Search Results (99)

Fused deposition modeling (FDM), a method of additive manufacturing (AM), comprises the extrusion of materials via a nozzle and the subsequent combining of the layers to create 3D-printed objects. FDM is a widely used method for 3D-printing objects since it is affordable, effective, and easy to use. Some defects such as poor infill, elephant foot, layer shift, and poor surface finish arise in the FDM components at the printing stage due to variations in printing parameters such as printing speed, change in nozzle, or bed temperature. Proper fault classification is required to identify the cause of faulty products. In this work, the multi-sensory data are gathered using different sensors such as vibration, current, temperature, and sound sensors. The data acquisition is performed by using the National Instrumentation (NI) Data Acquisition System (DAQ) which provides the synchronous multi-sensory data for the model training. To induce the faults, the data are captured under different conditions such as variations in printing speed, temperate, and jerk during the printing. The collected data are used to train the machine learning (ML) and deep learning (DL) classification models to classify the variation in printing parameters. The ML models such as k-nearest neighbor (KNN), decision tree (DT), extra trees (ET), and random forest (RF) with convolutional neural network (CNN) as a DL model are used to classify the variable operation printing parameters. Out of the available models, in ML models, the RF classifier shows a classification accuracy of around 91% whereas, in the DL model, the CNN model shows good classification performance with accuracy ranging from 92 to 94% under variable operating conditions. Full article

The risk posed by expansive soils can be lessened by placing foundations at a more deep level below the surface. Structures are able to withstand uplift forces because overburden pressure partially suppresses swelling pressure. In order to transfer the forces to a sufficiently deep depth, this study suggests introducing shafts of a low-expansion overburden material. Soil improved with cement is chosen for this purpose. This study suggests using sand with added excavated natural clay and cement. The expansive clay is added to sand in ratios of 10, 20, 30, 40 and 60%. The clay–sand mixture is then enhanced by cement of 1, 2, 4 and 8% by the weight of the mixture under four curing periods of 1, 7, 28, and 90 days. This material is recommended for use under lean concrete to transfer the loads to lower levels below the foundation depth. The thickness of this material depends on the stresses exerted, the type and the properties of the subsurface soils. The cement-enhanced clay–sand shaft’s properties are examined in this work with regard to the swelling potential, compressibility, and the unconfined compressive strength for different clay contents and curing conditions. Stiff shafts were formed and found to support stresses from 600 to 3500 kPa at cement additions in the range of 1% to 8%. Clay content above 30% is found to be not suitable for Al-Qatif clay due to the compressibility and low strength of the mixture. When two percent or more of cement is added, the swelling potential is significantly reduced. This is reliant on the pozzolanic interactions of soils and cement as well as the clay mineralogy. Determining how cement affects clay–sand combinations in regions with expansive soils would facilitate the introduction of a novel, inexpensive technology to support loads applied by the superstructure. Full article

Receiving uninterrupted videos from a scene with multiple cameras is a challenging task. One of the issues that significantly affects this task is called occlusion. In this paper, we propose an algorithm for occlusion handling in multi-camera systems. The proposed algorithm, which is called Real-time leader finder (Releaf), leverages mechanism design to assign leader and follower roles to each of the cameras in a multi-camera setup. We assign leader and follower roles to the cameras and lead the motion by the camera with the least occluded view using the Stackelberg equilibrium. The proposed approach is evaluated on our previously open-sourced tendon-driven 3D-printed robotic eye that tracks the face of a human subject. Experimental results demonstrate the superiority of the proposed algorithm over the Q-leaning and Deep Q Networks (DQN) baselines, achieving an improvement of $20\%$ and $18\%$ for horizontal errors and an enhancement of $81\%$ for vertical errors, as measured by the root mean squared error metric. Furthermore, Releaf has the superiority of real-time performance, which removes the need for training and makes it a promising approach for occlusion handling in multi-camera systems. Full article

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors, and complexity of character interactions. Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy. To address the dataset complexity and multi-targeting problems, feature extraction is optimized, and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of the YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students—raising their hands, reading, writing, playing on their cell phones, looking down, and leaning on the table—in high-definition images. And the accuracy and robustness of this network is verified. Compared with small-object detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network demonstrates good detection performance on low-resolution small objects, complex datasets with numerous targets, occlusion, and overlapping students. Full article

