Weight Adjustment Research Articles

Weight-adaptive augmented Lagrange multiplier sequential convex programming for nonlinear trajectory optimization

Sequential convex programming has become a prominent research focus in aerospace trajectory optimization due to its high computational efficiency. One critical challenge in sequential convex programming is the infeasibility of subproblems, which significantly impacts its stability. To address this issue, certain constraints must be relaxed using relaxation variables, which are then incorporated into the objective function as a penalty term. However, the choice of penalty weight greatly influences the optimality and convergence of sequential convex programming. Therefore, this paper proposes a weight-adaptive augmented Lagrange multiplier sequential convex programming algorithm to tackle the challenge. First, this paper analyzes the difficulty of determining an appropriate penalty weight from the perspective of its penalty effect. Based on this analysis, an augmented penalty term is introduced, and the update rule for the augmented Lagrange multiplier is formulated using the Karush-Kuhn-Tucker conditions. Subsequently, a method with adaptive weight adjustment is designed based on the change in the penalty term to further improve the algorithm's solving speed. Finally, the proposed method is validated through numerical simulations in a Mars-powered landing problem and a small glide vehicle reentry problem. The results show that the proposed method is 20.59 % and 25.16 % faster compared to the general sequential convex programming algorithm, respectively. Furthermore, the proposed method is demonstrated to be robust to the initial choice of penalty weight.

A New Data Fusion Method for GNSS/INS Integration Based on Weighted Multiple Criteria

The standard Kalman filter and most of its enhancements are typically designed based on the criterion that minimizes the mean squared error, with little discussion of multiple criteria in the positioning and navigation fields. Therefore, a novel data fusion method that takes into account weighted multiple criteria is proposed in this paper, implementing a filtering algorithm based on integrated criteria with different weights determined by a weight adjustment factor. The proposed algorithm and conventional filtering algorithms were utilized for data fusion in GNSS/INS integration. Experiments were conducted using actual data collected from an urban environment. Comparative analysis revealed that, when utilizing the proposed algorithm, the precision of the position, velocity, and attitude of the tested land vehicle could be improved by approximately 24%, 48%, and 35%, respectively. Furthermore, a series of filtering algorithms with different weight adjustment factors was performed to test their influence on the filtering. The application of the proposed algorithm should be accompanied by an appropriate weight adjustment factor.

Artificial neural networks in the retention of anthocyanins and total phenolics in the osmotic pre-treatment of Biloxi variety blueberry (Vaccinium corymbosum L.) jam

Blueberries are a fruit that is an important source of bioactive components beneficial to the human diet, such as anthocyanins and total phenolics, which are altered by the use of high temperatures during processing. This study aimed to evaluate the use of artificial neural networks in the optimization of sucrose concentration and time for the osmotic pre-treatment of blueberries of the Biloxi variety, to retain the greatest amount of anthocyanins and total phenolics in the subsequent preparation of jam. Artificial neural networks of the feedforward type were used, with a Backpropagation training algorithm with Levenberg-Marquardt weight adjustment, to achieve the optimal predicted combination that maximizes the retention of these bioactive components. The model achieved its best performance with 11 neurons in the hidden layer, achieving an R2 coefficient of 0.98 and a mean square error of 4.76, indicating a strong ability for generalization. Artificial neural networks allowed to obtain the best optimal combination of predicted multiple responses of factors consisting of a sucrose concentration of 1.64 M and a time of 211.52 min, which retained a higher content of total monomeric anthocyanins with 70.98 mg cyanidin-3-O-glucoside 100 g-1 of jam and total phenolics with 110.54 mg GAE g-1 of jam. On the other hand, through single-response optimization was obtained that the combination of experimental factors that maximized total anthocyanins (71.59 mg cyanidin-3-O-glucoside 100 g-1 of jam) was 1.54 M of sucrose and 232.73 min and for total phenols (111.06 mg GAE g-1 of jam) 1.79 M of sucrose and 196.36 min. The use of artificial neural networks is an excellent alternative for modeling phenomena, compared to traditional methods.

Dynamic and Static Workout of In Vitro Skeletal Muscle Tissue through a Weight Training Device.

