Tien-Yin Chou

Transitioning conventional brownfield metalworking facilities into smart factories often faces practical execution barriers, including legacy equipment constraints, high capital expenditures, and operational downtime risks. This study presents an empirical, longitudinal framework for Industry 4.0 transformation by integrating a 5C Cyber–Physical System (CPS) architecture with Lean Philosophy and Total Productive Maintenance (TPM) tools in a precision metal manufacturing factory in Taichung, Taiwan. Developed over a four-year lifecycle, the deployment utilizes a phased pilot strategy featuring Industrial Internet of Things (IIoT) data acquisition, Ultra-Wideband (UWB) indoor positioning, visual dashboards, and human-in-the-loop dispatching. Analysis of a two-year longitudinal operational dataset demonstrates marked operational enhancements. Value Stream Mapping (VSM) of the specific product on the pilot shop floor reveals a 3.7% decrease in processing time, a 40% reduction in waiting time, and a 20% cut in changeover time, while the operator-to-machine ratio improved from 1:4 to 1:6. Paired-sample t-tests performed using data from the whole pilot shop floor confirm statistically significant improvements in the production capacity achievement rate (PCAR, p (probability) < 0.05) and product defect rate (p < 0.05), with defect rates dropping to 0.19% alongside the decoupling of defect generation from machine failures. Furthermore, a SWOT analysis contextualizes the empirical outcomes, practical limitations, and future predictive maintenance pathways. The proposed methodology provides an actionable roadmap for small and medium-sized manufacturing enterprises (SMEs) pursuing smart manufacturing transitions.

Reliable, real-time river flow monitoring is essential for disaster prevention, but traditional in situ methods are costly and high-risk. Large-scale particle image velocimetry (LSPIV) offers a non-contact alternative, though its accuracy is often compromised by noise and non-water pixels, requiring intensive manual data processing. This study proposes an integrated framework for enhancing non-contact river surface velocity estimation by combining deep learning-based water surface segmentation with optimized LSPIV, using accessible smartphone imaging. The framework was tested on two urban rivers in Taichung, Taiwan. DeepLabV3+ was identified as the superior segmentation model based on MPA/PA and MIoU metrics. The DeepLabV3+-derived mask was integrated into the LSPIV workflow, which was optimized using a 32 × 32 pixels interrogation area (IA), reducing processing time by approximately 44%. By removing non-water pixels, the masked LSPIV yielded a 7% increase in mean surface velocity. This suggests that the inclusion of non-water elements diluted the average, underscoring their tendency to introduce a low-velocity bias in unmasked calculations. The overall validation showed mean absolute percentage errors below 6% compared to the radar velocimeter. Consequently, this integrated smartphone-based framework offers a cost-effective and precise solution for future large-scale deployment in urban flood monitoring and smart city hydrological management.

Images captured in rainy weather conditions often suffer from contamination, resulting in blurred or obscured objects, which can significantly impact detection performance due to the loss of identifiable texture and color information. Moreover, the quality of the detection model plays a pivotal role in determining detection outcomes. This study adopts a dual perspective, considering both pre-trained models and training data. It employs 15 image augmentation techniques, combined with neural style transfer (NST), CycleGAN, and an analytical method, to synthesize images under rainy conditions. The Real-Time Detection Transformer (RTDETR) and YOLOv8 pre-trained models are utilized to establish object detection frameworks tailored for rainy weather conditions. Testing is carried out using the DAWN (Detection in Adverse Weather Nature) dataset. The findings suggest compatibility between the pre-trained detection models and various data synthesis methods. Notably, YOLOv8 exhibits better compatibility with CycleGAN data synthesis, while RTDETR demonstrates a stronger alignment with the NST and analytical approaches. Upon the integration of synthesized rainy images into model training, RTDETR demonstrates significantly enhanced detection accuracy compared to YOLOv8, indicating a more pronounced improvement in performance. The proposed approach of combining RTDETR with NST in this study shows a significant improvement in Recall (R) and mAP50-95 by 16.35% and 15.50%, respectively, demonstrating the robust rainy weather resilience of this method. Additionally, RTDETR outperforms YOLOv8 in terms of inference speed and hardware requirements, making it easier to use and deploy in real-time applications.

Latent Low-Rank Representation (LatLRR) has emerged as a prominent approach for fusing visible and infrared images. In this approach, images are decomposed into three fundamental components: the base part, salient part, and sparse part. The aim is to blend the base and salient features to reconstruct images accurately. However, existing methods often focus more on combining the base and salient parts, neglecting the importance of the sparse component, whereas we advocate for the comprehensive inclusion of all three parts generated from LatLRR image decomposition into the image fusion process, a novel proposition introduced in this study. Moreover, the effective integration of Convolutional Neural Network (CNN) technology with LatLRR remains challenging, particularly after the inclusion of sparse parts. This study utilizes fusion strategies involving weighted average, summation, VGG19, and ResNet50 in various combinations to analyze the fusion performance following the introduction of sparse parts. The research findings show a significant enhancement in fusion performance achieved through the inclusion of sparse parts in the fusion process. The suggested fusion strategy involves employing deep learning techniques for fusing both base parts and sparse parts while utilizing a summation strategy for the fusion of salient parts. The findings improve the performance of LatLRR-based methods and offer valuable insights for enhancement, leading to advancements in the field of image fusion.

