Covid‐19 is an acute respiratory infection and presents various clinical features ranging from no symptoms to severe pneumonia and death. Medical expert systems, especially in diagnosis and ...monitoring stages, can give positive consequences in the struggle against Covid‐19. In this study, a rule‐based expert system is designed as a predictive tool in self‐pre‐diagnosis of Covid‐19. The potential users are smartphone users, healthcare experts and government health authorities. The system does not only share the data gathered from the users with experts, but also analyzes the symptom data as a diagnostic assistant to predict possible Covid‐19 risk. To do this, a user needs to fill out a patient examination card that conducts an online Covid‐19 diagnostic test, to receive an unconfirmed online test prediction result and a set of precautionary and supportive action suggestions. The system was tested for 169 positive cases. The results produced by the system were compared with the real PCR test results for the same cases. For patients with certain symptomatic findings, there was no significant difference found between the results of the system and the confirmed test results with PCR test. Furthermore, a set of suitable suggestions produced by the system were compared with the written suggestions of a collaborated health expert. The suggestions deduced and the written suggestions of the health expert were similar and the system suggestions in line with suggestions of the expert. The system can be suitable for diagnosing and monitoring of positive cases in the areas other than clinics and hospitals during the Covid‐19 pandemic. The results of the case studies are promising, and it demonstrates the applicability, effectiveness, and efficiency of the proposed approach in all communities.
With the extensive adoption of artificial intelligence (AI), construction engineering and management (CEM) is experiencing a rapid digital transformation. Since AI-based solutions in CEM has become ...the current research focus, it needs to be comprehensively understood. In this regard, this paper presents a systematic review under both scientometric and qualitative analysis to present the current state of AI adoption in the context of CEM and discuss its future research trends. To begin with, a scientometric review is performed to explore the characteristics of keywords, journals, and clusters based on 4,473 journal articles published in 1997–2020. It is found that there has been an explosion of relevant papers especially in the past 10 years along with the change in keyword popularity from expert systems to building information modeling (BIM), digital twins, and others. Then, a brief understanding of CEM is provided, which can be benefited from the emerging trend of AI in terms of automation, risk mitigation, high efficiency, digitalization, and computer vision. Special concerns have been put on six hot research topics that amply the advantage of AI in CEM, including (1) knowledge representation and reasoning, (2) information fusion, (3) computer vision, (4) natural language processing, (5) intelligence optimization, and (6) process mining. The goal of these topics is to model, predict, and optimize issues in a data-driven manner throughout the whole lifecycle of the actual complex project. To further narrow the gap between AI and CEM, six key directions of future researches, such as smart robotics, cloud virtual and augmented reality (cloud VR/AR), Artificial Intelligence of Things (AIoT), digital twins, 4D printing, and blockchains, are highlighted to constantly facilitate the automation and intelligence in CEM.
Display omitted
•A systematic review under both scientometric and qualitative analysis for the topic is provided.•A scientometric review is performed on 4,473 journal articles published in 1997–2020.•AI’s main benefits including modeling and pattern detection, prediction, and optimization•Special concerns have been put on six state-of-the-art applications of AI in CEM.•Key directions of future studies, like smart robotics, digital twins, and blockchains are provided.
As the generalization of fuzzy systems, the belief rule base (BRB) expert system is transparent and interpretable. However, the interpretability of BRB has almost been ignored recently and leads to ...the decrease of model credibility. The main reason is the lack of unified guidelines for establishing an interpretable BRB expert system. In this article, the interpretability characteristics of BRB are summarized systematically, which can be used as the guideline of BRB establishment. Four interpretability criteria are proposed to ensure the interpretability of BRB in the optimization. A modified optimization algorithm with the interpretability constraints transformed from the interpretability criteria is further developed. As such, an interpretable BRB can be established. A case study for health state evaluation of the aerospace relay is conducted to verify the effectiveness of the proposed method.