Enhancing muscle strength through workouts is a key factor inimproving physical activity and maintaining metabolic profiles. The controversial results concerning the impacts of weight training often arise from clinical experiments that require controlled experimental conditions. In this study, a weight training system for a muscle development model is presented, which is capable of performing weight training motions with adjustable weight loads. Through the implementation of cultured skeletal muscle tissue with floating structures and a flexible ribbon, both isotonic (dynamic change in muscle length) and isometric (static in muscle length) exercises can be performed without the deflection of the tissue. Quantitative analysis of contraction force, changes in metabolic processes, and muscle morphology under different weight training conditions demonstrates the effectiveness of the proposed system. Our proposed system holds potential for establishing effective muscle development and for further applications in rehabilitation training methods.

Optimal weight-based epinephrine dosing for patients with a low likelihood of survival following out-of-hospital cardiac arrest.

Cardiac arrest patients presenting with non-shockable rhythms have a low probability of survival, and epinephrine is one of the few pharmaceutical options for this group. The recommended 1.0mg adult dose is extrapolated from early animal studies and lacks adjustment for patient weight. Although several prior studies have investigated "low-" and "high-" dose epinephrine, none have identified a benefit to either strategy. To identify an optimal weight-based epinephrine dose for return-of-spontaneous-circulation (ROSC) after a single bolus among patients with low likelihood of survival. Included were adult patients who experienced a witnessed, non-traumatic out-of-hospital cardiac arrest prior to EMS arrival. Patients with shockable presenting rhythms or receiving bystander CPR were excluded. The AUROC was used to assess the predictive value of epinephrine dose (mg/kg) for ROSC following a single bolus. From the ROC curve, the optimal threshold dosage (OTD) was determined using the Youden Index. A logistic regression model calculated the adjusted odds ratio of OTD on ROSC. A total of 2,463 patients met inclusion criteria, of which 190 (7.7%) attained ROSC after the first epinephrine administration. The dosage AUROC for ROSC was 0.603 (p < 0.01). As calculated by the Youden index, the OTD was 0.013mg/kg. Patients receiving ≥ OTD were more likely to attain ROSC after a single epinephrine bolus (OR = 2.25,p < 0.001). Among patients with a low likelihood of survival, the optimal dose of epinephrine for attaining ROSC with a single bolus of epinephrine was 0.013mg/kg. These findings should inspire further investigation into optimal dosing strategies for epinephrine.

Correlation between Body Composition and Bone Mineral Density Differs by Sex and Skeletal Site in Overweight and Obese Chinese Subjects

Previous studies have yielded inconsistent results regarding the relationship between obesity and bone mineral density (BMD). The aim of this study was to determine the influence of body composition on BMD and the serum sclerostin level in overweight and obese adults. The study had a cross-sectional design and included 90 men and 118 women with a body mass index ≥25. Fat mass, lean mass, and spinal and pelvic BMD were measured using dual-emission X-ray absorptiometry. Subcutaneous fat, visceral fat, and lean mass were measured between L2 and L3 by 16-slice spiral computed tomography. The serum sclerostin level was determined by enzyme-linked immunosorbent assay. Pearson analysis showed that fat mass and appendicular lean mass were positively correlated with spinal BMD in both sexes. A positive association of both fat mass and lean mass with pelvic BMD, which was stronger in women, was also found. Partial correlation analysis showed the positive association between fat mass and BMD was significantly attenuated but the positive association between lean mass and pelvic BMD remained after adjustment for age and body weight. A negative correlation was observed between visceral fat and spinal and pelvic BMD only in women, and the positive association between lean mass with pelvic BMD was more obvious in women than in men, indicating body composition seemed to have a greater impact on the BMD in women. The serum sclerostin level was positively associated with BMD but not with body composition. These findings suggest that the correlation between body composition and BMD is influenced by sex and skeletal site.

Survival Outcome Superiority of Total Pharyngolaryngectomy Compared with Chemoradiotherapy for T4aM0 Hypopharyngeal Squamous Cell Carcinoma: A Nationwide Database Study of Japan.

