Automatic Optimization Research Articles

ChemMORT: an automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization.

Drug discovery and development constitute a laborious and costly undertaking. The success of a drug hinges not only good efficacy but also acceptable absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties. Overall, up to 50% of drug development failures have been contributed from undesirable ADMET profiles. As a multiple parameter objective, the optimization of the ADMET properties is extremely challenging owing to the vast chemical space and limited human expert knowledge. In this study, a freely available platform called Chemical Molecular Optimization, Representation and Translation (ChemMORT) is developed for the optimization of multiple ADMET endpoints without the loss of potency (https://cadd.nscc-tj.cn/deploy/chemmort/). ChemMORT contains three modules: Simplified Molecular Input Line Entry System (SMILES) Encoder, Descriptor Decoder and Molecular Optimizer. The SMILES Encoder can generate the molecular representation with a 512-dimensional vector, and the Descriptor Decoder is able to translate the above representation to the corresponding molecular structure with high accuracy. Based on reversible molecular representation and particle swarm optimization strategy, the Molecular Optimizer can be used to effectively optimize undesirable ADMET properties without the loss of bioactivity, which essentially accomplishes the design of inverse QSAR. The constrained multi-objective optimization of the poly (ADP-ribose) polymerase-1 inhibitor is provided as the case to explore the utility of ChemMORT.

Optimization of parameters for a fringe projection measurement system by use of an improved differential evolution method.

Fringe projection 3D measurement is widely used for object surface reconstruction. While improving measurement accuracy is a crucial task. Measurement accuracy is profoundly affected by various optical structural parameters. However, the current practice of system construction lacks theoretical guidelines and often relies on the experience of the operator, inevitably leading to unpredictable error. This paper investigates a theoretical optimization model and proposes an automatic optimization method for qualitatively determining the multiple optimal optical structural parameters in fringe projection measurement system. The aim is to enhance measurement accuracy conducting a rational comprehensive optimal structural parameters design prior to the system construction. Firstly, the mathematical model of the measurement system is established based on the principle of optical triangulation, and the phase sensitivity criterion is defined as the optimization norm. Within the full measurement range, the optimization merit function is formulated by combing three positions: the center position, the left and right boundary of the CCD. The imaging effectiveness criteria and sensor geometric dimensions are taken into account as the constraint boundaries. Subsequently, a combined improved differential evolution and Levy flight optimization algorithm is applied to search for the optimal parameters. The optimal structural parameters of the system were designed based on the optimization process. Experimental results validated the improvement in measurement accuracy achieved by the optimized structural parameters.

An improved workflow for the development of MS-compatible liquid chromatography assay purity and purification methods by using automated LC Screening instrumentation and in silico modeling.

The development of liquid chromatography UV and mass spectrometry (LC-UV-MS) assays in pharmaceutical analysis is pivotal to improve quality control by providing critical information about drug purity, stability, and presence and identity of byproducts and impurities. Analytical method development of these assays is time-consuming, which often causes it to become a bottle neck in drug development and poses a challenge for process chemists to quickly improve the chemistry. In this study, a systematic and efficient workflow was designed to develop purity assay and purification methods for a wide range of compounds including peptides, proteins, and small molecules with MS-compatible mobile phases (MP) by using automated LC screening instrumentation and in silico modeling tools. Initial LC MPs and chromatography column screening experiments enabled quick identification of conditions which provided the best resolution in the vicinity of the target compounds, which is further optimized using computer-assisted modeling (LC Simulator from ACD/Labs). The experimental retention times were in good agreement with the predicted retention times from LC Simulator (ΔtR < 7%). This workflow presents a practical workflow to significantly expedite the time needed to develop optimized LC-UV-MS methods, allowing for a facile, automatic method optimization and reducing the amount of manual work involved in developing new methods during drug development.

DockOpt: A Tool for Automatic Optimization of Docking Models.

Molecular docking is a widely used technique for leveraging protein structure for ligand discovery, but it remains difficult to utilize due to limitations that have not been adequately addressed. Despite some progress toward automation, docking still requires expert guidance, hindering its adoption by a broader range of investigators. To make docking more accessible, we developed a new utility called DockOpt, which automates the creation, evaluation, and optimization of docking models prior to their deployment in large-scale prospective screens. DockOpt outperforms our previous automated pipeline across all 43 targets in the DUDE-Z benchmark data set, and the generated models for 84% of targets demonstrate sufficient enrichment to warrant their use in prospective screens, with normalized LogAUC values of at least 15%. DockOpt is available as part of the Python package Pydock3 included in the UCSF DOCK 3.8 distribution, which is available for free to academic researchers at https://dock.compbio.ucsf.edu and free for everyone upon registration at https://tldr.docking.org.

