Deterministic Machine Research Articles

On decision problems concerning contextual insertions and deletions

The notions of stability, anti-stability, and error-correctability of a language that is modified by making contextual insertions in the words of the language were introduced in a previous paper by Bottoni et al. in 2011, where it was shown that these properties are decidable for regular languages. The authors proposed investigating the decidability of these properties for other classes of languages. Here, we derive necessary and sufficient conditions for a class of languages to have decidable stable, anti-stable, and error-correctable properties, and use these conditions to exhibit general classes of languages (strictly greater than the regular languages) for which the properties are decidable, and also simple classes (the first such classes) for which the properties are undecidable. We obtain identical results for the case when contextual deletions (instead of insertions) are made in the words of the language, and also with mixes of insertions and deletions. Our constructions also demonstrate that certain general problems involving nondeterministic generalized sequential machines (GSMs) applied to languages accepted by deterministic machine models are decidable, which is surprising as the deterministic language families do not need to be closed under GSM mappings.

Optimizing biomass energy production in the southern region of Iran: A deterministic MCDM and machine learning approach in GIS

This study employs a deterministic approach, distinguishing itself from other renewable energy evaluations, to assess the potential of electrical energy derived from biomass sources in the southern region of Iran. The primary objectives include pinpointing optimal locations for maximal biomass production and subsequent energy generation within distinct climates and topographies, using fuzzy- Analytic Hierarchy Process (AHP). Additionally, Principal Component Analysis (PCA) identify key factors influencing biomass and energy production. The study quantifies electrical and thermal energy derived from biomass sources across various climates. The findings indicate that regions with lower altitudes and humid climates (1530 km2) demonstrate superior biomass performance, leading to increased electrical and thermal energy production. The feature selection process highlights the significant impact of climate and soil characteristics on biomass production and energy output. Analysis of biomass energy production reveals maximum electrical energy production ranging from 674.88 kWh/ha to 711.36 kWh/ha. The results of the Long Short-Term Memory (LSTM) method confirm its high accuracy in estimating electrical energy, with a significant correlation coefficient of 0.98. We conclude that by identifying locations with the best biomass sources based on climate, it is possible to increase the derived electrical energy. These insights are critical for informing energy policies aimed at optimizing biomass energy production and its integration into sustainable power grids.

Advanced bladder analysis using ultrasonic and electrical impedance tomography with machine learning algorithms

Purpose: The primary purpose of the study is to reconstruct the bladder based on the tomographic measurements obtained. Depending on the type of tomography used, two approaches are presented. Methods: In the first presented case, the measurements were collected using ultrasonic tomography, while in the second one, they were gathered with electrical impedance tomography. Deterministic methods and machine learning algorithms, such as Elastic Net, Least Angle Regression, and a Neural Network, were used to obtain the bladder reconstruction. Results: The bladder's position and size can be recognized based on the tomographic measurements of the UST and EIT. Both methods allow for its effective reconstruction. Discussion: The research results are satisfactory, but their effectiveness is debatable. Future studies will focus on comparing and optimizing both solutions regarding reconstruction time.

Binary distinguishability operation

This paper analyzes a new distinguishability operation for finite deterministic machines and languages. The research was inspired by the “Gedanken experiments” on sequential machines performed by Moore in 1956, and extends the study of the unary distinguishability operation to a binary one. Besides studying the new operation's properties, we give a tight bound of its state complexity on regular languages, including the case for finite languages.