The purpose of this study is to elucidate whether total pharyngolaryngectomy (TPL) or chemoradiotherapy (CRT) provides a better prognostic outcome in patients with T4aM0 hypopharyngeal carcinoma (HPSCC) using a nationwide database. All data were obtained from the Head and Neck Cancer Registry of Japan, and information from patients who were newly diagnosed with T4aM0 HPSCC between 2011 and 2015 was extracted. The primary endpoint was disease-specific survival (DSS), and the secondary endpoint was overall survival (OS). The inverse probability of treatment weighting (IPTW) adjustments was used for survival analyses. Our cohort included 1143 patients. The TPL and CRT groups included 724 and 419 patients, respectively. Following IPTW adjustments, both the OS and DSS of the TPL group were significantly longer than those of the CRT group (P = .02 and P = .002, respectively). Survival superiority was demonstrated for patients with T4aM0 HPSCC treated with TPL compared with those treated with CRT.

GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework.

Particle-based Variational Inference (ParVI) methods have been widely adopted in deep Bayesian inference tasks such as Bayesian neural networks or Gaussian Processes, owing to their efficiency in generating high-quality samples given the score of the target distribution. Typically, ParVI methods evolve a weighted-particle system by approximating the first-order Wasserstein gradient flow to reduce the dissimilarity between the particle system's empirical distribution and the target distribution. Recent advancements in ParVI have explored sophisticated gradient flows to obtain refined particle systems with either accelerated position updates or dynamic weight adjustments. In this paper, we introduce the semi-Hamiltonian gradient flow on a novel Information-Fisher-Rao space, known as the SHIFR flow, and propose the first ParVI framework that possesses both accelerated position update and dynamical weight adjustment simultaneously, named the General Accelerated Dynamic-Weight Particle-based Variational Inference (GAD-PVI) framework. GAD-PVI is compatible with different dissimilarities between the empirical distribution and the target distribution, as well as different approximation approaches to gradient flow. Moreover, when the appropriate dissimilarity is selected, GAD-PVI is also suitable for obtaining high-quality samples even when analytical scores cannot be obtained. Experiments conducted under both the score-based tasks and sample-based tasks demonstrate the faster convergence and reduced approximation error of GAD-PVI methods over the state-of-the-art.

Preventing harm to the rare in combating the malicious: A filtering-and-voting framework with adaptive aggregation in federated learning

The distributed nature of Federated Learning (FL) introduces security vulnerabilities and issues related to the heterogeneous distribution of data. Traditional FL aggregation algorithms often mitigate security risks by excluding outliers, which compromises the diversity of shared information. In this paper, we introduce a novel filtering-and-voting framework that adeptly navigates the challenges posed by non-iid training data and malicious attacks on FL. The proposed framework integrates a filtering layer for defensive measures against the intrusion of malicious models and a voting layer to harness valuable contributions from diverse participants. Moreover, by employing Deep Reinforcement Learning (DRL) for dynamic aggregation weight adjustment, we ensure the optimized aggregation of participant data, enhancing the diversity of information used for aggregation and improving the performance of the global model. Experimental results demonstrate that the proposed framework presents superior accuracy over traditional and contemporary FL aggregation methods as diverse models are utilized. It also shows robust resistance against malicious poisoning attacks.

Multimodal urban mobility solutions for a smart campus using artificial neural networks for route determination and an algorithm for arrival time prediction

Artificial intelligence algorithms play a key role in solving multimodal urban mobility problems, this study outlines a scheme covering bus, boat, and pedestrian transport modes. This involves designing an Artificial Neural Network (ANN) model to classify the most suitable routes for passengers, together with an algorithm capable of estimating the arrival times of various transportation modes at designated stopping points or buildings within the smart campus. The information used to train the ANN is obtained from an Internet of Things (IoT) network and a database that includes the available routes within the campus (which is situated in the Brazilian Amazon), where there is a multimodal electric mobility service. In seeking to achieve the objectives, this ANN relied on the user's geographic location in the input layer, and route mapping data stored in the database in the output layer, as well as the backpropagation algorithm for computational processing and adjustments of synaptic weight. The algorithm for modal arrival time prediction used real-time geographic location data, together with the Haversine formula to calculate geographic distance, while the average speed was obtained from the IoT network. A range of different ANN parameters were included in the experiments. In the study case, the ANN results show an improvement of above 92% for determining the best routes and predicting arrival times. The findings show that ANNs can effectively find the best route within a real-world smart campus environment. Moreover, the results show the arrival time can be estimated by using real-time geographic location data.