Grain size analysis is used to study grain size and distribution. It is a critical indicator in sedimentary simulation experiments (SSEs), which aids in understanding hydrodynamic conditions and identifying the features of sedimentary environments. Existing methods for grain size analysis based on images primarily focus on scenarios where grain edges are distinct or grain arrangements are regular. However, these methods are not suitable for images from SSEs. We proposed a deep learning model incorporating histogram layers for the analysis of SSE images with fuzzy grain edges and irregular arrangements. Firstly, ResNet18 was used to extract features from SSE images. These features were then input into the histogram layer to obtain local histogram features, which were concatenated to form comprehensive histogram features for the entire image. Finally, the histogram features were connected to a fully connected layer to estimate the grain size corresponding to the cumulative volume percentage. In addition, an applied workflow was developed. The results demonstrate that the proposed method achieved higher accuracy than the eight other models and was highly consistent with manual results in practice. The proposed method enhances the efficiency and accuracy of grain size analysis for images with irregular grain distribution and improves the quantification and automation of grain size analysis in SSEs. It can also be applied for grain size analysis in fields such as soil and geotechnical engineering. Full article

Pork belly, prized for its unique flavor and texture, is often overlooked in breeding programs that prioritize lean meat production. The quality of pork belly is determined by the number and distribution of muscle and fat layers. This study aimed to assess the number of pork belly layers using deep learning techniques. Initially, semantic segmentation was considered, but the intersection over union (IoU) scores for the segmented parts were below 70%, which is insufficient for practical application. Consequently, the focus shifted to image classification methods. Based on the number of fat and muscle layers, a dataset was categorized into three groups: three layers (n = 1811), five layers (n = 1294), and seven layers (n = 879). Drawing upon established model architectures, the initial model was refined for the task of learning and predicting layer traits from B-ultrasound images of pork belly. After a thorough evaluation of various performance metrics, the ResNet18 model emerged as the most effective, achieving a remarkable training set accuracy of 99.99% and a validation set accuracy of 96.22%, with corresponding loss values of 0.1478 and 0.1976. The robustness of the model was confirmed through three interpretable analysis methods, including grad-CAM, ensuring its reliability. Furthermore, the model was successfully deployed in a local setting to process B-ultrasound video frames in real time, consistently identifying the pork belly layer count with a confidence level exceeding 70%. By employing a scoring system with 100 points as the threshold, the number of pork belly layers in vivo was categorized into superior and inferior grades. This innovative system offers immediate decision-making support for breeding determinations and presents a highly efficient and precise method for assessment of pork belly layers. Full article

The paper “Using Absorption Models for Insulin and Carbohydrates and Deep Leaning to Improve Glucose Level Predictions” (Sensors 2021, 21, 5273) proposes a novel approach to predicting blood glucose levels for people with type 1 diabetes mellitus (T1DM). By building exponential models from raw carbohydrate and insulin data to simulate the absorption in the body, the authors reported a reduction in their model’s root-mean-square error (RMSE) from $15.5$ mg/dL (raw) to $9.2$ mg/dL (exponential) when predicting blood glucose levels one hour into the future. In this comment, we demonstrate that the experimental techniques used in that paper are flawed, which invalidates its results and conclusions. Specifically, after reviewing the authors’ code, we found that the model validation scheme was malformed, namely, the training and test data from the same time intervals were mixed. This means that the reported RMSE numbers in the referenced paper did not accurately measure the predictive capabilities of the approaches that were presented. We repaired the measurement technique by appropriately isolating the training and test data, and we discovered that their models actually performed dramatically worse than was reported in the paper. In fact, the models presented in the that paper do not appear to perform any better than a naive model that predicts future glucose levels to be the same as the current ones. Full article

Integrating carbon capture and storage (CCS) technology into an integrated energy system (IES) can reduce its carbon emissions and enhance its low-carbon performance. However, the full CCS of flue gas displays a strong coupling between lean and rich liquor as carbon dioxide liquid absorbents. Its integration into IESs with a high penetration level of renewables results in insufficient flexibility and renewable curtailment. In addition, integrating split-flow CCS of flue gas facilitates a short capture time, giving priority to renewable energy. To address these limitations, this paper develops a carbon capture, utilization, and storage (CCUS) method, into which storage tanks for lean and rich liquor and a two-stage power-to-gas (P2G) system with multiple utilizations of hydrogen including a fuel cell and a hydrogen-blended CHP unit are introduced. The CCUS is integrated into an IES to build an electricity–heat–hydrogen–gas IES. Accordingly, a deep low-carbon economic optimization strategy for this IES, which considers stepwise carbon trading, coal consumption, renewable curtailment penalties, and gas purchasing costs, is proposed. The effects of CCUS, the two-stage P2G system, and stepwise carbon trading on the performance of this IES are analyzed through a case-comparative analysis. The results show that the proposed method allows for a significant reduction in both carbon emissions and total operational costs. It outperforms the IES without CCUS with an 8.8% cost reduction and a 70.11% reduction in carbon emissions. Compared to the IES integrating full CCS, the proposed method yields reductions of 6.5% in costs and 24.7% in emissions. Furthermore, the addition of a two-stage P2G system with multiple utilizations of hydrogen further amplifies these benefits, cutting costs by 13.97% and emissions by 12.32%. In addition, integrating CCUS into IESs enables the full consumption of renewables and expands hydrogen utilization, and the renewable consumption proportion in IESs can reach 69.23%. Full article

