Feature-Learning-Based Printed Circuit Board Inspection via Speeded-Up Robust Features and Random Forest

Semi-Supervised Defect Detection Method with Data-Expanding Strategy for PCB Quality Inspection

Printed circuit board (PCB) defect detection plays a crucial role in PCB production, and the popular methods are based on deep learning and require large-scale datasets with high-level ground-truth labels, in which it is time-consuming and costly to label these datasets. Semi-supervised learning (SSL) methods, which reduce the need for labeled samples by leveraging unlabeled samples, can address this problem well. However, for PCB defects, the detection accuracy on small numbers of labeled samples still needs to be improved because the number of labeled samples is small, and the training process will be disturbed by the unlabeled samples. To overcome this problem, this paper proposed a semi-supervised defect detection method with a data-expanding strategy (DE-SSD). The proposed DE-SSD uses both the labeled and unlabeled samples, which can reduce the cost of data labeling, and a batch-adding strategy (BA-SSL) is introduced to leverage the unlabeled data with less disturbance. Moreover, a data-expanding (DE) strategy is proposed to use the labeled samples from other datasets to expand the target dataset, which can also prevent the disturbance by the unlabeled samples. Based on the improvements, the proposed DE-SSD can achieve competitive results for PCB defects with fewer labeled samples. The experimental results on DeepPCB indicate that the proposed DE-SSD achieves state-of-the-art performance, which is improved by 4.7 mAP at least compared with the previous methods.

YOLOv4-MN3 for PCB Surface Defect Detection

Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. However, automatic detection of PCB surface defects is still a challenging task because, even within the same category of surface defect, defects present great differences in morphology and pattern. Although many computer vision-based detectors have been established to handle these problems, current detectors struggle to achieve high detection accuracy, fast detection speed and low memory consumption simultaneously. To address those issues, we propose a cost-effective deep learning (DL)-based detector based on the cutting-edge YOLOv4 to detect PCB surface defect quickly and efficiently. The YOLOv4 is improved upon with respect to its backbone network and the activation function in its neck/prediction network. The improved YOLOv4 is evaluated with a customized dataset, collected from a PCB factory. The experimental results show that the improved detector achieved a high performance, scoring 98.64% on mean average precision (mAP) at 56.98 frames per second (FPS), outperforming the other compared SOTA detectors. Furthermore, the improved YOLOv4 reduced the parameter space of YOLOv4 from 63.96 M to 39.59 M and the number of multiply-accumulate operations (Madds) from 59.75 G to 26.15 G.

Improving Sports Outcome Prediction Process Using Integrating Adaptive Weighted Features and Machine Learning Techniques

Developing an effective sports performance analysis process is an attractive issue in sports team management. This study proposed an improved sports outcome prediction process by integrating adaptive weighted features and machine learning algorithms for basketball game score prediction. The feature engineering method is used to construct designed features based on game-lag information and adaptive weighting of variables in the proposed prediction process. These designed features are then applied to the five machine learning methods, including classification and regression trees (CART), random forest (RF), stochastic gradient boosting (SGB), eXtreme gradient boosting (XGBoost), and extreme learning machine (ELM) for constructing effective prediction models. The empirical results from National Basketball Association (NBA) data revealed that the proposed sports outcome prediction process could generate a promising prediction result compared to the competing models without adaptive weighting features. Our results also showed that the machine learning models with four game-lags information and adaptive weighting of power could generate better prediction performance.

Classification of Microscopic Laser Engraving Surface Defect Images Based on Transfer Learning Method

Microscopic laser engraving surface defect classification plays an important role in the industrial quality inspection field. The key challenges of accurate surface defect classification are the complete description of the defect and the correct distinction into categories in the feature space. Traditional classification methods focus on the terms of feature extraction and independent classification; therefore, feed handcrafted features may result in useful feature loss. In recent years, convolutional neural networks (CNNs) have achieved excellent results in image classification tasks with the development of deep learning. Deep convolutional networks integrate feature extraction and classification into self-learning, but require large datasets. The training datasets for microscopic laser engraving image classification are small; therefore, we used pre-trained CNN models and applied two fine-tuning strategies. Transfer learning proved to perform well even on small future datasets. The proposed method was evaluated on the datasets consisting of 1986 laser engraving images captured by a metallographic microscope and annotated by experienced staff. Because handcrafted features were not used, our method is more robust and achieves better results than traditional classification methods. Under five-fold-validation, the average accuracy of the best model based on DenseNet121 is 96.72%.

