Flexible Machine Research Articles

Evaluating process flexibility in lot sizing problems: an approach based on multicriteria decision making

This paper presents a multicriteria analysis of the process flexibility in the context of the lot sizing problem with parallel machines. In the standard design for lot sizing problems, each machine can manufacture all products (total or complete flexibility). However, installing machines with complete flexibility for several practical applications can be costly. Therefore, it becomes interesting to implement only a limited amount of machine flexibility, where each machine can produce only a small number of different products. Recently, some works presented analyses of process flexibility by considering only the production cost as a criterion. However, the literature lacks a more comprehensive analysis that considers other essential criteria regarding the problem to compute the value of a flexibility configuration. Thus, we provide a detailed multicriteria analysis based on the TOPSIS method that produces a ranking of alternatives for the flexibility configurations. Extensive computational experiments and sensitivity analyses for different scenarios of the lot sizing problem compare individual flexibility configurations and evaluate its advantages in manufacturing planning. The computational results showed that limited flexibility configurations outperform the total flexibility in all scenarios. Moreover, different from the studies considering only the total cost as the criterion, investing in flexibility for all capacity levels has advantages.

Flexible Machine Learning Algorithms for Clinical Gait Assessment Tools.

The current gold standard of gait diagnostics is dependent on large, expensive motion-capture laboratories and highly trained clinical and technical staff. Wearable sensor systems combined with machine learning may help to improve the accessibility of objective gait assessments in a broad clinical context. However, current algorithms lack flexibility and require large training datasets with tedious manual labelling of data. The current study tests the validity of a novel machine learning algorithm for automated gait partitioning of laboratory-based and sensor-based gait data. The developed artificial intelligence tool was used in patients with a central neurological lesion and severe gait impairments. To build the novel algorithm, 2% and 3% of the entire dataset (567 and 368 steps in total, respectively) were required for assessments with laboratory equipment and inertial measurement units. The mean errors of machine learning-based gait partitions were 0.021 s for the laboratory-based datasets and 0.034 s for the sensor-based datasets. Combining reinforcement learning with a deep neural network allows significant reduction in the size of the training datasets to <5%. The low number of required training data provides end-users with a high degree of flexibility. Non-experts can easily adjust the developed algorithm and modify the training library depending on the measurement system and clinical population.

FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns

As an asset pricing model in economics and finance, factor model has been widely used in quantitative investment. Towards building more effective factor models, recent years have witnessed the paradigm shift from linear models to more flexible nonlinear data-driven machine learning models. However, due to low signal-to-noise ratio of the financial data, it is quite challenging to learn effective factor models. In this paper, we propose a novel factor model, FactorVAE, as a probabilistic model with inherent randomness for noise modeling. Essentially, our model integrates the dynamic factor model (DFM) with the variational autoencoder (VAE) in machine learning, and we propose a prior-posterior learning method based on VAE, which can effectively guide the learning of model by approximating an optimal posterior factor model with future information. Particularly, considering that risk modeling is important for the noisy stock data, FactorVAE can estimate the variances from the distribution over the latent space of VAE, in addition to predicting returns. The experiments on the real stock market data demonstrate the effectiveness of FactorVAE, which outperforms various baseline methods.

An approachable, flexible and practical machine learning workshop for biologists.

SummaryThe increasing prevalence and importance of machine learning in biological research have created a need for machine learning training resources tailored towards biological researchers. However, existing resources are often inaccessible, infeasible or inappropriate for biologists because they require significant computational and mathematical knowledge, demand an unrealistic time-investment or teach skills primarily for computational researchers. We created the Machine Learning for Biologists (ML4Bio) workshop, a short, intensive workshop that empowers biological researchers to comprehend machine learning applications and pursue machine learning collaborations in their own research. The ML4Bio workshop focuses on classification and was designed around three principles: (i) emphasizing preparedness over fluency or expertise, (ii) necessitating minimal coding and mathematical background and (iii) requiring low time investment. It incorporates active learning methods and custom open-source software that allows participants to explore machine learning workflows. After multiple sessions to improve workshop design, we performed a study on three workshop sessions. Despite some confusion around identifying subtle methodological flaws in machine learning workflows, participants generally reported that the workshop met their goals, provided them with valuable skills and knowledge and greatly increased their beliefs that they could engage in research that uses machine learning. ML4Bio is an educational tool for biological researchers, and its creation and evaluation provide valuable insight into tailoring educational resources for active researchers in different domains.Availability and implementationWorkshop materials are available at https://github.com/carpentries-incubator/ml4bio-workshop and the ml4bio software is available at https://github.com/gitter-lab/ml4bio.Supplementary information Supplementary data are available at Bioinformatics online.

