Speech Recognition Using Intelligent Piezoresistive Sensor Based on Polystyrene Sphere Microstructures

Rapid advances in wearable sensing technology have demonstrated unprecedented opportunities for artificial intelligence. In comparison with the traditional hand-held electrolarynx, a wearable and intelligent artificial throat with sound-sensing ability is a more comfortable and versatile method to assist disabled people with communication. Herein, a piezoresistive sensor with a novel configuration is demonstrated, which consists of polystyrene (PS) spheres as microstructures sandwiched between silver nanowires and reduced graphene oxide layers. In fact, changes in the device's conducting patterns are obtained by spay-coating the various weight ratios and sizes of the PS microspheres, which is a fast and convenient way to establish microstructures for improving sensitivity. The wearable artificial throat device also exhibits high sensitivity, fast response time, and ultralow intensity level detection. Moreover, the device's excellent mechanical-electrical performance allows it to detect subtle throat vibrations that can be converted into controllable sounds. In this case, an intelligent artificial throat is achieved by combining a deep learning algorithm with a highly flexible piezoresistive sensor to successfully recognize five different words (help, sick, patient, doctor, and COVID) with an accuracy exceeding 96%. Herein, new opportunities in voice control as well as other human-machine interface applications are opened.

Double-Network Protein Hydrogels as Flexible Pressure Sensors for Contactless Delivery

To meet the growing demand for sustainable development and ecofriendliness, hydrogels based on biopolymers have attracted widespread attention for developing flexible pressure sensors. Natural globular proteins exhibit great potential for developing biobased pressure sensors owing to their advantages of high water solubility, easy gelation, biocompatibility, and low production cost. However, realizing globular protein hydrogel-based sensors with interfacial and bulk toughness for pressure sensing and use in wearable devices remains a challenge. This study focuses on developing a high-performance flexible pressure sensor based on a biobased protein hydrogel. Consequently, a flexible protein/polyacrylamide (PAM) hydrogel with a featured double-network (DN) structure linked covalently with hydrogen bonds was first synthesized via a one-pot method based on natural ovalbumin (OVA). The unique DN structure of the as-synthesized OVA/PAM hydrogel affords excellent mechanical performance, flexibility, and adhesion properties. The mechanical properties of the DN hydrogel were enhanced after further cross-linking with Fe3+ and treatment with glycerol. Subsequently, the flexible pressure sensor was constructed by sandwiching a microstructured OVA/PAM dielectric layer between two flexible silver nanowire electrodes. The obtained sensor exhibits a high sensitivity of 2.9 kPa-1 and a short response time of 18 ms, ensuring the ability to monitor physiological signals. Based on its excellent performance, the fabricated sensor was used for monitoring the signals obtained using practical applications such as wrist bending, finger knocking, stretching, international Morse code, and pressure distribution. Particularly, we implemented a contactless delivery system using the fabricated OVA-based pressure sensors linked to unmanned vehicles and global positioning systems, providing a solution for low-risk commodity distribution during Coronavirus disease 2019 (COVID-19).

Measurement and prediction of systemic risk in China?s banking industry

This research uses a hybrid systemic risk indicator (rSYR) to measure the systemic financial risk of China's banking industry from 2009 to 2019 and combines rSYR with sSYR (new standardized rSYR) to more accurately determine systemic important banks. We also forecast systemic risk in the next period, finding that large-scale banks (such as ICBC, Bank of China, Agricultural Bank of China, and China Merchants Bank) have high systemic importance. After eliminating the impact of scale, we then pay attention to the possibility of systemic risk brought by some smaller banks (such as Huaxia Bank and Everbright Bank). Through the prediction of systemic risk in the next six months, we also find out that the possibility of systemic risk caused by possible capital shortage brought by Agricultural Bank of China, Ping An Bank, Bank of China and Everbright Bank is more obvious, which is worth paying greater attention.

Flexible sensing enabled intelligent manipulator system (FSIMS) for avocados (Persea Americana Mill)

In the face of the COVID-19 pandemic and the global sales trend of fruits, automatic ripeness grading of fruits is of great significance for enterprises, reducing labor-related costs and precise resource regulation of the fruit industry chain. The wrong ripeness grading may lead to inferior products entering the market chain and resulting in over ripeness, spoilage, quality degradation, and economic loss issues. Traditional manual grading and machine vision-enabled grading methods are facing a series of challenges, such as low efficiency, inconsistent grading standards, and vulnerability to environmental interferences. Therefore, a flexible sensing enabled intelligent manipulator system (FSIMS) is developed for efficient, automatic and accurate ripeness grading of avocados, one of the most popular and economically valuable fruits in the world. When avocados of different ripeness level are gripping, the flexible sensing units attached in the clamps can sense the firmness of the contact points and feedback different pressure values of the system, which could accurately determine four ripeness levels of avocados. Compared with traditional manual or machine vision enabled fruit ripeness grading methods, the designed FSIMS could achieve better grading effect (97.5% accuracy), and the system also has a faster grading speed (the fast-grading speed could reach 1.3 s/time) and high environmental robustness. The application of FSIMS could effectively reduce the waste of avocados in the market supply chain, greatly alleviating the labor-intensive and inefficiency problems of the fruits ripeness grading, thereby promoting the more sustainable and cleaner production of the avocado industry.

