phase induction motor (TIM). However, it faces challenges at low speeds or proportionally at low frequencies, often failing to operate below 20% of its rated speed. This control typically pairs with a PI controller (PIC) for closed loop speed regulation, but its limited control range hinders performance at low speeds. Although intelligent methods have been developed to improve scalar V/f control, attention is often focused on high speeds, while control at low speeds is overlooked. This paper presents the simulation of a fuzzy controller (FC) with a Mamdani-type structure designed to achieve effective low-speed control of a TIM using the V/f scalar control technique. The results not only show improvements in overshoot and settling time but also reveal that the FC can control speeds as low as 6.06% of the rated speed, and it ensures a starting current below the designed motor current under load. Comparative analysis indicates that the FC outperforms the PIC in low-speed control, and it provides an optimal inrush current across different low speeds
Deep learning-based evaluation for distributed denial of service attacks detection
Get PDFSoftware-defined network (SDN) introduces a programmable and centralized control mechanism for managing network infrastructure, enhancing flexibility and efficiency. However, this architecture is prone to security threats, particularly distributed denial of service (DDoS) attacks that exploit centralized control. This study presents a comparative analysis of several deep learning (DL) models—namely, multilayer perceptron (MLP), artificial neural network (ANN), convolutional neural network (CNN), recurrent neural network (RNN), and long short-term memory (LSTM)—for detecting DDoS threats within SDN environments. The research incorporates key preprocessing techniques such as feature selection and synthetic minority oversampling technique (SMOTE) to handle class imbalance. The results indicate that sequence-aware models like LSTM and RNN are highly effective in interpreting temporal network behavior, with LSTM achieving the highest performance (accuracy: 91%, precision: 86%, recall: 94%, and F1-score: 90%). These findings underscore the potential of advanced DL methods in fortifying SDN infrastructures against complex cyber threats
Enhanced classification of aromatic herbs using EfficientNet and transfer learning
Get PDFHerbs have long been used for culinary and medicinal purposes, as well as in religious rituals, due to their essential oils and aromatic properties. However, distinguishing between aromatic and medicinal herbs based on visual characteristics alone can be challenging. With recent advances in computer vision, plant identification from images has seen significant growth, offering promising applications in several domains. This article aims to evaluate the classification of aromatic herbs using the EfficientNet convolutional neural network (CNN) technique with transfer learning. The methodology used is experimental research, systematically manipulating variables to observe their effects on the object of study. The researcher plays an active role in this process, rather than being a passive observer. Based on the results and the literature review, it is evident that the objective of this research was achieved, as despite the opportunities for improvement in training to achieve accuracy above 0.8, it was possible to evaluate the classification of aromatic herbs using EfficientNet CNN through the transfer learning technique
Improved copy-move forgery detection through multilevel clustering
Get PDFCopy move forgery detection (CMFD) based on keypoints remains a widely used technique; however, it often struggles to effectively identify small and smoothly tampered regions within images. This paper introduces a CMFD method that enhances detection accuracy by integrating a double-matching process with advanced region localization techniques. Delaunay triangles formed by accelerated KAZE (AKAZE) and scale-invariant feature transform (SIFT) features are matched in the double-matching process to identify suspicious regions. To ensure sufficient keypoint pairs, the set of matching triangles is iteratively expanded to include neighboring triangles, covering the entire tampered area. Subsequently, a second matching with a looser threshold is performed on the vertices. In the region localization process, the multilevel density-based spatial clustering of applications with noise (DBSCAN) effectively handles scenarios involving multiple copied regions with varying sizes. Using the standard MICC-F600 and COVERAGE datasets, experiments demonstrate that the proposed CMFD method is robust and achieves better performance than state-of-the-art baselines.