The optimal dynamic treatment rule superlearner: considerations, performance, and application to criminal justice interventions.

The optimal dynamic treatment rule (ODTR) framework offers an approach for understanding which kinds of patients respond best to specific treatments - in other words, treatment effect heterogeneity. Recently, there has been a proliferation of methods for estimating the ODTR. One such method is an extension of the SuperLearner algorithm - an ensemble method to optimally combine candidate algorithms extensively used in prediction problems - to ODTRs. Following the ``causal roadmap," we causally and statistically define the ODTR and provide an introduction to estimating it using the ODTR SuperLearner. Additionally, we highlight practical choices when implementing the algorithm, including choice of candidate algorithms, metalearners to combine the candidates, and risk functions to select the best combination of algorithms. Using simulations, we illustrate how estimating the ODTR using this SuperLearner approach can uncover treatment effect heterogeneity more effectively than traditional approaches based on fitting a parametric regression of the outcome on the treatment, covariates and treatment-covariate interactions. We investigate the implications of choices in implementing an ODTR SuperLearner at various sample sizes. Our results show the advantages of: (1) including a combination of both flexible machine learning algorithms and simple parametric estimators in the library of candidate algorithms; (2) using an ensemble metalearner to combine candidates rather than selecting only the best-performing candidate; (3) using the mean outcome under the rule as a risk function. Finally, we apply the ODTR SuperLearner to the ``Interventions" study, an ongoing randomized controlled trial, to identify which justice-involved adults with mental illness benefit most from cognitive behavioral therapy to reduce criminal re-offending.

PREDICTIVE PERFORMANCE OF MACHINE LEARNING MODELS FOR DETECTION OF INCIDENT HEART FAILURE USING MULTI-CENTRE DATA

Objective: To mitigate the health and economic burden associated with heart failure (HF), primary prevention is of utmost importance. To effectively address the diverse range of individual health profiles, prediction models must be trained and validated on a wide range of population-based cohorts. We evaluated the predictive performance of Survival Gradient Boosting (SGB) and Coxnet (CN) for the detection of incident HF. In addition, we compared the models’ performance trained only on a single-centre cohort with those trained on diverse multi-centre cohorts. Design and method: We utilized 6 cohorts from the Heart ‘omics’ in AGEing (HOMAGE) project to evaluate two computational approaches. The dataset consists of 31,382 individuals (mean age 66 ± 10 years old), free of HF at the baseline. During a median follow-up of 5.36 years, 1,130 non-fatal HF events occurred. SGB is a non-linear machine learning method based on training regression trees with the objective of optimizing Cox partial likelihood. Coxnet is a standard linear Cox proportional hazard model, regularized by both L1 and L2 norms. To estimate the predictive accuracy of a single-centre model on a specific test cohort, we averaged the performance of single models trained on remaining cohorts one at a time. To develop models in multi-centre settings, we used 5 cohorts in every iteration as a training set and the remaining 1 cohort as a test set. We used 33 features, including clinical, ECG, and biochemical data. Results: Overall, multi-centre models achieved a higher c-index than those trained on single cohorts (Figure). For example, in the FLEMENGHO cohort, multi-centre SGB achieved 0.819, while only 0.664 in a single-centre setting. Additionally, non-linear SGB achieved a considerably higher c-index than linear CN in all but one cohort, especially in multi-centre settings, for example in the HVC cohort (SGB 0.689, CN 0.614). Conclusions: With a greater number and variety of training cohorts, the model learns a wider range of specific individual health characteristics. Flexible machine learning algorithms such as gradient boosting can be used to capture these diverse distributions and produce more precise, personalized models for the prediction of adverse events.

