Model-based Algorithm Research Articles

Investigating heterogeneity in IRTree models for multiple response processes with score-based partitioning.

Item response tree (IRTree) models form a family of psychometric models that allow researchers to control for multiple response processes, such as different sorts of response styles, in the measurement of latent traits. While IRTree models can capture quantitative individual differences in both the latent traits of interest and the use of response categories, they maintain the basic assumption that the nature and weighting of latent response processes are homogeneous across the entire population of respondents. In the present research, we therefore propose a novel approach for detecting heterogeneity in the parameters of IRTree models across subgroups that engage in different response behavior. The approach uses score-based tests to reveal violations of parameter heterogeneity along extraneous person covariates, and it can be employed as a model-based partitioning algorithm to identify sources of differences in the strength of trait-based responding or other response processes. Simulation studies demonstrate generally accurate Type I error rates and sufficient power for metric, ordinal, and categorical person covariates and for different types of test statistics, with the potential to differentiate between different types of parameter heterogeneity. An empirical application illustrates the use of score-based partitioning in the analysis of latent response processes with real data.

A comparative study of various recommendation algorithms based on E-commerce big data

With the rapid development of the Internet and the concomitant exponential growth of information, we have entered an era characterized by information overload. The abundance of data has rendered it increasingly arduous for users to pinpoint specific information they require. However, various forms of recommendation algorithms proffer solutions to this challenge. These algorithms predict items or products that may pique users’ interest based on their historical behavior, preferences, and interests. As one of the current hot research fields, recommendation algorithms are extensively employed across E-commerce platforms, movie streaming services, and various other contexts to cater to the diverse needs of users. In this context, a multi-recommendation algorithms comparison platform is proposed, which includes a two-fold model: online evaluation and offline evaluation. Taking the data set of the Chinese Amazon online shopping mall as the experimental data, item-based collaborative filtering (Item-CF) algorithm, content-based (TF-IDF) algorithm, item2vec model, alternating least squares (ALS) algorithm and neural network algorithm are evaluated in the offline model. In the real-time recommendation part, model-based algorithm is used to achieve the users’ rating mechanism. And the metrics used for evaluation include: precision, recall, accuracy and performance. The experimental results show that the average performance of hybrid algorithms such as ALS algorithm and neural network algorithm is higher than that of other traditional algorithms, and the real-time recommendation system achieves the purpose of improving recommendation speed. By integrating various recommender algorithms into the multi-recommendation algorithms comparison platform, this platform automatically computes and presents various performance indicators based on the user-provided dataset. It aids E-commerce platforms in making informed decisions regarding algorithm selection.

A Model-Based Reinforcement Learning Algorithm for Multi-Agent Cooperation Nash Equilibrium With Unstable Communication

Solving Nash equilibrium is important to multi-agent systems, in which the communication is an important factor. However, many proposed reinforcement learning (RL) based algorithms take into account the communication factors by assuming stable communication conditions, which does not hold in the real environment. In this paper, we analyze the effect of a typical RL algorithm in the cases of unstable communication and communication failure, which causes information loss between agents, leading to isolation of agents and affecting algorithm convergence. Then, we propose a model-based RL algorithm to solve Nash equilibrium for multi-agent systems when agents are isolated, and prove its convergence and rationality through mathematical proofs. The simulations results show the effectiveness of the proposed algorithm.

Improved heterogeneity handling in the collapsed cone dose engine for brachytherapy.

Model-based dose calculation algorithms (MBDCA), such as the Advanced Collapsed cone Engine (ACE) in Oncentra Brachy® can be used to overcome the limitations of the TG-43 formalism. ACE is a point kernel superposition algorithm that calculates the total dose separated into primary, first-scatter, and multiple-scatter dose. Albeit ACE yields accurate results under most circumstances, several studies have reported underestimations of the dose to cortical bone. These underestimations are likely caused by approximations in the handling of multiple-scatter dose for non-water media. Such would result in noticeable deviations where the multiple-scatter is a considerable fraction of the total dose, that is, at greater distances from the source. To improve and test the accuracy of the multiple-scatter dose component in the ACE algorithm to remedy its inaccuracy for non-water geometries. A careful analysis of the transport and absorption of the multiple-scatter energy fluence revealed an inconsistency in the scaling of energy absorption ratios for non-water media of the multiple-scatter kernel. We implemented an updated algorithm version, ACEcorr, and tested it for three different geometries. All had a single 192Ir-source at the center of a cubic water phantom with a box-shaped heterogeneity of either cortical bone or air, positioned at different distances from the source. Dose distributions for the three cases were calculated with ACE and ACEcorr and compared to Monte Carlo simulations, using the percentage dose difference ratio as figure-of-merit. All dose calculation methods scored separately the dose deposited by primary, first-scattered, and multiple-scattered photons. The accuracy of the updated algorithm ACEcorr was superior to ACE. In the cortical bone heterogeneity, the mean percentage dose difference ratio for the total dose improved from to (in the worst case) by our update. Less impact was seen in the air heterogeneity, where both ACE and ACEcorr deviated less than 2% from the Monte Carlo results. The algorithm update mainly concerns the multiple-scattered dose component, but an accompanying data processing update also had a small effect ( 0.5% difference) on the primary and first-scattered dose. The calculation times were not affected. The updates to ACE improved the accuracy of multiple-scatter dose calculation for non-water media, without increasing calculation times.

