Black swan event small-sample transfer learning (BEST-L) and its case study on electrical power prediction in COVID-19

2022 ◽  
Vol 309 ◽  
pp. 118458
Author(s):  
Chenxi Hu ◽  
Jun Zhang ◽  
Hongxia Yuan ◽  
Tianlu Gao ◽  
Huaiguang Jiang ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Electrical Power ◽  
Small Sample ◽  
Black Swan ◽  
Power Prediction ◽  
Sample Transfer

ER rule classifier with an optimization operator recommendation

2021 ◽  
pp. 1-13
Author(s):  
Xiaoyan Wang ◽  
Jianbin Sun ◽  
Qingsong Zhao ◽  
Yaqian You ◽  
Jiang Jiang
Keyword(s):  
Classification Accuracy ◽  
Comprehensive Analysis ◽  
Small Sample ◽  
Empirical Knowledge ◽  
Classification Methods ◽  
Turbofan Engine ◽  
Training Samples ◽  
Optimization Operator ◽  
Recommendation Strategy

It is difficult for many classic classification methods to consider expert experience and classify small-sample datasets well. The evidential reasoning rule (ER rule) classifier can solve these problems. The ER rule has strong processing and comprehensive analysis abilities for diversified mixed information and can solve problems with expert experience effectively. Moreover, the initial parameters of the classifier constructed based on the ER rule can be set according to empirical knowledge instead of being trained by a large number of samples, which can help the classifier classify small-sample datasets well. However, the initial parameters of the ER rule classifier need to be optimized, and choosing the best optimization algorithm is still a challenge. Considering these problems, the ER rule classifier with an optimization operator recommendation is proposed in this paper. First, the initial ER rule classifier is constructed based on training samples and expert experience. Second, the adjustable parameters are optimized, in which the optimization operator recommendation strategy is applied to select the best algorithm by partial samples, and then experiments with full samples are carried out. Finally, a case study on a turbofan engine degradation simulation dataset is carried out, and the results indicate that the ER rule classifier has a higher classification accuracy than other classic classifiers, which demonstrates the capability and effectiveness of the proposed ER rule classifier with an optimization operator recommendation.

Temporal dynamics of encrusting communities during the Late Devonian: a case study from the Central Devonian Field, Russia

Paleobiology ◽  
2017 ◽  
Vol 43 (4) ◽  
pp. 550-568 ◽  
Author(s):  
Michał Zatoń ◽  
Tomasz Borszcz ◽  
Michał Rakociński
Keyword(s):  
Temporal Dynamics ◽  
Small Sample ◽  
Time Interval ◽  
Faunal Turnover ◽  
Central Devonian Field ◽  
Before And After ◽  
Substrate Size ◽  
Mass Extinction Event ◽  
Diversity Dynamics

AbstractIn this study we focused on the dynamics of encrusting assemblages preserved on brachiopod hosts collected from upper Frasnian and lower Famennian deposits of the Central Devonian Field, Russia. Because the encrusted brachiopods come from deposits bracketing the Frasnian/Famennian (F/F) boundary, the results also shed some light on ecological differences in encrusting communities before and after the Frasnian–Famennian (F-F) event. To explore the diversity dynamics of encrusting assemblages, we analyzed more than 1300 brachiopod valves (substrates) from two localities. Taxon accumulation plots and shareholder quorum subsampling (SQS) routines indicated that a reasonably small sample of brachiopod host valves (n=50) is sufficient to capture the majority of the encrusting genera recorded at a given site. The richness of encrusters per substrate declined simultaneously with the number of encrusting taxa in the lower Famennian, accompanied by a decrease in epibiont abundance, with a comparable decrease in mean encrustation intensity (percentage of bioclasts encrusted by one or more epibionts). Epibiont abundance and occupancy roughly mirror each other. Strikingly, few ecological characteristics are correlated with substrate size, possibly reflecting random settlement of larvae. Evenness, which is negatively correlated with substrate size, shows greater within-stage variability among samples than between Frasnian and Famennian intervals and may indicate the instability of early Famennian biocenoses following the faunal turnover. The occurrence distribution of encrusters points to nonrandom associations and exclusions among several encrusting taxa. However, abundance and occupancy of microconchids remained relatively stable throughout the sampled time interval. The notable decline in abundance (~60%) and relatively minor decline in diversity (~30%) suggest jointly that encrusting communities experienced ecological collapse rather than a major mass extinction event. The differences between the upper Frasnian and lower Famennian encrusting assemblages may thus record a turnover associated with the F-F event.

