Query-Based Machine Learning Model for Data Analysis of Infrasonic Signals in Wireless Sensor Networks

Chang, Ray-I; Huang, Chien‐Chang; Lai, L.L.; Lee, Chia‐Yun

doi:10.1145/3193025.3193031

Cited by 3 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear regression showed a better prediction performance than the other algorithms for product quality prediction. According to previous studies, query-based learning exhibits an excellent computing performance because of its advantages in generating new learning samples and training the model with different parameters [ 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 ]. This study obtained similar results.…”

Section: Resultsmentioning

confidence: 99%

“…This study obtained similar results. The proposed query-based regression model can search a larger solution space than the original preliminary function [ 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 ]. Thus, it exhibited a good prediction ability in the case study.…”

Section: Resultsmentioning

confidence: 99%

“…The proposed method has promising advantages in predicting product quality in textile manufacturing. Previous studies have stated that query-based learning leads to excellent computing performances because it has the advantage of tuning models to evolve dynamically [ 45 , 46 , 47 , 48 , 49 ]. The current study obtained similar results.…”

Section: Discussionmentioning

confidence: 99%

“…This study proposes query-based learning, which takes advantage of the generative and interactive reinforcement methods by creating new learning instances and bi-direction interactions in the solution space. Query-based learning [ 45 , 46 , 47 , 48 , 49 ] is an active learning technique that effectively enhances the model performance by incorporating key data points. Figure 4 illustrates the concept of query-based learning using a simple binary classification example.…”

Section: Methodsmentioning

confidence: 99%

“… Step 5. According to the two learning strategies, by adding samples to the DD, the training sample set consists of either (a) samples of the most correct prediction, which is learning from the strong learners [ 47 , 49 ], or (b) samples of the least correct prediction, for which the weak learners are used to explore the fuzzy or unexplored solution spaces [ 48 ]. …”

Section: Methodsmentioning

confidence: 99%

See 4 more Smart Citations

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

Chang,

Lin,

Hung

2024

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract