Search Results (10,206)

Anomaly detection in industrial imaging is critical for ensuring quality and reliability in automated manufacturing processes. While recently several methods have been reported in the literature that have demonstrated impressive detection performance on standard benchmarks, they necessarily rely on computationally intensive CNN architectures and post-processing techniques, necessitating access to high-end GPU hardware and limiting practical deployment in resource-constrained settings. In this study, we introduce a novel anomaly detection framework that leverages feature maps from a lightweight convolutional neural network (CNN) backbone, MobileNetV2, and cascaded detection to achieve notable accuracy as well as computational efficiency. The core of our method consists of two main components. First is a PCA-based anomaly detection module that specifically exploits near-zero variance features. Contrary to traditional PCA methods, which tend to focus on the high-variance directions that encapsulate the dominant patterns in normal data, our approach demonstrates that the lower variance directions (which are typically ignored) form an approximate null space where normal samples project near zero. However, the anomalous samples, due to their inherent deviations from the norm, lead to projections with significantly higher magnitudes in this space. This insight not only enhances sensitivity to true anomalies but also reduces computational complexity by eliminating the need for operations such as matrix inversion or the calculation of Mahalanobis distances for correlated features otherwise needed when normal behavior is modeled as Gaussian distribution. Second, our framework consists of a cascaded multi-stage decision process. Instead of combining features across layers, we treat the local features extracted from each layer as independent stages within a cascade. This cascading mechanism not only simplifies the computations at each stage by quickly eliminating clear cases but also progressively refines the anomaly decision, leading to enhanced overall accuracy. Experimental evaluations on MVTec and VisA benchmark datasets demonstrate that our proposed approach achieves superior anomaly detection performance (99.4% and 91.7% AUROC respectively) while maintaining a lower computational overhead compared to other methods. This framework provides a compelling solution for practical anomaly detection challenges in diverse application domains where competitive accuracy is needed at the expense of minimal hardware resources. Full article

A principal factor of the fourth Industrial Revolution is the Internet of Things (IoT), a network of “smart” objects that communicate by exchanging helpful information about themselves and their environment. Our research aims to address the gaps in the existing literature regarding the educational and technological affordances of IoT applications in learning environments in secondary education. Our systematic review using the PRISMA method allowed us to extract 25 empirical studies from the last 10 years. We present the categorization of educational and technological affordances, as well as the devices used in these environments. Moreover, our findings indicate widespread adoption of organized educational activities and design-based learning, often incorporating tangible interfaces, smart objects, and IoT applications, which enhance student engagement and interaction. Additionally, we identify the impact of IoT-based learning on knowledge building, autonomous learning, student attitude, and motivation. The results suggest that the IoT can facilitate personalized and experiential learning, fostering a more immersive and adaptive educational experience. Based on these findings, we discuss key recommendations for educators, policymakers, and researchers, while also addressing this study’s limitations and potential directions for future research. Full article

This paper presents WaveCORAL-DCCA, an unsupervised domain adaptation (UDA) framework specifically developed to address data distribution shifts and operational variabilities (OVs) in rotor fault diagnosis. The framework introduces the novel integration of discrete wavelet transformation for robust time–frequency feature extraction and an enhanced deep canonical correlation analysis (DCCA) network with correlation alignment (CORAL) loss for superior domain-invariant representation learning. This combination enables more effective alignment of source and target feature distributions without requiring any labelled data from the target domain. Comprehensive validation on both experimental and numerically simulated rotor datasets across three health conditions—i.e., normal, unbalanced, and misaligned—demonstrates that WaveCORAL-DCCA achieves an average diagnostic accuracy of 95%. Notably, it outperforms established UDA benchmarks by at least 5–17% in cross-domain scenarios. These results confirm that WaveCORAL-DCCA provides robust generalisation across machines, fault severities, and operational conditions, even with scarce target domain samples, offering a scalable and practical solution for industrial rotor fault diagnosis. Full article

The growing need for rapid screening of adsorption energies in organic materials has driven substantial progress in developing various architectures of equivariant graph neural networks (eGNNs). This advancement has largely been enabled by the availability of extensive Density Functional Theory (DFT)-generated datasets, sufficiently large to train complex eGNN models effectively. However, certain material groups with significant industrial relevance, such as aromatic compounds, remain underrepresented in these large datasets. In this work, we aim to bridge the gap between limited, domain-specific DFT datasets and large-scale pretrained eGNNs. Our methodology involves creating a specialized dataset by segregating aromatic compounds after a targeted ensemble extraction process, then fine-tuning a pretrained model via approaches that include full retraining and systematically freezing specific network sections. We demonstrate that these approaches can yield accurate energy and force predictions with minimal domain-specific training data and computation. Additionally, we investigate the effects of augmenting training datasets with chemically related but out-of-domain groups. Our findings indicate that incorporating supplementary data that closely resembles the target domain, even if approximate, would enhance model performance on domain-specific tasks. Furthermore, we systematically freeze different sections of the pretrained models to elucidate the role each component plays during adaptation to new domains, revealing that relearning low-level representations is critical for effective domain transfer. Overall, this study contributes valuable insights and practical guidelines for efficiently adapting deep learning models for accurate adsorption energy predictions, significantly reducing reliance on extensive training datasets. Full article