Probabilistic fatigue life prediction using multi-layer perceptron with maximum entropy algorithm

In the structural fatigue fields, such as aerospace, maritime, and civil engineering, the accurate construction of the Probability-Stress-Life (P-S-N) curve is crucial for preventing unexpected structural failures and is fundamental to the engineering design process. Conventional methods usually assume that the fatigue life distribution follows a normal or weibull distribution, which overlooks the differences of life distribution at different stress levels and introduces subjective errors. To address this issue, this paper proposes a new approach based a multi-layer perceptron model with maximum entropy algorithm (MPME) for probabilistic fatigue life prediction. During the derivation of life probability distribution function in this approach, the type not require any pre-assumption, thus effectively avoiding the introduction of subjective errors. Specifically, the dispersed information of fatigue life is quantified as various life distribution statistical features such as mean, variance, skewness, and kurtosis. Next, learn the continuous functional relationship between stress and these features using a multi-layer perceptron (MLP). Finally, the target probability distribution is derived using the maximum entropy algorithm, with the predicted distribution features obtained from the MLP serving as constraints for it. In addition, to ensure the consistency between the prediction of MLP and physical laws, we encode physical knowledge into the network loss to guide the updating of network parameters. Experimental results of two different material fatigue data demonstrate that, compared to traditional deterministic model-based methods and machine learning methods, the MPME in this paper can more accurately predict the probabilistic fatigue life.

State Machines for Large Scale Computer Software and Systems

The behavior and architecture of large scale discrete state systems found in computer software and hardware can be specified and analyzed using a particular class of primitive recursive functions. This article begins with an illustration of the utility of the method via a number of small examples and then via longer specification and verification of the “Paxos” distributed consensus algorithm [ 26 ]. The “sequence maps” are then shown to provide an alternative representation of deterministic state machines and products of state machines. Distributed and composite systems, parallel and concurrent computation, and real-time behavior can all be specified naturally with these methods—which require neither extensions to the classical state machine model nor any axiomatic methods or other techniques from formal logic or other foundational methods. Compared to state diagrams or tables or the standard set-tuple-transition-maps, sequence maps are more concise and better suited to describing the behavior and compositional architecture of computer systems. Staying strictly within the boundaries of classical deterministic state machines anchors the methods to the algebraic structures of automata and makes the specifications faithful to engineering practice.

The Executioner Paradox: understanding self-referential dilemma in computational systems

AbstractAs computational systems burgeon with advancing artificial intelligence (AI), the deterministic frameworks underlying them face novel challenges, especially when interfacing with self-modifying code. The Executioner Paradox, introduced herein, exemplifies such a challenge where a deterministic Executioner Machine (EM) grapples with self-aware and self-modifying code. This unveils a self-referential dilemma, highlighting a gap in current deterministic computational frameworks when faced with self-evolving code. In this article, the Executioner Paradox is proposed, highlighting the nuanced interactions between deterministic decision-making and self-aware code, and the ensuing challenges. This article advocates for a re-evaluation of existing deterministic frameworks, emphasizing the need for adaptive decision-making mechanisms in computational systems. By dissecting the Executioner Paradox, the aim is to foster a robust discussion on evolving deterministic frameworks to accommodate the dynamic nature of self-modifying code, thereby contributing a forward-looking lens to the discourse on computational systems amidst advancing AI.

Robust face recognition using quaternion interval type II fuzzy logic-based feature extraction on colour images.

In this paper, we propose a new robust and fast learning technique by investigating the effect of integration of quaternion and interval type II fuzzy logic along with non-iterative, parameter free deterministic learning machine (DLM) pertaining to face recognition problem. The traditional learning techniques did not account colour information and degree of pixel wise association of individual pixel of a colour face image in their network. Therefore, this paper presents a new technique named quaternion interval type II based deterministic learning machine (QIntTyII-DLM), which considers the interrelationship between three colour channels viz. red, green, and blue (RGB) by representing each colour pixel of a colour image in quaternion number sequence. Here, quaternion vector representation of a colour face image is fuzzified using interval type II fuzzy logic. This reduces the redundancy between pixels of different colour channels and also transforms colour channels of the image to orthogonal colour space. Thereafter, classification is performed using DLM. Experiments performed (on four standard datasets AR, Georgia Tech, Indian, face (female) and faces 94 (male) face datasets) and comparison done with other existing techniques proves that the proposed technique gives better results in terms of percentage error rate (reduces approximately 10-12%) and computational speed.

