In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-based defective bean inspection scheme (DL-DBIS), together with a GAN (generative-adversarial network)-structured automated labeled data augmentation method (GALDAM) for enhancing the proposed scheme, so that the automation degree of bean removal with robotic arms can be further improved for coffee industries. The proposed scheme is aimed at providing an effective model to a deep-learning-based object detection module for accurately identifying defects among dense beans. The proposed GALDAM can be used to greatly reduce labor costs, since the data labeling is the most labor-intensive work in this sort of solutions. Our proposed scheme brings two main impacts to intelligent agriculture. First, our proposed scheme is can be easily adopted by industries as human effort in labeling coffee beans are minimized. The users can easily customize their own defective bean model without spending a great amount of time on labeling small and dense objects. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time and can be easily extended if more classes of defective beans are added. These two advantages increase the degree of automation in the coffee industry. The prototype of the proposed scheme was developed for studying integrated tests. Testing results of a case study reveal that the proposed scheme can efficiently and effectively generate models for identifying defective beans with accuracy and precision values up to $80\%$ .

Airborne particulate matter 2.5 (PM2.5) can have a profound effect on the health of the population. Many researchers have been reporting highly accurate numerical predictions based on raw PM2.5 data imported directly into deep learning models; however, there is still considerable room for improvement in terms of implementation costs due to heavy computational overhead. From the perspective of environmental science, PM2.5 values in a given location can be attributed to local sources as well as external sources. Local sources tend to have a dramatic short-term impact on PM2.5 values, whereas external sources tend to have more subtle but longer-lasting effects. In the presence of PM2.5 from both sources at the same time, this combination of effects can undermine the predictive accuracy of the model. This paper presents a novel combinational Hammerstein recurrent neural network (CHRNN) to enhance predictive accuracy and overcome the heavy computational and monetary burden imposed by deep learning models. The CHRNN comprises a based-neural network tasked with learning gradual (long-term) fluctuations in conjunction with add-on neural networks to deal with dramatic (short-term) fluctuations. The CHRNN can be coupled with a random forest model to determine the degree to which short-term effects influence long-term outcomes. We also developed novel feature selection and normalization methods to enhance prediction accuracy. Using real-world measurement data of air quality and PM2.5 datasets from Taiwan, the precision of the proposed system in the numerical prediction of PM2.5 levels was comparable to that of state-of-the-art deep learning models, such as deep recurrent neural networks and long short-term memory, despite far lower implementation costs and computational overhead.

Computer numerical control (CNC) tool-wear prediction (TWPred) is an important issue in the industry. Recently, researchers have demonstrated that deep-learning models (DLMs) are effective in TWPred. However, DLMs are ill-suited to small- and medium-scale manufacturers due to high computational costs. Methods exist to reduce the computational costs of DLMs, but most of them depend on overly-complex pruning processes that are not appropriate for the low-end computers used by the above manufacturers. Therefore, we developed a lightweight DLM and an automated framework for TWPred. The framework is based on two concepts: 1) the DLM was pruned by reducing the number of input data fields so the model itself remains unchanged and 2) we designed a framework that enables the automatic establishment of a lightweight DLM. These two concepts make the overall framework applicable to small- and medium-scale manufacturers. Finally, we used real-world dataset PHM 2010 to verify that the lightweight DLM can achieve almost the same reminding useful life (RUL) accuracy as the DLM (DLM: 95.55% and lightweight DLM: 95.51%) using only 0.88% of DLM parameters, which verifies the low cost and high precision of the proposed model.