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

General General

Machine learning and density functional theory simulation of the electronic structural properties for novel quaternary semiconductors.

In Physical chemistry chemical physics : PCCP

In order to accelerate the application of quaternary optoelectronic materials in the field of luminescence, it is crucial to develop new quaternary semiconductor materials with excellent properties. However, faced with vast alternative quaternary semiconductors, traditional trial-and-error methods tend to be laborious and inefficient. Here, we combined machine learning (ML) with density functional theory (DFT) calculation to predict the bandgaps of 2180 quaternary semiconductors, most of which were undeveloped but environmentally friendly. The evaluation coefficient (R2) of the model using a random forest algorithm was up to 0.93 in ML. Four novel quaternary semiconductors with direct bandgaps: Ag2InGaS4, AgZn2InS4, Ag2ZnSnS4, and AgZn2GaS4, were selected from the ML model. Then their electronic structures and optical properties were further verified and studied by DFT calculations, which demonstrated that the four quaternary semiconductors had direct bandgaps, a small effective mass, and a large exciton binding energy and Stokes shift. Our calculation could significantly speed up the discovery of novel optoelectronic semiconductors and has a certain reference value for the study of luminescent materials and devices.

Gao Mengwei, Cai Bo, Liu Gaoyu, Xu Lili, Zhang Shengli, Zeng Haibo

2023-Mar-20

General General

Are emerging technologies unlocking the potential of sustainable practices in the context of a net-zero economy? An analysis of driving forces.

In Environmental science and pollution research international

Increasing globalization and climate change have significantly affected business activities. Government and other stakeholders are creating pressure to have a sustainable business model for efficient resource utilization and minimizing negative environmental impact. Many organizations have started focusing on sustainable and cleaner production through the adoption of net-zero economy (NZE) practices. Certain technological advancements are required to put these concepts into practice. Firms have begun to adopt digital technologies (such as big data analytics, artificial intelligence, and internet of things), and have been widely used in practice to achieve NZE. Is digitalization unlocking the potential of sustainable practices in the context of a net-zero economy? This question is still unanswered; therefore, this study aims to identify and analyze the drivers of digitalization that ensure sustainable practices to achieve net-zero economy. Through an extensive literature review and experts' opinions, a list of drivers was identified. An empirical investigation was conducted to validate the identified drivers and further understand the influencing relationship among the drivers, Pythagorean fuzzy decision-making trial and evaluation laboratory (PF-DEMATEL) was employed. The findings of the study show that "high degree of automation," "enhancing the flexibility in the manufacturing process," and "real-time sensing capability" are the main influencer drivers among all cause group forces. The present study can be a source for industrial practitioners and academia that can provide significant guidance on how the adoption of digitalization can unlock the potential to achieve CE, which can lead us toward net-zero.

Agrawal Rohit, Priyadarshinee Pragati, Kumar Anil, Luthra Sunil, Garza-Reyes Jose Arturo, Kadyan Sneha

2023-Mar-18

Circular economy, Drivers, Emerging technologies, Net-zero economy, Pythagorean fuzzy DEMATEL, Sustainable practices

General General

Optimization of biocementation responses by artificial neural network and random forest in comparison to response surface methodology.

In Environmental science and pollution research international

In this article, the optimization of the specific urease activity (SUA) and the calcium carbonate (CaCO3) using microbially induced calcite precipitation (MICP) was compared to optimization using three algorithms based on machine learning: random forest regressor, artificial neural networks (ANNs), and multivariate linear regression. This study applied the techniques in two existing response surface method (RSM) experiments involving MICP technique. Random forest-based models and artificial neural network-based models were submitted through the optimization of hyperparameters via cross-validation technique and grid search, to select the best-optimized model. For this study, the random forest-based algorithm is aimed at having the best performance of 0.9381 and 0.9463 in comparison to the original r2 of 0.9021 and 0.8530, respectively. This study is aimed at exploring the capability of using machine learning-based models in small datasets for the purpose of optimization of experimental variables in MICP technique and the meaningfulness of the models by their specificities in the small experimental datasets applied to experimental designs. This study is aimed at exploring the capability of using machine learning-based models in small datasets for experimental variable optimization in MICP technique. The use of these techniques can create prerogatives to scale and mitigate costs in future experiments associated to the field.

