scholarly journals Monitoring perception reliability in autonomous driving: Distributional shift detection for estimating the impact of input data on prediction accuracy

2021 ◽  
Author(s):  
Franz Hell ◽  
Gereon Hinz ◽  
Feng Liu ◽  
Sakshi Goyal ◽  
Ke Pei ◽  
...  
Keyword(s):  
Prediction Accuracy ◽  
Input Data ◽  
Autonomous Driving ◽  
Shift Detection ◽  
The Impact

scholarly journals The importance of input data on landslide susceptibility mapping

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Krzysztof Gaidzik ◽  
María Teresa Ramírez-Herrera
Keyword(s):  
Landslide Susceptibility ◽  
Prediction Accuracy ◽  
Input Data ◽  
Susceptibility Mapping ◽  
Landslide Inventory ◽  
Landslide Susceptibility Mapping ◽  
Topographic Data ◽  
Susceptibility Maps ◽  
Landslide Mass ◽  
The Impact

AbstractLandslide detection and susceptibility mapping are crucial in risk management and urban planning. Constant advance in digital elevation models accuracy and availability, the prospect of automatic landslide detection, together with variable processing techniques, stress the need to assess the effect of differences in input data on the landslide susceptibility maps accuracy. The main goal of this study is to evaluate the influence of variations in input data on landslide susceptibility mapping using a logistic regression approach. We produced 32 models that differ in (1) type of landslide inventory (manual or automatic), (2) spatial resolution of the topographic input data, (3) number of landslide-causing factors, and (4) sampling technique. We showed that models based on automatic landslide inventory present comparable overall prediction accuracy as those produced using manually detected features. We also demonstrated that finer resolution of topographic data leads to more accurate and precise susceptibility models. The impact of the number of landslide-causing factors used for calculations appears to be important for lower resolution data. On the other hand, even the lower number of causative agents results in highly accurate susceptibility maps for the high-resolution topographic data. Our results also suggest that sampling from landslide masses is generally more befitting than sampling from the landslide mass center. We conclude that most of the produced landslide susceptibility models, even though variable, present reasonable overall prediction accuracy, suggesting that the most congruous input data and techniques need to be chosen depending on the data quality and purpose of the study.

The Impact of Mental States on Semi-autonomous Driving Takeover Performance: A Systematic Review

2020 ◽  
Vol 64 (1) ◽  
pp. 1372-1376
Author(s):  
Gaojian Huang ◽  
Christine Petersen ◽  
Brandon J. Pitts
Keyword(s):  
Systematic Review ◽  
Autonomous Vehicles ◽  
Response Times ◽  
Autonomous Driving ◽  
Mental States ◽  
Manual Control ◽  
Monitoring Systems ◽  
Wide Range ◽  
Different Types ◽  
The Impact

Semi-autonomous vehicles still require drivers to occasionally resume manual control. However, drivers of these vehicles may have different mental states. For example, drivers may be engaged in non-driving related tasks or may exhibit mind wandering behavior. Also, monitoring monotonous driving environments can result in passive fatigue. Given the potential for different types of mental states to negatively affect takeover performance, it will be critical to highlight how mental states affect semi-autonomous takeover. A systematic review was conducted to synthesize the literature on mental states (such as distraction, fatigue, emotion) and takeover performance. This review focuses specifically on five fatigue studies. Overall, studies were too few to observe consistent findings, but some suggest that response times to takeover alerts and post-takeover performance may be affected by fatigue. Ultimately, this review may help researchers improve and develop real-time mental states monitoring systems for a wide range of application domains.

scholarly journals Landscape pattern and economic factors’ effect on prediction accuracy of cellular automata-Markov chain model on county scale

2020 ◽  
Vol 12 (1) ◽  
pp. 626-636
Author(s):  
Wang Song ◽  
Zhao Yunlin ◽  
Xu Zhenggang ◽  
Yang Guiyan ◽  
Huang Tian ◽  
...  
Keyword(s):  
Land Use ◽  
Markov Chain ◽  
Cellular Automata ◽  
Markov Model ◽  
Prediction Accuracy ◽  
Driving Mechanism ◽  
Economic Factors ◽  
Chain Model ◽  
The Impact ◽  
County Scale

AbstractUnderstanding and modeling of land use change is of great significance to environmental protection and land use planning. The cellular automata-Markov chain (CA-Markov) model is a powerful tool to predict the change of land use, and the prediction accuracy is limited by many factors. To explore the impact of land use and socio-economic factors on the prediction of CA-Markov model on county scale, this paper uses the CA-Markov model to simulate the land use of Anren County in 2016, based on the land use of 1996 and 2006. Then, the correlation between the land use, socio-economic data and the prediction accuracy was analyzed. The results show that Shannon’s evenness index and population density having an important impact on the accuracy of model predictions, negatively correlate with kappa coefficient. The research not only provides a reference for correct use of the model but also helps us to understand the driving mechanism of landscape changes.