Investigation of the thermal analysis of a wavy fin with radiation impact: an application of extreme learning machine

The combined impact of radiation and convection on the heat transfer of a wavy fin is scrutinized in the present analysis. The novelty of this research work is that it proposes a deterministic machine learning model known as an extreme learning machine to address the heat transfer problem of a wavy fin. The effect of radiation on convective heat transfer and the Rosseland approximation for the radiation heat exchange have been considered in the investigation. The nonlinear ordinary differential equation (ODE) is converted to its nondimensional form using the appropriate dimensionless variables. Runge-Kutta-Fehlberg's fourth-fifth order technique (RKF 45) is used to solve the nondimensional ODE numerically. The roles of convection-conduction, radiation-conduction, thermal conductivity, and radiation parameters have been discussed for satisfying a prescribed temperature distribution in rectangular and wavy fins with graphical visualization. A rise in convection-conduction and radiation-conduction variables decreased the thermal distribution of both the wavy fin and rectangular fin. Further, ANSYS simulation analyzes the variation of temperature and total heat flux in both rectangular and wavy fins. The study demonstrates the effectiveness of the model selected through the obtained results, which indicate the potential of the regression model for providing an accurate prediction.

Voting based double-weighted deterministic extreme learning machine model and its application

Voting based double-weighted deterministic extreme learning machine model and its application

Embracing Heterogeneity: Challenging the Paradigm of Replisomes as Deterministic Machines.

The paradigm of cellular systems as deterministic machines has long guided our understanding of biology. Advancements in technology and methodology, however, have revealed a world of stochasticity, challenging the notion of determinism. Here, we explore the stochastic behavior of multi-protein complexes, using the DNA replication system (replisome) as a prime example. The faithful and timely copying of DNA depends on the simultaneous action of a large set of enzymes and scaffolding factors. This fundamental cellular process is underpinned by dynamic protein-nucleic acid assemblies that must transition between distinct conformations and compositional states. Traditionally viewed as a well-orchestrated molecular machine, recent experimental evidence has unveiled significant variability and heterogeneity in the replication process. In this review, we discuss recent advances in single-molecule approaches and single-particle cryo-EM, which have provided insights into the dynamic processes of DNA replication. We comment on the new challenges faced by structural biologists and biophysicists as they attempt to describe the dynamic cascade of events leading to replisome assembly, activation, and progression. The fundamental principles uncovered and yet to be discovered through the study of DNA replication will inform on similar operating principles for other multi-protein complexes.

Toward high-performance energy and power battery cells with machine learning-based optimization of electrode manufacturing

The optimization of the electrode manufacturing process is important for upscaling the application of Lithium-Ion Batteries (LIBs) to cater for growing energy demand. LIB manufacturing is important to be optimized because it determines the practical performance of the cells when the latter are being used in applications such as electric vehicles. In this study, we tackled the issue of high-performance electrodes for desired battery applications by proposing a data-driven approach supported by a deterministic machine learning-assisted pipeline for bi-objective optimization of the electrochemical performances. This pipeline allows the inverse design of the process parameters to adopt to manufacture electrodes for energy or power applications. This work is an analogy to our previous work that addressed the optimization of the electrode microstructures for kinetic, ionic, and electronic transport properties improvement. An electrochemical model is fed with the electrode properties characterizing the electrode microstructures generated by manufacturing simulations, and used to simulate the electrochemical performances. Secondly, the resulting dataset was used to train a deterministic model to implement fast optimizations to identify optimal electrodes. Our results suggested a high amount of active material, combined with intermediate values of solid content in the slurry and calendering degree, to achieve the optimal electrodes.