TiN/TiOx/WOx/Pt heterojunction memristor for sensory and neuromorphic computing

The advancement of artificial intelligence (AI) has spurred increasing demands for efficiency, as AI technologies require rapid processing and large-scale data handling to perform complex tasks and enable real-time decision-making. By incorporating biological nociceptor functions, memristors have become instrumental in E-Skin applications, aiding robotics in assessing potential danger. Moreover, in pursuit of energy-efficient data processing, researchers have turned their attention to neuromorphic computing, mimicking the operations of the human brain. In this context, the multifunctional capabilities of individual memristors are pivotal for their utility across diverse conditions. To enhance efficiency, this study investigated the observation of both synaptic and nociceptive behaviors within a heterojunction memristor comprising a TiN/TiOx/WOx/Pt stack. By employing a controlled pulse scheme, advanced sensing capabilities were discovered within our memristor, mimicking key functions of nociceptors such as threshold detection, lack of adaptation, relaxation, and sensitization. Additionally, the processes of potentiation and depression were leveraged to demonstrate the linear adjustment of synaptic weights based on applied pulse schemes, exhibiting various synapse-like behaviors, and enabling advanced computing functions. Consequently, both sensing and computing functionalities of the memristor were achieved using a singular TiN/TiOx/WOx/Pt memristor.

Energy-saving scheduling strategy for variable-speed flexible job-shop problem considering operation-dependent energy consumption

The rapid growth of industrial production signifies its CO2 footprint and climate impact, highlighting the demand for efficient and energy-saving production scheduling. Generally, a single production job comprises multiple operations on various machines. Existing studies estimate job energy consumption from a broader perspective, often disregarding the detailed scheduling of operations. This simplification may result in inaccurate evaluations of energy consumption and savings, as energy consumption can differ significantly among operations, with each requiring specific levels of energy on various machines. Proposing a new scheduling framework to replace the classical strategy is challenging yet necessary due to these variations. This study aims to investigate the multiobjective flexible job-shop scheduling problem by considering operation-dependent energy consumption and to improve the accuracy and thoroughness of the energy-consumption evaluation framework. First, a core metamodel for energy assessment is established and a mathematical model is introduced to minimize the manufacturing span and total energy consumption. Subsequently, a dynamic diffusion weight adjustment for a multiobjective evolutionary algorithm based on decomposition (MOEA/D-DDWA) is proposed. Operation-dependent energy consumption and processing quality are discussed, and a superior unified energy-saving strategy is designed to facilitate the selection of the processing-speed range, balancing energy consumption and saving. Finally, numerical experiments are conducted based on datasets of various scales, demonstrating that the core metamodel for energy assessment can achieve significant energy savings. Compared with other classical multiobjective optimization algorithms, the MOEA/D-DDWA is more energy efficient.

An intelligent obfuscated mobile malware detection using deep supervised learning algorithms

Obfuscated mobile malware (OMM) is a malicious software in mobile that hides to avoid detection and annihilation. These types of malwares are thorny to identify due to their inevitable nature. Deep learning (DL) algorithms are the most desirable to detect obfuscated malware based on the ‘n’ number of iterations with adjustable weights and neurons. This study investigates the accurate detection of OMM using significant DL algorithms such as multi-layer perceptron (MLP), self-organizing maps (SOM), long short-term memory (LSTM) networks, auto encoders (AE), and convolutional neural network (CNN) based on appropriate parameter tuning. The dataset taken for the study is CICMalMem2022 that contains 58,596 samples with 57 features which is basically designed for OMM detection. The dataset comprises Spyware, Ransomware, Trojan horse, and Benign. The DL models are evaluated based on performance metrics such as precision, recall, accuracy, training accuracy, test accuracy, validation accuracy, training loss, validation loss and receiver operating characteristic (ROC) curve. Based on the experimental evaluation, the study reveals that LSTM outperforms with 100% accuracy and MLP achieves 99.9% accuracy in detecting and classifying the OMM using deep supervised learning (SL) mechanism.

