In modern semiconductor manufacturing, accurately classifying wafer bin map (WBM) defect patterns is essential for ensuring productivity. While recent studies increasingly employ deep learning-based approaches, their effectiveness often depends on large-scale labeled datasets that are costly to obtain. Active learning (AL) offers a practical solution by querying the most informative samples, thereby reducing labeling costs. However, existing AL strategies cannot be effectively utilized due to the existence of noisy labels from human annotation errors, which often leads to incorrect decision boundaries, confirmation bias, and performance deterioration. To address these limitations, this work proposes a hybrid deep AL framework for WBM defect classification under noisy labels. The proposed framework presents three novel techniques. First, a coverage-based diversity sampling identifies candidate samples that provide broad, non-redundant coverage of the unlabeled pool. Second, a Bayesian-based uncertainty sampling ranks the candidates based on information gain. Third, a loss-based noise filtering mechanism using a Gaussian mixture model distinguishes clean samples from noisy ones. Instead of discarding noisy samples, their neighborhoods are marked as unexplored, allowing subsequent diversity sampling to revisit and mitigate confirmation bias. The effectiveness of the proposed framework is validated using a real-world WBM dataset under AL with a noisy oracle setup. The comprehensive experimental results demonstrate that the proposed framework substantially outperforms conventional AL baselines and state-of-the-art AL methods under different label noise rates. Extensive ablation studies also verify the effects of the proposed framework’s techniques on robustness and label efficiency. • Deep active learning is utilized for wafer bin map defect classification. • Coverage-based diversity sampling is performed to select representative candidates. • Efficient Bayesian epistemic uncertainty is employed with Monte Carlo dropout. • Loss-based Gaussian mixture modeling is applied to filter noisy from clean labels. • The proposed method outperforms existing methods under noisy label conditions.

Renewable energy sources (RESs) are expected to play a key role in supporting frequency stability in modern power systems, and thus, a variety of inertia-control methods have been developed. However, many RESs are installed behind the meter (BTM), and their data often remain inaccessible to the energy management systems (EMS) operated by utilities. As a result, their contributions to system inertia are frequently overlooked in stability evaluations. Although several inertia estimation methods have been proposed, most assume full availability of RES data. In practice, however, access to some data is often restricted to utilities, which limits the applicability of conventional methods, particularly for BTM-installed RESs. This article presents two data driven approaches for estimating the synthetic inertia and droop coefficients of BTM RESs, explicitly considering data availability under both normal and dynamic conditions. The first approach uses steady state EMS and RES data with different sampling intervals, while the second relies only on EMS dynamic data recorded during contingencies, avoiding dependence on RES measurements. Verification on the Jeju Island power system with practical measured EMS and RES data validate the proposed approaches and emphasize the influence of sampling intervals on estimation accuracy. The results show that the proposed methods provide an effective solution for assessing inertia and droop of BTM RESs with only limited data access, enabling utilities to conduct more reliable frequency stability analysis in low inertia grids.

Delamination is a prevalent issue in carbon fiber-reinforced plastic (CFRP) drilling, significantly compromising the mechanical properties of the material. Considering that delamination can impact the long-term durability of the final products, it is essential for operators to promptly identify it. This paper proposes a machined surface image generation model, called Sensor2Image, that employs time-series force sensor data as input and generates drilled-hole surface images as output. Sensor2Image first encodes the force sensor data into images using the Gramian angular field (GAF) method. Subsequently, it applies an image-to-image translation technique to generate the final machined surface images. The proposed model was trained and evaluated using experimental data gathered from drilling CFRP specimens under an industrial robot machining system. The results demonstrated the versatility of the proposed model for practical applications, regardless of the delamination factor. The proposed method offers significant advantages over existing methods through its intuitive visual representation approach. It facilitates the visual inspection of delamination while enabling surface quality analysis of the drilled hole and identification of defects or irregularities that may impact the mechanical properties of the material. The proposed approach can enhance the efficiency and reliability of industrial processes, particularly those involving complex delamination factors. It is a valuable tool for optimizing the CFRP drilling process and enhancing drilled-hole quality in a user-friendly manner.

Due to the increase in motor vehicle accidents, there is a growing need for high-performance car crash detection systems. The authors of this research propose a car crash detection system that uses both video data and audio data from dashboard cameras in order to improve car crash detection performance. While most existing car crash detection systems depend on single modal data (i.e., video data or audio data only), the proposed car crash detection system uses an ensemble deep learning model based on multimodal data (i.e., both video and audio data), because different types of data extracted from one information source (e.g., dashboard cameras) can be regarded as different views of the same source. These different views complement one another and improve detection performance, because one view may have information that the other view does not contain. In this research, deep learning techniques, gated recurrent unit (GRU) and convolutional neural network (CNN), are used to develop a car crash detection system. A weighted average ensemble is used as an ensemble technique. The proposed car crash detection system, which is based on multiple classifiers that use both video and audio data from dashboard cameras, is validated using a comparison with single classifiers that use video data or audio data only. Car accident YouTube clips are used to validate this research. The experimental results indicate that the proposed car crash detection system performs significantly better than single classifiers. It is expected that the proposed car crash detection system can be used as part of an emergency road call service that recognizes traffic accidents automatically and allows immediate rescue after transmission to emergency recovery agencies.

The authors propose a time series model that predicts future values of various types of liquid cargo traffic based on long short-term memory (LSTM), a deep learning technique. Existing liquid cargo traffic prediction models are based on traditional time series models, such as autoregressive integrated moving average (ARIMA) and vector autoregression (VAR). Some of these models, which do not consider linear dependencies among the values of different types of liquid cargo traffic, have limitations on their prediction performance, because the values of different types of liquid cargo traffic are dependent on one another. These models’ prediction performance are also limited due to the problem of vanishing gradients, which hinders the learning of long-range time series records. Missing values that exist on real-world liquid cargo traffic records reduce prediction performance as well. The proposed LSTM-based time series model handles missing values on liquid cargo traffic records and predicts future values of liquid cargo traffic. In addition, additional indices, such as inflation rates, exchange rates for dollars, GDP values, and the international prices of oil, are used to improve prediction performance. A case study involving real-world liquid cargo traffic records at the Port of Ulsan, Republic of Korea, for 216 months is used to validate prediction performance of the proposed LSTM-based prediction model compared with traditional ARIMA-based and VAR-based prediction models.