AFCM-LSMA: New intelligent model based on Lévy slime mould algorithm and adaptive fuzzy C-means for identification of COVID-19 infection from chest X-ray images

Problem

A worldwide challenge is to provide medical resources required for COVID-19 detection. They must be effective tools for fast detection and diagnose of the virus using a large number of tests; besides, they should be low-cost developments. While a chest X-ray scan is a powerful candidate tool, if several tests are carried out, the images produced by the devices must be interpreted accurately and rapidly. COVID-19 induces longitudinal pulmonary parenchymal ground-glass and consolidates pulmonary opacity, in some cases with rounded morphology and peripheral lung distribution, which is very difficult to predict in an early stage.

Aim

In this paper, we aim to develop a robust model to extract high-level features of COVID-19 from chest X-ray (CXR) images to help in rapid diagnosis. In specific, this paper proposes an optimization model for COVID-19 diagnosis based on adaptive Fuzzy C-means (AFCM) and improved Slime Mould Algorithm (SMA) based on Lévy distribution, namely AFCM-LSMA.

Methods

The SMA optimizer is proposed to adapt weights in oscillation mode and to mimic the process of generating positive and negative feedback from the propagation wave to shape the optimum path for food connectivity. Lévy motion is used as a permutation to perform a local search and to adapt SMA optimizer (LSMA) by generating several solutions that are apart from current candidates. Furthermore, it permits the optimizer to escape from local minima, examine large search areas and reach optimal solutions in fewer iterations with high convergence speed. The FCM algorithm is used to segment pulmonary regions from CXR images and is adapted to reduce time and amount of computations using histogram of the image intensities during the clustering process.

Results

The performance of the proposed AFCM-LSMA has been validated on CXR images and compared with different conventional machine learning and deep learning techniques, meta-heuristics methods, and different chaotic maps. The accuracies achieved by the proposed model are around (ACC = 0.96, RMSE = 0.23, Prec. = 0.98, F1_score = 0.98, MCC = 0.79, and Kappa = 0.79).

Conclusion

The experimental findings indicate that the proposed new method outperforms all other methods, which will be beneficial to the clinical practitioner for the early identification of infected COVID-19 patients.

Why Is Deep Learning Challenging for Printed Circuit Board (PCB) Component Recognition and How Can We Address It?

In this paper, we present the need for specialized artificial intelligence (AI) for counterfeit and defect detection of PCB components. Popular computer vision object detection techniques are not sufficient for such dense, low inter-class/high intra-class variation, and limited-data hardware assurance scenarios in which accuracy is paramount. Hence, we explored the limitations of existing object detection methodologies, such as region based convolutional neural networks (RCNNs) and single shot detectors (SSDs), and compared them with our proposed method, the electronic component localization and detection network (ECLAD-Net). The results indicate that, of the compared methods, ECLAD-Net demonstrated the highest performance, with a precision of 87.2% and a recall of 98.9%. Though ECLAD-Net demonstrated decent performance, there is still much progress and collaboration needed from the hardware assurance, computer vision, and deep learning communities for automated, accurate, and scalable PCB assurance.

SMT Assembly Inspection Using Dual-Stream Convolutional Networks and Two Solder Regions

The automated optical inspection of a surface mount technology line inspects a printed circuit board for quality assurance, and subsequently classifies the chip assembly defects. However, it is difficult to improve the accuracy of previous defect classification methods using full chip component images with single-stream convolutional neural networks due to interference elements such as silk lines included in a printed circuit board image. This paper proposes a late-merge dual-stream convolutional neural network to increase the classification accuracy. Two solder regions are extracted from a printed circuit board image and are input to a convolutional neural network with a merge stage. A new convolutional neural network structure is then proposed that is able to classify for defects. Since defect features are concentrated in solder regions, the classification accuracy is increased. In addition, the network weight is reduced due to a reduction of the input data. Experimental results for the proposed method show a 5.3% higher performance in F1-score than a single-stream convolutional neural network based on full chip component images.