That's Not a Hybrid: How to Distinguish Patterns ofAdmixture and Isolation By Distance.

Describing naturally occurring genetic variation is a fundamental goal of molecular phylogeography and population genetics. Popular methods for this task include STRUCTURE, a model-based algorithm that assigns individuals to genetic clusters, and principal component analysis (PCA), a parameter-free method. The ability of STRUCTURE to infer mixed ancestry makes it popular for documenting natural hybridisation, which is of considerable interest to evolutionary biologists, given that such systems provide a window into the speciation process. Yet, STRUCTURE can produce misleading results when its underlying assumptions are violated, like when genetic variation is distributed continuously across geographic space. To test the ability of STRUCTURE and PCA to accurately distinguish admixture from continuous variation, we use forward-time simulations to generate population genetic data under three demographic scenarios: two involving admixture and one with isolation by distance (IBD). STRUCTURE and PCA alone cannot distinguish admixture from IBD, but complementing these analyses with triangle plots, which visualise hybrid index against interclass heterozygosity, provides more accurate inference of demographic history, especially in cases of recent admixture. We demonstrate that triangle plots are robust to missing data, while STRUCTURE and PCA are not, and show that setting a low allele frequency difference threshold for ancestry-informative marker (AIM) identification can accurately characterise the relationship between hybrid index and interclass heterozygosity across demographic histories of admixture and range expansion. While STRUCTURE and PCA provide useful summaries of genetic variation, results should be paired with triangle plots before admixture is inferred.

A Large Model-Derived Algorithm for Complex Organoids with Internal Morphogenesis and Digital Marker Derivation.

Automated segmentation and evaluation algorithms have been demonstrated to enhance the simplicity and translational utility of organoid technology. However, there is a pressing need for the development of complex organoids that possess epithelium environmental elements, dense regional cell aggregation, and intraorganoid morphologies. Nevertheless, there has been limited progress, including both the construction of data sets and the development of algorithms, in the use of user-friendly microscopy to address such complex organoids. In this study, a data set of bright-field and living cell fluorescence images in paired forms and with temporal variance was constructed using droplet-engineered lung organoids. Additionally, a large model-based algorithm was developed. Both the organoid contours and intraorganoid morphologies were included in the data set, and their physical parameters were included and screened to form multiplex digital markers for organoid evaluation. The algorithm has been demonstrated to outperform existing methods and is therefore suitable for the evaluation of complex organoids. It is expected that the algorithm will facilitate the successful demonstration of AI in organoid evaluation and decision-making regarding their status.

The dosimetric accuracy of a commercial model-based dose calculation algorithm in modeling a six-groove direction modulated brachytherapy tandem applicator