Taiwan is located at the junction of plates in which the stratum is relatively unstable, resulting in frequent earthquakes. Driftwood has always been regarded as a precious asset that enables ecoscientists to track earthquakes. In the event of a typhoon or heavy rain, the surface water flows to flush the woods from the hills to the coast. More specifically, a large rainfall or earthquake may cause floods and collapses, and the trees in the forest will be washed down. Therefore, this study used high-resolution images to build an image database of the new north coast of Taiwan, and a deep learning approach is incorporated to classify the driftwoods. To improve the interpretation of driftwood in the remote images, we initially import eight pieces of textured information which are employed to the raw bands (B, G, R, and IR). The usage of spatial information image extraction technology is incorporated into a deep learning analysis using two parallel approaches. The generative adversarial network (GAN) is used to analyze the color images alongside an ancillary image with texture information. Most of the salt–pepper effects are produced by applying a high-resolution thematic map, and an error matrix is generated to compare the differences between them. The raw data (original R + G + B + IR) images, when analyzed using GAN, have about 70% overall classification outcomes. Not all of the driftwood can be detected. By applying the texture information to the parallel approach, the overall accuracy is enhanced to 78%, and about 80% of the driftwood can be recognized.

Convenience store chains are many people’s top choice for dining and leisure and have logistics procedures that involve each store receiving multiple deliveries because of the varying delivery periods and suitable temperatures for different goods. The estimated arrival time for each delivery has a huge impact on the route arrangement and convenience store preparation for dispatchers to schedule future deliveries. This study collected global positioning system travel data from a fleet of one of the top convenience store chains in Taiwan between April 2021 and March 2022 and proposed machine learning to establish a model to predict travel times. For unavailable data, we proposed the nonlinear regression equation to fill in the missing GPS data. Moreover, the study used the data between April 2022 and September 2022 with mean absolute percentage error to validate the prediction effects exceeding 97%. Therefore, the proposed model based on historical data and the machine learning algorithm in this study can help logistics fleets estimate accurate travel times for their scheduling of future delivery tasks and arranging routes.

Although many machine learning methods have been widely used to predict PM2.5 concentrations, these single or hybrid methods still have some shortcomings. This study integrated the advantages of convolutional neural network (CNN) feature extraction and the regression ability of random forest (RF) to propose a novel CNN-RF ensemble framework for PM2.5 concentration modeling. The observational data from 13 monitoring stations in Kaohsiung in 2021 were selected for model training and testing. First, CNN was implemented to extract key meteorological and pollution data. Subsequently, the RF algorithm was employed to train the model with five input factors, namely the extracted features from the CNN and spatiotemporal factors, including the day of the year, the hour of the day, latitude, and longitude. Independent observations from two stations were used to evaluate the models. The findings demonstrated that the proposed CNN–RF model had better modeling capability compared with the independent CNN and RF models: the average improvements in root mean square error (RMSE) and mean absolute error (MAE) ranged from 8.10% to 11.11%, respectively. In addition, the proposed CNN–RF hybrid model has fewer excess residuals at thresholds of 10 μg/m³, 20 μg/m³, and 30 μg/m³. The results revealed that the proposed CNN–RF ensemble framework is a stable, reliable, and accurate method that can generate superior results compared with the single CNN and RF methods. The proposed method could be a valuable reference for readers and may inspire researchers to develop even more effective methods for air pollution modeling. This research has important implications for air pollution research, data analysis, model estimation, and machine learning.

The Global Positioning System (GPS) is satellite-based, with receiving equipment worldwide utilizing geographic positioning satellites in Earth orbit. The system is unaffected by the radio positioning system, so it provides highly accurate three-dimensional positioning, velocity, and time data to users. In this paper, Alishan Township, Chiayi County, central Taiwan, is selected to test an automatic real-time monitoring system comprising of one machine with multiple GPS antennas. To this end, the Alishan Public Works Section installed advanced measuring instruments and a landslide-monitoring system composed of a high-efficiency transmission system. A pre- and post-rainfall data survey was conducted on this slope section. Together with the rainfall records, real-time ground-slip monitoring data was collected, and subsequently analyzed to understand the disaster situation and ground slip characteristics of the Alishan Highway following an earthquake (1998). In the future, more effective management values will be set to reduce the loss of slope disasters to conserve land and public safety. For the first time in Taiwan, this paper presents displacement data indicating that after the typhoon rains, a maximum surface movement velocity of 2.5 cm every six days is attained, while the total displacement per month is as high as 10 cm. These data can be used as for the remediation of this section of the Alishan Highway.