A Flexible Deep Learning Method for Energy Forecasting

Load prediction with higher accuracy and less computing power has become an important problem in the smart grids domain in general and especially in demand-side management (DSM), as it can serve to minimize global warming and better integrate renewable energies. To this end, it is interesting to have a general prediction model which uses different standard machine learning models in order to be flexible enough to be used in different regions and/or countries and to give a prediction for multiple days or weeks with relatively good accuracy. Thus, we propose in this article a flexible hybrid machine learning model that can be used to make predictions of different ranges by using both standard neural networks and an automatic process of updating the weights of these models depending on their past errors. The model was tested on Mayotte Island and the mean absolute percentage error (MAPE) obtained was 1.71% for 30 min predictions, 3.5% for 24 h predictions, and 5.1% for one-week predictions.

Grouping technology and a hybrid genetic algorithm‐desirability function approach for optimum design of cellular manufacturing systems

Cell formation and machine layout in cellular manufacturing systems (CMs) design are considered as a crucial, yet hard and complex decision process. Owing to the nondeterministic polynomial time (NP) and combinatorial class of this problem, this paper presents an innovative heuristic approach to re-arrange machines enabling the minimisation of inter/intra- cellular movements as well as the cost of material handling between machines, therefore increasing group efficiency and efficacy. The heuristic approach, which is based on group technology, genetic algorithms, and desirability function, determines the optimal solution for flexible cell formation and machine layout within each cell. Flexibility refers to an explicit improvement using the desirability function to modify cell design by altering the ratio data; that is, the weight factor to meet demand flexibility. Specifically, the desirable function proposed here to provide the optimal setting of the weighting factor as a key factor which enables CMs design the flexibility to control the cell size. Promised results were obtained when the proposed approach was applied to a case study. Practical implications and recommendations are provided for use by decision makers in the design of CMs.

On Predictive Modeling Using a New Flexible Weibull Distribution and Machine Learning Approach: Analyzing the COVID-19 Data

Predicting and modeling time-to-events data is a crucial and interesting research area. For modeling and predicting such types of data, numerous statistical models have been suggested and implemented. This study introduces a new statistical model, namely, a new modified flexible Weibull extension (NMFWE) distribution for modeling the mortality rate of COVID-19 patients. The introduced model is obtained by modifying the flexible Weibull extension model. The maximum likelihood estimators of the NMFWE model are obtained. The evaluation of the estimators of the NMFWE model is assessed in a simulation study. The flexibility and applicability of the NMFWE model are established by taking two datasets representing the mortality rates of COVID-19-infected persons in Mexico and Canada. For predictive modeling, we consider two pure statistical models and two machine learning (ML) algorithms. The pure statistical models include the autoregressive moving average (ARMA) and non-parametric autoregressive moving average (NP-ARMA), and the ML algorithms include neural network autoregression (NNAR) and support vector regression (SVR). To evaluate their forecasting performance, three standard measures of accuracy, namely, root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) are calculated. The findings demonstrate that ML algorithms are very effective at predicting the mortality rate data.

Prediction of protein–ligand binding affinity from sequencing data with interpretable machine learning

Protein–ligand interactions are increasingly profiled at high throughput using affinity selection and massively parallel sequencing. However, these assays do not provide the biophysical parameters that most rigorously quantify molecular interactions. Here we describe a flexible machine learning method, called ProBound, that accurately defines sequence recognition in terms of equilibrium binding constants or kinetic rates. This is achieved using a multi-layered maximum-likelihood framework that models both the molecular interactions and the data generation process. We show that ProBound quantifies transcription factor (TF) behavior with models that predict binding affinity over a range exceeding that of previous resources; captures the impact of DNA modifications and conformational flexibility of multi-TF complexes; and infers specificity directly from in vivo data such as ChIP-seq without peak calling. When coupled with an assay called KD-seq, it determines the absolute affinity of protein–ligand interactions. We also apply ProBound to profile the kinetics of kinase–substrate interactions. ProBound opens new avenues for decoding biological networks and rationally engineering protein–ligand interactions.