Objective.With advancements in high-dose rate brachytherapy, the clinical translation of intensity modulated brachytherapy (IMBT) innovations necessitates utilization of model-based dose calculation algorithms (MBDCA) for accurate and rapid dose calculations. This study uniquely benchmarks a commercial MBDCA, BrachyVision ACUROSTM(BVA), against Monte Carlo (MC) simulations, evaluating dose distributions for a novel IMBT applicator, termed as thesix-grooveDirection Modulated Brachytherapy (DMBT) tandem, expanding beyond previous focus on partially shielded vaginal cylinder applicators, through a novel methodology.Approach.The DMBT tandem applicator, made of a tungsten alloy with six evenly spaced grooves, was simulated using the GEANT4 MC code. Subsequently, two main scenarios were created using the BVA and reproduced by the MC simulations: 'Source at the Center of the Water Phantom (SACWP)' and 'Source at the Middle of the Applicator (SAMA)' for three cubical virtual water phantoms (20 cm)3, (30 cm)3, and (40 cm)3. A track length estimator was utilized for dose calculation and 2D/3D scoring were performed. The difference in isodose surfaces/lines (i.e. coverage) at each voxel,ΔDIsodose Levels/Lines, was thus calculated for relevant normalization points (rref).Results.The coverage was comparable, based on 2D scoring, between the BVA and MC isodose surfaces/lines for the region of clinical relevance, (i.e. within 5 cm radius from the source) withΔDIsodose Lines(rref: 1 cm from the source) falling within 2% for the two scenarios for all phantom sizes. For the phantom (20 cm)3,ΔDIsodose Levels(3D scoring) recorded the range [-3.0% +6.5%] ([-7.4% +7.3%]) for 95% of the voxels of the same scoring volume for the SACWP (SAMA) scenario.Significance.The results indicated that the BVA could render comparable coverage as compared to the MC simulations in the region of clinical relevance for different phantom sizes.ΔDIsodose Linesmay offer an advantageous metric for evaluation of MBDCAs in clinical setting.

Improved active vibration control of a cantilever beam using MFC actuators with Hammerstein model-based hysteresis modeling and VSS-FxLMS control algorithm

This study aims to enhance active vibration control in a cantilever beam using macro fiber composite (MFC) actuators. To address the challenge of accurately modeling the complex hysteresis behavior of MFC actuators, an advanced hysteresis modeling technique is employed, integrating a non-symmetric Bouc–Wen model with an Auto-Regressive model with eXogenous inputs (ARX). The parameter estimation of this model is optimized using an adaptive mutation factor, and multiple mutation strategy differential evolution (AmFMMDE) algorithm. Additionally, a Variable Step Size Filtered-x Least Mean Square (VSS-FxLMS) algorithm with step size adaptation based on normalized error change is utilized for effective vibration control. This approach shows promising potential for practical engineering applications requiring precise and efficient active vibration control.

Retrospective assessment of HDR brachytherapy dose calculation methods in locally advanced cervical cancer patients: AcurosBV vs. AAPM TG43 formalism.

This retrospective analysis was completed to investigate the use of a model-based dose calculation algorithm (MBDCA) AcurosBV, for use in HDR BT treatments for locally advanced cervical cancer treated with tandem and ovoid applicators with interstitial needles. A cohort of 32 patients receiving post-EBRT HDR brachytherapy boost with a prescription dose of 5.5Gy × 5 fractions to the high-risk clinical target volume (CTVHR) were selected for this study. For standard TG43 dose calculation, applicators were manually digitized on the planning images, while for AcurosBV calculations, solid renderings of Titanium Fletcher Suite Delclos (FSD) applicators included in BrachyVision were matched to those used clinically and Ti needles were manually digitized. The dose was recalculated using Varian's AcurosBV 13.5 and dose-to-medium-in-medium (Dm,m) was reported. EQD2 values for targets and organs at risk were compared between dose calculation formalisms. D90% and D98% values were reported for the high and intermediate-risk CTVs, and values were reported for OARs including bladder, rectum, sigmoid, bowel, and vagina. Due to variability within the patient cohort, the dosimetric impact of AcurosBV was investigated corresponding to planning image modality (CT vs. CBCT), presence of Ti needles, and contrast within vaginal balloons used to stabilize implants. AcurosBV showed lower dosimetric values for all plans compared to TG43. The average±standard deviation of dosimetric reduction in D90% was 4.33±0.09% for CTVHR and 4.12±0.09% for CTVIR. The reduction to OARs was: 4.99±0.15% for bladder, 7.87±0.16% for rectum, 5.79±0.17% for sigmoid, 6.91±0.14% for bowel, and 4.55±0.14% for vagina. AcurosBV should be utilized for HDR BT GYN cases, treated with tandem and ovoid applicators, with high degrees of heterogeneity and calculated in tandem with TG43.

