H.3.7. Learning
Malihe Danesh; Zahra Ahmadi
Abstract
In recent years, sign language recognition has emerged as a major challenge in the fields of image processing and machine learning. People with hearing impairments use sign language to communicate, but the lack of automated tools to translate it has created significant communication barriers. This study ...
Read More
In recent years, sign language recognition has emerged as a major challenge in the fields of image processing and machine learning. People with hearing impairments use sign language to communicate, but the lack of automated tools to translate it has created significant communication barriers. This study presents a hybrid model based on convolutional neural networks (CNNs), transformers, and hidden Markov models (HMMs) to accurately recognize sign language gestures using the MNIST sign language dataset. The model first extracts image features from handwritten images using CNNs and then feeds these features into the Transformer model to process complex and long-term dependencies in the feature sequence. In the next step, to smooth the predictions and improve accuracy, a hidden Markov model is employed, which adjusts the final predictions based on previous sequences. The results show that the proposed model utilizing HMM achieves an accuracy of 99% and a sign error rate of 0.0098, demonstrating its high efficiency in recognizing hand gestures. This research represents an important step toward developing assistive devices for the deaf and enhancing human interaction.
H.6. Pattern Recognition
Samira Mavaddati
Abstract
Brain tumors are among the most life-threatening neurological conditions, requiring precise and early diagnosis for effective treatment planning. Traditional deep learning models, such as Convolutional Neural Networks (CNNs) and ResNet-based architectures, have demonstrated promising results in brain ...
Read More
Brain tumors are among the most life-threatening neurological conditions, requiring precise and early diagnosis for effective treatment planning. Traditional deep learning models, such as Convolutional Neural Networks (CNNs) and ResNet-based architectures, have demonstrated promising results in brain tumor classification. However, these models often struggle to capture long-range dependencies within MRI images, which are crucial for accurate classification. To overcome this limitation, we propose a Hybrid CNN-ViT model, combining the strengths of Vision Transformers (ViT) and CNNs to achieve high-precision brain tumor classification. The CNN component effectively extracts local spatial features, while the ViT module captures global contextual relationships within MRI scans. The model is evaluated on a four-class dataset of Glioma, Meningioma, Pituitary tumors, and non-tumor images, achieving an impressive accuracy of 98.37%, surpassing conventional CNN-based methods. By leveraging transfer learning, the approach enhances classification performance while reducing reliance on large-scale labeled datasets. The proposed Hybrid CNN-ViT model offers a scalable, robust, and efficient solution for real-world neuro-oncological diagnostics, significantly improving the accuracy of MRI-based brain tumor detection.
H.3. Artificial Intelligence
Thomas Njoroge Kinyanjui; Kelvin Mugoye; Rachael Kibuku
Abstract
This paper presents a Multi-Head Self-Attention Fusion Network (MHSA-FN) for real-time crop disease classification, addressing key limitations in existing models, including suboptimal feature extraction, inefficient feature recalibration, and weak multi-scale fusion. Unlike prior works that rely solely ...
Read More
This paper presents a Multi-Head Self-Attention Fusion Network (MHSA-FN) for real-time crop disease classification, addressing key limitations in existing models, including suboptimal feature extraction, inefficient feature recalibration, and weak multi-scale fusion. Unlike prior works that rely solely on CNNs or transformers, MHSA-FN integrates MobileNetV2, EfficientNetV2, and Vision Transformers (ViTs) with a structured multi-level attention framework for enhanced feature learning. A gated fusion mechanism and a Multiscale Fusion Module (MSFM) optimize local texture details and global spatial relationships. The model was trained on a combined dataset of PlantVillage and locally collected images, improving adaptability to real-world conditions. It achieved 98.66% training accuracy and 99.0% test accuracy across 76 disease classes, with 99.34% precision, 99.01% recall, and 99.04% F1 score. McNemar’s test (p = 0.125) and Bayesian superiority probability (0.851) validated its robustness. Confidence variance analysis (0.000010) outperformed existing models, demonstrating MHSA-FN as a scalable, high-performance AI solution for precision agriculture in resource-constrained environments.
H. Sarabi Sarvarani; F. Abdali-Mohammadi
Abstract
Bone age assessment is a method that is constantly used for investigating growth abnormalities, endocrine gland treatment, and pediatric syndromes. Since the advent of digital imaging, for several decades the bone age assessment has been performed by visually examining the ossification of the left hand, ...
Read More
Bone age assessment is a method that is constantly used for investigating growth abnormalities, endocrine gland treatment, and pediatric syndromes. Since the advent of digital imaging, for several decades the bone age assessment has been performed by visually examining the ossification of the left hand, usually using the G&P reference method. However, the subjective nature of hand-craft methods, the large number of ossification centers in the hand, and the huge changes in ossification stages lead to some difficulties in the evaluation of the bone age. Therefore, many efforts were made to develop image processing methods. These methods automatically extract the main features of the bone formation stages to effectively and more accurately assess the bone age. In this paper, a new fully automatic method is proposed to reduce the errors of subjective methods and improve the automatic methods of age estimation. This model was applied to 1400 radiographs of healthy children from 0 to 18 years of age and gathered from 4 continents. This method starts with the extraction of all regions of the hand, the five fingers and the wrist, and independently calculates the age of each region through examination of the joints and growth regions associated with these regions by CNN networks; It ends with the final age assessment through an ensemble of CNNs. The results indicated that the proposed method has an average assessment accuracy of 81% and has a better performance in comparison to the commercial system that is currently in use.
H.3. Artificial Intelligence
M. Kurmanji; F. Ghaderi
Abstract
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement ...
Read More
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total frames of a video. So far, both 2D and 3D convolutional neural networks have been used to manipulate the temporal dynamics of the video frames. 3D CNNs can extract the changes in the consecutive frames and tend to be more suitable for the video classification task, however, they usually need more time. On the other hand, by using techniques like tiling it is possible to aggregate all the frames in a single matrix and preserve the temporal and spatial features. This way, using 2D CNNs, which are inherently simpler than 3D CNNs can be used to classify the video instances. In this paper, we compared the application of 2D and 3D CNNs for representing temporal features and classifying hand gesture sequences. Additionally, providing a two-stage two-stream architecture, we efficiently combined color and depth modalities and 2D and 3D CNN predictions. The effect of different types of augmentation techniques is also investigated. Our results confirm that appropriate usage of 2D CNNs outperforms a 3D CNN implementation in this task.