scholarly journals Augmenting Crop Detection for Precision Agriculture with Deep Visual Transfer Learning—A Case Study of Bale Detection

2020 ◽  
Vol 13 (1) ◽  
pp. 23
Author(s):  
Wei Zhao ◽  
William Yamada ◽  
Tianxin Li ◽  
Matthew Digman ◽  
Troy Runge
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Precision Agriculture ◽  
Crop Production ◽  
Domain Adaptation ◽  
Training Data ◽  
Detection Accuracy ◽  
Detection Model ◽  
Agriculture Products

In recent years, precision agriculture has been researched to increase crop production with less inputs, as a promising means to meet the growing demand of agriculture products. Computer vision-based crop detection with unmanned aerial vehicle (UAV)-acquired images is a critical tool for precision agriculture. However, object detection using deep learning algorithms rely on a significant amount of manually prelabeled training datasets as ground truths. Field object detection, such as bales, is especially difficult because of (1) long-period image acquisitions under different illumination conditions and seasons; (2) limited existing prelabeled data; and (3) few pretrained models and research as references. This work increases the bale detection accuracy based on limited data collection and labeling, by building an innovative algorithms pipeline. First, an object detection model is trained using 243 images captured with good illimitation conditions in fall from the crop lands. In addition, domain adaptation (DA), a kind of transfer learning, is applied for synthesizing the training data under diverse environmental conditions with automatic labels. Finally, the object detection model is optimized with the synthesized datasets. The case study shows the proposed method improves the bale detecting performance, including the recall, mean average precision (mAP), and F measure (F1 score), from averages of 0.59, 0.7, and 0.7 (the object detection) to averages of 0.93, 0.94, and 0.89 (the object detection + DA), respectively. This approach could be easily scaled to many other crop field objects and will significantly contribute to precision agriculture.

Exploring trainers’ engaging instructional practices: a collective case study

2016 ◽  
Vol 40 (2) ◽  
pp. 111-127 ◽  
Author(s):  
Vishal Arghode ◽  
Jia Wang
Keyword(s):  
Learning Styles ◽  
Learning Outcomes ◽  
Training Session ◽  
Research Area ◽  
Small Sample ◽  
Training Context ◽  
Content Type ◽  
Collective Case Study ◽  
Study Approach

Purpose – This study aims to explore the phenomenon of training engagement from the trainers’ perspective. Specifically, two questions guided this inquiry. First, how do trainers define engagement in the training context? and What strategies do trainers use to engage trainees? Design/methodology/approach – The collective case study approach was adopted for this qualitative study. Seven cases were selected for in-depth analyses. Data were collected through individual, face-to-face interviews and analyzed using the constant comparative analysis method. Findings – Major findings suggest that engaging training practices take various forms. They include being trainee-centered, maximizing learning through entertaining and interesting instruction, accommodating different learning styles, eliciting trainee participation by creating an encouraging learning environment and connecting with trainees by building rapport early in a training session. Research limitations/implications – The small sample limits the generalizability of the findings. However, this study expands training literature by focusing on an under-explored research area, the role of engaging trainees in maximizing learning outcomes. Practical implications – For trainers, this study offered some specific strategies they can use to engage learners in the training context to achieve desired learning outcomes. In addition, the seven cases selected for this study may be used as a benchmark against which both experienced and novice trainers compared their own practices. Originality/value – This is one of very few qualitative studies with a focus on emotional aspects involved in training. The rich data from this study shed light on areas for future improvement, particularly regarding how to effectively engage trainees to maximize learning outcomes.

Pengaruh Curah Hujan dan Debit Air Terhadap Produktivitas Energi Listrik yang Dihasilkan Pada Pembangkit Listrik Tenaga Air (Studi Kasus: Sub Unit PLTA Kracak, Kabupaten Bogor Jawa Barat)

2020 ◽  
Vol 5 (1) ◽  
pp. 56-60
Author(s):  
Wildan Gunawan ◽  
Suyitno Muslim ◽  
Imam Arif Rahardjo
Keyword(s):  
River Discharge ◽  
Research Method ◽  
Rainfall Intensity ◽  
Discharge Rate ◽  
Electrical Power ◽  
Electric Energy ◽  
Energy Productivity ◽  
Rain Fall ◽  
Average Rain