Assessing the population structure and genetic diversity of wheat germplasm with the iPBS-retrotransposons marker system

Context Wheat (Triticum aestivum L.) is an important crop that provides food to millions of people all over the world. Currently, wheat production is limited due to various biotic and abiotic stresses resulting from uneven patterns of climate change. Therefore, it is very important to develop climate-resilient wheat cultivars. Crop genetic diversity allows the scientific community to identify genetic variations that can be utilised in the development of improved cultivars. Aims This study planned to characterise the wheat germplasm with the iPBS-retrotransposons marker system. Methods A total of 30 iPBS-retrotransposons markers were screened and among these, the 12 most polymorphic markers were selected for further analysis. Key results Molecular characterisation yielded a total of 170 bands, of which 143 were polymorphic. A substantial level of genetic diversity was observed (mean effective number of alleles: 1.37, Shannon’s information index: 0.23, gene diversity: 0.35). Maximum genetic distance was observed in G9 and G60 genotypes. Analysis of molecular variance revealed that most genetic variation (95%) occurred within the populations. The model-based structure algorithm divided the studied germplasm into three populations based on their collection regions. Similarly, the neighbour-joining analysis also divided 70 tested wheat genotypes into three populations, whereas principal coordinate analysis divided the evaluated germplasm into four populations. Conclusions This study confirms the iPBS-retrotransposons as an ideal marker for the genetic diversity assessment studies for any crop, especially for wheat. Implications The results presented here will be helpful for the scientific community in the marker-assisted breeding of wheat.

B-170 Age-Specific reference intervals for ethanolamine plasmalogen species in red blood cells using liquid chromatography tandem mass spectrometry

Abstract Background Plasmalogens are critical membrane structural components that are mainly generated by de novo synthesis starting in peroxisomes. Hence, patients with defects in peroxisome biogenesis (PBD) exhibit markedly reduced plasmalogen levels. Plasmalogen ratios are traditionally measured by gas chromatography-mass spectrometry (GC-MS); however, this method entails a lengthy sample extraction and derivatization and does not report concentrations of individual plasmalogen species. We have developed a robust and easy-to-implement liquid chromatography-tandem mass spectrometry (LC-MS/MS) method to quantify the 18 most abundant ethanolamine plasmalogen (PlsEtn) species in packed red blood cells (RBCs). However, no reference intervals have been published for individual PlsEtn. Here, we describe the establishment of age-specific reference intervals for individual PlsEtn species and their total values (16:0, 18:0, 18:1 species, and total plasmalogens). Methods Plasmalogens were extracted using methanol containing two labeled internal standards, shaking for one hour at room temperature. Chromatographic separation was performed using an Acquity Premier BEH C18 UPLC column with a binary gradient of 5 mM ammonium acetate in water:methanol (15:85) and 5 mM ammonium acetate in methanol. Analysis was performed using a XEVO TQ-XS Mass Spectrometer with Ultra-High Performance Liquid Chromatography (Waters) in multiple reaction monitoring mode. Eighteen PlsEtn species were quantified using four commercially available standards; additionally, totals were calculated for 16:0, 18:0 or 18:1 species, and for total plasmalogens. Reference intervals were established using 376 RBCs from self-reported healthy volunteers and de-identified clinical samples referred for unrelated testing (182 females and 194 males; range 0 to 88 years). Data was analyzed using the R programming language. The study was approved by the Institutional Review Board of the University of Utah. Results Initial age groups were identified using a model-based clustering algorithm followed by iterative Harris-Boyd analysis. Finally, the adjacent groups were merged if their means differed by less than 10%. Once the final age groups were partitioned, data in each individual age group were analyzed using parametric or non-parametric statistics to determine reference intervals (95%, with 90%confidence intervals). PlsEtn species displayed the lowest concentration in the first few months of life, which increased in childhood until adolescence or adulthood (depending on PlsEtn). For most species, the concentrations increased over time reaching a plateau between 18 and 48 years of age, and then starting to decrease. The total values followed the same trend, with neonates showing significantly lower values compared to other age groups. Conclusions We applied a novel statistical approach to identify age groups and determine age-specific reference intervals for 18 individual PlsEtn in RBC and their totals. Lacking previously published data, this study is critical for supporting test implementation in clinical laboratories.

Auxiliary model-based maximum likelihood multi-innovation recursive least squares identification for multiple-input multiple-output systems

The aim of this paper is to propose novel identification methods for multiple-input multiple-output systems. Through decomposing a system into subsystems, the system identification model is derived. Based on the obtained sub-model, an auxiliary model-based maximum likelihood recursive least squares algorithm is derived for parameter estimation. For further enhancing the estimation accuracy, the auxiliary model-based maximum likelihood multi-innovation recursive least squares algorithm (AM-ML-MIRLS) is proposed based on the proposed algorithm. Simulation results test the proposed algorithms are all effective, and proves that the proposed AM-ML-MIRLS algorithm has the superior performances in capturing the dynamic properties of the system.

Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm.

The majority of theoretical analyses of evolutionary algorithms in the discrete domain focus on binary optimization algorithms, even though black-box optimization on the categorical domain has a lot of practical applications. In this paper, we consider a probabilistic model-based algorithm using the family of categorical distributions as its underlying distribution and set the sample size as two. We term this specific algorithm the categorical compact genetic algorithm (ccGA). The ccGA can be considered as an extension of the compact genetic algorithm (cGA), which is an efficient binary optimization algorithm. We theoretically analyze the dependency of the number of possible categories K, the number of dimensions D, and the learning rate η on the runtime. We investigate the tail bound of the runtime on two typical linear functions on the categorical domain: categorical OneMax (COM) and KVAL. We derive that the runtimes on COM and KVAL are O(Dln(DK)/η) and Θ(DlnK/η) with high probability, respectively. Our analysis is a generalization for that of the cGA on the binary domain.

Sound source localization via distance metric learning with regularization

Sound source localization (SSL) or simply direction of arrival (DOA) classification is an important ingredient in acoustic applications. Traditional model-based algorithms are susceptible to the effects of noise and reverberation, while data-driven deep learning algorithms maintain strong performance across a variety of acoustic circumstances, but typically require a large amount of labeled data. Nevertheless, the existing datasets for SSL are not sufficiently big and diverse to achieve the full potential of deep learning algorithms. Then, it is an imperative work to develop a non-data-hungry algorithm of SSL using small or medium data volume. To this end, we propose a regularized distance metric learning algorithm, that is, by means of the kernel method, we design a nonlinear feature transformation from two aspects: feature points and feature distributions. It transforms the data into a new feature space that brings features of the same class as close as possible and removes features of different classes as far away as possible, which can significantly improve the output of a DOA classifier that follows. Experimental results show that the proposed algorithm outperforms deep learning algorithms in diverse acoustic conditions.

Impact of Data Corruption and Operating Temperature on Performance of Model-Based SoC Estimation

Electric vehicles (EVs) are becoming popular around the world. Making a lithium battery (LIB) pack with a robust battery management system (BMS) for an EV to operate under different complex environments is both a challenge and a requirement for engineers. A BMS can intelligently manage LIB systems by estimating the battery state of charge (SoC). Due to the nonlinear characteristics of LIB, influenced by factors such as the harsh environment and data corruption caused by electromagnetic interference (EMI) inside electric vehicles, SoC estimation should consider available capacity, model parameters, operating temperature and reductions in data sampling time. The widely used model-based algorithms, such as the extended Kalman filter (EKF) have limitations. Therefore, a detailed review of the balance between temperature, data sampling time, and different model-based algorithms is necessary. Firstly, a state of charge—open-circuit voltage (SoC-OCV) curve of LIB is obtained by the polynomial curve fitting (PCF) method. Secondly, a first-order RC (1-RC) equivalent circuit model (ECM) is applied to identify the battery parameters using a forgetting factor-based recursive least squares algorithm (FF-RLS), ensuring accurate internal battery parameters for the next step of SoC estimation. Thirdly, different model-based algorithms are utilized to estimate the SoC of LIB under various operating temperatures and data sampling times. Finally, the experimental data by dynamic stress test (DST) is collected at temperatures of 10 °C, 25 °C, and 40 °C, respectively, to verify and analyze the impact of operating temperature and data sampling time to provide a practical reference for the SoC estimation.

Bidirectional Corrective Model-Contrastive Federated Adversarial Training

When dealing with non-IID data, federated learning confronts issues such as client drift and sluggish convergence. Therefore, we propose a Bidirectional Corrective Model-Contrastive Federated Adversarial Training (BCMCFAT) framework. On the client side, we design a category information correction module to correct biases caused by imbalanced local data by incorporating the local client’s data distribution information. Through local adversarial training, more robust local models are obtained. Secondly, we propose a model-based adaptive correction algorithm in the server that leverages a self-attention mechanism to handle each client’s data distribution information and introduces learnable aggregation tokens. Through the self-attention mechanism, model contrast learning is conducted on each client to obtain aggregation weights of corrected client models, thus addressing the issues of accuracy degradation and slow convergence caused by client drift. Our algorithm achieves the best natural accuracy on the CIFAR-10, CIFAR-100, and SVHN datasets and demonstrates excellent adversarial defense performance against FGSM, BIM, and PGD attacks.