Despite their high prediction accuracy, deep learning-based soft sensor (DLSS) models face challenges related to adversarial robustness against malicious adversarial attacks, which hinder their widespread deployment and safe application. Although adversarial training is the primary method for enhancing adversarial robustness, existing adversarial-training-based defense methods often struggle with accurately estimating transfer gradients and avoiding adversarial robust overfitting. To address these issues, we propose a novel adversarial training approach, namely domain-adaptive adversarial training (DAAT). DAAT comprises two stages: historical gradient-based adversarial attack (HGAA) and domain-adaptive training. In the first stage, HGAA incorporates historical gradient information into the iterative process of generating adversarial samples. It considers gradient similarity between iterative steps to stabilize the updating direction, resulting in improved transfer gradient estimation and stronger adversarial samples. In the second stage, a soft sensor domain-adaptive training model is developed to learn common features from adversarial and original samples through domain-adaptive training, thereby avoiding excessive leaning toward either side and enhancing the adversarial robustness of DLSS without robust overfitting. To demonstrate the effectiveness of DAAT, a DLSS model for crystal quality variables in silicon single-crystal growth manufacturing processes is used as a case study. Through DAAT, the DLSS achieves a balance between defense against adversarial samples and prediction accuracy on normal samples to some extent, offering an effective approach for enhancing the adversarial robustness of DLSS. Full article

Artificial Intelligence (AI) is revolutionising many aspects of radiotherapy (RT), opening scenarios that were unimaginable just a few years ago. The aim of this study is to propose a Deep Leaning (DL) approach able to quickly generate synthetic Computed Tomography (CT) images from low-dose Cone Beam CT (CBCT) acquired on a modern linear accelerator integrating AI. Methods: A total of 53 patients treated in the pelvic region were enrolled and split into training (30), validation (9), and testing (14). A Generative Adversarial Network (GAN) was trained for 200 epochs. The image accuracy was evaluated by calculating the mean and mean absolute error (ME and ME) between sCT and CT. RT treatment plans were calculated on CT and sCT images, and dose accuracy was evaluated considering Dose Volume Histogram (DVH) and gamma analysis. Results: A total of 4507 images were selected for training. The MAE and ME values in the test set were 36 ± 6 HU and 7 ± 6 HU, respectively. Mean gamma passing rates for 1%/1 mm, 2%/2 mm, and 3%/3 mm tolerance criteria were respectively 93.5 ± 3.4%, 98.0 ± 1.3%, and 99.2 ± 0.7%, with no difference between curative and palliative cases. All the DVH parameters analysed were within 1 Gy of the difference between sCT and CT. Conclusion: This study demonstrated that sCT generation using the DL approach is feasible on low-dose CBCT images. The proposed approach can represent a valid tool to speed up the online adaptive procedure and remove CT simulation from the RT workflow. Full article

The development of predictive approaches to estimate supplier delivery risks has become vital for companies that rely heavily on outsourcing practices and lean management strategies in the era of the shortage economy. However, the literature that presents studies proposing the development of such approaches is still in its infancy, and several gaps have been found. In particular, most of the current studies present approaches that can only estimate whether suppliers will be late or not. Moreover, even if autocorrelation in data has been widely considered in demand forecasting, it has been neglected in supplier delivery risk predictions. Finally, current approaches struggle to consider macroeconomic data as input and rely mostly on machine learning models, while deep learning ones have rarely been investigated. The main contribution of this study is thus to propose a new approach that for the first time simultaneously adopts a deep learning model able to capture autocorrelation in data and integrates several macroeconomic indicators as input. Furthermore, as a second contribution, the performance of the proposed approach has been investigated in a real automotive case study and compared with those studies resulting from approaches that adopt traditional statistical models and models that do not consider macroeconomic indicators as additional inputs. The results highlight the capabilities of the proposed approach to provide good forecasts and outperform benchmarks for most of the considered predictions. Furthermore, the results provide evidence of the importance of considering macroeconomic indicators as additional input. Full article

