Pneumoconiosis remains one of the most common and harmful occupational diseases in China, leading to huge economic losses to society with its high prevalence and costly treatment. Diagnosis of pneumoconiosis still strongly depends on the experience of radiologists, which affects rapid detection on large populations. Recent research focuses on computer-aided detection based on machine learning. These have achieved high accuracy, among which artificial neural network (ANN) shows excellent performance. However, due to imbalanced samples and lack of interpretability, wide utilization in clinical practice meets difficulty. To address these problems, we first establish a pneumoconiosis radiograph dataset, including both positive and negative samples. Second, deep convolutional diagnosis approaches are compared in pneumoconiosis detection, and a balanced training is adopted to promote recall. Comprehensive experiments conducted on this dataset demonstrate high accuracy (88.6%). Third, we explain diagnosis results by visualizing suspected opacities on pneumoconiosis radiographs, which could provide solid diagnostic reference for surgeons.

In this paper, an encoding system is proposed to further reduce the power consumption in parallel video encoding based on difference detection and Hilbert transform based workload estimation (HTWE). The proposed parallel encoding system provides an average of 40% computational complexity reduction for parallel encoding without objective performance loss. For the multi-core platform with frequency and voltage scalability, up to 78% of power reduction can be achieved.

With development of multi-core system, parallel encoder with fast algorithm is widely used to improve video encoding speed. In this paper, a dynamic slice-resize algorithm is proposed to balance workload and increase encoding speed for slice-level parallel encoder. This algorithm retrieves encoding workload from previous encoded frames and dynamically changes the slice size for the following frames to balance the encoding workload among slices. By applying the proposed algorithm, an average of 21% encoding speed improvement can be achieved for parallel video encoder without loss in objective performance.

The diagnosis-related group (DRG) system classifies patients into different groups in order to facilitate decisions regarding medical insurance payments. Currently, more than 600 standard DRGs exist in China. Payment details represented by DRG weights must be adjusted during decision-making. After modeling the DRG weight-determining process as a parameter-searching and optimization-solving problem, we propose a stochastic gradient tracking algorithm (SGT) and compare it with a genetic algorithm and sequential quadratic programming. We describe diagnosis-related groups in China using several statistics based on sample data from one city. We explored the influence of the SGT hyperparameters through numerous experiments and demonstrated the robustness of the best SGT hyperparameter combination. Our stochastic gradient tracking algorithm finished the parameter search in only 3.56 min when the insurance payment rate was set at 95%, which is acceptable and desirable. As the main medical insurance payment scheme in China, DRGs require quantitative evidence for policymaking. The optimization algorithm proposed in this study shows a possible scientific decision-making method for use in the DRG system, particularly with regard to DRG weights.

In this demo, a low power H.264/AVC video encoding system is demonstrated for surveillance video compression, which is based on our proposed algorithms as difference detection and Hilbert transform based workload estimation. Two surveillance video coding schemes (with and without our proposed methods, respectively) are implemented on multi-core embedded platform and compared side by side. The power consumption of each encoding scheme is measured during video encoding and displayed explicitly to show a more than 60% power reduction introduced by the proposed methods. The reconstructed video is also synchronized and displayed as the video is encoded to present a maximum of 50 times higher encoding speed.