Deep learning technology has rapidly evolved in recent years. Bone age assessment (BAA) is a typical object detection and classification problem that would benefit from deep learning. Convolutional neural networks (CNNs) and their variants are hence increasingly used for automating BAA, and they have shown promising results. In this paper, we propose a complete end-to-end BAA system to automate the entire process of the Tanner-Whitehouse 3 method, starting from localization of the epiphysis-metaphysis growth regions within 13 different bones and ending with estimation of the corresponding BA. Specific modifications to the CNNs and other stages are proposed to improve results. In addition, an annotated database of 3300 X-ray images is built to train and evaluate the system. The experimental results show that the average top-1 and top-2 prediction accuracies for skeletal bone maturity levels for 13 regions of interest are 79.6% and 97.2%, respectively. The mean absolute error and root mean squared error in age prediction are 0.46 years and 0.62 years, respectively, and accuracy within one year of the ground truth of 97.6% is achieved. The proposed system is shown to outperform a commercially available Greulich-Pyle-based system, demonstrating the potential for practical clinical use. INDEX TERMS Bone age assessment, deep learning, GP, TW3.

Due do the various requirements of sensor applications, it is desired to design a neighbor discovery protocol that supports both symmetric and asymmetric duty cycles. This letter proposes a new block-based neighbor discovery protocol for asymmetric sensor networks by adapting the theory of balanced incomplete block designs and the Chinese remainder theorem. Through the simulation study, it is demonstrated that the proposed block-based neighbor discovery protocol outperforms other neighbor discovery methods, such as Disco, U-Connect, SearchLight, Hedis, and Todis.

No abstract

In wireless body sensor network systems (WB-SNSs), the sensor nodes have very limited battery power because they are tiny, lightweight, and wearable or implantable. As a result, WB-SNSs require a very efficient transmission power control (TPC) algorithm for effectively reducing energy consumption and extending the lifetime of sensor nodes. To achieve this goal, we propose a novel TPC algorithm referred to as hybrid TPC. The hybrid TPC algorithm adaptively selects a conservative or an aggressive control mechanism depending on current channel conditions. The conservative control mechanism, which slowly changes transmission power level (TPL), is suitable in a dynamic environment. On the other hand, the aggressive control mechanism, which rapidly changes TPL, is ideal in a static environment. In order to evaluate the effectiveness of the hybrid TPC algorithm, we implemented various TPC algorithms and compared their performances against the hybrid TPC algorithm in different channel environments. The experimental results showed that the hybrid TPC algorithm outperformed other TPC algorithms in all channel environments.

Abstract. Wireless body sensor network systems (WB-SNSs) can use diverse radio modules. However, previous studies did not consider different characteristics of radio modules, which deeply impact the performance of WBSNSs.In this paper, we analyze the performance of WB-SNSs using the representative radio modules CC2420 and CC1000. In this environment, we collected log data from real sensor devices deployed on the human body. After log data collection, we first show that CC2420 and CC1000 have different radio characteristics from diverse views, such as the received signal strength indication (RSSI) average and deviation, transmission power levels, and body movement. Through the analysis, we also find that an efficient transmission power control (TPC) algorithm should consider these diverse factors due to different radio modules.