Interaction mechanisms and damage formation in laser cutting of CFRP laminates obtained by recycled carbon fibre

The increase in the use of composite materials poses the problem of their disposal/recycling after the End of Life (EOL). Different strategies were developed to recycle composite material, resulting in the availability of new raw materials, characterised by overall good mechanical properties and significantly low cost. However, the applicability of these materials to industrial production also depends on the possibility of producing and processing them with likewise available technologies. Among the production and processing technologies that can be adopted for recycled composite materials, resin infusion under flexible tooling (RIFT) and laser machining, respectively, stand out above all due to the high production/machining speed compared to the cost. This paper investigates the possibility to apply both these technologies to carbon fibre–reinforced polymer laminates obtained by adopting recycled carbon fibres. Recycled CFRP plates of about 2.7 mm in thickness were produced by RIFT and characterised in tensile and flexural tests. After mechanical characterisation, cutting tests were performed by using a 450 W QCW fibre laser, varying the pulse power, the pulse length, and the pulse overlap. The kerf geometries and the HAZ extension were measured at the upper and bottom parts as well as in the section. Analysis of variance was adopted to define which and how the process parameters affect the kerf dimension and HAZ extension. Results showed that it is possible to cut the composite at a cutting speed up to 2000 mm/s, obtaining, in the best conditions, narrow kerf, limited HAZ, and taper angle of about 0°.Graphical abstract

Robust scheduling for flexible machining job shop subject to machine breakdowns and new job arrivals considering system reusability and task recurrence

This paper focuses on the production scheduling problem of flexible job shops. In the production process of flexible job shop, there are dynamic events such as machine breakdowns or new job arrivals, which will interfere with the implementation of scheduling scheme and reduce the stability of the system. In response to this problem, this paper proposes a new robust optimization method that considers dynamic events and designs two indicators for evaluating the robustness of the system, namely the reusability of the system and the reproducibility of processing tasks. Two indicators are used to evaluate the comprehensive reusability of the system jointly. In the process of system rescheduling, this paper proposes a dynamic event response strategy (DERS) considering the comprehensive reusability of the system and establishes a multi-objective optimization model considering the total energy consumption, the makespan, and the comprehensive reusability of the system. In order to solve the model efficiently and obtain the optimal Pareto frontier, a multi-objective particle swarm arithmetic optimization (PSAO) is proposed in this paper. Finally, this paper designs experiments based on standard data cases, solves them based on this model and compares them with other algorithms. The final results show that in the flexible job-shop scheduling process, this method can effectively adjust the scheduling plan to respond to dynamic events to achieve stable scheduling in an uncertain environment.

ANALISIS MATERIAL HANDLING PADA PRODUKSI POT BUNGA DI UMKM CV SURYATAMA BETON

The development of the industrial world is currently growing very rapidly over time, and so is the progress of existing technology. Micro, Small and Medium Enterprises (MSMEs) are economic business activities owned by individuals or groups in accordance with the criteria stipulated by Law no. 20 of 2008. In this case, of course, MSME actors have a superior product that is produced in it. One of the SMEs in Sumbawa by producing a product, namely CV Suryatama Beton. This company produces paving blocks, profile poles, concrete buis, finished mamak, flower pots, iron wire pallets, road pavers, km stakes and wall paving blocks. The number of types of products produced certainly requires a high level of flexibility in machines and production processes. Flexible manufacturing system or FMS (Flexible manufacturing system) is a manufacturing system that can react flexibly to changes. The two kinds of system changes can be changes in the type of product to be produced (machine flexibility), as well as changes in the sequence of processes in the manufacture of these products (routing flexibility). The advantage of using FMS in a mass production system is the high flexibility in allocating time and effort, so as to increase productivity and product quality and reduce production costs. correct equipment and methods. Material handling system planning is an important component in facility planning, especially in relation to layout design.&#x0D;

Explainable multiview framework for dissecting spatial relationships from highly multiplexed data

The advancement of highly multiplexed spatial technologies requires scalable methods that can leverage spatial information. We present MISTy, a flexible, scalable, and explainable machine learning framework for extracting relationships from any spatial omics data, from dozens to thousands of measured markers. MISTy builds multiple views focusing on different spatial or functional contexts to dissect different effects. We evaluated MISTy on in silico and breast cancer datasets measured by imaging mass cytometry and spatial transcriptomics. We estimated structural and functional interactions coming from different spatial contexts in breast cancer and demonstrated how to relate MISTy’s results to clinical features.

