Syngenta is one of the world's leading agriculture companies. Our ambition is to help safely feed the world while taking care of the planet. We aim to improve the sustainability, quality and safety of agriculture with world class science and innovative crop solutions. Our technologies enable millions of farmers around the world to make better use of limited agricultural resources. With 28,000 people in more than 90 countries we are working to transform how crops are grown.

Process mining is a methodology for the derivation and analysis of process models based on the event log. When process mining is employed to analyze business processes, the process discovery step, the conformance checking step, and the enhancements step are repeated. If a user wants to analyze a process from multiple perspectives (such as activity perspectives, originator perspectives, and time perspectives), the above procedure, inconveniently, has to be repeated over and over again. Although past studies involving process mining have applied detailed stepwise methodologies, no attempt has been made to incorporate and optimize multi-perspective process mining procedures. This paper contributes to developing a solution approach to this problem. First, we propose an automatic discovery framework of a multi-perspective process model based on deep Q-Learning. Our Dual Experience Replay with Experience Distribution (DERED) approach can automatically perform process model discovery steps, conformance check steps, and enhancements steps. Second, we propose a new method that further optimizes the experience replay (ER) method, one of the key algorithms of deep Q-learning, to improve the learning performance of reinforcement learning agents. Finally, we validate our approach using six real-world event datasets collected in port logistics, steel manufacturing, finance, IT, and government administration. We show that our DERED approach can provide users with multi-perspective, high-quality process models that can be employed more conveniently for multi-perspective process mining.

Pretraining molecular representation models without labels is fundamental to various applications. Conventional methods mainly process 2D molecular graphs and focus solely on 2D tasks, making their pretrained models incapable of characterizing 3D geometry and thus defective for downstream 3D tasks. In this work, we tackle 3D molecular pretraining in a complete and novel sense. In particular, we first propose to adopt an equivariant energy-based model as the backbone for pretraining, which enjoys the merits of fulfilling the symmetry of 3D space. Then we develop a node-level pretraining loss for force prediction, where we further exploit the Riemann-Gaussian distribution to ensure the loss to be E(3)-invariant, enabling more robustness. Moreover, a graph-level noise scale prediction task is also leveraged to further promote the eventual performance. We evaluate our model pretrained from a large-scale 3D dataset GEOM-QM9 on two challenging 3D benchmarks: MD17 and QM9. Experimental results demonstrate the efficacy of our method against current state-of-the-art pretraining approaches, and verify the validity of our design for each proposed component.

In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision-based structural health monitoring (SHM). However, both data deficiency and class-imbalance hinder the wide adoption of DL in practical applications of SHM. Common mitigation strategies include transfer learning, over-sampling, and under-sampling, yet these ad-hoc methods only provide limited performance boost that varies from one case to another. In this work, we introduce one variant of the Generative Adversarial Network (GAN), named the balanced semi-supervised GAN (BSS-GAN). It adopts the semi-supervised learning concept and applies balanced-batch sampling in training to resolve low-data and imbalanced-class problems. A series of computer experiments on concrete cracking and spalling classification were conducted under the low-data imbalanced-class regime with limited computing power. The results show that the BSS-GAN is able to achieve better damage detection in terms of recall and $F_\beta$ score than other conventional methods, indicating its state-of-the-art performance.

For conceptual design, engineers rely on conventional iterative (often manual) techniques. Emerging parametric models facilitate design space exploration based on quantifiable performance metrics, yet remain time-consuming and computationally expensive. Pure optimisation methods, however, ignore qualitative aspects (e.g. aesthetics or construction methods). This paper provides a performance-driven design exploration framework to augment the human designer through a Conditional Variational Autoencoder (CVAE), which serves as forward performance predictor for given design features as well as an inverse design feature predictor conditioned on a set of performance requests. The CVAE is trained on 18'000 synthetically generated instances of a pedestrian bridge in Switzerland. Sensitivity analysis is employed for explainability and informing designers about (i) relations of the model between features and/or performances and (ii) structural improvements under user-defined objectives. A case study proved our framework's potential to serve as a future co-pilot for conceptual design studies of pedestrian bridges and beyond.

