In the assembly process of printed circuit boards (PCBs), most of the errors are caused by solder joints in surface mount devices (SMDs). In the literature, traditional feature extraction-based methods require designing hand-crafted features and rely on the tiered red green blue (RGB) illumination to detect solder joint errors, whereas the supervised convolutional neural network (CNN)-based approaches require a lot of labeled abnormal samples (defective solder joints) to achieve high accuracy. To solve the optical inspection problem in unrestricted environments with no special lighting and without the existence of error-free reference boards, we propose a new beta-variational autoencoder (beta-VAE) architecture for anomaly detection that can work on both integrated circuit (IC) and non-IC components. We show that the proposed model learns disentangled representation of data, leading to more independent features and improved latent space representations. We compare the activation and gradient-based representations that are used to characterize anomalies and observe the effect of different beta parameters on accuracy and untwining the feature representations in beta-VAE. Finally, we show that anomalies on solder joints can be detected with high accuracy via a model trained directly on normal samples without designated hardware or feature engineering.

Surface Mount Technology (SMT) is a procedure for mounting electronic components to the surface of the printed circuit boards (PCB). Although the SMT procedure is more reliable than the conventional through-hole mounting, many errors may occur in SMT lines. In this paper, we surveyed methods presented for the optical inspection of solder joints on PCBs. The methods are grouped by problem-solving approach: reference-based, machine learning/computer vision, deep learning, and 3D reconstruction. We compare and discuss these approaches according to their advantages and disadvantages, with a focus on the more recent deep learning and 3D reconstruction techniques, and list the public datasets for solder joints inspection. Since defective samples rarely occur in the SMT manufacturing lines, public datasets have few defective samples that are essential for the inspection task. To fill this gap, we publish a public dataset with both normal and different types of SMT errors. Our dataset can be used as a benchmark to compare different algorithms. The dataset is available at https://github.com/furkanulger/solder-joint-dataset.

A novel multiple-instance hidden Markov model (MI-HMM) is introduced for classification of time-series data, and its training is developed using stochastic expectation maximization. The MI-HMM provides a single statistical form to learn the parameters of an HMM in a multiple-instance learning framework without introducing any additional parameters. The efficacy of the model is shown both on synthetic data and on a real landmine data set. Experiments on both the synthetic data and the landmine data set show that an MI-HMM can achieve statistically significant performance gains when compared with the best existing HMM for the landmine detection problem, eliminate the ad hoc approaches in training set selection, and introduce a principled way to work with ambiguous time-series data.

In the United States, more than 12000 renal transplantations are performed annually; but the transplanted kidneys face a number of surgical and medical complications that cause a decrease in their functionality. In an effort to understand the reasons for this functionality decrease, considerable attention has recently been focused on Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) due to its superior functional and anatomical information. The biggest challenge in the analysis of DCE-MRI is the segmentation of kidneys from abdomen images because of the high noise and partial volume effects introduced during the rapid and repeated scanning process. In this paper, a general framework is introduced for the segmentation of kidneys from DCE-MR images of the abdomen. The proposed segmentation algorithm consists of three main steps. In the first step, an average kidney shape is constructed from a dataset of previously segmented kidneys, and an average signed distance map density is obtained describing the shape of the kidneys. In the second step, the gray level density is calculated for a given new kidney image using a modified expectation maximization (EM) algorithm. In the third step, a deformable model is evolved based on the two density functions obtained from the previous two steps: the first one describes the prior shape of the kidney, and the second one describes the distribution of the gray level inside and outside the kidney region. The new deformable model is able to handle intricate shapes without getting stuck in edge points; and gives very promising results that are comparable to radiologists' segmentation.

Assigning medical codes for patients is essential for healthcare organizations, not only for billing purposes but also for maintaining accurate records of patients' medical histories and analyzing the outputs of certain procedures. Due to the abundance of disease codes, it can be laborious and time-consuming for medical specialists to manually assign these codes to each procedure. To address this problem, we discuss the automatic prediction of ICD-9 codes, the most popular and widely accepted system of medical coding. We introduce a two-stream deep learning framework specifically designed to analyze multi-modal data. This framework is applied to the extensive and publicly available MIMIC-III dataset, enabling us to leverage both numerical and text-based data for improved ICD-9 code prediction. Our system uses text representation models to understand the text-based medical records; the Gated Recurrent Unit (GRU) to model the numerical health records; and fuses these two streams to automatically predict the ICD-9 codes used in the intensive care unit. We discuss the preprocessing and classification methods and demonstrate that our proposed two-stream model outperforms other state-of-the-art studies in the literature.