Poor placental development and placental defects can lead to adverse pregnancy outcomes such as pre-eclampsia, fetal growth restriction, and stillbirth. This study introduces two sensors, which use a near-infrared spectroscopy (NIRS) technique to measure placental oxygen saturation transabdominally. The first one, an NIRS sensor, is a wearable device consisting of multiple NIRS channels. The second one, a Multimodal sensor, which is an upgraded version of the NIRS sensor, is a wireless and wearable device, integrating a motion sensor and multiple NIRS channels. A pilot clinical study was conducted to assess the feasibility of the two sensors in measuring transabdominal placental oxygenation in 36 pregnant women (n = 12 for the NIRS sensor and n = 24 for the Multimodal sensor). Among these subjects, 4 participants had an uncomplicated pregnancy, and 32 patients had either maternal pre-existing conditions/complications, neonatal complications, and/or placental pathologic abnormalities. The study results indicate that the patients with maternal complicated conditions (69.5 ± 5.4%), placental pathologic abnormalities (69.4 ± 4.9%), and neonatal complications (68.0 ± 5.1%) had statistically significantly lower transabdominal placental oxygenation levels than those with an uncomplicated pregnancy (76.0 ± 4.4%) (F (3,104) = 6.6, p = 0.0004). Additionally, this study shows the capability of the Multimodal sensor in detecting the maternal heart rate and respiratory rate, fetal movements, and uterine contractions. These findings demonstrate the feasibility of the two sensors in the real-time continuous monitoring of transabdominal placental oxygenation to detect at-risk pregnancies and guide timely clinical interventions, thereby improving pregnancy outcomes.

In this paper, we present a coarse-to-fine convolutional neural network (CF-CNN) for learning multilabel classes. The basis of the proposed CF-CNN is a disjoint grouping method that first creates a class group with hierarchical association, and then assigns a new label to a class belonging to each group so that each class acquires multiple labels. CF-CNN consists of one main network and two subnetworks. Each subnetwork performs coarse prediction using the group labels created by the disjoint grouping method. The main network includes a refine convolution layer and performs fine prediction to fuse the feature maps acquired from the subnetwork. The generated class set in the upper level has the same classification boundary to that in the lower level. Since the classes belonging to the upper level label are classified with a higher priority, parameter optimization becomes easier. In experimental results, the proposed method is applied to various classification tasks to show a higher classification accuracy by up to 3% with a much smaller number of parameters without modification of the baseline model.

The emergence of the global coronavirus pandemic in 2019 (COVID-19 disease) created a need for remote methods to detect and continuously monitor patients with infectious respiratory diseases. Many different devices, including thermometers, pulse oximeters, smartwatches, and rings, were proposed to monitor the symptoms of infected individuals at home. However, these consumer-grade devices are typically not capable of automated monitoring during both day and night. This study aims to develop a method to classify and monitor breathing patterns in real-time using tissue hemodynamic responses and a deep convolutional neural network (CNN)-based classification algorithm. Tissue hemodynamic responses at the sternal manubrium were collected in 21 healthy volunteers using a wearable near-infrared spectroscopy (NIRS) device during three different breathing conditions. We developed a deep CNN-based classification algorithm to classify and monitor breathing patterns in real time. The classification method was designed by improving and modifying the pre-activation residual network (Pre-ResNet) previously developed to classify two-dimensional (2D) images. Three different one-dimensional CNN (1D-CNN) classification models based on Pre-ResNet were developed. By using these models, we were able to obtain an average classification accuracy of 88.79% (without Stage 1 (data size reducing convolutional layer)), 90.58% (with 1 × 3 Stage 1), and 91.77% (with 1 × 5 Stage 1).

Recently, the stereo imaging-based image enhancement approach has attracted increasing attention in the field of video analysis. This paper presents a dual camera-based stereo image defogging algorithm. Optical flow is first estimated from the stereo foggy image pair, and the initial disparity map is generated from the estimated optical flow. Next, an initial transmission map is generated using the initial disparity map. Atmospheric light is then estimated using the color line theory. The defogged result is finally reconstructed using the estimated transmission map and atmospheric light. The proposed method can refine the transmission map iteratively. Experimental results show that the proposed method can successfully remove fog without color distortion. The proposed method can be used as a pre-processing step for an outdoor video analysis system and a high-end smartphone with a dual camera system.

This paper presents a novel hybrid sensor-based intrusion detection system for low-power surveillance in an empty, sealed indoor space with or without illumination. The proposed system includes three functional steps: (i) initial detection of an intrusion event using a sound field sensor; (ii) automatic lighting control based on the detected event, and (iii) detection and tracking the intruder using an image sensor. The proposed hybrid sensor-based surveillance system uses a sound field sensor to detect an abnormal event in a very low-light or completely dark environment for 24 h a day to reduce the power consumption. After detecting the intrusion by the sound sensor, a collaborative image sensor takes over an accurate detection and tracking tasks. The proposed hybrid system can be applied to various surveillance environments such as an office room after work, empty automobile, safety room in a bank, and armory room. This paper deals with fusion of computer-aided pattern recognition and physics-based sound field analysis that reflects the symmetric aspect of computer vision and physical analysis

Most currently available wearable devices to noninvasively detect hypoxia use the spatially resolved spectroscopy (SRS) method to calculate cerebral tissue oxygen saturation (StO₂). This study applies the single source—detector separation (SSDS) algorithm to calculate StO₂. Near-infrared spectroscopy (NIRS) data were collected from 26 healthy adult volunteers during a breath-holding task using a wearable NIRS device, which included two source—detector separations (SDSs). These data were used to derive oxyhemoglobin (HbO) change and StO₂. In the group analysis, both HbO change and StO₂ exhibited significant change during a breath-holding task. Specifically, they initially decreased to minimums at around 10 s and then steadily increased to maximums, which were significantly greater than baseline levels, at 25–30 s (p-HbO < 0.001 and p-StO₂ < 0.05). However, at an individual level, the SRS method failed to detect changes in cerebral StO₂ in response to a short breath-holding task. Furthermore, the SSDS algorithm is more robust than the SRS method in quantifying change in cerebral StO₂ in response to a breath-holding task. In conclusion, these findings have demonstrated the potential use of the SSDS algorithm in developing a miniaturized wearable biosensor to monitor cerebral StO₂ and detect cerebral hypoxia.