Predictive heating load management and energy flexibility analysis in residential sector using an archetype gray-box modeling approach: Application to an experimental house in Québec.

This paper presents a methodology to develop archetype gray-box models and use them in an economic model-based predictive control algorithm to simulate optimal heating load management in response to a newly-introduced static time-of-use tariff for Québec's residential sector, rate Flex-D. The methodology is evaluated through a case study, wherein in situ measurements from a two-storey unoccupied research house of Hydro-Québec are used to develop an 11R6C network with a heuristic zoning-by-floor approach and compute the sequence of optimal electric heating input for the next control horizon. Properly-tuned economic model-based predictive control under rate Flex-D shows potential for an approximately 30% reduction in daily heating cost compared to the reference operation, with a minimal average deviation of indoor air temperature from the reference setpoint. Also, the analysis of the response's sensitivity to weather forecast uncertainties indicates that the most influential uncontrolled input directing the performance of economic model-based predictive control is the structure price signal, rendering the impact of uncertainty in the weather forecast negligible.

Model-based fault detection algorithm for liquid hydrogen refueling system using CUSUM method

The global focus on the role of hydrogen energy in achieving carbon neutrality is increasing, particularly in transportation. Establishing and operating hydrogen refueling stations for fuel cell electric vehicles (FCEVs) are gaining prominence. This study proposes a model-based fault detection algorithm to enhance safety at large-capacity liquid hydrogen (LH2) refueling stations. First, the LH2 refueling system is modeled using Aspen HYSYS, estimating the heat transfer coefficient of the storage tank to meet the normal evaporation rate (NER) specification of 0.9 % per day. Second, diverse fault scenarios are identified via a Hazard and Operability Study (HAZOP), and simulation data are generated for the normal and fault scenarios. Finally, a fault detection algorithm utilizing the cumulative summation (CUSUM) is developed, with its threshold determined by risk levels analyzed in HAZOP. This allowed for tighter fault detection as risk levels increased. The algorithm successfully identified faults for all 11 scenarios.

Association Model-Based Intermittent Connection Fault Diagnosis for Controller Area Networks

Controller Area Networks (CANs) play an important role in many safety-critical industrial systems, which places high demands on their reliability performance. However, the intermittent connection (IC) of network cables, a random and transient connectivity problem, is a common but hard troubleshooting fault that can cause network performance degradation, system-level failures, and even safety issues. Therefore, to ensure the reliability of CANs, a fault symptom association model-based IC fault diagnosis method is proposed. Firstly, the symptoms are defined by examining the error records, and the domains of the symptoms are derived to represent the causal relationship between the fault locations and the symptoms. Secondly, the fault probability for each location is calculated by minimizing the difference between the symptom probabilities calculated from the count information and those fitted by the total probability formula. Then, the fault symptom association model is designed to synthesize the causal and the probabilistic diagnostic information. Finally, a model-based maximal contribution diagnosis algorithm is developed to locate the IC faults. Experimental results of three case studies show that the proposed method can accurately and efficiently identify various IC fault location scenarios in networks.

Three-dimensional magnetization reconstruction from electron optical phase images with physical constraints

The ability to characterize three-dimensional (3D) magnetization distributions in nanoscale magnetic materials and devices is essential to fully understand their static and dynamic magnetic properties. Phase contrast techniques in the transmission electron microscope (TEM), such as electron holography and electron ptychography, can be used to record two-dimensional (2D) projections of the in-plane magnetic induction of 3D nanoscale objects. Although the 3D magnetic induction can in principle be reconstructed from one or more tilt series of such 2D projections, conventional tomographic reconstruction algorithms do not recover the 3D magnetization within a sample directly. Here, we use simulations to describe the basis of an improved model-based algorithm for the tomographic reconstruction of a 3D magnetization distribution from one or more tilt series of electron optical phase images recorded in the TEM. The algorithm allows a wide range of physical constraints, including a priori information about the sample geometry and magnetic parameters, to be specified. It also makes use of minimization of the micromagnetic energy in the loss function. We demonstrate the reconstruction of the 3D magnetization of a localized magnetic soliton — a hopfion ring — and discuss the influence of noise, choice of magnetic constants, maximum tilt angle and number of tilt axes on the result. The algorithm can in principle be adapted for other magnetic contrast imaging techniques in the TEM, as well as for other magnetic characterization techniques, such as those based on X-rays or neutrons.