Identifying optimal combinations of synchronous condensers for minimum grid strength compliance

This paper proposes a method for the automatic optimization of the size and location of synchronous condensers (SCs) to meet a minimum grid strength requirement that enables the high penetration of inverter-based resources (IBRs) in a weak network. The grid strength is quantified by the effective short-circuit ratio (ESCR), which is an heuristic index that accounts for the voltage interactions between IBRs. The basin hopping algorithm (BHA) is used in combination with the Nelder–Mead algorithm to minimize the total additional short-circuit contribution from the SCs, subject to a minimum ESCR constraint. It is shown that this optimization problem has several solutions with the minimum values of the objective function lying within a narrow range but different allocation of the SCs’ capacities to the candidate buses. Therefore, the BHA is iteratively applied to identify the area of the search space in which the optimum solutions are located, and additional criteria are proposed to rank the solutions based on cost and reliability attributes. The effectiveness of the proposed approach is shown using a modified 39-bus New England benchmark system in which conventional synchronous generators were replaced by IBRs, thus leading to weak network conditions.

Microclimate-Adaptive Morphological Parametric Design of Streets and Alleys in Traditional Villages

Microclimate is a reflection of the climatic conditions within the scope of human daily activities, so it is closely related to human activities. This paper uses Qingshui Village in Hancheng as the research object and the purpose of this paper was to study the influence mechanism of the traditional street spatial form on microclimate and thermal comfort, emphasizing the use of parameterized design platforms in technical methods to construct performance simulations and obtain relatively optimal solutions that are suitable for the spatial form of rural streets and alleys in the region. We select the Universal Thermal Climate Evaluation Index (UTCI) as the evaluation index for microclimate comfort and construct a performance-driven automatic optimization method for street and alley spaces. The results showed that: (1) When the street is in the northeast-southwest direction, the width is taken in the range of 6.5 m–7.3 m, the height of the building on the north side of the street is about 6.0 m, and the height of the building on the south side of the street is about 5.7 m, the comfort rate can reach up to 33.8%. (2) As for street and alley intersections, the focus remains on retaining their original forms while primarily controlling the scale changes. Within streets, the height of the building in the east-west direction is controlled at 5.6 m–6.1 m, the building in the north-south direction is controlled at 7 m–7.4 m, and street widths are controlled between 5.4 m and 6.3 m, resulting in a comfort level of 32.0%; (3) In alleys, east-west building heights are kept between 4.2 m and 5.5 m, and north-south building heights range from 4.5 m to 5.3 m, with widths at around 4.5 m, resulting in a similar comfort level of 32.0%. The research outcomes offer a scientific foundation for the design, creation, and enhancement of the physical environment of local village streets and alleys.

High-impedance arc fault modeling for distribution networks based on dynamic geometry dimension

Accurate modeling of high-impedance arc fault (HIAF) is of great significance for studying the characteristics of arc fault and suppressing its harm. In traditional arc models, the arc column is usually considered a cylindrical channel with constant length and diameter. However, the arc-burning process is susceptible to the environment. The changes in arc length and diameter present complex characteristics. Therefore, this study proposes a new HIAF model for distribution networks based on the arc's dynamic geometry dimension (DGD). First, the arc length, diameter, and field strength expressions are improved based on the classical cybernetic model. Next, an automatic parameter optimization method for the DGD model is proposed, and then this model is compared with existing advanced models. After that, the effects of the variable parameters of this model on arc characteristics are analyzed. Finally, the practical application effect of this model is tested. The experimental results show that the DGD model can accurately describe the dynamic arc development process, approximate the given arc waveform closely, and generate high-quality samples, which has certain advantages.

Photonic generation of microwave waveform using delay feedback photonic reservoir computing system with SOA

This paper proposes and demonstrates a model for generating microwave waveforms using a delay feedback photonic reservoir computing system with SOA. Our scheme involves building a photonic reservoir computer with SOA, which provides rich nonlinearity functionalities and memory capability for the reservoir. The automatic optimization of output waveform is implemented through the incorporation of gradient descent regression and a reservoir output layer. In theory, the system is capable of generating arbitrary microwave waveforms towards the target automatically. In our work, the capacity of the model is tested through theoretical analysis and simulation. We also compared the optimization effects of several regression algorithms applied to the reservoir computing, and generated six typical microwave waveforms, including triangle, square, sawtooth, negative, oblique triangle 1, and oblique triangle 2.

