We propose efficient multiple machine learning (ML) models using specifically polynomial and logistic regression ML methods to predict the optimal design of proton exchange membrane (PEM) electrolyzer cells. The models predict eleven different parameters of the cell components for four different input parameters such as hydrogen production rate, cathode area, anode area, and the type of cell design (e.g., single or bipolar). The models fit well as we trained multiple machine learning models on 148 samples and validated the model performance on a test set of 16 samples. The average accuracy of the classification model and the mean absolute error is 83.6% and 6.825, respectively, which indicates that the proposed technique performs very well. We also measured the hydrogen production rate using a custom-made PEM electrolyzer cell fabricated based on the predicted parameters and compared it to the simulation result. Both results are in excellent agreement and within a negligible experimental uncertainty (i.e., a mean absolute error of 0.615). Finally, optimal PEM electrolyzer cells for commercial-scaled hydrogen production rates ranging from 500 to 5000 mL/min were designed using the machine learning models. To the best of our knowledge, we are the first group to model the PEM design problem with such large parameter predictions using machine learning with those specific input parameters. This study opens the route for providing a form of technology that can greatly save the cost and time required to develop water electrolyzer cells for future hydrogen production.

The latest research in computer vision highlighted the effectiveness of the vision transformers (ViT) in performing several computer vision tasks; they can efficiently understand and process the image globally unlike the convolution which processes the image locally. ViTs outperform the convolutional neural networks in terms of accuracy in many computer vision tasks but the speed of ViTs is still an issue, due to the excessive use of the transformer layers that include many fully connected layers. Therefore, we propose a real-time ViT-based monocular depth estimation (depth estimation from single RGB image) method with encoder-decoder architectures for indoor and outdoor scenes. This main architecture of the proposed method consists of a vision transformer encoder and a convolutional neural network decoder. We started by training the base vision transformer (ViT-b16) with 12 transformer layers then we reduced the transformer layers to six layers, namely ViT-s16 (the Small ViT) and four layers, namely ViT-t16 (the Tiny ViT) to obtain real-time processing. We also try four different configurations of the CNN decoder network. The proposed architectures can learn the task of depth estimation efficiently and can produce more accurate depth predictions than the fully convolutional-based methods taking advantage of the multi-head self-attention module. We train the proposed encoder-decoder architecture end-to-end on the challenging NYU-depthV2 and CITYSCAPES benchmarks then we evaluate the trained models on the validation and test sets of the same benchmarks showing that it outperforms many state-of-the-art methods on depth estimation while performing the task in real-time (∼20 fps). We also present a fast 3D reconstruction (∼17 fps) experiment based on the depth estimated from our method which is considered a real-world application of our method.

We propose a high-speed convolutional neural network approach for weakly supervised localization (WSL) and weakly supervised object detection (WSOD). The proposed method, called center-of-features localization (COFL), performs localization of objects in a visual scene by combining both multi-label classification and regression for the number of instances of each class object. A modified Xception network architecture is used as the main feature extractor, and a classification-plus-regression loss function is used to perform the detection task. The method does not require bounding box annotations but only image labels and counts of the objects of each class in the image. This combination can produce a clear localization of objects in the scene through a masking technique between class activation maps (CAMs) and regression activation maps (RAMs). The proposed method was trained and tested on the PASCAL VOC2007 and VOC2012 datasets; it attained a mean average precision (mAP) of 47.0% and a correct localization CorLoc of 64.1% on PASCAL VOC2007 and a mAP of 42.3% and a CorLoc of 65.5% on PASCAL VOC2012 while performing object detection at a speed of ~50 fps. These results demonstrate that the network can perform object detection accurately in real-time using only image labels and object counts, which are inexpensive to annotate compared with the bounding box annotations typically employed in fully supervised object detection methods. The network far outperforms other weakly supervised methods and some fully supervised methods in terms of processing time while achieving fair accuracy.

Although Light-Field (LF) technology attracts attention due to its large number of applications, especially with the introduction of consumer LF cameras and its frequent use, reconstructing densely sampled LF images represents a great challenge to the use and development of LF technology. Our paper proposes a learning-based method to reconstruct densely sampled LF images from a sparse set of input images. We trained our model with raw LF images rather than using multiple images of the same scene. Raw LF can represent the two-dimensional array of images captured in a single image. Therefore, it enables the network to understand and model the relationship between different images of the same scene well and thus restore more texture details and provide better quality. Using raw images has transformed the task from image reconstruction into image-to-image translation. The feature of small-baseline LF was used to define the images to be reconstructed using the nearest input view to initialize input images. Our network was trained end-to-end to minimize the sum of absolute errors between the reconstructed and ground-truth images. Experimental results on three challenging real-world datasets demonstrate the high performance of our proposed method and its outperformance over the state-of-the-art methods.