This research is aimed to understand the effects of  rain fall and discharge rate towards hydro electric power plant productivity (case study at Kracak Sub Unit HPP, Bogor Regency Jawa Barat). Multiple regression tecnique analysis is used as research method with quantitative approach for describing the effects of rain fall and discharge rate towards hydro electric energy productivity. Based on Sub Unit PLTA Kracak during a highest down pour in June 2018 has gained electrical power about 173,583 kWh for 15,84 mm rain fall and the lowest rain fall in July 2018 is 0,86 mm only obtain 49,772 kWh electrical power with the average rain fall record in three stations is 8,9592 mm. Mean while, for the highest river discharge rate happened in February is 10,08 m3/detik which produce 198,296 kWh electrical power and the lowest in June that only gained 3,53 m3/detik which produce 49,772 kWh electrical power with the average of river discharge rate in 2018 is only 7,9858 m3/detik. The average of electrical power it self is only 156,0105 kWh for 8,9592 mm of rainfall and 7,9858 m3/detik river discharge rate record in 2018. The conclusion oh this research is the discharge rate in headwaters area is affected by rainfall intensity, but not necessarily affected to hydro electric energy productivity.   ABSTRAK Tujuan dari penelitian ini adalah untuk mengetahui pengaruh curah hujan dan debit air terhadap produktivitas energi listrik yang dihasilkan pada pembangkit listrik tenaga air (Studi Kasus: Sub Unit PLTA Kracak, Kabupaten Bogor Jawa Barat). Metode yang digunakan dalam penelitian ini adalah metode deskriptif dengan pendekatan kuantitatif teknik analisis data regresi berganda untuk mendiskripsikan data penelitian curah hujan dan debit air terhadap produktivitas energi listrik yang dihasilkan. Berdasarkan data hasil penelitian yang diperoleh di Sub Unit PLTA Kracak data curah hujan tertinggi pada tahun 2018 di Bulan Juni sebesar 15,84 mm dapat menghasilkan energi listrik sebesar 173,593 kWh dan terendah di Bulan Juli sebesar 0,86 mm dapat menghasilkan energi listrik sebesar  49,772 kWh dengan rata-rata pertahun 2018 yaitu sebesar 8,9592 mm di tiga stasiun. Sedangkan data debit air pada tahun 2018 tertinggi di Bulan Februari sebesar 10,08 m3/detik dapat menghasilkan energi listrik sebesar 198,296 kWh dan terendah di Bulan Juli sebesar 3,53 m3/detik dapat menghasilkan energi listrik sebesar 49,772 dengan rata-rata pertahun 2018 debit air sebesar 7,9858 m3/detik. Dengan rata-rata curah hujan 8,9592 mm dan debit air 7,9858 m3/detik dapat menghasilkan energi listrik rata-rata pertahun 2018 sebesar 156,0105 kWh selama tahun 2018. Dapat disimpulkan curah hujan tidak berpengaruh langsung terhadap produktivitas energi listrik yang dihasilkan sedangkan debit air berpengaruh terhadap produktivitas energi listrik.

The influence of homeschooling on entrepreneurial activities: a collective case study

2017 ◽  
Vol 59 (7/8) ◽  
pp. 706-719 ◽  
Author(s):  
Sarah Jeanne Pannone
Keyword(s):  
Locus Of Control ◽  
Small Sample Size ◽  
Research Literature ◽  
Small Sample ◽  
Content Type ◽  
Collective Case Study ◽  
Internal Locus Of Control ◽  
Entrepreneurial Characteristics ◽  
Entrepreneurial Activities

Purpose The purpose of this paper is to investigate how a homeschool education influences entrepreneurial characteristics and activity. Design/methodology/approach A collective case study design was used to investigate how a homeschool education influences entrepreneurial characteristics and activity. Findings From the participant interviews, surveys, and document analysis, three salient themes emerged. First, participants noted that their home education, at least in later years, was largely self-directed and that this independent, self-motivated type of learning impacted their subsequent entrepreneurial activities. Next, participants also related that they believed the alternative nature of their homeschooling education and its emphasis on being comfortable with being different influenced their entrepreneurial pathway. Finally, the third theme to surface was the idea that homeschooling helped develop an internal locus of control, a belief that is helpful in entrepreneurial undertakings. Research limitations/implications Research limitations included a lack of generalizability due to a small sample size and possible selection bias. Practical implications Despite these shortcomings, however, several implications exist. For example, the findings from this study show that homeschooling may be a viable alternative education method for parents looking to encourage entrepreneurial traits and activities in their children. Social implications Future areas of research were also identified, including a call to research the role locus of control plays in homeschooled students. Originality/value This study addresses an area that, to the knowledge of this researcher, is completely lacking from the research literature.

Sign in / Sign up

Export Citation Format

Share Document