COVID-19 crisis impact on the stability between parties in crowdfunding and crowdsourcing

This research reviews challenges in building sustainable relationships between the parties involved in the crowdfunding and crowdsourcing projects, which are running in extreme situations, such as the COVID-19 pandemic. This study aims to solve problems that generate the crowdsourcing concerns and to find better alternatives to increase trust for crowdfunding among donors, as this impacts their strategic sustainability in the conditions of turbulence and COVID-induced financial crisis. It was found that factors influence donor decisions in different ways, yet the common tendency for donor activity is non-monotonicity. Future development in the field of sustainable relationships should focus on creating a donor classification system.

     

Visual privacy attacks and defenses in deep learning: a survey

The concerns on visual privacy have been increasingly raised along with the dramatic growth in image and video capture and sharing. Meanwhile, with the recent breakthrough in deep learning technologies, visual data can now be easily gathered and processed to infer sensitive information. Therefore, visual privacy in the context of deep learning is now an important and challenging topic. However, there has been no systematic study on this topic to date. In this survey, we discuss algorithms of visual privacy attacks and the corresponding defense mechanisms in deep learning. We analyze the privacy issues in both visual data and visual deep learning systems. We show that deep learning can be used as a powerful privacy attack tool as well as preservation techniques with great potential. We also point out the possible direction and suggestions for future work. By thoroughly investigating the relationship of visual privacy and deep learning, this article sheds insights on incorporating privacy requirements in the deep learning era.

     

Failure Prediction of Municipal Water Pipes Using Machine Learning Algorithms

Pipe failure prediction has become a crucial demand of operators in daily operation and asset management due to the increase in operation risks of water distribution networks. In this paper, two machine learning algorithms, namely, random forest (RF) and logistic regression (LR) algorithms are employed for pipe failure prediction. RF algorithm consists of a group of decision trees that predicts pipe failure independently and makes the final decision by voting together. For the LR algorithm, the mapping relationship between existing data and decision variables is expressed by the logistic function. Then, the prediction is made by comparing the conditional probability with the fixed threshold value. The proposed algorithms are illustrated using an actual water distribution network in China. Results indicate that the RF algorithm performs better than the LR algorithm in terms of accuracy, recall, and area under the receiver operating characteristic curve. The effects of seven characteristics on pipe failures are analyzed, and diameter and length are identified as the top two influential factors.

Graphical Abstract

     

Homogeneous reinforcement as a strategy for the efficient preparation of high-strength,insulating and high heat-resistant PBO composite paper

Journal of Materials Science - Poly(p-phenylene benzobisoxazole) (PBO) fibre-based specialty paper has become a promising candidate for high-performance insulating materials due to the remarkable...     

Engineering A-site cation deficiency into LaCoO3 thin sheets for improved microwave absorption performance

Journal of Materials Science - Rationally designing microwave absorption materials with highly efficient and tunable bandwidth is in great demand but remains a huge challenge. In this study,...     

Germination improves the functional properties of soybean and enhances soymilk quality

The effects of soybean variety and germination time on structural changes, antinutritional factor content, antioxidant activity of germinated soybean, and on the functional properties of soymilk were comprehensively investigated. The results showed that the antioxidant activity increased with increasing germination time. The content of antinutritional factors decreased with increasing germination time. Soybean varieties with the lowest tannin and trypsin inhibitor content were DN690 and HJ1. Lipoxygenase activity and phytic acid content showed no significant differences among soybean varieties. The content of α-helices and β-turns in soybean protein decreased with increasing germination time, while the content of β-sheets was increased. Soybean protein was progressively broken down into smaller molecular peptides during the germination process. The digestion and content of soluble protein in soymilk increased with germination. In summary, we show that germination is an effective, cheap, and green method that improves the functional properties of soybean and soymilk.     

Facial-sketch Synthesis: A New Challenge

Machine Intelligence Research - This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high cost of obtaining hand-drawn sketch datasets, there is a...     

An Enhanced Beetle Antennae Search Algorithm Based Comprehensive Water Quality Index for Urban River Water Quality Assessment

Water Resources Management - Urban river not only has the important function in urban hydrological environment, but also is an area for entertainment. Water quality assessment is the core technique...