Leakage in water supply pipelines remains a significant challenge. It leads to resource and economic waste. Researchers have developed several leak detection methods, including the use of embedded sensors and pressure prediction. The former approach involves pre-installing detectors inside pipelines to detect leaks. This method allows for the precise localization of leak points. The stability is compromised because of the wireless signal strength. The latter approach, which relies on pressure measurements to predict leak events, does not achieve precise leak point localization. To address these challenges, in this paper, a coherent optical time-domain reflectometry (φ-OTDR) system is employed to capture vibration signal phase information. Subsequently, two pre-trained neural network models based on CNN and Resnet18 are responsible for processing this information to accurately identify vibration events. In an experimental setup simulating water pipelines, phase information from both leaking and non-leaking pipe segments is collected. Using this dataset, classical CNN and ResNet18 models are trained, achieving accuracy rates of 99.7% and 99.5%, respectively. The multi-leakage point experiment results indicate that the Resnet18 model has better generalization compared to the CNN model. The proposed solution enables long-distance water-pipeline precise leak point localization and accurate vibration event identification. Full article

X-ray photoelectron spectroscopy (XPS) remains a fundamental technique in materials science, offering invaluable insights into the chemical states and electronic structure of a material. However, the interpretation of XPS spectra can be complex, requiring deep expertise and often sophisticated curve-fitting methods. In this study, we present a novel approach to the analysis of XPS data, integrating the utilization of large language models (LLMs), specifically OpenAI’s GPT-3.5/4 Turbo to provide insightful guidance during the data analysis process. Working in the framework of the CIRCE-NAPP beamline at the CELLS ALBA Synchrotron facility where data are obtained using ambient pressure X-ray photoelectron spectroscopy (APXPS), we implement robust curve-fitting techniques on APXPS spectra, highlighting complex cases including overlapping peaks, diverse chemical states, and noise presence. Post curve fitting, we engage the LLM to facilitate the interpretation of the fitted parameters, leaning on its extensive training data to simulate an interaction corresponding to expert consultation. The manuscript presents also a real use case utilizing GPT-4 and Meta’s LLaMA-2 and describes the integration of the functionality into the TANGO control system. Our methodology not only offers a fresh perspective on XPS data analysis, but also introduces a new dimension of artificial intelligence (AI) integration into scientific research. It showcases the power of LLMs in enhancing the interpretative process, particularly in scenarios wherein expert knowledge may not be immediately available. Despite the inherent limitations of LLMs, their potential in the realm of materials science research is promising, opening doors to a future wherein AI assists in the transformation of raw data into meaningful scientific knowledge. Full article

Furniture production is a specific industrial sector with a high human labor demand, a wide range of materials processed, and short production runs caused by high customization of end products. The difficulty of measuring the aesthetic requirements of customers is also specific to furniture. This review of academic papers identifies and explains effective quality management strategies in furniture production. The reviewed literature highlights a range of quality management methodologies, including concurrent engineering (CE), total quality management (TQM), lean manufacturing, lean six sigma, and kaizen. These strategies encompass a variety of pro-quality tools, such as 5S, statistical process control (SPC), quality function deployment (QFD), and failure mode and effects analysis (FMEA). The strengths of these quality management strategies lie in their ability to enhance efficiency, reduce waste, increase product diversity, and improve product quality. However, the weaknesses concern implementation challenges and the need for culture change within organizations. Successful quality management in furniture production requires tailoring strategies to the specific context of the furniture production industry. Additionally, the importance of sustainability in the furniture industry is emphasized, which entails incorporating circular economy principles and resource-efficient practices. The most important finding from the literature analysis is that early detection and correction of poor quality yields the most beneficial outcomes for the manufacturer. Therefore, it is essential to strengthen the rigor of quality testing and analysis during the early stages of product development. Consequently, a deep understanding of consumer perspectives on required furniture quality is crucial. The review identified two research gaps: (1) the impact of unnecessary product over-quality on the efficiency of furniture production and (2) the influence of replacing CAD drawings with a model-based definition (MBD) format on quality management in furniture production. Full article

A flame’s structural feature is a crucial parameter required to comprehensively understand the interaction between turbulence and flames. The generation and evolution processes of the structure feature have rarely been investigated in lean blowout (LBO) flame instability states. Hence, to understand the precursor features of the LBO flame, this work employed high-speed OH-PLIF measurements to acquire time-series LBO flame images and developed a novel feature extraction method based on a deep neural network to quantify the LBO features in real time. Meanwhile, we proposed a deep neural network segmentation method based on a tri-map called the Fire-MatteFormer, and conducted a statistical analysis on flame surface features, primarily holes. The statistical analysis results determined the relationship between the life cycle of holes (from generation to disappearance) and their area, perimeter, and total number. The trained Fire-MatteFormer model was found to represent a viable method for determining flame features in the detection of incipient LBO instability conditions. Overall, the model shows significant promise in ascertaining local flame structure features. Full article