YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

Robust optimal operation of continuous catalytic reforming process under feedstock uncertainty

The continuous catalytic regenerative (CCR) reforming process is one of the most significant sources of hydrogen production in the petroleum refining process. However, the fluctuations in feedstock composition and flow rate could significantly affect both product distribution and energy consumption. In this study, a robust deviation criterion based multi-objective optimization approach is proposed to perform the optimal operation of CCR reformer under feedstock uncertainty, with simultaneous maximization of product yields and minimization of energy consumption. Minimax approach is adopted to handle these uncertain objectives, and the Latin hypercube sampling method is then used to calculate these robust deviation criteria. Multi-objective surrogate-based optimization methods are next introduced to effectively solve the robust operational problem with high computational cost. The level diagram method is finally utilized to assist in multi-criteria decision-making. Two robust operational optimization problems with different objectives are solved to demonstrate the effectiveness of the proposed method for robust optimal operation of the CCR reforming process under feedstock uncertainty.     

Tabular data: Deep learning is not all you need

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.     

Development of high pressure membraneless alkaline electrolyzer

A technology for cyclic generation of hydrogen and oxygen using electrodes made of variable valency material that does not need the use of separating ion-exchange membranes is presented. The technological solution enables to fabricate electrolyzers for uninterrupted producing high-pressure hydrogen with reduced energy intensity of the production. The total work for compressing 1 m³ of hydrogen and 0.5 m³ of oxygen has been estimated. Results of investigation of influence of discrete supply of DC current to the electrolysis cell, in order to improve the processes of gas evolution and to simplify the power systems of the electrolysis plant, have been considered. There is also considered an electrolysis installation equipped with a thermosorption compressor in which LaNi₅ is used as a hydride-forming compound. The comparative characteristics of the developed electrolyzer and the currently used hydrogen generators are given.     

Structure-sensitive semantic matching for aggregate question answering over knowledge base

Aggregate question answering essentially returns answers for given questions by obtaining query graphs with unique dependencies between values and corresponding objects. Word order dependency, as the key to uniquely identify dependency of the query graph, reflects the dependencies between the words in the question. However, due to the semantic gap caused by the expression difference between questions encoded with word vectors and query graphs represented with logical formal elements, it is not trivial to match the correct query graph for the question. Most existing approaches design more expressive query graphs for complex questions and rank them just by directly calculating their similarities, ignoring the semantic gap between them. In this paper, we propose a novel Structure-sensitive Semantic Matching(SSM) approach that learns aligned representations of dependencies in questions and query graphs to eliminate their gap. First, we propose a cross-structure matching module to bridge the gap between two modalities(i.e., textual question and query graph). Then, we propose an entropy-based gated AQG filter to remove the structural noise caused by the uncertainty of dependencies. Finally, we present a two-channel query graph representation that fuses the semantics of abstract structure and grounding content of the query graph explicitly. Experimental results show that SSM could learn aligned representations of questions and query graphs to eliminate the gaps between their dependencies, and improves up to 12% (F1 score) on aggregation questions of two benchmark datasets.     

Feature selection methods for root-cause analysis among top-level product attributes

Manufacturing companies not only strive to deliver flawless products but also monitor product failures in the field to identify potential quality issues. When product failures occur, quality engineers must identify the root cause to improve any affected product and process. This root-cause analysis can be supported by feature selection methods that identify relevant product attributes, such as manufacturing dates with an increased number of product failures. In this paper, we present different methods for feature selection and evaluate their ability to identify relevant product attributes in a root-cause analysis. First, we compile a list of feature selection methods. Then, we summarize the properties of product attributes in warranty case data and discuss these properties regarding the challenges they pose for machine learning algorithms. Next, we simulate datasets of warranty cases, which emulate these product properties. Finally, we compare the feature selection methods based on these simulated datasets. In the end, the univariate filter information gain is determined to be a suitable method for a wide range of applications. The comparison based on simulated data provides a more general result than other publications, which only focus on a single use case. Due to the generic nature of the simulated datasets, the results can be applied to various root-cause analysis processes in different quality management applications and provide a guideline for readers who wish to explore machine learning methods for their analysis of quality data.     

A robust model-free controller for a three-phase grid-connected photovoltaic system based on ultra-local model

In this paper, a robust model-free controller for a grid-connected photovoltaic (PV) system is designed. The system consists of a PV generator connected to a three-phase grid by a DC/AC converter. The control objectives of the overall system are to extract maximum power from the PV source, to control reactive power exchange and to improve the quality of the current injected into the grid. The model-free control technique is based on the use of an ultra-local model instead of the dynamic model of the overall system. The local model is continuously updated based on a numerical differentiator using only the input–output behavior of the controlled system. The model-free controller consists of a classical feedback controller and a compensator for the effects of internal parameter changes and external disturbances. Simulation results illustrate the efficiency of the controller for grid-connected PV systems.     

Optimization of flow in additively manufactured porous columns with graded permeability

Chemical engineering systems often involve a functional porous medium, such as in catalyzed reactive flows, fluid purifiers, and chromatographic separations. Ideally, the flow rates throughout the porous medium are uniform, and all portions of the medium contribute efficiently to its function. The permeability is a property of a porous medium that depends on pore geometry and relates flow rate to pressure drop. Additive manufacturing techniques raise the possibilities that permeability can be arbitrarily specified in three dimensions, and that a broader range of permeabilities can be achieved than by traditional manufacturing methods. Using numerical optimization methods, we show that designs with spatially varying permeability can achieve greater flow uniformity than designs with uniform permeability. We consider geometries involving hemispherical regions that distribute flow, as in many glass chromatography columns. By several measures, significant improvements in flow uniformity can be obtained by modifying permeability only near the inlet and outlet.     

An integrated dimensionality reduction and surrogate optimization approach for plant-wide chemical process operation

With liquefied natural gas becoming increasingly prevalent as a flexible source of energy, the design and optimization of industrial refrigeration cycles becomes even more important. In this article, we propose an integrated surrogate modeling and optimization framework to model and optimize the complex CryoMan Cascade refrigeration cycle. Dimensionality reduction techniques are used to reduce the large number of process decision variables which are subsequently supplied to an array of Gaussian processes, modeling both the process objective as well as feasibility constraints. Through iterative resampling of the rigorous model, this data-driven surrogate is continually refined and subsequently optimized. This approach was not only able to improve on the results of directly optimizing the process flow sheet but also located the set of optimal operating conditions in only 2 h as opposed to the original 3 weeks, facilitating its use in the operational optimization and enhanced process design of large-scale industrial chemical systems.