Developing a Novel Machine Learning-Based Classification Scheme for Predicting SPCs in Colorectal Cancer Survivors

Colorectal cancer is ranked third and fourth in terms of mortality and cancer incidence in the world. While advances in treatment strategies have provided cancer patients with longer survival, potentially harmful second primary cancers can occur. Therefore, second primary colorectal cancer analysis is an important issue with regard to clinical management. In this study, a novel predictive scheme was developed for predicting the risk factors associated with second colorectal cancer in patients with colorectal cancer by integrating five machine learning classification techniques, including support vector machine, random forest, multivariate adaptive regression splines, extreme learning machine, and extreme gradient boosting. A total of 4287 patients in the datasets provided by three hospital tumor registries were used. Our empirical results revealed that this proposed predictive scheme provided promising classification results and the identification of important risk factors for predicting second colorectal cancer based on accuracy, sensitivity, specificity, and area under the curve metrics. Collectively, our clinical findings suggested that the most important risk factors were the combined stage, age at diagnosis, BMI, surgical margins of the primary site, tumor size, sex, regional lymph nodes positive, grade/differentiation, primary site, and drinking behavior. Accordingly, these risk factors should be monitored for the early detection of second primary tumors in order to improve treatment and intervention strategies.

Side-Scan Sonar Image Fusion Based on Sum-Modified Laplacian Energy Filtering and Improved Dual-Channel Impulse Neural Network

The operation mode of a single strip provides incomplete side-scan sonar image in a specific environment and range, resulting in the overlapping area between adjacent strips often with imperfect detection information or inaccurate target contour. In this paper, a sum-modified Laplacian energy filtering (SMLF) and improved dual-channel pulse coupled neural network (IDPCNN) are proposed for image fusion of side-scan sonar in the domain of nonsubsampled contourlet transform (NSCT). Among them, SMLF energy is applied to extract the fusion coefficients of the low frequency sub-band, which combines the characteristics of energy information, human visual contrast, and guided filtering to eliminate the pseudo contour effect of block flow. In addition, the IDPCNN model, which utilizes the average gradient, soft limit function, and novel sum-modified Laplacian (NSML) to adaptively represent the corresponding excitation parameters, is applied to improve the depth and activity of pulse ignition, so as to quickly and accurately select the image coefficients of the high frequency sub-band. The experimental results show that the proposed method displays fine geomorphic information and clear target contour in the overlapping area of adjacent strips. The objective index values are generally optimal, which reflect the information of image edge, clarity, and overall similarity.

Chassis Assembly Detection and Identification Based on Deep Learning Component Instance Segmentation

Chassis assembly quality is a necessary step to improve product quality and yield. In recent years, with the continuous expansion of deep learning method, its application in product quality detection is increasingly extensive. The current limitations and shortcomings of existing quality detection methods and the feasibility of improving the deep learning method in quality detection are presented and discussed in this paper. According to the characteristics of numerous parts and complex types of chassis assembly components, a method for chassis assembly detection and identification based on deep learning component segmentation is proposed. In the proposed method, assembly quality detection is first performed using the Mask regional convolutional neural network component instance segmentation method, which reduces the influence of complex illumination conditions and background detection. Next, a standard dictionary of chassis assembly is built, which is connected with Mask R-CNN in a cascading way. The component mask is obtained through the detection result, and the component category and assembly quality information is extracted to realize chassis assembly detection and identification. To evaluate the proposed method, an industrial assembly chassis was used to create datasets, and the method is effective in limited data sets of industrial assembly chassis. The experimental results indicate that the accuracy of the proposed method can reach 93.7%. Overall, the deep learning method realizes complete automation of chassis assembly detection.

Prediction and Knowledge Mining of Outdoor Atmospheric Corrosion Rates of Low Alloy Steels Based on the Random Forests Approach

The objective of this paper is to develop an approach to forecast the outdoor atmospheric corrosion rate of low alloy steels and do corrosion-knowledge mining by using a Random Forests algorithm as a mining tool. We collected the corrosion data of 17 low alloy steels under 6 atmospheric corrosion test stations in China over 16 years as the experimental datasets. Based on the datasets, a Random Forests model is established to implement the purpose of the corrosion rate prediction and data-mining. The results showed that the random forests can achieve the best generalization results compared to the commonly used machine learning methods such as the artificial neural network, support vector regression, and logistic regression. In addition, the results also showed that regarding the effect to the corrosion rate, environmental factors contributed more than chemical compositions in the low alloy steels, but as exposure time increases, the effect of the environmental factors will gradually become less. Furthermore, we give the effect changes of six environmental factors (Cl− concentration, SO2 concentration, relative humidity, temperature, rainfall, and pH) on corrosion with exposure time increasing, and the results illustrated that pH had a significant contribution to the corrosion of the entire process. The paper also dealt with the problem of the corrosion rate forecast, especially for changing environmental factors situations, and obtained the qualitative and quantitative results of influences of each environmental factor on corrosion.