Optimization study of three-stage assembly flowshop problem in pharmacy automation dispensing systems

Along with the rising prevalence of chronic diseases and the increasing complexity of pharmaceutical care, pharmacy automation dispensing systems (PADS)s are utilized to improve the quality of patient care, reduce dispensing-related medication errors, and cut down medication-related expenses. After PADSs fulfill prescription orders, patients still have to dispense medications for each meal by themselves. It is well known that dispensing medications is time-consuming and exhausting, especially for chronic patients. During the manual dispensing process, some unexpected medical errors might appear, which would result in discomfort, harm, and even death. To provide efficient and patient-centered pharmacy care, we proposed automatically dispensing prescriptions by meal orders in PADS. Specifically, we formulated a novel three-stage assembly flowshop problem to fulfill prescription orders at the level of meal orders to minimize the total completion times of packing prescription orders. In our studied PADS, there are fully flexible parallel machines dispensing medication jobs and collating sub-orders (meal prescription orders) in the first and second stages, and one assembly machine packing prescription orders in the third stage. Based on the properties of the optimal schedule, we proposed a branch-and-bound (B&B) algorithm embedded with a constructive heuristic (CH) to obtain a tight upper bound. Since the three-stage assembly flowshop problem in PADS is strongly NP-hard, we also presented an improved tabu search (iTS) heuristic for the practical data size. Finally, we conducted a series of numerical experiments based on artificial data sets guided by characteristics obtained from practical pharmacy data sets. The computational results showed that the proposed CH algorithm is efficient, and when the computational time was allowed, the iTS algorithm could further enhance the performance. Moreover, the efficiency of collating sub-orders has a significant impact on the overall performance of PADS.

Industry 4.0 enabling manufacturing flexibility: technology contributions to individual resource and shop floor flexibility

PurposeThis paper focuses on understanding the contribution of Industry 4.0 technologies to manufacturing flexibility.Design/methodology/approachA multiple-case study was conducted through interviews and complementary data from 12 adopters of Industry 4.0 technologies from the industrial sector. To enable a broad perspective, cases from 5 industry sectors with different technological intensity levels were studied.FindingsThe findings show that Industry 4.0 technologies are mostly used to improve machine flexibility since there is a major focus on technological approaches rather than on wider flexibility. The results also showed that cloud services, IoT, and data analytics provide the basis for flexible operation, and collaborative robots, ERP/MES/PLM, AGVs, and traceability devices are the most commonly implemented technologies for flexibility. However, inherent contingency factors such as production complexity and product life cycle need to be considered.Originality/valueThis article expands the research on manufacturing flexibility, considering new capabilities introduced by Industry 4.0.

Utility based approach in individualized optimal dose selection using machine learning methods.

The goal in personalized medicine is to individualize treatment using patient characteristics and improve health outcomes. Selection of optimal dose must balance the effect of dose on both treatment efficacy and toxicity outcomes. We consider a setting with one binary efficacy and one binary toxicity outcome. The goal is to find the optimal dose for each patient using clinical features and biomarkers from available dataset. We propose to use flexible machine learning methods such as random forest and Gaussian process models to build models for efficacy and toxicity depending on dose and biomarkers. A copula is used to model the joint distribution of the two outcomes and the estimates are constrained to have non‐decreasing dose‐efficacy and dose‐toxicity relationships. Numerical utilities are elicited from clinicians for each potential bivariate outcome. For each patient, the optimal dose is chosen to maximize the posterior mean of the utility function. We also propose alternative approaches to optimal dose selection by adding additional toxicity based constraints and an approach taking into account the uncertainty in the estimation of the utility function. The proposed methods are evaluated in a simulation study to compare expected utility outcomes under various estimated optimal dose rules. Gaussian process models tended to have better performance than random forest. Enforcing monotonicity during modeling provided small benefits. Whether and how, correlation between efficacy and toxicity, was modeled, had little effect on performance. The proposed methods are illustrated with a study of patients with liver cancer treated with stereotactic body radiation therapy.