Arithmetic artificial bee colony optimization algorithm with flexible manipulator system
Get PDFThe artificial bee colony (ABC) algorithm, a well-known swarm intelligence-based metaheuristic inspired by the food foraging behavior of honeybees, has been widely applied to solve complex optimization problems. Despite its effectiveness, the standard ABC algorithm suffers from drawbacks such as slow convergence rates, limited balance between exploration and exploitation, and a tendency to get stuck in local optima, thereby hindering its overall performance. This study introduces an enhanced variant of the ABC algorithm, integrating the exploration strategy of the arithmetic optimization algorithm (AOA) to overcome these limitations. The enhanced algorithm is thoroughly tested on a set of benchmark functions as well as a flexible manipulator system model. Comprehensive statistical analyses are employed to evaluate and compare the performance of the improved algorithm against the original ABC. The results demonstrate that the enhanced ABC algorithm delivers superior performance in both benchmark scenarios and the flexible manipulator application
Explainable artificial intelligence with anchors method for breast cancer treatment recommendation
Get PDFIn the search of precision medicine for breast cancer, the integration of artificial intelligence (AI) offers unprecedented opportunities to improve diagnosis, prognosis, and treatment strategies. This paper discovers the prospective of explainable artificial intelligence (XAI) to demystify the black-box landscape of AI, fostering both transparency and trust. We introduce an XAI-based approach, anchored by the anchors explanation method, to provide interpretable predictions for breast cancer treatment. Our results demonstrate that while anchors improve the interpretability of model predictions, the precision and coverage of these explanations vary, highlighting the challenges of achieving high-fidelity explanations in complex clinical scenarios. Our findings underscore the importance of balancing the trade-off between model complexity and explainability. They advocate for the iterative development of AI systems with iterative feedback loops from clinicians to align the model's logic with clinical reasoning. We propose a framework for the clinical deployment of XAI in breast cancer. Ultimately, XAI, equipped with techniques like Anchors, holds the promise of enhancing precision medicine by making AI-assisted decisions more transparent and trustworthy, empowering clinicians and enabling patients to engage in informed discussions about their treatment options. However, anchors lag in the accuracy of rules and remains a challenge to the AI developers
Combining convolutional operators in unsupervised networks for kidney abnormalities
Get PDFDeep learning plays a pivotal role in advancing the diagnosis of renal dysfunction, achieving performance levels comparable to those of medical experts. However, disease domain variations and model differences can impact learning quality. To address renal dysfunction, we propose dual stream convolutional (DSC) and dual-input convolutional (DIC) for unsupervised learning. The proposed network is designed to process multi scale data and employs parallel data aggregation to enhance learning capabilities, improving the reliability of the experimental results. DSC achieved training losses of 0.0069, 0.0056, 0.0042, and 0.0048 for normal, cyst, stone, and tumor datasets, respectively, while DIC achieved losses of 0.0066, 0.0063, 0.0044, and 0.0058 for the same categories. The experimental results demonstrate that our proposed models outperform state of-the-art approaches, making them well-suited for broad application in clinical research studies
Computer vision syndrome prevention: detection of expression and eye distance with monitor screens
Get PDFComputer vision syndrome (CVS) is a vision-related complaint caused by computer usage. CVS can be analyzed through facial expressions detected by a camera. Expression detection is categorized into two groups: safe and dangerous. The safe category comprises happy, neutral, disgusted, sad, angry, and surprised, while the dangerous category includes sad and fearful emotions. This division is based on the similarity of CVS symptoms to facial emotion characteristics. Additionally, an additional feature is implemented to detect the distance between the screen and the user's eyes using the FaceMeshModule to prevent the user's eyes from getting too close to the screen. Both detections will provide warning notifications when a dangerous category expression is detected ≥70% every minute, and when the distance between the screen and the eyes is ≤40 cm. Notifications in this program use the Tkinter library as a graphical user interface (GUI) message box. In this research, facial expressions are detected using the CascadeClassifier for face detection and the extreme inception (Xception) as the facial expression classifier. The results of expression detection achieved an accuracy of 94%, an F1-score of 94%, precision of 95%, and recall of 94%
Enhancing academic conferences with AI: defining the role of the human AI editor
Get PDFAcademic conferences serve as key platforms for knowledge exchange, yet they face challenges in managing large volumes of content efficiently while maintaining academic rigor. To address these challenges, this study introduces and evaluates the "AI editor": a novel human expert role who, using tools like ChatGPT, supervises, refines, and structures artificial intelligence (AI)-generated content in real time. Through a mixed-methods approach, we examine the role of AI in enhancing content creation and engagement. This approach included the experimental deployment of the AI editor in three sustainability-focused European academic conferences (in Spain and UK) and formative workshops with 127 university students from the same countries. While AI-assisted tools improve efficiency, concerns persist regarding traceability, reliability, and ethical oversight. Our findings indicate that AI by itself cannot guarantee scholarly integrity; continuous human oversight is indispensable. The AI editor ensures coherence, quality control, and compliance with academic standards, addressing a critical gap in AI adoption within research environments. This study contributes to the discourse on responsible AI use in academia by proposing a structured framework for its integration into conferences, balancing automation with human oversight. Moreover, it highlights the growing need for digital intelligence that enables researchers to interact ethically and effectively with AI and other digital technologies, fostering responsible and informed academic innovation
Abstractive summarization using multilingual text-to-text transfer transformer for the Turkish text
Get PDFToday, with the increase in text data, the application of automatic techniques such as automatic text summarization, which is one of the most critical natural language processing (NLP) tasks, has attracted even more attention and led to more research in this area. Nowadays, with the developments in deep learning, pre-trained sequence-to-sequence (text-to-text transfer converter (T5) and bidirectional encoder representations from transformers (BERT) algorithm) encoder-decoder models are used to obtain the most advanced results. However, most of the studies were done in the English language. With the help of the recently emerging monolingual BERT model and multilingual pre-trained sequence-to-sequence models, it has led to the use of state-of-the-art models in languages with fewer resources and studies, such as Turkish. This article used two datasets for Turkish text summarization. First, Google multilingual text-to-text transfer transformer (mT5)-small model was applied on multilingual summarization (MLSUM), which is a large-scale Turkish news dataset, and success was examined. Then, success was evaluated by first applying BERT extractive summarization and then abstractive summarization on 1010 articles collected on the Dergipark site. Rouge measures were used for performance evaluation. This study is one of the first examples in the Turkish language and it is considered to provide a basis for future studies with good results