Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Reconstructing seen image from brain activity by visually-guided cognitive representation and adversarial learning.

In NeuroImage ; h5-index 117.0

Reconstructing perceived stimulus (image) only from human brain activity measured with functional Magnetic Resonance Imaging (fMRI) is a significant task in brain decoding. However, the inconsistent distribution and representation between fMRI signals and visual images cause great 'domain gap'. Moreover, the limited fMRI data instances generally suffer from the issues of low signal noise ratio (SNR), extremely high dimensionality, and limited spatial resolution. Existing methods are often affected by these issues so that a satisfactory reconstruction is still an open problem. In this paper, we show that it is possible to obtain a promising solution by learning visually-guided latent cognitive representations from the fMRI signals, and inversely decoding them to the image stimuli. The resulting framework is called Dual-Variational Autoencoder/ Generative Adversarial Network (D-Vae/Gan), which combines the advantages of adversarial representation learning with knowledge distillation. In addition, we introduce a novel three-stage learning strategy which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process. Extensive experimental results on both artificial and natural images have demonstrated that our method could achieve surprisingly good results and outperform the available alternatives.

Ren Ziqi, Li Jie, Xue Xuetong, Li Xin, Yang Fan, Jiao Zhicheng, Gao Xinbo

2021-Jan-01

Generative adversarial networks, Variational autoencoders, Visual reconstruction, fMRI

General General

Disassembly Sequence Planning of Waste Auto Parts.

In Journal of the Air & Waste Management Association (1995)

The disassembly of used products is a critical procedure in remanufacturing, and different disassembly strategies are often obtained from different perspectives. To describe the disassembly process more accurately, the uncertainty of the information in the disassembly process should be considered. Therefore, random variables are introduced for disassembly time, cost and effort. Based on the extended stochastic Petri net modeling method and stochastic programming theory, a stochastic optimization algorithm combined with artificial intelligence technology and a multiobjective genetic algorithm are designed, and a multi-objective optimization model for the disassembly sequence of used car parts under uncertain conditions is successfully constructed. This model Consider the viewpoint of the decision maker. Moreover, the Monte Carlo method is applied to solve the multio-bjective optimization model, and the validity and practicability of the model are verified by an example of an automotive transmission. Implications Statement With the rapid development of the economy and the shortening of the product life cycle, the rate of product renewal is getting faster and faster, which also leads to the production of a large number of waste products. According to the forecast of the relevant departments, it is estimated that in 2020, there will be about 35 million used televisions, 15 million used refrigerators, 13 million used washing machines, 12 million used air conditioners, 57 million used computers 8.3 million scrapped cars. Waste products contain a lot of renewable resources. If they cannot be effectively recycled, it will be a great waste of resources, and unreasonable disposal of waste products may have a negative impact on the environment. Therefore, due to environmental pressure and economic drive, product recycling and remanufacturing activities have caused widespread concern in society. Disassembly is defined as the operation or activity of disassembling an assembly such as a product, assembly, or component, and is the result of multiple removal operations of the product . It is a prerequisite for the efficient recycling of products and the first link in remanufacturing, that is, disassembly as a new production activity, which can provide raw materials for the smooth progress of the remanufacturing production plan, that is, old rough or used parts . Efficient dismantling not only saves natural resources and energy, but also effectively reduces environmental pollution. It is also an important guarantee for promoting the healthy development of the circular economy and achieving sustainable industrial development. The length of time required for the dismantling process, the level of costs and the amount of profits obtained will directly affect the economic benefits of the recycling of end-of-life products. Therefore, the evaluation and optimization of the dismantling process of waste products have become one of the current hot issues. The research on the dismantling of waste products is conducive to speeding up the recycling process of waste, to a greater extent, the rapid and full recovery of resources, and to a certain extent, it will provide value basis and theoretical significance for subsequent research.

Mao Jia, Hong Dou, Chen Zhe, Changhai Ma, Weiwen Li, Wang Ju

2021-Jan-04

Disassembly sequence planning, extended stochastic Petri nets, multi-objective stochastic optimization, stochastic simulation

General General

Evidence of vascular endothelial dysfunction in Wooden Breast disorder in chickens: Insights through gene expression analysis, ultra-structural evaluation and supervised machine learning methods.