Identification of concrete surface damage based on probabilistic deep learning of images

Crack is common damage that can reduce the durability of concrete structures and accelerate structural degradation. With intent to improve the accuracy and efficiency of image-based crack detection, deep learning has been extensively used. However, the current deep learning paradigms for this purpose are deterministic machine learning approaches that cannot evaluate the uncertainty of diagnosis results. To bridge this gap, this paper proposes a hybrid probabilistic deep learning method for concrete surface damage classification. In the proposed method, Bayesian inference is embedded in a deep convolutional neural network, and the parameters in probability layers are modified from deterministic values to Gaussian distributions. Experimental results showed that it can identify cracks with an accuracy of 0.9909. The quantitative indicator of uncertainty in the identification results increases with the noise level and the degree of occlusion, which can reflect the ability of the model to capture uncertainty well. In addition, the hybrid probability method based on transfer learning can significantly improve the recognition accuracy, which can reach 0.9249 in complex crack images. Even if the image contains more noise, it can be recognized accurately but the uncertainty indicator is greater than 0.07.

Risk-informed decision-making and control strategies for autonomous vehicles in emergency situations

This paper proposes risk-informed decision-making and control methods for autonomous vehicles (AVs) under severe driving conditions, where many vehicle interactions occur on slippery roads. We assume that the AV should approach a specific safe zone in case of vehicle malfunctioning. In normal situations, the driving behavior of the AV is based on the deterministic finite-state machine (FSM) that makes an appropriate real-time decision depending on the driving condition, which is efficient when compared with some conventional decision-making algorithms; alternatively, in emergency situations, the AV first has to be prevented the rear-end conflicts while the specific safe zone is simultaneously determined by evaluating the level of risk via two safety level indicators, i.e., Time-To-Collision (TTC) and Deceleration Rate to Avoid the Crash (DRAC). The safe path that guides the AV to avoid car crashes is generated based on the trajectory optimization theory (i.e., Pontryagin maximum principle), and the AV follows it based on the linear time-varying model predictive control (LTV-MPC), which ensures the AV’s lateral stability. We verify the effectiveness of the proposed decision-making and control strategies in various test scenarios, and the results show that the AV behaves appropriately according to the behaviors of surrounding vehicles and road condition.

Machine Learning-Assisted Multi-Objective Optimization of Battery Manufacturing from Synthetic Data Generated by Physics-Based Simulations