Establishment of General Oil Pipeline Scheduling Model and Research on Interface Tracking Calculation Method

In order to understand the establishment of oil pipeline scheduling model and interface tracking calculation method, a research on the establishment of a universal product oil pipeline scheduling model and interface tracking calculation method has been proposed. Establish an automatic formulation and optimization model for the scheduling plan of finished oil pipelines with the objective of minimizing the consumption cost of the entire pump unit. The model mainly adopts a centralized distribution method, considering the hydraulic constraints of the pipeline, and adopts a genetic algorithm to optimize and solve the model. This article provides a detailed introduction to the encoding method of genetic algorithm for optimizing the scheduling plan of finished oil pipelines, the selection of main operators in the algorithm, the establishment of fitness functions, and the introduction of penalty functions. Based on the established mathematical model, an automatic programming and optimization program for product oil pipeline scheduling plan was developed using C language in Windows 7 environment. Secondly, through practical applications, the actual pipeline operation data is basically consistent with the software calculation results, with an error of no more than 5%; As the running time changes, the pump cost fluctuates greatly; Using a larger throughput can reduce the amount of mixed oil; Therefore, this mathematical model can better meet the actual needs of pipeline operation, facilitate the rapid identification of the most sensitive parameter indicators, and adjust the scheduling plan in a timely manner, reduce operational economic losses, and improve the efficiency of product oil pipeline scheduling and operation.

Automatic Generation and Optimization Framework of NoC-Based Neural Network Accelerator Through Reinforcement Learning

Automatic Generation and Optimization Framework of NoC-Based Neural Network Accelerator Through Reinforcement Learning

Automatic evaluation and optimization of map registration based on feature overlap area ratio

Due to the differences in methods for collecting and processing data and map expression forms, two maps from different sources may have deviations in some objective evaluation metrics and fail to reflect the registration accuracy correctly, even though there are no geographic deviations. To address this issue, an objective evaluation metric based on the Feature Overlap Area Ratio (FOA) is proposed to reflect the accuracy of map registration in complex scenes. The proposed method uses different feature extraction methods to binarize different types of maps, and the registration accuracy is determined by calculating the ratio between the feature overlap area and the smaller value of the feature area in the map. The experiments prove that: the FOA metric is highly robust, and not affected by map types, map levels, and registration algorithms. Compared with other objective metrics, there is a stronger linear correlation between the FOA metric and the registration errors. The FOA metric is more sensitive to the errors and reflects the degree of map registration more accurately. Based on the above research, better registration result can be obtained by panning the two registered tile maps until the FOA value is maximized.

Application of machine learning methods for automatic test pattern generation process optimization during circuit design

Application of machine learning methods for automatic test pattern generation process optimization during circuit design

Non-linear Model Predictive Control to Improve the Mineralogical Efficiency of Flotation Circuits

Flotation optimisation strategies often trade off grade for recovery, without attempting to improve the mineralogical efficiency of the flotation process as part of the automatic control and optimisation strategy. Non-linear flotation characteristics such as air recovery complicate the implementation of such an optimisation strategy due to rapidly changing dynamics, and consequently there is a need for a non-linear controller implementation with real-time parameter estimation, to perform the optimisation. This simulation study demonstrates how the parameters of an air recovery model can be estimated dynamically from measurements commonly available on an industrial flotation circuit, and how dynamic optimisation of the flotation process - in the form of non-linear model predictive control - shifts the grade-recovery curve upwards - implying improved metallurgical efficiency through air recovery maximisation.

Potentiality of automatic parameter tuning suite available in ACTS track reconstruction software framework

Particle tracking is among the most sophisticated and complex part of the full event reconstruction chain. A number of reconstruction algorithms work in a sequence to build these trajectories from detector hits. Each of these algorithms use many configuration parameters that need to be fine-tuned to properly account for the detector/experimental setup, the available CPU budget and the desired physics performance. Few examples of such parameters include the cut values limiting the search space of the algorithm, the approximations accounting for complex phenomena or the parameters controlling algorithm performance. The most popular method to tune these parameters is hand-tuning using brute-force techniques. These techniques can be inefficient and raise issues for the long-term maintainability of such algorithms. The opensource track reconstruction software framework known as “A Common Tracking Framework (ACTS)” offers an alternative solution to these parameter tuning techniques through the use of automatic parameter optimization algorithms. ACTS come equipped with an auto-tuning suite that provides necessary setup for performing optimization of input parameters belonging to track reconstruction algorithms. The user can choose the tunable parameters in a flexible way and define a cost/benefit function for optimizing the full reconstruction chain. The fast execution speed of ACTS allows the user to run several iterations of optimization within a reasonable time bracket. The performance of these optimizers has been demonstrated on different track reconstruction algorithms such as trajectory seed reconstruction and selection, particle vertex reconstruction and generation of simplified material map, and on different detector geometries such as Generic Detector and Open Data Detector (ODD). We aim to bring this approach to all aspects of trajectory reconstruction by having a more flexible integration of tunable parameters within ACTS.