Enhancing Suppression of Chain Transfer via Installing Bulky N‐ortho‐Aryl Substituents into α‐Diimine Nickel System

AbstractRecently, the important role of sterically bulky aromatic substituents at the axial position of the metal center for synthesizing high‐performance catalysts were recognized. In this study, a series of α‐diimine nickel complexes with bulky N‐ortho‐aryl substituents were designed and synthesized. The as‐synthesized nickel complexes showed high activities (up to 2.3×107 g ⋅ mol−1 ⋅ h−1) and superior thermostability, giving access to moderately branched polyethylenes (35–86/1000 C) with high molecular weights (up to 197.5×104 g ⋅ mol−1). The polyethylene materials generated by these nickel complexes at 80 °C exhibited outstanding tensile mechanical. In addition, these nickel complexes could also catalyze the copolymerization of ethylene and polar monomer with modest activity (such as undecenoic acid, 10‐undecen‐1‐ol and 6‐chlorohex‐1‐ene), yielding functionalized polyolefin with adjustable molecular weights (6.8–222.9×104 g ⋅ mol−1) and incorporation ratios (0.2–4.3 mol %).

Large-scale analysis to identify risk factors for ovarian cancer

ObjectiveOvarian cancer is characterized by late-stage diagnoses and poor prognosis. We aimed to identify factors that can inform prevention and early detection of ovarian cancer.MethodsWe used a data-driven machine learning...

Advanced UAV Material Transportation and Precision Delivery Utilizing the Whale-Swarm Hybrid Algorithm (WSHA) and APCR-YOLOv8 Model

This paper proposes an effective material delivery algorithm to address the challenges associated with Unmanned Aerial Vehicle (UAV) material transportation and delivery, which include complex route planning, low detection precision, and hardware limitations. This novel approach integrates the Whale-Swarm Hybrid Algorithm (WSHA) with the APCR-YOLOv8 model to enhance efficiency and accuracy. For path planning, the placement paths are transformed into a Generalized Traveling Salesman Problem (GTSP) to be able to compute solutions. The Whale Optimization Algorithm (WOA) is improved for balanced global and local searches, combined with an Artificial Bee Colony (ABC) Algorithm and adaptive weight adjustment to quicken convergence and reduce path costs. For precise placement, the YOLOv8 model is first enhanced by adding the SimAM attention mechanism to the C2f module in the detection head, focusing on target features. Secondly, GhoHGNetv2 using GhostConv is the backbone of YOLOv8 to ensure accuracy while reducing model Params and FLOPs. Finally, a Lightweight Shared Convolutional Detection Head (LSCDHead) further reduces Params and FLOPs through shared convolution. Experimental results show that WSHA reduces path costs by 9.69% and narrows the gap between the best and worst paths by about 34.39%, compared to the Improved Whale Optimization Algorithm (IWOA). APCR-YOLOv8 reduces Params and FLOPs by 44.33% and 34.57%, respectively, with mAP@0.5 increasing from 88.5 to 92.4 and FPS reaching 151.3. This approach can satisfy the requirements for real-time responsiveness while effectively preventing missed, false, and duplicate detections during the inspection of emergency airdrop stations. In conclusion, combining bionic optimization algorithms and image processing significantly enhances the efficiency and precision of material placement in emergency management.

