Jashila Nair Mogan

Generally, accurate gait analysis plays a vital role in assessing neurological disorders, human walking patterns, fall risk predictions, etc. In this work, a deep learning framework was implemented using three different deep learning models for gait phase detection. The dataset consists of 756 comma-separated value (CSV) files acquired by the Qualisys motion capture system and the Bertec instrumented treadmill. Further, these six kinematic signals with X, Y, and Z positional coordinates and Roll, Pitch, and Yaw rotational angles are utilized to train the models, namely Bidirectional Long-Short Term Memory (BiLSTM), Temporal Convolution Network (TCN) and Transformer Encoder (TE). Also, the performance of the proposed models was evaluated using standard performance metrics. TCN exhibited an accuracy of 96.24%, a precision of 96.33%, a recall of 96.24%, an F1-Score of 0.9623 and a Mean Absolute Error (MAE) of 0.3264, which was superior to other utilized models. In addition, the TE model exhibited moderate performance with an accuracy of 93.82% and a MAE of 0.4715. In contrast, the BiLSTM model performed the worst, with an accuracy of 92.94% and MAE of 0.4934. From this study, we can infer that the TCN model is highly suitable for gait classification, which offers high clinical and practical feasibility for the detection of gait phase using a Qualisys motion capture system and end-to-end learning approach.

The rapid growth of artificial intelligence (AI) has enabled efficient crop disease detection even in data-scarce agricultural settings. This study proposes AgriFewNet, a few-shot learning framework designed to improve classification accuracy using RGB imagery captured from publicly available datasets. The objective is to enable fast model adaptation to new disease classes using minimal labeled samples while maintaining high reliability in real-world conditions. AgriFewNet employs a hierarchical attention-enhanced ResNet-18 backbone incorporating dual spatial and channel attention to extract discriminative RGB features. A Model-Agnostic Meta-Learning (MAML) approach facilitates quick generalization to previously unexplored illness categories, while a prototype-based classifier guarantees compact representation learning. Using only RGB images, experiments on the PlantVillage and New PlantVillage datasets produced accuracies of 87.3% (1-shot), 94.8% (5-shot), and 97.1% (10-shot), surpassing leading few-shot baselines by as much as 7.9%. The findings show that AgriFewNet offers a resource-efficient and scalable method for intelligent crop monitoring, enhancing food security and precision agriculture.

Driver drowsiness and alcohol impairment are major causes of traffic accidents, making road safety a main concern. This study highlights the importance of addressing these issues through improved driver monitoring technologies. A prototype combining MQ-3 alcohol sensors, and facial detection was created, integrating with IoT via a Raspberry Pi to monitor and alert on drowsiness and alcohol levels. The developments use the NTHU-DDD dataset, which supports a supervised learning approach to develop a reliable drowsiness detection model. The study explored various machine learning algorithms such as Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), K-nearest neighbors (KNN), Gradient Boosting Classifier, and Gaussian Naive Bayes, with Random Forest and Gradient Boosting emerging as top performers, particularly suited to complex non-linear data. The system effectively used supervised learning techniques to differentiate drowsy and non-drowsy images and exhibited consistent accuracy in detecting drowsiness, especially when the driver’s face was centered. However, accuracy decreased when faces were tilted, highlighting areas for refinement. Moreover, the environmental tests on the MQ-3 sensor demonstrated its sensitivity to alcohol presence, even distinguishing the intensity based on beverage type and concentration. The findings underscore the efficacy of using sensor-based technologies in real-world conditions and provide a foundation for optimizing the system's detection capabilities across various scenarios.

Globally traffic accidents are influenced by factors such as drowsiness and alcohol consumption. Consequently, there has been a considerable focus on the development of detection systems as part of ongoing efforts to mitigate these risks. This review paper aims to offer a comprehensive analysis of various drowsiness and alcohol detection methods. The paper particularly emphasizes drowsiness and alcohol detection methods, including those centered on sensor-based approaches, physiological-based techniques, and visual analysis of the eye and mouth state. The aim is to evaluate their method, effectiveness and highlight recent advancements within this domain. Additionally, this review paper evaluates the research gaps of these detection methods, considering factors such as precision, sensitivity, specificity, and adaptability to different environmental conditions.