scholarly journals Co-Simulation Framework for Optimal Allocation and Power Management of DGs in Power Distribution Networks Based on Computational Intelligence Techniques

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1648
Author(s):  
Marinko Barukčić ◽  
Toni Varga ◽  
Vedrana Jerković Jerković Štil ◽  
Tin Benšić
Keyword(s):  
Power System ◽  
Power Management ◽  
Computational Intelligence ◽  
Input Data ◽  
Optimization Problem ◽  
Optimal Allocation ◽  
Distribution Networks ◽  
Distributed Generations ◽  
Data Resolution ◽  
The Impact

The paper researches the impact of the input data resolution on the solution of optimal allocation and power management of controllable and non-controllable renewable energy sources distributed generation in the distribution power system. Computational intelligence techniques and co-simulation approach are used, aiming at more realistic system modeling and solving the complex optimization problem. The optimization problem considers the optimal allocation of all distributed generations and the optimal power control of controllable distributed generations. The co-simulation setup employs a tool for power system analysis and a metaheuristic optimizer to solve the optimization problem. Three different resolutions of input data (generation and load profiles) are used: hourly, daily, and monthly averages over one year. An artificial neural network is used to estimate the optimal output of controllable distributed generations and thus significantly decrease the dimensionality of the optimization problem. The proposed procedure is applied on a 13 node test feeder proposed by the Institute of Electrical and Electronics Engineers. The obtained results show a huge impact of the input data resolution on the optimal allocation of distributed generations. Applying the proposed approach, the energy losses are decreased by over 50–70% by the optimal allocation and control of distributed generations depending on the tested network.

Using Deep Learning to Understand Travel Demands in Different Urban Districts

2021 ◽  
pp. 036119812199458
Author(s):  
Shunhua Bai ◽  
Junfeng Jiao
Keyword(s):  
Built Environment ◽  
Travel Behavior ◽  
Prediction Accuracy ◽  
Travel Demand ◽  
Short Term Memory ◽  
Future Research ◽  
Demand Forecast ◽  
Time And Space ◽  
The University ◽  
The Impact

Travel demand forecast plays an important role in transportation planning. Classic models often predict people’s travel behavior based on the physical built environment in a linear fashion. Many scholars have tried to understand built environments’ predictive power on people’s travel behavior using big-data methods. However, few empirical studies have discussed how the impact might vary across time and space. To fill this research gap, this study used 2019 anonymous smartphone GPS data and built a long short-term memory (LSTM) recurrent neural network (RNN) to predict the daily travel demand to six destinations in Austin, Texas: downtown, the university, the airport, an inner-ring point-of-interest (POI) cluster, a suburban POI cluster, and an urban-fringe POI cluster. By comparing the prediction results, we found that: the model underestimated the traffic surge for the university in the fall semester and overestimated the demand for downtown on non-working days; the prediction accuracy for POI clusters was negatively related to their adjacency to downtown; and different POI clusters had cases of under- or overestimation on different occasions. This study reveals that the impact of destination attributes on people’s travel demand can vary across time and space because of their heterogeneous nature. Future research on travel behavior and built environment modeling should incorporate the temporal inconsistency to achieve better prediction accuracy.

The Impact of Macroeconomic Factors on Environmental Loss Ratio: Evidence from Taiwanese Insurance Data

2018 ◽  
Vol 21 (03) ◽  
pp. 1850020
Author(s):  
Li-Hua Lai ◽  
Ching-Hao Chen ◽  
Tung-Cheng Chang
Keyword(s):  
Input Data ◽  
Economic Loss ◽  
Environmental Condition ◽  
Loss Ratio ◽  
Negative Effects ◽  
Macroeconomic Factors ◽  
Macroeconomic Factor ◽  
Environmental Loss ◽  
The Impact ◽  
Insurance Data

Environmental insurance (EI) protections help resolve the firm-industry economic loss problem. However, the loss ratio of EI is positively affected by itself from one period ahead. The positive and negative effects of macroeconomic factor on the loss ratio of EIs are not necessarily consistent, but they are dependent on the effect of the year’s environmental condition. The economic variables affecting the loss ratio of EI are quite inconsistent, so insurance prices and liability reserves should be modified every year. While the investigations are the special properties of our input data of Taiwan, the prescription of this paper could provide cross-references with other countries.

scholarly journals Application of the SWAT (Soil and Water Assessment Tool) model in the Ronnea catchment of Sweden

2013 ◽  
Vol 7 (3) ◽  
pp. 252-257
Keyword(s):  
Input Data ◽  
Management Practices ◽  
Assessment Tool ◽  
Swat Model ◽  
Soil Parameters ◽  
Daily Step ◽  
Calibration And Validation ◽  
The Impact ◽  
Water Assessment ◽  
Soil And Water