Multi-objective optimization design of rail grinding profile in Curve Section of Subway based on wear Evolution and representative worn profile

Curve rail grinding has always been one of the key points of subway maintenance and repair. The appropriate grinding can effectively reduce wear. A multi-objective optimization design method for grinding profiles in curved sections is proposed. Firstly, representative grinding profiles are selected as the initial population using the dynamic time regularization algorithm (DTW). Then, the optimal design range is determined based on wear characterization analysis, and mathematical expressions of wheel profiles are chosen as design variables to establish a parametric model. Next, the prediction model considering the evolution of wheel wear is incorporated into the multi-objective function, and objective function adaptive weight adjustment coefficient factors are introduced to establish the multi-objective optimization model for wheel profiles. The Latin hypercubic sampling method is employed to establish the RBF agent model for simulation calculation, and the optimization design of wheel profiles is carried out using the TS-NSGA-II multi-objective algorithm.

Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study.

The application of machine learning in health care often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications, respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the "curse of dimensionality" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD and ATC codes and the hierarchical structures of these systems. The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of patients with coronary artery disease in different aspects of performance and complexity and select the best set of features representing these patients. We compared several unsupervised feature selection methods for 2 ICD and 1 ATC code databases of 51,506 patients with coronary artery disease in Alberta, Canada. Specifically, we used the Laplacian score, unsupervised feature selection for multicluster data, autoencoder-inspired unsupervised feature selection, principal feature analysis, and concrete autoencoders with and without ICD or ATC tree weight adjustment to select the 100 best features from over 9000 ICD and 2000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of the selected features by mean code level in the ICD or ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis. In feature space reconstruction and mortality prediction, the concrete autoencoder-based methods outperformed other techniques. Particularly, a weight-adjusted concrete autoencoder variant demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong and McNemar tests (P<.05). Concrete autoencoders preferred more general codes, and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted concrete autoencoders yielded higher Shapley values in mortality prediction than most alternatives. This study scrutinized 5 feature selection methods in ICD and ATC code data sets in an unsupervised context. Our findings underscore the superiority of the concrete autoencoder method in selecting salient features that represent the entire data set, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the concrete autoencoders specifically tailored for ICD and ATC code data sets to enhance the generalizability and interpretability of the selected features.

Investment Portfolio with Convex Optimization and Risk Adjustment Using Multi-Factor Model and Multi-Armed Bandit Algorithm

This paper examines the creation of investment portfolios through convex optimization, multifactor models, and the multi-armed bandit (MAB) algorithms, focusing on the KL-UCB strategy to optimize decisions in uncertain settings. It explores the impact of systematic risk factors using the Fama-French three-factor model, estimating the influence of market, size, and value premiums via linear regression. The use of Monte Carlo simulation is detailed for generating potential asset allocations and calculating their expected returns, volatility, and Sharpe ratios. The optimize minimize function from the SciPy library is employed to construct an efficient frontier and determine optimal asset allocation, aiming to maximize returns or minimize volatility across various risk levels. The findings suggest that the strategy of dynamic weight adjustments combined with the KL-UCB algorithm enhances portfolio returns, particularly during market volatility. The research also reveals a portfolio inclination towards large-cap growth stocks due to the negative impacts of size and value premiums. It concludes that dynamic weight adjustment strategies offer significant potential in optimizing portfolio performance in complex market conditions, though leveraging increases risk and should be carefully managed according to investor risk tolerance.

Multi-kernel support vector regression with improved moth-flame optimization algorithm for software effort estimation

In this paper, a novel Moth-Flame Optimization (MFO) algorithm, namely MFO algorithm enhanced by Multiple Improvement Strategies (MISMFO) is proposed for solving parameter optimization in Multi-Kernel Support Vector Regressor (MKSVR), and the MISMFO-MKSVR model is further employed to deal with the software effort estimation problems. In MISMFO, the logistic chaotic mapping is applied to increase initial population diversity, while the mutation and flame number phased reduction mechanisms are carried out to improve the search efficiency, as well the adaptive weight adjustment mechanism is used to accelerate convergence and balance exploration and exploitation. The MISMFO model is verified on fifteen benchmark functions and CEC 2020 test set. The results show that the MISMFO has advantages over other meta-heuristic algorithms and MFO variants in terms of convergence speed and accuracy. Additionally, the MISMFO-MKSVR model is tested by simulations on five software effort datasets and the results demonstrate that the proposed model has better performance in software effort estimation problem. The Matlab code of MISMFO can be found at https://github.com/loadstar1997/MISMFO.