"Testing two NIRs instruments to predict chicken breast meat quality and exploiting machine learning approaches to discriminate among genotypes and presence of …" LINK "Discrimination of Minced Mutton Adulteration Based on Sized-Adaptive Online NIRS Information and 2D Conventional Neural Network" LINK "Sequential data-fusion of near-infrared and mid-infrared spectroscopy data for improved prediction of quality traits in tuber flours" LINK "End-point determination of the extraction processes for Stevia rebaudiana Bertoni leaves by near-infrared spectroscopy" LINK "Rapid detection of adulteration in powder of ginger (Zingiber officinale Roscoe) by FT-NIR spectroscopy combined with chemometrics" LINK "Extended molar absorption analysis of confined states of water in reverse micelles using near-infrared spectroscopy" LINK "Online quantitative substrate, product, and cell concentration in citric acid fermentation using near-infrared spectroscopy combined with chemometrics" LINK "Discrimination of Chemical Oxygen Demand Pollution in Surface Water Based on Visible Near-Infrared Spectroscopy" LINK "Handheld NIR Spectral Sensor Module Based on a Fully-Integrated Detector Array" LINK "Spectra Transfer based Learning for Predicting and Classifying Soil Texture with Short-Ranged Vis-NIRS Sensor" LINK "AS-polRI: Analysis of apparent spectral polarization radiant intensity in the midwave infrared band for man-made object detection" LINK "Sensors: Single Seed Identification in Three Medicago Species via Multispectral Imaging Combined with Stacking Ensemble Learning" LINK "Transfer Strategy for Near Infrared Analysis Model of Holocellulose and Lignin Based on Improved Slope/Bias Algorithm" LINK "Flipped detection of psychoactive substances in complex mixtures using handheld Raman spectroscopy coupled to chemometrics" LINK "Adaptive Spectral Model for abnormality detection based on physiological status monitoring of dairy cows" LINK "Foods: A Rapid Prediction Method of Moisture Content for Green Tea Fixation Based on WOA-Elman" LINK "Fibers: Numerical Study of Mid-IR Ultrashort Pulse Reconstruction Based on Processing of Spectra Converted in Chalcogenide Fibers with High Kerr Nonlinearity" LINK "Evaluation of a digital micro-mirror device based near-infrared spectrometer for rapid and accurate prediction of quality attributes in poultry feed" LINK "Agriculture: Grazing Intensity Has More Effect on the Potential Nitrification Activity Than the Potential Denitrification Activity in An Alpine Meadow" LINK

With rapid development of blockchain technology as well as integration of various application areas, performance evaluation, performance optimization, and dynamic decision in blockchain systems are playing an increasingly important role in developing new blockchain technology. This paper provides a recent systematic overview of this class of research, and especially, developing mathematical modeling and basic theory of blockchain systems. Important examples include (a) performance evaluation: Markov processes, queuing theory, Markov reward processes, random walks, fluid and diffusion approximations, and martingale theory; (b) performance optimization: Linear programming, nonlinear programming, integer programming, and multi-objective programming; (c) optimal control and dynamic decision: Markov decision processes, and stochastic optimal control; and (d) artificial intelligence: Machine learning, deep reinforcement learning, and federated learning. So far, a little research has focused on these research lines. We believe that the basic theory with mathematical methods, algorithms and simulations of blockchain systems discussed in this paper will strongly support future development and continuous innovation of blockchain technology.

Air pollution is a vital issue emerging from the uncontrolled utilization of traditional energy sources as far as developing countries are concerned. Hence, ingenious air pollution forecasting methods are indispensable to minimize the risk. To that end, this paper proposes an Internet of Things (IoT) enabled system for monitoring and controlling air pollution in the cloud computing environment. A method called Linear Regression and Multiclass Support Vector (LR-MSV) IoT-based Air Pollution Forecast is proposed to monitor the air quality data and the air quality index measurement to pave the way for controlling effectively. Extensive experiments carried out on the air quality data in the India dataset have revealed the outstanding performance of the proposed LR-MSV method when benchmarked with well-established state-of-the-art methods. The results obtained by the LR-MSV method witness a significant increase in air pollution forecasting accuracy by reducing the air pollution forecasting time and error rate compared with the results produced by the other state-of-the-art methods

Oxidation states are the charges of atoms after their ionic approximation of their bonds, which have been widely used in charge-neutrality verification, crystal structure determination, and reaction estimation. Currently only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition based oxidation state prediction still remains elusive so far, which is more important in new material discovery for which the structures are not even available. This work proposes a novel deep learning based BERT transformer language model BERTOS for predicting the oxidation states of all elements of inorganic compounds given only their chemical composition. Oxidation states (OS) are the charges of atoms after their ionic approximation of their bonds, which are the fundamental attributes of elements that help to explain redox reactions, reactivity, chemical bonding, and chemical properties of different elements and compounds. In electrochemistry, oxidation states are used to represent relevant compounds and ions in Latimer and Frost diagrams, and they can also be used to calculate the charge neutrality of chemical compounds to screen potential hypothetical materials generated by computational design algorithms. Oxidation states have also been used to study the complexes of transition metals.

Civilizations have tried to make drinking water safe to consume for thousands of years. The process of determining water contaminants has evolved with the complexity of the contaminants due to pesticides and heavy metals. The routine procedure to determine water safety is to use targeted analysis which searches for specific substances from some known list; however, we do not explicitly know which substances should be on this list. Before experimentally determining which substances are contaminants, how do we answer the sampling problem of identifying all the substances in the water? Here, we present an approach that builds on the work of Jaanus Liigand et al., which used non-targeted analysis that conducts a broader search on the sample to develop a random-forest regression model, to predict the names of all the substances in a sample, as well as their respective concentrations[1]. This work utilizes techniques from dimensionality reduction and linear decompositions to present a more accurate model using data from the European Massbank Metabolome Library to produce a global list of chemicals that researchers can then identify and test for when purifying water.