Composing recurrent spiking neural networks using locally-recurrent motifs and risk-mitigating architectural optimization.

In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce rich dynamics that are critical for memory formation and learning, systemic architectural optimization of RSNNs is still an open challenge. We aim to enable systematic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization. We compose RSNNs based on a layer architecture called Sparsely-Connected Recurrent Motif Layer (SC-ML) that consists of multiple small recurrent motifs wired together by sparse lateral connections. The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes. We further propose a method called Hybrid Risk-Mitigating Architectural Search (HRMAS) to systematically optimize the topology of the proposed recurrent motifs and SC-ML layer architecture. HRMAS is an alternating two-step optimization process by which we mitigate the risk of network instability and performance degradation caused by architectural change by introducing a novel biologically-inspired "self-repairing" mechanism through intrinsic plasticity. The intrinsic plasticity is introduced to the second step of each HRMAS iteration and acts as unsupervised fast self-adaptation to structural and synaptic weight modifications introduced by the first step during the RSNN architectural "evolution." We demonstrate that the proposed automatic architecture optimization leads to significant performance gains over existing manually designed RSNNs: we achieve 96.44% on TI46-Alpha, 94.66% on N-TIDIGITS, 90.28% on DVS-Gesture, and 98.72% on N-MNIST. To the best of the authors' knowledge, this is the first work to perform systematic architecture optimization on RSNNs.

Human Activity Discovery With Automatic Multi-Objective Particle Swarm Optimization Clustering With Gaussian Mutation and Game Theory

Despite many advances in Human Activity Recognition (HAR), most existing works are conducted with supervision. Supervised methods rely on labeled training data. However, obtaining labeled data is difficult, costly, and time-consuming. In this paper, we introduce an automatic multi-objective particle swarm optimization clustering based on Gaussian mutation and game theory (MOPGMGT) to provide fully unsupervised human activity discovery. Furthermore, we map the multi-objective clustering problem to game theory to get the best optimal solution. The proposed algorithm can accurately find the number of activities without any prior knowledge. Multi-objective optimization problems typically cannot have a single optimal solution. We solve this problem by applying, Nash Equilibrium (NE) to the pareto front as the decision-making for choosing the best solution. NE does not just look for the best solution but tries to optimize the final solution by considering the effect of choosing each of the solutions as the best solution on the other solutions and one with the best impact is chosen. Moreover, a Gaussian mutation is applied on the pareto front to avoid premature convergence. As far as we know, this is the first time that human activity discovery is performed fully unsupervised, and a multi-objective PSO is mapped to the game theory space for finding the best solution. Experiments on six challenging human activity datasets demonstrate the capability of the proposed approach in achieving the best accuracy in human activity discovery and determining the optimal number of clusters. In comparison to well-known multi-objective algorithms, the MOPGMGT significantly improves the clustering outcomes on six benchmark clustering datasets.

Improved dark channel priori single image defogging technique using image segmentation and joint filtering.

Foggy images affect image analysis and measurement because of their low definition and blurred details. Despite numerous studies on haze in natural images in hazy environments, the recovery effect is not ideal for processing hazy images in sky areas. A dark channel priori technique for processing haze images with sky areas where atmospheric light values are misestimated and halo artefacts are produced, as well as an improved dark channel priori single-image defogging technique based on image segmentation and joint filtering, are proposed. First, an estimation method of the atmospheric illumination value using image segmentation is proposed to obtain the atmospheric illumination value. The probability density distribution function of the haze-grey image was constructed during image segmentation. The probability density distribution function of the grey image value, the K-means clustering technique, and the method for estimating atmospheric illumination values are combined to improve image segmentation techniques and achieve the segmentation of sky and non-sky areas in hazy images. Based on the segmentation threshold, the number of pixels in the sky and non-sky areas, as well as the normalisation results, were counted to calculate the atmospheric illumination values. Second, to address the halo artefact phenomenon, a method for optimising the image transmittance map using joint filtering is proposed. The image transmittance map was optimised by combining fast-guided filtering and weighted least-squares filtering to retain the edge information and smooth the gradient change of the internal region. Finally, gamma correction and automatic level optimisation are used to improve the brightness and contrast of the defogged images. The experimental results show that the proposed technique can effectively achieve sky segmentation. Compared to the traditional dark-channel prior technique, the proposed technique suppress halo artefacts and improve image detail recovery. Compared to other techniques, the proposed technique exhibited excellent performance in subjective and objective evaluations.