Recent efforts in the ongoing energy transition showed that Lithium-Ion Batteries (LIBs) represent a suitable technology for portable devices and electric vehicles due to their high performances and relatively good cell durability. However, the optimization of the electrode manufacturing process establishes a critical step to ensure high-quality LIBs. Nowadays, such optimization is currently based on trial-and-error and costly approaches. Indeed, LIB electrode manufacturing is a complex process involving multiple interlinked steps, including numerous process parameters that unravel sparse conditions to explore. In that sense, the digitalization of the manufacturing process highlights deep insights into its impact on the electrode and cell properties to accelerate and support autonomous productions and the prototyping activities at the experimental level. [1] We have shown in previous works that 3D-resolved physics-based models constitute meaningful tools to simulate the manufacturing process chain and bring to the community a series of unique computational 3D-resolved models for unlocking the relationships between fabrication parameters and electrode properties. [2, 3] Nevertheless, the physics-based models can still have a huge computational cost for high-throughput screening and their integration in optimization loops. In this work, we reported an innovative computational approach for digital-based manufacturing process optimization. Supported by a deterministic Machine Learning (ML)-based pipeline, we raised a multi-objective optimization of LIB electrode properties and inverse design of its fabrication process using synthetic data, as Figure 1A illustrates. In the end, this gave us the possibility to manufacture the real electrode to validate its physical relevance. To do so, we first focused on the setting of a smart design of experiments based on low-discrepancy sequences, exploring our manufacturing parameters space, to then evaluate various synthetic electrode properties related to the kinetic, ionic, and electronic transport properties of 3D-generated microstructures. The latter are generated using the ARTISTIC physics-based models' chain. [2, 3] Those synthetic data constituted a relevant database, to train and validate an accurate deterministic regression approach for fitting the electrode properties as a function of the manufacturing parameters. These so-derived regression models represented a meaningful tool to bypass the manufacturing physical modeling chain for focusing on unexplored manufacturing conditions. [4] Indeed, we took the benefits of combining these models to raise a multi-objective optimization loop using the Bayesian optimization (BO) framework to pinpoint the optimal manufacturing conditions to produce a high-performance 3D microstructure (Figure 1B). [5] This objective function granted equal weights for each electrode property when optimizing to guarantee a good balance of the optimal properties with minimal tortuosity factor, maximal effective electronic conductivity, maximal active surface area between active material and pores, and maximal density. The good results were carried out by combining BO and regression functions to considerably accelerate the search for the best manufacturing parameters to adopt. In the end, we have manufactured the electrode cell using the aforementioned optimal condition predicted by the optimization loop, to experimentally validate the physical relevance of this BO prediction. As a perspective in our future research, we aim to extend this study to more manufacturing steps (e.g. electrolyte infiltration, formation, and electrochemical performance) and additional fabrication parameters (e.g. calendering speed, particle size) and show that our approach can be transferred to accelerate the manufacturing of battery technologies and the manufacturing of composite materials in general.[1] Meyer, C, Kosfeld, M., Haselrieder, W., Kwade, A. Process modeling of the electrode calendering of lithium-ion batteries regarding the variation of cathode active materials and mass loadings. Journal of Energy Storage, 18, 2018[2] Lombardo, T., Caro, F., Ngandjong, A. C., Hoock, J-B., Duquesnoy, M., Delepine, J-C., Ponchelet, A., Doison, S., Franco, A. A. The ARTISTIC online calculator: exploring the impact of lithium-ion battery electrode manufacturing parameters interactively through your browser. Batteries & Supercaps, 5(3), 2022.[3] Duquesnoy, M., Lombardo, T., Caro, F., Haudiquez, F., Ngandjong, A. C., Xu, J., Oularbi, H., Franco, A. A. Functional data-driven framework for fast forecasting of electrode slurry rheology simulated by molecular dynamics. npj Computational Materials, 8(161), 2022.[4] ARTISTIC Project. https://www.erc-artistic.eu/. Accessed on November 2022.[5] Gunantara, N. A review of multi-objective optimization: methods and its applications. Cogent Engineering, 5(1), 2018. Figure 1

Correcting retrace and system imaging errors to achieve nanometer accuracy in full aperture, single-shot Fizeau interferometry.

X-ray mirrors with single-digit nanometer height errors are required to preserve the quality of ultra-intense photon beams produced at synchrotron or free electron laser sources. To fabricate suitable X-ray mirrors, accurate metrology data is needed for deterministic polishing machines. Fizeau phase-shifting interferometers are optimized to achieve accurate results under nulled conditions. However, for curved or aspheric mirrors, a limited choice of reference optic often necessitates measurement under non-nulled conditions, which can introduce retrace error. Using experimental measurements of a multi-tilted calibration mirror, we have developed an empirical model of Fizeau retrace error, based on Zernike polynomial fitting. We demonstrate that the model is in good agreement with measurements of ultra-high quality, weakly-curved X-ray mirrors with sags of only a few tens of microns. Removing the predicted retrace error improves the measurement accuracy for full aperture, single shot, Fizeau interferometry to < 2 nm RMS.

Probabilistic deep learning of turbulent premixed combustion

A probabilistic data-driven approach that models the filtered reaction rate in large-eddy simulation (LES) is investigated. We propose a novel framework that incorporates a conditional generative adversarial network and a Gaussian mixture model to take into account the statistical fluctuations that are present in LES of turbulent reacting flows due to non-resolved subgrid structures, which cannot be predicted by purely deterministic models and machine learning algorithms. The data from a direct numerical simulation of turbulent premixed combustion are spatially filtered using a wide range of filter widths and employed for the training. We extract physically relevant parameters from the database and reduce the input features to the network to the most influential ones based on the result of feature importance analysis. The trained model is then tested on unseen timesteps and untrained LES filter widths, where it is able to accurately predict the distribution of the filtered reaction rate.

