Electrical impedance tomography (EIT), a noninvasive and radiation-free medical imaging technique, has been used for continuous real-time regional lung aeration. However, adhesive electrodes could cause discomfort and increase the risk of skin injury during prolonged measurement. Additionally, the conductive gel between the electrodes and skin could evaporate in long-term usage and deteriorate the signal quality. To address these issues, in this work, textile electrodes integrated with a clothing belt are proposed to achieve EIT lung imaging along with a custom portable EIT system. The simulation and experimental results have verified the validity of the proposed portable EIT system. Furthermore, the imaging results of using the proposed textile electrodes were compared with commercial electrocardiogram electrodes to evaluate their performance.

Photoacoustic imaging (PAI) has become a popular technique for biomedical diagnosis. However, current systems are overly complex or use bulky piezoelectric materials, necessitating options other than these methods for future PAI systems. In this study, a wearable transparent ultrasonic transducer was developed and applied in a PAI system with excellent performance. The acoustic sensor was fabricated with a sandwich structure consisting of 150 nm thick amorphous indium tin oxide on both sides of a $110~\mu \text{m}$ commercial polyvinylidene fluoride film. This single-element sensor exhibited the performance of a 6.7 MHz center frequency, an 86.3% −3 dB fractional bandwidth, and a $20\times20\,\,\times $ 36 mm ³ volumetric imaging field. Modified imaging phantoms were made to evaluate the lateral resolution, imaging depth, ability to make a convex photoacoustic image, quality of 3D imaging, and capability to perform PAI directly in the ambient environment with a customized phantom. In summary, the study has demonstrated the sensor’s potential for large-field PAI application in wearable health devices at a low cost.

Acoustic pyrometer is expected to be a useful non-invasive method for monitoring gas temperature distribution inside a steel making furnace. On the superficial layer above the burden of blast furnace, most of the high temperature gas is concentrated near the center and tracking the position of the hotspot is critical for the productivity. However, most of the existing acoustic temperature distribution reconstruction algorithms are developed with relatively uniform temperature distribution environments. Besides, their capabilities of tracking the pinnacle of temperature distribution in the region of interest (ROI) are rarely discussed. In this research, a reconstruction method of acoustic temperature tomography dedicated for highly centralized gas temperature distribution is proposed and demonstrated. The key metrics include the reproducibility of two-dimensional temperature distribution, the sensitivity of hotspot shift, and the accuracy of point-to-point/peak temperature. To optimize the result of each metric, previous approaches of acoustic temperature tomography have been firstly evaluated. Then, investigation of effects from shape and size of meshes are proceeded to improve the performance. After that, a novel method to address convergence issues while using iterative method is introduced. Consequently, the reconstruction method proposed in this paper could effectively visualize the temperature map while hotspot moves to different locations. It could also sense the occurrence of a hotspot (2.56% of ROI) traveled from center to 1% of ROI’s diameter. Moreover, a competitive accuracy with 5.89% and 1.46% error at point-to-point root-mean-square (RMS) and peak temperature is achieved respectively. Finally, a practical acoustic 2D pyrometer consisted by 12 ultrasonic transducers arranged in a circular pattern with 1m width of ROI successfully detected the shift of a hotspot when the displacement of a heater reaches 5cm.

Computer vision has been applied in many fields recently to extract useful information from images. One such application is the monitoring of various aquaculture species to increase production. By monitoring the locations and quantities of the white shrimp, the aquaculture farmers could deliver the feed more precisely. Besides, the information about the length of the white shrimp could make the farmers estimate the delivery time accurately. Usually, to ensure the accuracy of computer vision, a relatively high-quality picture is required. However, the quality of underwater photography is easily influenced by the light, color, and turbidity of the medium. Compared to optical photos, the imaging mechanism of ultrasound is less affected by these effects. This study proposes an innovative white shrimp monitoring system that combines ultrasound imaging technology with YOLOv4. The database of the shrimps’ ultrasound images was built by imaging the different parts of the shrimp from various viewing angles with a linear ultrasonic probe. Four models using training data of different scenarios were successfully trained to recognize the locations of the shrimps from the ultrasound images. Among these models, the best was the one trained with 650 one-shrimp and 1080 two-shrimp practical transverse ultrasound images and 6500 images from data augmentation. Unlike optical pictures, ultrasound images are cross-sectional images that slice across certain parts of the shrimps. Therefore, a bi-directional scanning approach was adopted in this study. The ultrasound probe was carried by a two-axis motor to capture the images from two orthogonal viewing angles within a 12.69 cm × 12.69 cm region of interest. After 260 images were captured, the locations of the shrimps in each image were recognized and the centers of the bounding boxes were marked. To determine the number of shrimps, a voting method was developed based on the spectral clustering algorithm to group the marked coordinates. Finally, the number, lengths, and positions of the shrimps were reported. To evaluate the accuracy of the proposed monitoring system, 100 shrimps with 40 different layouts containing 1 to 4 shrimps were tested. The averaged quantity error, position error, and length error were 97.3%, 0.97 cm, and 8.99%, respectively. The standard deviation of the position error and the length error were 0.55 cm and 5.42%, respectively. The results demonstrated that the proposed system can provide useful information on shrimps and is feasible for shrimp farming applications.

Acoustic tomography (AT) is considered a promising visualization technique for gas temperature distribution (TD). Generally, a temperature map of a region of interest (ROI) is reconstructed with acoustic velocities of multiple routes inside the ROI using an AT reconstruction algorithm. To improve the accuracy of the reconstruction, increasing the number of iterations is inevitable, which may be time-consuming. Besides, existing reconstruction algorithms rarely consider utilizing practical measurements to improve their performance. In this study, a convolutional neural network is proposed to train a machine learning model that can reconstruct a gas TD from acoustic velocities. By adjusting the label and the loss function, a practical training approach was found. Six models were successfully trained to reconstruct a gas TD. Two were trained with the ideal TD, three with a reconstructed TD, and one with temperatures from specific locations. After that, a TD with peak temperatures located in 13 different positions was applied to test the models’ performance in tracking the hot spot. The results were compared with an existing reconstruction method. Besides, the acoustic velocities from three gas TDs were applied to evaluate the 2D visualization performance. One of them was similar to the training data and the other two were different. The results indicated that the models trained with the ideal gas TD could track the hot spot more closely, and the models trained with reconstructed gas TDs had similar performance as the selected reconstruction algorithm. However, the 2D visualization results using models trained with the ideal gas TD were poor compared with models trained with reconstructed TDs when the input acoustic velocities were different from the training data. This indicated that the proposed method could successfully learn the relationship between TD and acoustic velocities from an ordinary reconstruction algorithm. Furthermore, the execution time of the proposed model was 0.109s, which is 96% less than the selected iterative reconstruction method. Consequently, the proposed neural networks should be considered a reliable and efficient 2D gas TD reconstruction methodology.