[Epidemiological characteristics of 2019-nCoV Delta variant in Gansu province].

Objective: To analyze the epidemiological characteristics of COVID-19 caused by 2019-nCoV Delta variant (B.1.617.2) in Gansu province, and provide evidence for the prevention and control of COVID-19. Methods: The information of COVID-19 cases, including demographic characteristics, epidemiological history, onset date, diagnosis date, exposure place, detection way and infection source, in Gansu from 17 October to 25 November, 2021 were collected. Software Excel 2016,SPSS 22 and ArcGIS 10.7 were used for data process and analysis. Results: As of November 25, 2021, a total of 146 COVID-19 cases had been reported in Gansu and the epidemic affected 10 counties (districts) in 5 cities. The epidemic of COVID-19 in Gansu had three stages: imported case stage,imported-local case stage and local case stage. The age of cases ranged from 1 to 87 years,and the cases in age group 18-59 years accounted for 59.59% (87/146). The male to female ratio of the cases was 1∶1.12 (69∶77). The cases were mainly people engaged in business services (17.12%, 25/146),retirees (15.75%, 23/146),students (13.70%, 20/146),the jobless and unemployed (12.33%, 18/146). In 3 epidemic stages, the cases aged 18-59 years accounted for 44.44%,54.41% and 70.00% respectively,showing an upward trend,and there were differences among different populations (trend χ2=23.24, P<0.001). Also, the incubation period of the cases tended to decrease, and severe cases accounted for 33.33% (6/18), 19.12% (13/68) and 3.33% (2/60) respectively, showing a downward trend. Community screening (25.34%, 37/146) and close contact screening were the main ways to detect cases,the cases detected by close contact screening in 3 epidemic stages accounted for 50.00% (9/18), 66.18% (45/68) and 86.67% (52/60) respectively. The epidemic had obvious case clustering in confined places,and the main exposure modes were living together (24.66%), working/studying together (11.64%), taking same transportation (9.59%) and dining together (9.59%). Conclusions: The COVID-19 epidemic in Gansu was caused by 2019-nCoV Delta variant from imported cases. The virus was mainly transmitted through travel, sharing transportation, dining together and home contact. The characteristics of COVID-19 epidemic in Gansu changed with time, the case's clinical symptoms were not obvious and the incubation period became shorter. The infections mainly occurred in group aged 18 years and above.

[Epidemiological characteristics of COVID-19 in Gansu province].

Objective: To understand the epidemiological characteristics of COVID-19 cases in different epidemic stages in Gansu province. Methods: Epidemiological investigation was conducted to collect the information of confirmed COVID-19 cases, including demographic, epidemiological and clinical information. Results: As of 25 February 2020, a total of 91 confirmed COVID-19 cases had been reported in Gansu. The epidemic of COVID-19 in Gansu can be divided as three different stages, i.e. imported case stage, imported-case plus indigenous case stage, and indigenous case stage. A total of 63 cases were clustered cases (69.23%), 3 cases were medical staff infected with non-occupational exposure. The initial symptoms included fever (54.95%, 50/91), cough (52.75%, 48/91), or fatigue (28.57%, 26/91), the proportion of each symptom showed a decreasing trend along with the three epidemic stages, but only the differences in proportions of fever (trend χ2=2.20, P<0.05) and fatigue (trend χ2=3.18, P<0.05) among the three epidemic stages were statistically significant. The cases with critical severe symptoms accounted for 42.85% (6/14), 23.73% (14/59) and 16.67% (3/18), respectively, in three epidemic stages, showed a decreasing trend (H=6.45, P<0.05). Also, the incubation period prolonged along with the epidemic stage (F=51.65, P<0.01), but the intervals between disease onset and hospital visit (F=5.32, P<0.01), disease onset and diagnosis (F=5.25, P<0.01) became shorter along with the epidemic stage. Additionally, the basic reproduction number (R0) had decreased from 2.61 in imported case stage to 0.66 in indigenous case stage. Conclusions: The COVID-19 epidemic in Gansu was caused by the imported cases, and about 2/3 cases were clustered ones. No medical worker was observed to be infected by occupational exposure. With the progression of COVID-19 epidemic in Gansu, the change in initial symptom and incubation period suggests, the early screening cannot only depend on body temperature monitoring.