Generalizability and portability of natural language processing system to extract individual social risk factors

ObjectiveThe objective of this study is to validate and report on portability and generalizability of a Natural Language Processing (NLP) method to extract individual social factors from clinical notes, which was originally developed at a different institution. Materials and MethodsA rule-based deterministic state machine NLP model was developed to extract financial insecurity and housing instability using notes from one institution and was applied on all notes written during 6 months at another institution. 10% of positively-classified notes by NLP and the same number of negatively-classified notes were manually annotated. The NLP model was adjusted to accommodate notes at the new site. Accuracy, positive predictive value, sensitivity, and specificity were calculated. ResultsMore than 6 million notes were processed at the receiving site by the NLP model, which resulted in about 13,000 and 19,000 classified as positive for financial insecurity and housing instability, respectively. The NLP model showed excellent performance on the validation dataset with all measures over 0.87 for both social factors. DiscussionOur study illustrated the need to accommodate institution-specific note-writing templates as well as clinical terminology of emergent diseases when applying NLP model for social factors. A state machine is relatively simple to port effectively across institutions. Our study.showed superior performance to similar generalizability studies for extracting social factors. ConclusionRule-based NLP model to extract social factors from clinical notes showed strong portability and generalizability across organizationally and geographically distinct institutions. With only relatively simple modifications, we obtained promising performance from an NLP-based model.

USE OF THE THEORY OF FINITE AUTOMATA FOR SUPERVISION OF THE OPERATION OF THE COMPRESSOR UNIT

The purpose of the publication is to develop a methodology for presenting the unit "6 kV compressor-synchronous electric motor" in the form of a finite state machine.&#x0D; It is hypothesized that the behavior of the compressor unit can be associated with the behavior of an abstract deterministic finite state machine.&#x0D; The theory of finite state machines and graphs is applied to analyze the operation of a compressor installation using the example of a compressor of a large-tonnage shop for the production of ammonia. It is shown that the theory of finite state machines allows combining all possible modes of operation and shutdown of compressor units. Coding of reasons for compressor shutdown due to problems in the electrical or mechanical parts of the compressor unit is proposed. A diagram of state transitions has been developed for it. Such a diagram can be useful for compiling a concise description and understanding of the operation of a compressor unit, advanced training of technological personnel during industrial training, for emergency training, etc. &#x0D; A graphical analysis of the obtained diagram was carried out. The optimal (most perceived in terms of energy efficiency) route of the graph is determined.&#x0D; The proposed form of abbreviated recording of the compressor operation cycle and the electronic mileage log, which allows you to calculate the remaining resource of the compressor installation and the compressor operation time.&#x0D; The implemented methods make it possible to identify bottlenecks in the complex electrical and technological equipment of industrial enterprises.

Mlf-core: a framework for deterministic machine learning.

Machine learning has shown extensive growth in recent years and is now routinely applied to sensitive areas. To allow appropriate verification of predictive models before deployment, models must be deterministic. Solely fixing all random seeds is not sufficient for deterministic machine learning, as major machine learning libraries default to the usage of nondeterministic algorithms based on atomic operations. Various machine learning libraries released deterministic counterparts to the nondeterministic algorithms. We evaluated the effect of these algorithms on determinism and runtime. Based on these results, we formulated a set of requirements for deterministic machine learning and developed a new software solution, the mlf-core ecosystem, which aids machine learning projects to meet and keep these requirements. We applied mlf-core to develop deterministic models in various biomedical fields including a single-cell autoencoder with TensorFlow, a PyTorch-based U-Net model for liver-tumor segmentation in computed tomography scans, and a liver cancer classifier based on gene expression profiles with XGBoost. The complete data together with the implementations of the mlf-core ecosystem and use case models are available at https://github.com/mlf-core.