In the era of Industry 5.0, future wireless networks are increasingly shifting from traditional symmetric architectures toward heterogeneous and asymmetric paradigms, driven by the demand for diversified and dynamic services. This architectural evolution gives rise to complex and asymmetric flows, such as the coexistence of periodic and burst flows with varying latency, jitter, and deadline constraints, posing new challenges for deterministic transmission. Traditional time-sensitive networking (TSN) is well-suited for periodic flows but lacks the flexibility to effectively handle dynamic, asymmetric traffi. To address this limitation, we propose a two-stage asymmetric flow scheduling framework with dynamic deadline control, termed A-TSN. In the first stage, we design a Deep Q-Network-based Dynamic Injection Time Slot algorithm (DQN-DITS) to optimize slot allocation for periodic flows under varying network loads. In the second stage, we introduce the Dynamic Deadline Online (DDO) scheduling algorithm, which enables real-time scheduling for asymmetric flows while satisfying flow deadlines and capacity constraints. Simulation results demonstrate that our approach significantly reduces end-to-end latency, improves scheduling efficiency, and enhances adaptability to high-volume asymmetric traffic, offering a scalable solution for future deterministic wireless networks. Full article

The original Modbus specification for RS-485 and RS-232 buses supported broadcast transmission. As the protocol evolved into Modbus-TCP, to use the TCP transport, this useful feature was lost, likely due to the point-to-point nature of TCP connections. Later proposals did not restore the broadcast transmission capability, although they used UDP as transport and UDP, by itself, would have supported it. Moreover, they did not address the inherent lack of reliable delivery of UDP, leaving datagram loss detection and recovery to the application layer. This paper describes a novel redesign of Modbus-UDP that addresses the aforementioned shortcomings. It achieves a mean round-trip time of only 38% with respect to Modbus-TCP and seamlessly supports a previously published protocol based on Modbus broadcast. In addition, the built-in retransmission of Modbus-UDP reacts more efficiently than the equivalent Modbus-TCP mechanism, exhibiting 50% of its round-trip standard deviation when subject to a 1% two-way IP datagram loss probability. Combined with the lower overhead of UDP versus TCP, this makes the redesigned Modbus-UDP protocol better suited for a variety of Industrial Internet of Things systems with limited computing and communication resources. Full article

Automatic component recognition plays a crucial role in intelligent ship manufacturing, but existing methods suffer from low recognition accuracy and high computational cost in industrial scenarios involving small samples, component stacking, and diverse categories. To address the requirements of shipbuilding industrial applications, a Triplet Spatial Reconstruction Attention (TSA) mechanism that combines threshold-based feature separation with triplet parallel processing is proposed, and a lightweight You Only Look Once Ship (YOLO-Ship) detection network is constructed. Unlike existing attention mechanisms that focus on either spatial reconstruction or channel attention independently, the proposed TSA integrates triplet parallel processing with spatial feature separation–reconstruction techniques to achieve enhanced target feature representation while significantly reducing parameter count and computational overhead. Experimental validation on a small-scale actual ship component dataset demonstrates that the improved network achieves 88.7% mean Average Precision (mAP), 84.2% precision, and 87.1% recall, representing improvements of 3.5%, 2.2%, and 3.8%, respectively, compared to the original YOLOv8n algorithm, requiring only 2.6 M parameters and 7.5 Giga Floating-point Operations per Second (GFLOPs) computational cost, achieving a good balance between detection accuracy and lightweight model design. Future research directions include developing adaptive threshold learning mechanisms for varying industrial conditions and integration with surface defect detection capabilities to enhance comprehensive quality control in intelligent manufacturing systems. Full article

The growing need to improve the management of end-of-life vehicle (ELV) waste and mitigate its environmental impact is a global concern. One promising approach to enhancing the recyclability of these vehicles is leveraging synergies between the automotive and construction industries as part of a circular economy strategy. In this context, ELV waste emerges as a valuable source of secondary raw materials, enabling the development of sustainable innovations that capitalize on its physical and mechanical properties. This paper aims to develop and evaluate construction industry composites incorporating waste from ELV carpets, with a focus on maintaining or enhancing performance compared to conventional materials. To achieve this, an experimental program was designed to assess cementitious composites, specifically subfloor mortars, incorporating automotive carpet waste (ACW). The results demonstrate that, beyond the physical and mechanical properties of the developed composites, the dynamic stiffness significantly improved across all tested waste incorporation levels. This finding highlights the potential of these composites as an alternative material for impact noise insulation in flooring systems. From an academic perspective, this research advances knowledge on the application of ACW in cement-based composites for construction. In terms of managerial contributions, two key market opportunities emerge: (1) the commercial exploitation of composites produced with ELV carpet waste and (2) the development of a network of environmental service providers to ensure a stable waste supply chain for innovative and sustainable products. Both strategies contribute to reducing landfill disposal and mitigating the environmental impact of ELV waste, reinforcing the principles of the circular economy. Full article