Hydrologic similarity based on width function and hypsometry: An unsupervised learning approach

The prediction of hydrologic conditions in watersheds has manifold applications, ranging from flood disaster preparedness to water supply and environmental flow management. In watersheds with scarce or no flow data, it is difficult to make accurate hydrologic predictions. Past work has used similarity in single-valued properties of the terrain (for example, drainage area, mean slope) as the basis to relate flow conditions in gauged watersheds to the ungauged ones. The resulting predictions show modest accuracy and have a weak physical basis. In this study, we develop a physics-informed machine learning approach to extract features that represent the hydrologic dynamics — width function and hypsometric curve. These two geomorphometric measures are computed using functional forms fitted to estimates derived from digital elevation data. Furthermore, dynamically-similar groups are identified based on results from unsupervised clustering and divergence measures. Our approach paves the way towards a flexible and scalable machine learning approach that can be used to assess hydrologic similarity and improve prediction, one informed by physics of surface flow generation and transport in watersheds. A case study involving 72 sub-watersheds in the Narmada River Basin (India) is used to illustrate the new methodology.

Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations.

3D-grid-based chemical transport models, such as the Community Multiscale Air Quality (CMAQ) modeling system, have been widely used for predicting concentrations of ambient air pollutants. However, typical horizontal resolutions of nationwide CMAQ simulations (12 × 12 km2) cannot capture local-scale gradients for accurately assessing human exposures and environmental justice disparities. In this study, a Bayesian ensemble machine learning (BEML) framework, which integrates 13 learning algorithms, was developed for downscaling CMAQ estimates of ozone daily maximum 8 h averages to the census tract level, across the contiguous US, and was demonstrated for 2011. Three-stage hyperparameter tuning and targeted validations were designed to ensure the ensemble model's ability to interpolate, extrapolate, and capture concentration peaks. The Shapley value metric from coalitional game theory was applied to interpret the drivers of subgrid gradients. The flexibility (transferability) of the 2011-trained BEML model was further tested by evaluating its ability to estimate fine-scale concentrations for other years (2012-2017) without retraining. To demonstrate the feasibility of using the BEML approach to strictly "data-limited" situations, the model was applied to downscale CMAQ outputs for a future-year scenario-based simulation that considers effects of variations in meteorology associated with climate change.

Probing Herbicide Toxicity to Algae (Selenastrum capricornutum) by Lipid Profiling with Machine Learning and Microchip/MALDI-TOF Mass Spectrometry.

Matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS)-based lipid profiling is a powerful method to study the cytotoxicity of chemical exposure to microorganisms at the single cell level. We report here a combined approach of machine learning (ML) and microchip-based MALDI-time of flight (TOF) mass spectrometry to investigate the cytotoxic effect of herbicides on algae through single cell lipid profiling. Algal species Selenastrum capricornutum was chosen as the target system, and its exposure to different doses of common chemical herbicides and the resulting cytotoxic behaviors under various stress conditions were characterized. A lipid library for S. capricornutum has been established with 63 identified lipids that include glycosyldiacylglycerols and triacylglycerols. We demonstrated that major alternations occurred for lipids with functional groups of digalactosyldiacylglycerol (DGDG), triacylglycerol (TAG), and monogalactosyldiacylglycerol (MGDG). DGDG was shown to decrease upon exposure to herbicides of norflurazon and atrazine, while some MGDG and TAG lipids would increase for norflurazon. Compared to other algae, S. capricornutum was more strongly impacted by norflurazon than atrazine while the latter was observed to have a greater effect on C. reinhardtii. Machine learning algorithms have been applied to improve the classification of herbicide impact and help identify lipid species affected by the chemical exposure. A total of 69 machine learning models were trained and tested for the identification of ideal algorithms in the classification process, in which flexible discriminant analysis and support vector machine model were found to be the most accurate and consistent. The ML algorithms accurately differentiated herbicide impact and have identified cytotoxic differences that were previously hidden. The results suggest that herbicides express toxicity among different algae likely on the basis of metabolic differences. The ML-assisted method proves to be highly effective and can provide an advanced technological platform for probing cytotoxicity for bacterial species and in metabolic pathway analysis.