The subject of this article is the estimation of quantitative (hydrological) and qualitative parameters in the catchment of Ronnea (1800 Km2, located in south western Sweden) through the application of the Soil and Water Assessment Tool (SWAT). SWAT is a river basin model that was developed for the U.S.D.A. Agricultural Research Service, by the Blackland Research Center in Texas. The SWAT model is a widely known tool that has been used in several cases world-wide. It has the ability to predict the impact of land management practices on water, sediment and agricultural chemical yield in large complex watersheds. The present work investigates certain capabilities of the SWAT model which have not identified up to now. More in specific, the main targets of the work carried out are the following: • Identification of the existing hydrological and qualitative conditions • Preparation - Processing of data required to be used as input data of the model • Hydrological calibration - validation of the model, in 7 subbasins of the Catchment of Ronnea • Estimation and evaluation of the simulated qualitative parameters of the model All available data were offered by the relevant Institutes of Sweden, in the framework of the European program EUROHARP. The existing conditions in the catchment of Ronnea, are described in detail including topography, land uses, soil types, pollution sources, agricultural management practices, precipitation, temperature, wind speed, humidity, solar radiation as well as observed discharges and Nitrogen and Phosphorus substances concentrations. Most of the above data were used as input data for the application of SWAT model. Adequate methods were also used to complete missing values in time series and estimate additional parameters (such as soil parameters) required by the model. Hydrological calibration and validation took place for each outlet of the 7 subbasins of Ronnea catchment in an annual, monthly and daily step. The calibration was achieved by estimating parameters related to ground water movement and evaluating convergence between simulated and observed discharges by using mainly the Nash & Sutcliffe coefficient (NTD). Through the sensitivity analysis, main parameters of the hydrological simulation, were detected. According to the outputs of the SWAT model, the water balance of Ronnea catchment was also estimated. Hydrological calibration and validation is generally considered sufficient in an annual and monthly step. Hydrological calibration – validation in daily step, generally does not lead to high values of the NTD indicator. However, when compared to results obtained by the use of SWAT in Greece, a relatively high value of NTD is achieved in one subbasin. Finally, a comparison between the simulated and observed concentrations of total Phosphorus and Nitrogen was carried out.

scholarly journals Application of Various Machine Learning Models for Process Stability of Bio-Electrochemical Anaerobic Digestion

Processes ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 158
Author(s):  
Ain Cheon ◽  
Jwakyung Sung ◽  
Hangbae Jun ◽  
Heewon Jang ◽  
Minji Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Anaerobic Digestion ◽  
Prediction Accuracy ◽  
Input Data ◽  
Process Stability ◽  
Operational Parameters ◽  
Monitoring Parameter ◽  
Efficient Prediction ◽  
Single Input ◽  
Machine Learning Models

The application of a machine learning (ML) model to bio-electrochemical anaerobic digestion (BEAD) is a future-oriented approach for improving process stability by predicting performances that have nonlinear relationships with various operational parameters. Five ML models, which included tree-, regression-, and neural network-based algorithms, were applied to predict the methane yield in BEAD reactor. The results showed that various 1-step ahead ML models, which utilized prior data of BEAD performances, could enhance prediction accuracy. In addition, 1-step ahead with retraining algorithm could improve prediction accuracy by 37.3% compared with the conventional multi-step ahead algorithm. The improvement was particularly noteworthy in tree- and regression-based ML models. Moreover, 1-step ahead with retraining algorithm showed high potential of achieving efficient prediction using pH as a single input data, which is plausibly an easier monitoring parameter compared with the other parameters required in bioprocess models.

scholarly journals Airbnb Short-term Housing Rental Status Prediction Model Under the Impact of the COVID-19 Pandemic

2021 ◽  
Vol 251 ◽  
pp. 01017
Author(s):  
Zhixiang Lu
Keyword(s):  
Machine Learning ◽  
New York ◽  
Regional Differences ◽  
Prediction Accuracy ◽  
Visual Analysis ◽  
Sharing Economy ◽  
Short Term ◽  
Emerging Industries ◽  
Machine Learning Model ◽  
The Impact

With the vigorous development of the sharing economy, the short-term rental industry has also spawned many emerging industries that belong to the sharing economy. However, due to the impact of the COVID-19 pandemic in 2020, many sharing economy industries, including the short-term housing leasing industry, have been affected. This study takes the rental information of 1,004 short-term rental houses in New York in April 2020 as an example, through machine learning and quantitative analysis, we conducted statistical and visual analysis on the impact of different factors on the housing rental status. This project is based on the machine learning model to predict the changes in the rental status of the house on the time series. The results show that the prediction accuracy of the random forest model has reached more than 94%, and the prediction accuracy of the logistic model has reached more than 74%. At the same time, we have further explored the impact of time span differences and regional differences on the housing rental status.

Sign in / Sign up

Export Citation Format

Share Document