•A land suitability analysis (LSA) model was developed to find suitable areas for cassava production.•A fuzzy expert system was used with a multicriteria decision for LSA.•Yield prediction method was ...developed using satellite remote sensing-based vegetation datasets.•NDVI, SAVI, IRECI, LAI, and fAPAR were used to develop the yield prediction model.•Ground reference validation was incorporated for yield prediction according to land suitability.
Cassava has the potential to be a promising crop that can adapt to changing climatic conditions in Indonesia due to its low water requirement and drought tolerance. However, inappropriate land selection decisions limit cassava yields and increase production-related costs to farmers. As a root crop, yield prediction using vegetation indices and biophysical properties is essential to maximize the yield of cassava before harvesting. Therefore, the purpose of this research was to develop a yield prediction model based on suitable areas that assess with land suitability analysis (LSA). For LSA, the priority indicators were identified using a fuzzy expert system combined with a multicriteria decision method including ecological categories. Furthermore, the yield prediction method was developed using satellite remote sensing datasets. In this analysis, Sentinel-2 datasets were collected and analyzed in SNAP® and ArcGIS® environments. The multisource database of ecological criteria for cassava production was built using the fuzzy membership function. The results showed that 42.17% of the land area was highly suitable for cassava production. Then, in the highly suitable area, the yield prediction model was developed using the vegetation indices based on Sentinel-2 datasets with 10 m resolution for the accuracy assessment. The vegetation indices were used to predict cassava growth, biophysical condition, and phenology over the growing seasons. The NDVI, SAVI, IRECI, LAI, and fAPAR were used to develop the model for predicting cassava growth. The generated models were validated using regression analysis between observed and predicted yield. As the vegetation indices, NDVI showed higher accuracy in the yield prediction model (R2 = 0.62) compared to SAVI and IRECI. Meanwhile, LAI had a higher prediction accuracy (R2 = 0.70) than other biophysical properties, fAPAR. The combined model using NDVI, SAVI, IRECI, LAI, and fAPAR reported the highest accuracy (R2 = 0.77). The ground truth data were used for the evaluation of satellite remote sensing data in the comparison between the observed and predicted yields. This developed integrated model could be implemented for the management of land allocation and yield assessment in cassava production to ensure regional food security in Indonesia.
•State-of-the-art for the application of AI in streamflow forecasting presented.•The authors defined each data-driven of AI and AI-complementary model.•An assessment and evaluation have been carried ...out for the literature review.•Several recommended researches have been proposed for future research.
The use of Artificial Intelligence (AI) has increased since the middle of the 20th century as seen in its application in a wide range of engineering and science problems. The last two decades, for example, has seen a dramatic increase in the development and application of various types of AI approaches for stream-flow forecasting. Generally speaking, AI has exhibited significant progress in forecasting and modeling non-linear hydrological applications and in capturing the noise complexity in the dataset. This paper explores the state-of-the-art application of AI in stream-flow forecasting, focusing on defining the data-driven of AI, the advantages of complementary models, as well as the literature and their possible future application in modeling and forecasting stream-flow. The review also identifies the major challenges and opportunities for prospective research, including, a new scheme for modeling the inflow, a novel method for preprocessing time series frequency based on Fast Orthogonal Search (FOS) techniques, and Swarm Intelligence (SI) as an optimization approach.
•Proposed P-1D-CNN model for detecting epilepsy that has far less learnable parameters.•To deal with the small amount of available data, proposed two augmentation schemes.•Proposed an epilepsy ...detection system as an ensemble of P-1D-CNN models.•Thoroughly evaluated the augmentation schemes and the deep models.•The system gives an accuracy of 99.1 ± 0.9% on the University of Bonn dataset.