The increase in the number of wildfires in recent years in different parts of the world has caused growing concern among the population, since the consequences of these fires go beyond the destruction of the ecosystem. With the growing relevance of the Internet of Things (IoT) industry, developing solutions for the early detection of fires is of critical importance. This paper proposes a low-cost network based on Long-Range (LoRa) technology to autonomously assess the level of fire risk and the presence of a fire in rural areas. The system consists of several LoRa nodes with sensors to measure environmental variables such as temperature, humidity, carbon monoxide, air quality, and wind speed. The data collected is sent to a central gateway, where it is stored, processed, and later sent to a website for graphical visualization of the results. In this paper, a survey of the requirements of the devices and sensors that compose the system was made. After this survey, a market study of the available sensors was carried out, ending with a comparison between the sensors to determine which ones met the objectives. Using the chosen sensors, a study was made of possible power solutions for this prototype, considering the expected conditions of use. The system was tested in a real environment, and the results demonstrate that it is possible to cover a circular area with a radius of 2 km using a single gateway. Our system is prepared to trigger fire hazard alarms when, for example, the signals for relative humidity, ambient temperature, and wind speed are below or equal to 30%, above or equal to 30 °C, and above or equal to 30 m/s, respectively (commonly known as the 30-30-30 rule). Full article

In this paper, a novel online detection system is designed to enhance accuracy and operational efficiency in the outbound logistics of automotive components after production. The system consists of a scanning portal system and an improved YOLOv12-based detection algorithm which captures images of automotive parts passing through the scanning portal in real time. By integrating deep learning, the system enables real-time monitoring and identification, thereby preventing misdetections and missed detections of automotive parts, in this way promoting intelligent automotive part recognition and detection. Our system introduces the A2C2f-SA module, which achieves an efficient feature attention mechanism while maintaining a lightweight design. Additionally, Dynamic Space-to-Depth (Dynamic S2D) is employed to improve convolution and replace the stride convolution and pooling layers in the baseline network, helping to mitigate the loss of fine-grained information and enhancing the network’s feature extraction capability. To improve real-time performance, a GFL-MBConv lightweight detection head is proposed. Furthermore, adaptive frequency-aware feature fusion (Adpfreqfusion) is hybridized at the end of the neck network to effectively enhance high-frequency information lost during downsampling, thereby improving the model’s detection accuracy for target objects in complex backgrounds. On-site tests demonstrate that the system achieves a comprehensive accuracy of 97.3% and an average vehicle detection time of 7.59 s, exhibiting not only high precision but also high detection efficiency. These results can make the proposed system highly valuable for applications in the automotive industry. Full article

Thermal Power Plants (TPPs), as widely used industrial facilities for electricity generation, represent a key task in remote sensing image interpretation. However, detecting TPPs remains a challenging task due to their complex and irregular composition. Many traditional approaches focus on detecting compact, small-scale objects, while existing composite object detection methods are mostly part-based, limiting their ability to capture the structural and textural characteristics of composite targets like TPPs. Moreover, most of them rely on single-modality data, failing to fully exploit the rich information available in remote sensing imagery. To address these limitations, we propose a novel Cross-Modal Frequency-Responsive Attention Network (CFRANet). Specifically, the Modality-Aware Fusion Block (MAFB) facilitates the integration of multi-modal features, enhancing inter-modal interactions. Additionally, the Frequency-Responsive Attention (FRA) module leverages both spatial and localized dual-channel information and utilizes Fourier-based frequency decomposition to separately capture high- and low-frequency components, thereby improving the recognition of TPPs by learning both detailed textures and structural layouts. Experiments conducted on our newly proposed AIR-MTPP dataset demonstrate that CFRANet achieves state-of-the-art performance, with a ${\mathrm{mAP}}_{50}$ of 82.41%. Full article