Health and comfort oriented automatic generative design and optimization of residence space layout: An integrated data-driven and knowledge-based approach

During the initial design phase, space layout design plays a critical role in ensuring the ultimate performance of a residence. However, physical performance like energy consumption is usually prioritized, while health and comfort performance of residence is less explored. This study proposes an integrated data-driven and knowledge-based approach for automatic generative design of residence space layout focusing on health and comfort performance. First, explicit knowledge about key parameters of the layout design is obtained through quantitative analysis of large-scale health data. Second, with health and comfort as performance oriented, adjacency preference and noise score are introduced as objective functions and automatic generative design is carried out to obtain multiple layout alternatives. Finally, multi-objective deviation analysis is conducted to determine the optimal layout scheme. This study offers a practical and efficient tool through the whole design process, including pre-parameters analysis, during-process generation, and post-scheme evaluation, which contributes to improve decision-making.

Improved Design for Hardware Implementation of Graph-Based Large Margin Classifiers for Embedded Edge Computing.

The number of connected embedded edge computing Internet of Things (IoT) devices has been increasing over the years, contributing to the significant growth of available data in different scenarios. Thereby, machine learning algorithms arise to enable task automation and process optimization based on those data. However, due to some learning methods' computational complexity implementing geometric classifiers, it is a challenge to map these on embedded systems or devices with limited resources in size, processing, memory, and power, to accomplish the desired requirements. This hampers the applicability of these methods to complex industrial embedded edge applications. This work evaluates strategies to reduce classifiers' implementation costs based on the CHIP-clas model, independent of hyperparameter tuning and optimization algorithms. The proposal aims to evaluate the tradeoff between numerical precision and model performance and analyze the hardware implementations of a distance-based classifier. Two 16 -b floating-point formats were compared to the 32 -b floating-point precision implementation. Also, a new hardware architecture was developed and then compared to the state-of-the-art reference. The results indicate that the model is robust to low precision computation, providing statistically equivalent results compared to the baseline model, also pointing out statistically equivalent performance and a global speed-up factor of approx 4.39 in processing time.

Influence of quality factor on operating mode of TM&lt;sub&gt;02&lt;/sub&gt; mode relativistic backwave oscillator

&lt;sec&gt;The mode competition in an overmoded relativistic backward wave oscillator is studied through theoretical analysis and three-dimensional particle-in-cell simulation in this work. Based on the quality factor and coupling impedance, the mode selection for a TM&lt;sub&gt;02&lt;/sub&gt; mode backward wave oscillator is achieved, and its output power and magnetic field strength are optimized in the simulation.&lt;/sec&gt;&lt;sec&gt;The quality factor is related to the group velocity and end reflection of each mode. The dispersion curves of some non-axisymmetric modes are very close, and the group velocities are basically equal. Therefore, the end reflection needs considering to distinguish between the quality factors of different modes. In frequency domain simulation, analyzing the quality factor of each mode by using the &lt;i&gt;S&lt;/i&gt;&lt;sub&gt;11&lt;/sub&gt; parameter curve can avoid calculating the end reflection.&lt;/sec&gt;&lt;sec&gt;The three-dimensional simulation results show that the coupling impedance and quality factor jointly affect the operating mode. When the coupling impedance advantage of the working mode is not obvious, changing the resonant frequency of the high-frequency structure can affect the beam-wave interaction process, thereby changing the excitation mode. When the advantage is obvious, the beam-wave interaction of the excitation mode will not be destroyed by the resonant mode, and other modes of microwave output mainly come from the conversion of the same frequency modes. Due to the constant dispersion curve, the effect of resonance on the mode is essentially the effect of the quality factor on the mode dominated by the end reflection.&lt;/sec&gt;&lt;sec&gt;The insensitive parameters and the electron beam radius obtained from the simulation are used as the optimal parameters, and the automatic optimization algorithm is used in combination with the two-dimensional simulation to perform multi-objective optimization design in the above device. The final output power of the backward wave oscillator reaches 534 MW, with an efficiency of 23.64%, an increase of 221.7% compared with the efficiency of the original device. The device operating mode remains stable, with a power ratio of TM&lt;sub&gt;02&lt;/sub&gt; mode reaching 94.95%.&lt;/sec&gt;