Epilepsy is a life-threatening and challenging neurological disorder, which is affecting a large number of people all over the world. For its detection, encephalography (EEG) is a commonly used clinical approach, but manual inspection of EEG brain signals is a time-consuming and laborious process, which puts a heavy burden on neurologists and affects their performance. Several automatic systems have been proposed using traditional approaches to assist neurologists, which perform well in detecting binary epilepsy scenarios e.g. normal vs. ictal, but their performance degrades in classifying ternary case e.g. ictal vs. normal vs. inter-ictal. To overcome this problem, we propose a system that is an ensemble of pyramidal one-dimensional convolutional neural network (P-1D-CNN) models. Though a CNN model learns the internal structure of data and outperforms hand-engineered techniques, the main issue is the large number of learnable parameters, whose learning requires a huge volume of data. To overcome this issue, P-1D-CNN works on the concept of refinement approach and it involves 61% fewer parameters compared to standard CNN models and as such it has better generalization. Further to overcome the limitations of the small amount of data, we propose two augmentation schemes. We tested the system on the University of Bonn dataset, a benchmark dataset; in almost all the cases concerning epilepsy detection, it gives an accuracy of 99.1 ± 0.9% and outperforms the state-of-the-art systems. In addition, while enjoying the strength of a CNN model, P-1D-CNN model requires 61% less memory space and its detection time is very short (< 0.000481 s), as such it is suitable for real-time clinical setting. It will ease the burden of neurologists and will assist the patients in alerting them before the seizure occurs. The proposed P-1D-CNN model is not only suitable for epilepsy detection, but it can be adopted in developing robust expert systems for other similar disorders.
The deep sea remains the largest unknown territory on Earth because it is so difficult to explore
. Owing to the extremely high pressure in the deep sea, rigid vessels
and pressure-compensation ...systems
are typically required to protect mechatronic systems. However, deep-sea creatures that lack bulky or heavy pressure-tolerant systems can thrive at extreme depths
. Here, inspired by the structure of a deep-sea snailfish
, we develop an untethered soft robot for deep-sea exploration, with onboard power, control and actuation protected from pressure by integrating electronics in a silicone matrix. This self-powered robot eliminates the requirement for any rigid vessel. To reduce shear stress at the interfaces between electronic components, we decentralize the electronics by increasing the distance between components or separating them from the printed circuit board. Careful design of the dielectric elastomer material used for the robot's flapping fins allowed the robot to be actuated successfully in a field test in the Mariana Trench down to a depth of 10,900 metres and to swim freely in the South China Sea at a depth of 3,224 metres. We validate the pressure resilience of the electronic components and soft actuators through systematic experiments and theoretical analyses. Our work highlights the potential of designing soft, lightweight devices for use in extreme conditions.
•Deep learning networks are applied to stock market analysis and prediction.•A comprehensive analysis with different data representation methods is offered.•Five-minute intraday data from the Korean ...KOSPI stock market is used.•The network applied to residuals of autoregressive model improves prediction.•Covariance estimation for market structure analysis is improved with the network.
We offer a systematic analysis of the use of deep learning networks for stock market analysis and prediction. Its ability to extract features from a large set of raw data without relying on prior knowledge of predictors makes deep learning potentially attractive for stock market prediction at high frequencies. Deep learning algorithms vary considerably in the choice of network structure, activation function, and other model parameters, and their performance is known to depend heavily on the method of data representation. Our study attempts to provides a comprehensive and objective assessment of both the advantages and drawbacks of deep learning algorithms for stock market analysis and prediction. Using high-frequency intraday stock returns as input data, we examine the effects of three unsupervised feature extraction methods—principal component analysis, autoencoder, and the restricted Boltzmann machine—on the network’s overall ability to predict future market behavior. Empirical results suggest that deep neural networks can extract additional information from the residuals of the autoregressive model and improve prediction performance; the same cannot be said when the autoregressive model is applied to the residuals of the network. Covariance estimation is also noticeably improved when the predictive network is applied to covariance-based market structure analysis. Our study offers practical insights and potentially useful directions for further investigation into how deep learning networks can be effectively used for stock market analysis and prediction.