Cloud-Based Machine Learning Methods for Parameter Prediction in Textile Manufacturing

In traditional textile manufacturing, downstream manufacturers use raw materials, such as Nylon and cotton yarns, to produce textile products. The manufacturing process involves warping, sizing, beaming, weaving, and inspection. Staff members typically use a trial-and-error approach to adjust the appropriate production parameters in the manufacturing process, which can be time consuming and a waste of resources. To enhance the efficiency and effectiveness of textile manufacturing economically, this study proposes a query-based learning method in regression analytics using existing manufacturing data. Query-based learning allows the model training to evolve its decision-making process through dynamic interactions with its solution space. In this study, predefined target parameters of quality factors were first used to validate the training results and create new training patterns. These new patterns were then imported into the solution space of the training model. In predicting product quality, the results show that the proposed query-based regression algorithm has a mean squared error of 0.0153, which is better than those of the original regression-related methods (Avg. mean squared error = 0.020). The trained model was deployed as an application programing interface (API) for cloud-based analytics and an extensive auto-notification service.

Smartwatch Sensors with Deep Learning to Predict the Purchase Intentions of Online Shoppers

In the past decade, the scale of e-commerce has continued to grow. With the outbreak of the COVID-19 epidemic, brick-and-mortar businesses have been actively developing online channels where precision marketing has become the focus. This study proposed using the electrocardiography (ECG) recorded by wearable devices (e.g., smartwatches) to judge purchase intentions through deep learning. The method of this study included a long short-term memory (LSTM) model supplemented by collective decisions. The experiment was divided into two stages. The first stage aimed to find the regularity of the ECG and verify the research by repeated measurement of a small number of subjects. A total of 201 ECGs were collected for deep learning, and the results showed that the accuracy rate of predicting purchase intention was 75.5%. Then, incremental learning was adopted to carry out the second stage of the experiment. In addition to adding subjects, it also filtered five different frequency ranges. This study employed the data augmentation method and used 480 ECGs for training, and the final accuracy rate reached 82.1%. This study could encourage online marketers to cooperate with health management companies with cross-domain big data analysis to further improve the accuracy of precision marketing.

Scale-Mark-Based Gauge Reading for Gauge Sensors in Real Environments with Light and Perspective Distortions

Nowadays, many old analog gauges still require the use of manual gauge reading. It is a time-consuming, expensive, and error-prone process. A cost-effective solution for automatic gauge reading has become a very important research topic. Traditionally, different types of gauges have their own specific methods for gauge reading. This paper presents a systematized solution called SGR (Scale-mark-based Gauge Reading) to automatically read gauge values from different types of gauges. Since most gauges have scale marks (circular or in an arc), our SGR algorithm utilizes PCA (principal components analysis) to find the primary eigenvector of each scale mark. The intersection of these eigenvectors is extracted as the gauge center to ascertain the scale marks. Then, the endpoint of the gauge pointer is found to calculate the corresponding angles to the gauge's center. Using OCR (optical character recognition), the corresponding dial values can be extracted to match with their scale marks. Finally, the gauge reading value is obtained by using the linear interpolation of these angles. Our experiments use four videos in real environments with light and perspective distortions. The gauges in the video are first detected by YOLOv4 and the detected regions are clipped as the input images. The obtained results show that SGR can automatically and successfully read gauge values. The average error of SGR is nearly 0.1% for the normal environment. When the environment becomes abnormal with respect to light and perspective distortions, the average error of SGR is still less than 0.5%.

Edge Computing of Online Bounded-Error Query for Energy-Efficient IoT Sensors

Since the power of transmitting one-bit data is higher than that of computing one thousand lines of code in IoT (Internet of Things) applications, it is very important to reduce communication costs to save battery power and prolong system lifetime. In IoT sensors, the transformation of physical phenomena to data is usually with distortion (bounded-error tolerance). It introduces bounded-error data in IoT applications according to their required QoS² (quality-of-sensor service) or QoD (quality-of-decision making). In our previous work, we proposed a bounded-error data compression scheme called BESDC (Bounded-Error-pruned Sensor Data Compression) to reduce the point-to-point communication cost of WSNs (wireless sensor networks). Based on BESDC, this paper proposes an online bounded-error query (OBEQ) scheme with edge computing to handle the entire online query process. We propose a query filter scheme to reduce the query commands, which will inform WSN to return unnecessary queried data. It not only satisfies the QoS²/QoD requirements, but also reduces the communication cost to request sensing data. Our experiments use real data of WSN to demonstrate the query performance. Results show that an OBEQ with a query filter can reduce up to 88% of the communication cost when compared with the traditional online query process.

Machine Learning for Texture Segmentation and Classification of Comic Image in SVG Compression

Raster comic would result in bad quality while zooming in/out. Different approaches were proposed to convert comic into vector format to resolve this problem. The authors have proposed methods to vectorize comic contents to provide not only small SVG file size and rendering time, but also better perceptual quality. However, they do not process texture in the comic images. In this paper, the authors improve their previously developed system to recognize texture elements in the comic and use these texture elements to provide better compression and faster rendering time. They propose texture segmentation techniques to partition comic into texture segments and non-texture segments. Then, the <pattern> element of SVG is applied to represent texture segments. Their method uses CSG (Composite Sub-band Gradient) vector as texture descriptor and uses SVM (Support Vector Machine) to classify texture area in the comic. Then, the ACM (Active Contour Model) combining with CSG vectors is introduced to improve the segmentation accuracy on contour regions. Experiments are conducted using 150 comic images to test the proposed method. Results show that the space savings of our method is over 66% and it can utilize the reusability of SVG syntax to support comic with multiple textures. The average rendering time of the proposed method is over three times faster than the previous methods. It lets vectorized comics have higher performance to be illustrated on modern e-book devices.

Comparing LR, GP, BPN, RBF and SVR for Self-Learning Pattern Matching in WSN Indoor Localization

It is a challenging issue to apply WSN (Wireless Sensor Network) to achieve accurate location information. PM (Pattern Matching), known as one of the most famous localization methods, has the drawback of requiring high initialization effort to predict/train MF (Matching Function). In this paper, the authors propose SPM (Self-learning PM) to improve not only the localization accuracy but also the initialization effort of PM. SPM applies a divide-and-conquer self-learning scheme to reduce the number of training patterns in training. Additionally, it introduces a Bayesian filtering scheme to remove the noise signal caused by multipath effects so as to enhance localization accuracy accordingly. This paper applies different training methods (linear regression, Gaussian process, backpropagation network, radial basis function, and support vector regression) to evaluate the performances of SPM and PM in a complicated indoor environment. Experiments show that SPM is better than PM for all training methods applied. SPM can use up to 72% fewer training patterns than PM to achieve the same localization accuracy. If the same number of training patterns is utilized, SPM can achieve up to 58% higher localization accuracy than PM.