GLFNet: Global-local fusion network for the segmentation in ultrasound images.

Ultrasound imaging, as a portable and radiation-free modality, presents challenges for accurate segmentation due to the variability of lesions and the similar intensity values of surrounding tissues. Current deep learning approaches leverage convolution for extracting local features and self-attention for handling global dependencies. However, traditional CNNs are spatially local, and Vision Transformers lack image specific bias and are computationally demanding. In response, we propose the Global-Local Fusion Network (GLFNet), a hybrid structure addressing the limitations of both CNNs and Vision Transformers. The GLFNet, featuring Global-Local Fusion Blocks (GLFBlocks), integrates global semantic information with local details to improve segmentation. Each GLFBlock comprises Global and Local Branches for feature extraction in parallel. Within the Global and Local Branches, we introduce the Self-Attention Convolution Fusion Block (SACFBlock), which includes a Spatial-Attention Module and Channel-Attention Module. Experimental results show that our proposed GLFNet surpasses its counterparts in the segmentation tasks, achieving the overall best results with an mIoU of 79.58% and Dice coefficient of 74.62% in the DDTI dataset, an mIoU of 76.61% and Dice coefficient of 71.04% in the BUSI dataset, and an mIoU of 86.77% and Dice coefficient of 87.38% in the BUID dataset. The fusion of local and global features contributes to enhanced performance, making GLFNet a promising approach for ultrasound image segmentation.

Location verification algorithm of wearable sensors for wireless body area networks.

BACKGROUND: Knowledge of the location of sensor devices is crucial for many medical applications of wireless body area networks, as wearable sensors are designed to monitor vital signs of a patient while the wearer still has the freedom of movement. However, clinicians or patients can misplace the wearable sensors, thereby causing a mismatch between their physical locations and their correct target positions. An error of more than a few centimeters raises the risk of mistreating patients. OBJECTIVE: The present study aims to develop a scheme to calculate and detect the position of wearable sensors without beacon nodes. METHODS: A new scheme was proposed to verify the location of wearable sensors mounted on the patient's body by inferring differences in atmospheric air pressure and received signal strength indication measurements from wearable sensors. Extensive two-sample t tests were performed to validate the proposed scheme. RESULTS: The proposed scheme could easily recognize a 30-cm horizontal body range and a 65-cm vertical body range to correctly perform sensor localization and limb identification. CONCLUSIONS: All experiments indicate that the scheme is suitable for identifying wearable sensor positions in an indoor environment.

Differential barometric-based positioning technique for indoor elevation measurement in IoT medical applications.

BACKGROUND: Medical applications have begun to benefit from Internet of Things (IoT) technology through the introduction of wearable devices. Several medical applications require accurate patient location as various changes affect pressure parameters inside the body. OBJECTIVE: This study aims to develop a system to measure indoor altitude for IoT medical applications. METHODS: We propose a differential barometric-based positioning system to estimate the altitude between a reference sensor and a localizing sensor connected to the human body. The differential barometric altimetry model is introduced to estimate indoor elevations and eliminate environmental artifacts. In addition, a Gaussian filter processing is adopted to remove noise from the elevation measurements. The proposed system is then investigated through extensive experiments, using various evaluation criteria. RESULTS: The results indicate that the proposed system yielded good accuracy with reduced implementation complexity and fewer costs. CONCLUSIONS: The proposed system is resilient compared to other indoor localization approaches, even when numerous environmental artifacts in indoor environments are present.

Energy Efficient Moving Target Tracking in Wireless Sensor Networks.

Moving target tracking in wireless sensor networks is of paramount importance. This paper considers the problem of state estimation for L-sensor linear dynamic systems. Firstly, the paper establishes the fuzzy model for measurement condition estimation. Then, Generalized Kalman Filter design is performed to incorporate the novel neighborhood function and the target motion information, improving with an increasing number of active sensors. The proposed measurement selection approach has some advantages in time cost. As such, if the desired accuracy has been achieved, the parameter initialization for optimization can be readily resolved, which maximizes the expected lifespan while preserving tracking accuracy. Through theoretical justifications and empirical studies, we demonstrate that the proposed scheme achieves substantially superior performances over conventional methods in terms of moving target tracking under the resource-constrained wireless sensor networks.

Towards an optimal energy consumption for unattended mobile sensor networks through autonomous sensor redeployment.

Energy hole is an inherent problem caused by heavier traffic loads of sensor nodes nearer the sink because of more frequent data transmission, which is strongly dependent on the topology induced by the sensor deployment. In this paper, we propose an autonomous sensor redeployment algorithm to balance energy consumption and mitigate energy hole for unattended mobile sensor networks. First, with the target area divided into several equal width coronas, we present a mathematical problem modeling sensor node layout as well as transmission pattern to maximize network coverage and reduce communication cost. And then, by calculating the optimal node density for each corona to avoid energy hole, a fully distributed movement algorithm is proposed, which can achieve an optimal distribution quickly only by pushing or pulling its one-hop neighbors. The simulation results demonstrate that our algorithm achieves a much smaller average moving distance and a much longer network lifetime than existing algorithms and can eliminate the energy hole problem effectively.