Pacheco Vinicius Luiz, Bragagnolo Lucimara, Dalla Rosa Francisco, Thomé Antonio

2023-Mar-18

Artificial neural networks, Cross-validation, MICP, Random forest, Response surface method

Surgery Surgery

Semantic segmentation of surgical hyperspectral images under geometric domain shifts

ArXiv Preprint

Robust semantic segmentation of intraoperative image data could pave the way for automatic surgical scene understanding and autonomous robotic surgery. Geometric domain shifts, however, although common in real-world open surgeries due to variations in surgical procedures or situs occlusions, remain a topic largely unaddressed in the field. To address this gap in the literature, we (1) present the first analysis of state-of-the-art (SOA) semantic segmentation networks in the presence of geometric out-of-distribution (OOD) data, and (2) address generalizability with a dedicated augmentation technique termed "Organ Transplantation" that we adapted from the general computer vision community. According to a comprehensive validation on six different OOD data sets comprising 600 RGB and hyperspectral imaging (HSI) cubes from 33 pigs semantically annotated with 19 classes, we demonstrate a large performance drop of SOA organ segmentation networks applied to geometric OOD data. Surprisingly, this holds true not only for conventional RGB data (drop of Dice similarity coefficient (DSC) by 46 %) but also for HSI data (drop by 45 %), despite the latter's rich information content per pixel. Using our augmentation scheme improves on the SOA DSC by up to 67 % (RGB) and 90 % (HSI) and renders performance on par with in-distribution performance on real OOD test data. The simplicity and effectiveness of our augmentation scheme makes it a valuable network-independent tool for addressing geometric domain shifts in semantic scene segmentation of intraoperative data. Our code and pre-trained models will be made publicly available.

Jan Sellner, Silvia Seidlitz, Alexander Studier-Fischer, Alessandro Motta, Berkin Özdemir, Beat Peter Müller-Stich, Felix Nickel, Lena Maier-Hein

2023-03-20

General General

Lightweight saliency detection method for real-time localization of livestock meat bones.

In Scientific reports ; h5-index 158.0

Existing salient object detection networks are large, have many parameters, are bulky and take up a lot of computational resources. Seriously hinder its application and promotion in boning robot. To solve this problem, this paper proposes a lightweight saliency detection algorithm for real-time localization of livestock meat bones. First, a lightweight feature extraction network based on multi-scale attention is constructed in the encoding stage. To ensure that more adequate salient object features are extracted with fewer parameters. Second, the fusion of jump connections is introduced in the decoding phase. Used to capture fine-grained semantics and coarse-grained semantics at full scale. Finally, we added a residual refinement module at the end of the backbone network. For optimizing salient target regions and boundaries. Experimental results on both publicly available datasets and self-made Pig leg X-ray (PLX) datasets show that. The proposed method is capable of ensuring first-class detection accuracy with 40 times less parameters than the conventional model. In the most challenging SOD dataset. The proposed algorithm in this paper achieves a value of Fωβ of 0.699. And the segmentation of livestock bones can be effectively performed on the homemade PLX dataset. Our model has a detection speed of 5fps on industrial control equipment.

Xu Tao, Zhao Weishuo, Cai Lei, Shi Xiaoli, Wang Xinfa

2023-Mar-18

General General

Agent-based Simulation for Online Mental Health Matching

ArXiv Preprint

Online mental health communities (OMHCs) are an effective and accessible channel to give and receive social support for individuals with mental and emotional issues. However, a key challenge on these platforms is finding suitable partners to interact with given that mechanisms to match users are currently underdeveloped. In this paper, we collaborate with one of the world's largest OMHC to develop an agent-based simulation framework and explore the trade-offs in different matching algorithms. The simulation framework allows us to compare current mechanisms and new algorithmic matching policies on the platform, and observe their differing effects on a variety of outcome metrics. Our findings include that usage of the deferred-acceptance algorithm can significantly better the experiences of support-seekers in one-on-one chats while maintaining low waiting time. We note key design considerations that agent-based modeling reveals in the OMHC context, including the potential benefits of algorithmic matching on marginalized communities.

Yuhan Liu, Anna Fang, Glen Moriarty, Robert Kraut, Haiyi Zhu

2023-03-20