Automated quality control plays a critical role in modern industries, particularly in environments that handle large volumes of packaged products requiring fast, accurate, and consistent inspections. This work presents an anomaly detection system for candle jars commonly used in industrial and commercial applications, where obtaining labeled defective samples is challenging. Two anomaly detection strategies are explored: (1) a baseline model using convolutional neural networks (CNNs) as an end-to-end classifier and (2) a hybrid approach where features extracted by CNNs are fed into One-Class classification (OCC) algorithms, including One-Class SVM (OCSVM), One-Class Isolation Forest (OCIF), One-Class Local Outlier Factor (OCLOF), One-Class Elliptic Envelope (OCEE), One-Class Autoencoder (OCAutoencoder), and Support Vector Data Description (SVDD). Both strategies are trained primarily on non-defective samples, with only a limited number of anomalous examples used for evaluation. Experimental results show that both the pure CNN model and the hybrid methods achieve excellent classification performance. The end-to-end CNN reached 100% accuracy, precision, recall, F1-score, and AUC. The best-performing hybrid model CNN-based feature extraction followed by OCIF also achieved 100% across all evaluation metrics, confirming the effectiveness and robustness of the proposed approach. Other OCC algorithms consistently delivered strong results, with all metrics above 95%, indicating solid generalization from predominantly normal data. This approach demonstrates strong potential for quality inspection tasks in scenarios with scarce defective data. Its ability to generalize effectively from mostly normal samples makes it a practical and valuable solution for real-world industrial inspection systems. Future work will focus on optimizing real-time inference and exploring advanced feature extraction techniques to further enhance detection performance. Full article

Accurate weld defect detection is critical for ensuring structural safety and evaluating welding quality in industrial applications. Manual inspection methods have inherent limitations, including inefficiency and inadequate sensitivity to subtle defects. Existing detection models, primarily designed for natural images, struggle to adapt to the characteristic challenges of weld X-ray images, such as high noise, low contrast, and inter-defect similarity, particularly leading to missed detections and false positives for small defects. To address these challenges, a multi-dimensional feature fusion model (MADet), which is a multi-branch deep fusion network for weld defect detection, was proposed. The framework incorporates two key innovations: (1) A multi-scale feature fusion network integrated with lightweight attention residual modules to enhance the perception of fine-grained defect features by leveraging low-level texture information. (2) An anchor-based feature-selective detection head was used to improve the discrimination and localization accuracy for five typical defect categories. Extensive experiments on both public and proprietary weld defect datasets demonstrated that MADet achieved significant improvements over the state-of-the-art YOLO variants. Specifically, it surpassed the suboptimal model by 7.41% in mAP@0.5, indicating strong industrial applicability. Full article

To tackle the challenges of detecting complex cracks on large stone slabs with noisy textures, this paper presents the first domain-optimized framework for stone slab cracks, an improved semantic segmentation model (YOLOv8-Seg) synergistically integrating U-NetV2, DSConv, and DySample. The network uses the lightweight U-NetV2 backbone combined with dynamic feature recalibration and multi-scale refinement to better capture fine crack details. The dynamic up-sampling module (DySample) helps to adaptively reconstruct curved boundaries. In addition, the dynamic snake convolution head (DSConv) improves the model’s ability to follow irregular crack shapes. Experiments on the custom-built ST stone crack dataset show that YOLOv8-Seg achieves an mAP@0.5 of 0.856 and an mAP@0.5–0.95 of 0.479. The model also reaches a mean intersection over union (MIoU) of 79.17%, outperforming both baseline and mainstream segmentation models. Ablation studies confirm the value of each module. Comparative tests and industrial validation demonstrate stable performance across different stone materials and textures and a 30% false-positive reduction in real production environments. Overall, YOLOv8-Seg greatly improves segmentation accuracy and robustness in industrial crack detection on natural stone slabs, offering a strong solution for intelligent visual inspection in real-world applications. Full article

Cold rolling is widely recognized as a key industrial process for enhancing the mechanical properties of materials, particularly hardness, through strain hardening. Despite its importance, accurately predicting the final hardness remains a challenge due to the inherently nonlinear nature of the deformation. While several studies have employed artificial neural networks to predict mechanical properties, architectural parameters still need to be investigated to understand their effects on network behavior and model performance, ultimately supporting the design of more effective architectures. This study investigates hyperparameter tuning in artificial neural networks trained using Resilient Backpropagation by evaluating the impact of varying number of hidden layers and neurons on the prediction accuracy of hardness in 70-30 brass specimens subjected to cold rolling. A dataset of 1000 input–output pairs, containing dimensional and hardness measurements from multiple rolling passes, was used to train and evaluate 819 artificial neural network architectures, each with a different configuration of 1 to 3 hidden layers and 4 to 12 neurons per layer. Each configuration was tested over 50 runs to reduce the influence of randomness and enhance result consistency. Enhancing the network depth from one to two hidden layers improved predictive performance. Architectures with two hidden layers achieved better performance metrics, faster convergence, and lower variation than single-layer networks. Introducing a third hidden layer did not yield meaningful improvements over two-hidden-layer architectures in terms of performance metrics. While the top three-layer model converged in fewer epochs, it required more computational time due to increased model complexity and weight elements. Full article