In PloS one ; h5-index 176.0

Several gene expression studies have been previously conducted to characterize molecular basis of Wooden Breast myopathy in commercial broiler chickens. These studies have generally used a limited sample size and relied on a binary disease outcome (unaffected or affected by Wooden Breast), which are appropriate for an initial investigation. However, to identify biomarkers of disease severity and development, it is necessary to use a large number of samples with a varying degree of disease severity. Therefore, in this study, we assayed a relatively large number of samples (n = 96) harvested from the pectoralis major muscle of unaffected (U), partially affected (P) and markedly affected (A) chickens. Gene expression analysis was conducted using the nCounter MAX Analysis System and data were analyzed using four different supervised machine-learning methods, including support vector machines (SVM), random forests (RF), elastic net logistic regression (ENET) and Lasso logistic regression (LASSO). The SVM method achieved the highest prediction accuracy for both three-class (U, P and A) and two-class (U and P+A) classifications with 94% prediction accuracy for two-class classification and 85% for three-class classification. The results also identified biomarkers of Wooden Breast severity and development. Additionally, gene expression analysis and ultrastructural evaluations provided evidence of vascular endothelial cell dysfunction in the early pathogenesis of Wooden Breast.

Abasht Behnam, Papah Michael B, Qiu Jing

2021

General General

The effects of intrinsic motivation on mental fatigue.

In PloS one ; h5-index 176.0

There have been many studies attempting to disentangle the relation between motivation and mental fatigue. Mental fatigue occurs after performing a demanding task for a prolonged time, and many studies have suggested that motivation can counteract the negative effects of mental fatigue on task performance. To complicate matters, most mental fatigue studies looked exclusively at the effects of extrinsic motivation but not intrinsic motivation. Individuals are said to be extrinsically motivated when they perform a task to attain rewards and avoid punishments, while they are said to be intrinsically motivated when they do for the pleasure of doing the activity. To assess whether intrinsic motivation has similar effects as extrinsic motivation, we conducted an experiment using subjective, performance, and physiological measures (heart rate variability and pupillometry). In this experiment, 28 participants solved Sudoku puzzles on a computer for three hours, with a cat video playing in the corner of the screen. The experiment consisted of 14 blocks with two alternating conditions: low intrinsic motivation and high intrinsic motivation. The main results showed that irrespective of condition, participants reported becoming fatigued over time. They performed better, invested more mental effort physiologically, and were less distracted in high-level than in low-level motivation blocks. The results suggest that similarly to extrinsic motivation, time-on-task effects are modulated by the level of intrinsic motivation: With high intrinsic motivation, people can maintain their performance over time as they seem willing to invest more effort as time progresses than in low intrinsic motivation.

Herlambang Mega B, Cnossen Fokie, Taatgen Niels A

2021

General General

Semi-Supervised Capsule cGAN for Speckle Noise Reduction in Retinal OCT Images.

In IEEE transactions on medical imaging ; h5-index 74.0

Speckle noise is the main cause of poor optical coherence tomography (OCT) image quality. Convolutional neural networks (CNNs) have shown remarkable performances for speckle noise reduction. However, speckle noise denoising still meets great challenges because the deep learning-based methods need a large amount of labeled data whose acquisition is time-consuming or expensive. Besides, many CNNs-based methods design complex structure based networks with lots of parameters to improve the denoising performance, which consume hardware resources severely and are prone to overfitting. To solve these problems, we propose a novel semi-supervised learning based method for speckle noise denoising in retinal OCT images. First, to improve the model's ability to capture complex and sparse features in OCT images, and avoid the problem of a great increase of parameters, a novel capsule conditional generative adversarial network (Caps-cGAN) with small number of parameters is proposed to construct the semi-supervised learning system. Then, to tackle the problem of retinal structure information loss in OCT images caused by lack of detailed guidance during unsupervised learning, a novel joint semi-supervised loss function composed of unsupervised loss and supervised loss is proposed to train the model. Compared with other state-of-the-art methods, the proposed semi-supervised method is suitable for retinal OCT images collected from different OCT devices and can achieve better performance even only using half of the training data.

Wang Meng, Zhu Weifang, Yu Kai, Chen Zhongyue, Shi Fei, Zhou Yi, Ma Yuhui, Peng Yuanyuan, Bao Dengsen, Feng Shuanglang, Ye Lei, Xiang Dehui, Chen Xinjian

2021-Jan-04

General General

Summary of Radiation Research Society Online 66th Annual Meeting, Symposium on "Epidemiology: Updates on epidemiological low dose studies", including Discussion.

In International journal of radiation biology ; h5-index 29.0

N/A.

Milder Cato M, Kendall Gerald M, Arsham Aryana, Schöllnberger Helmut, Wakeford Richard, Cullings Harry M, Little Mark P

2021-Jan-04

Japanese atomic bomb survivors, circulatory disease, leukaemia, low dose risk, machine learning