Browsing by Author "Zhao, Yang"
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
- Anomaly Detection from Patient Visit Data
Perustieteiden korkeakoulu | Master's thesis(2016-10-27) Zhao, YangHospital operation cost rises due to the growing demand for outpatient services by increasing elderly population. To reduce the operation cost and serve the patients better, improvements on the efficiency in healthcare service institutes are required. Among several potential aspects of efficiency improvements, smoother patient visits are highly desired. Thanks to the digital era, patient visits to the hospital can be recorded with all details. The Oulu Hospital in Finland starts to gather patient visits data since 2011, using queue system provided by X-Akseli company. Utilizing these collected data, this thesis aims at designing a practical way of detecting anomalies from patient visits. With the help from this system, the hospital administrative staff could analyze the performance of the queue procedure in the hospital and optimize the procedure. Even better, the system can identify anomalies in real-time so that the patient can get immediate help when it is needed. The thesis explored two categories of methods: clustering methods and generative methods. Four candidate algorithms, K-Means, DBSCAN, Markov Chain, and Hidden Markov Model, are discussed. The discussion suggests that DBSCAN and Hidden Markov Model are more practical. Then we proposed a new data representation and used negative binomial distribution in Hidden Markov Model to model patient states durations. The experiment result was visualized using t- SNE and evaluated by user interpretation. The analyses show that both DBSCAN and Hidden Markov Model can effectively detect anomalies from patient visits data. But in terms of time and space complexity, and real-time detection, Hidden Markov Model is a better choice. - Hyperdoping-regulated room-temperature NO2 gas sensing performances of black silicon based on lateral photovoltaic effect
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2023-05-01) Wang, Wenjing; Li, Hua; Liu, Xiaolong; Ma, Shengxiang; Zhao, Yang; Dong, Binbin; Li, Yuan; Ning, Xijing; Zhao, Li; Zhuang, JunBlack silicon co-hyperdoped with sulfur and nitrogen in different ratios is prepared by femtosecond laser-assisted chemical etching in the mixed atmosphere of SF6 and NF3 with varying gas pressure ratios. Their room-temperature NO2 gas sensing capability is studied systematically, in which the photocurrent as a readout signal is generated by the lateral photovoltaic effect of black silicon under an asymmetrical light illumination. These co-hyperdoped black silicon exhibits high response, fast response/recovery, ultrawide detection range from 29 ppb to 2000 ppm, excellent selectivity and acceptable long-term durability over 3 months. Moreover, NO2 gas sensing performances are effectively tuned or optimized by deliberately changing the co-doping ratio of sulfur and nitrogen, as different photovoltaic characteristics are induced by changes in morphology and structural defects resulting from different hyperdoping. Specifically, ultra-high relative gas response (~3955%@20 ppm NO2) and superior selectivity are obtained at the SF6/NF3 pressure ratio of 56/14, while faster response/recovery time (17 s/ 47 s@20 ppm NO2) and response photocurrent with a weaker disturbance by humidity are given by the samples with SF6/NF3 of 7/63 and 63/7, respectively. Therefore, such black silicon material has good potential to meet different application needs. - Light-optimized photovoltaic self-powered NO2 gas sensing based on black silicon
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2021-08-01) Zhao, Yang; Liu, Xiao Long; Ma, Sheng Xiang; Wang, Wen Jing; Ning, Xi Jing; Zhao, Li; Zhuang, JunThe NO2 sensing performance of a special lateral photovoltaic self-powered gas sensor based on the N-hyperdoped microstructured silicon (N-Si) is systematically studied under the different light illumination. The dependence of sensing characteristics on light intensity and wavelength is obtained, respectively. Results show that the sensing properties can be changed effectively by the different intensities and wavelengths, suggesting that a multidimensional regulation/optimization for the sensing characteristics is possible by light. More interestingly, the light with wavelength of 940 nm and intensity of ∼18 μW/cm2 could bring a comprehensive optimization for gas sensing, under which the N-Si sensor exhibits the excellent overall performance with simultaneously the low light power needed, good gas response, high sensitivity, wide detectable range and short response time at room temperature.