An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance.

An essential aspect of controlling and preventing mosquito-borne diseases is to reduce mosquitoes that carry viruses. We designed a smart mosquito trap system to reduce the density of mosquito vectors and the spread of mosquito-borne diseases. This smart trap uses computer vision technology and deep learning networks to identify features of live Aedes aegypti and Culex quinquefasciatus in real-time. A unique mechanical design based on the rotation concept is also proposed and implemented to capture specific living mosquitoes into the corresponding chambers successfully. Moreover, this system is equipped with sensors to detect environmental data, such as CO2 concentration, temperature, and humidity. We successfully demonstrated the implementation of such a tool and paired it with a reliable capture mechanism for live mosquitos without destroying important morphological features. The neural network achieved 91.57% accuracy with test set images. When the trap prototype was applied in a tent, the accuracy rate in distinguishing live Ae. aegypti was 92%, with a capture rate reaching 44%. When the prototype was placed into a BG trap to produce a smart mosquito trap, it achieved a 97% recognition rate and a 67% catch rate when placed in the tent. In a simulated living room, the recognition and capture rates were 90% and 49%, respectively. This smart trap correctly differentiated between Cx. quinquefasciatus and Ae. aegypti mosquitoes, and may also help control mosquito-borne diseases and predict their possible outbreak.

The application of artificial intelligence to support biliary atresia screening by ultrasound images: A study based on deep learning models.

PURPOSE: Early confirmation or ruling out biliary atresia (BA) is essential for infants with delayed onset of jaundice. In the current practice, percutaneous liver biopsy and intraoperative cholangiography (IOC) remain the golden standards for diagnosis. In Taiwan, the diagnostic methods are invasive and can only be performed in selective medical centers. However, referrals from primary physicians and local pediatricians are often delayed because of lacking clinical suspicions. Ultrasounds (US) are common screening tools in local hospitals and clinics, but the pediatric hepatobiliary US particularly requires well-trained imaging personnel. The meaningful comprehension of US is highly dependent on individual experience. For screening BA through human observation on US images, the reported sensitivity and specificity were achieved by pediatric radiologists, pediatric hepatobiliary experts, or pediatric surgeons. Therefore, this research developed a tool based on deep learning models for screening BA to assist pediatric US image reading by general physicians and pediatricians. METHODS: De-identified hepatobiliary US images of 180 patients from Taichung Veterans General Hospital were retrospectively collected under the approval of the Institutional Review Board. Herein, the top network models of ImageNet Large Scale Visual Recognition Competition and other network models commonly used for US image recognition were included for further study to classify US images as BA or non-BA. The performance of different network models was expressed by the confusion matrix and receiver operating characteristic curve. There were two methods proposed to solve disagreement by US image classification of a single patient. The first and second methods were the positive-dominance law and threshold law. During the study, the US images of three successive patients suspected to have BA were classified by the trained models. RESULTS: Among all included patients contributing US images, 41 patients were diagnosed with BA by surgical intervention and 139 patients were either healthy controls or had non-BA diagnoses. In this study, a total of 1,976 original US images were enrolled. Among them, 417 and 1,559 raw images were from patients with BA and without BA, respectively. Meanwhile, ShuffleNet achieved the highest accuracy of 90.56% using the same training parameters as compared with other network models. The sensitivity and specificity were 67.83% and 96.76%, respectively. In addition, the undesired false-negative prediction was prevented by applying positive-dominance law to interpret different images of a single patient with an acceptable false-positive rate, which was 13.64%. For the three consecutive patients with delayed obstructive jaundice with IOC confirmed diagnoses, ShuffleNet achieved accurate diagnoses in two patients. CONCLUSION: The current study provides a screening tool for identifying possible BA by hepatobiliary US images. The method was not designed to replace liver biopsy or IOC, but to decrease human error for interpretations of US. By applying the positive-dominance law to ShuffleNet, the false-negative rate and the specificities were 0 and 86.36%, respectively. The trained deep learning models could aid physicians other than pediatric surgeons, pediatric gastroenterologists, or pediatric radiologists, to prevent misreading pediatric hepatobiliary US images. The current artificial intelligence (AI) tool is helpful for screening BA in the real world.

Noninvasive blood oxygen, heartbeat rate, and blood pressure parameter monitoring by photoplethysmography signals.

The popularization of long-term invasive tools for continuously monitoring blood pressure remains challenging. However, with the rising popularity of wearable personal health management devices, non-cuff blood pressure measurement technology that applies electrocardiography (ECG) and photoplethysmography (PPG) has gradually received increasing attention. In particular, whether blood pressure can be measured continuously by the PPG signal alone is of great interest. In this study, we aim to develop a device that includes systolic and diastolic blood pressure calculation formulas derived from characteristic waveform points in the PPG time domain and that can measure blood oxygenation and heart rate. This device applies empirical formulas developed by PPG waveforms in the PhysioNet MIMIC-II database to calculate blood pressure. The systolic and diastolic pressures are then compared with the actual blood pressures obtained from invasive blood pressure waveforms to verify the effectiveness and feasibility of the complete developed system. Overall, 263 waveforms with double peaks and 261 waveforms with only a single peak totaling 524 sets of data are used to derive the empirical formulas. The systolic blood pressure estimation result using single peak analysis has an excessively large error exceeding ±40 mmHg, providing no reference value. However, systolic blood pressure estimation is notably better in double peak analysis, with error values reducing to approximately 23 mmHg. Diastolic pressure estimation errors are low with both single (±7 mmHg) and double peak (±4 mmHg) analyses. The error is lower in double-peak analysis than in single-peak analysis for obtaining systolic pressure from PPG waves. We plan to use PPG to detect additional physiological parameters in the future, e.g., respiratory rate, heart rate variability, or irregular heartbeat, to further enhance the functionality of PPG-based wearable devices.