Individual deep learning models showcase impressive performance; however, the capacity of a single model might fall short in capturing the full spectrum of intricate patterns present in the input data. Thus, relying solely on a single model may hamper the attainment of optimal results and broader generalization. In light of this, the paper presents an ensemble method that leverages the strengths of multiple Convolutional Neural Networks (CNNs) and Transformer models to elevate gait recognition performance. Additionally, a novel gait representation named windowed Gait Energy Image (GEI) is introduced, obtained by averaging gait frames irrespective of gait cycles. Firstly, the windowed GEI is input to the Convolutional Neural Networks and Transformer models to learn significant gait features. Each model is followed by a Multilayer Perceptron (MLP) to encode the relationship between the extracted features and corresponding class labels. Subsequently, the extracted gait features from each model are flattened and concatenated into a cohesive feature representation before passing through another MLP for subject classification. The performance of the proposed method was assessed on three datasets: OU-ISIR dataset D, CASIA-B, and OU-LP dataset. Experimental results demonstrated remarkable improvements compared to existing methods across all three datasets. The proposed method achieved accuracy rates of 100% on OU-ISIR D, 99.93% on CASIA-B, and 99.94% on OU-LP, showcasing the superior performance of the Ensemble CNN-ViT model using feature-level fusion compared to state-of-the-art methods.

Gait recognition, the task of identifying an individual based on their unique walking style, can be difficult because walking styles can be influenced by external factors such as clothing, viewing angle, and carrying conditions. To address these challenges, this paper proposes a multi-model gait recognition system that integrates Convolutional Neural Networks (CNNs) and Vision Transformer. The first step in the process is to obtain a gait energy image, which is achieved by applying an averaging technique to a gait cycle. The gait energy image is then fed into three different models, DenseNet-201, VGG-16, and a Vision Transformer. These models are pre-trained and fine-tuned to encode the salient gait features that are specific to an individual’s walking style. Each model provides prediction scores for the classes based on the encoded features, and these scores are then summed and averaged to produce the final class label. The performance of this multi-model gait recognition system was evaluated on three datasets, CASIA-B, OU-ISIR dataset D, and OU-ISIR Large Population dataset. The experimental results showed substantial improvement compared to existing methods on all three datasets. The integration of CNNs and ViT allows the system to learn both the pre-defined and distinct features, providing a robust solution for gait recognition even under the influence of covariates.

Identifying an individual based on their physical/behavioral characteristics is known as biometric recognition. Gait is one of the most reliable biometrics due to its advantages, such as being perceivable at a long distance and difficult to replicate. The existing works mostly leverage Convolutional Neural Networks for gait recognition. The Convolutional Neural Networks perform well in image recognition tasks; however, they lack the attention mechanism to emphasize more on the significant regions of the image. The attention mechanism encodes information in the image patches, which facilitates the model to learn the substantial features in the specific regions. In light of this, this work employs the Vision Transformer (ViT) with an attention mechanism for gait recognition, referred to as Gait-ViT. In the proposed Gait-ViT, the gait energy image is first obtained by averaging the series of images over the gait cycle. The images are then split into patches and transformed into sequences by flattening and patch embedding. Position embedding, along with patch embedding, are applied on the sequence of patches to restore the positional information of the patches. Subsequently, the sequence of vectors is fed to the Transformer encoder to produce the final gait representation. As for the classification, the first element of the sequence is sent to the multi-layer perceptron to predict the class label. The proposed method obtained 99.93% on CASIA-B, 100% on OU-ISIR D and 99.51% on OU-LP, which exhibit the ability of the Vision Transformer model to outperform the state-of-the-art methods.

Identifying people’s identity by using behavioral biometrics has attracted many researchers’ attention in the biometrics industry. Gait is a behavioral trait, whereby an individual is identified based on their walking style. Over the years, gait recognition has been performed by using handcrafted approaches. However, due to several covariates’ effects, the competence of the approach has been compromised. Deep learning is an emerging algorithm in the biometrics field, which has the capability to tackle the covariates and produce highly accurate results. In this paper, a comprehensive overview of the existing deep learning-based gait recognition approach is presented. In addition, a summary of the performance of the approach on different gait datasets is provided.

Gait is a pattern of a person’s walking. The body movements of a person while walking makes the gait unique. Regardless of the uniqueness, the gait recognition process suffers under various factors, namely the viewing angle, carrying condition, and clothing. In this paper, a pre-trained VGG-16 model is incorporated with a multilayer perceptron to enhance the performance under various covariates. At first, the gait energy image is obtained by averaging the silhouettes over a gait cycle. Transfer learning and fine-tuning techniques are then applied on the pre-trained VGG-16 model to learn the gait features of the attained gait energy image. Subsequently, a multilayer perceptron is utilized to determine the relationship among the gait features and the corresponding subject. Lastly, the classification layer identifies the corresponding subject. Experiments are conducted to evaluate the performance of the proposed method on the CASIA-B dataset, the OU-ISIR dataset D, and the OU-ISIR large population dataset. The comparison with the state-of-the-art methods shows that the proposed method outperforms the methods on all the datasets.