Machine learning with active pharmaceutical ingredient/polymer interaction mechanism:Prediction for complex phase behaviors of pharmaceuticals and formulations

The high throughput prediction of the thermodynamic phase behavior of active pharmaceutical ingredients(APIs)with pharmaceutically relevant excipients remains a major scientific challenge in the screening of pharmaceutical formulations.In this work,a developed machine-learning model efficiently predicts the solubility of APIs in polymers by learning the phase equilibrium principle and using a few molecular descriptors.Under the few-shot learning framework,thermodynamic theory(perturbed-chain statistical associating fluid theory)was used for data augmentation,and computational chemistry was applied for molecular descriptors'screening.The results showed that the developed machine-learning model can predict the API-polymer phase diagram accurately,broaden the solubility data of APIs in polymers,and reproduce the relationship between API solubility and the interaction mechanisms between API and polymer successfully,which provided efficient guidance for the development of pharmaceutical formulations.

Machine learning and human‐machine trust in healthcare:A systematic survey

As human‐machine interaction(HMI)in healthcare continues to evolve,the issue of trust in HMI in healthcare has been raised and explored.It is critical for the development and safety of healthcare that humans have proper trust in medical machines.Intelligent machines that have applied machine learning(ML)technologies continue to penetrate deeper into the medical environment,which also places higher demands on intelligent healthcare.In order to make machines play a role in HMI in healthcare more effectively and make human‐machine cooperation more harmonious,the authors need to build good humanmachine trust(HMT)in healthcare.This article provides a systematic overview of the prominent research on ML and HMT in healthcare.In addition,this study explores and analyses ML and three important factors that influence HMT in healthcare,and then proposes a HMT model in healthcare.Finally,general trends are summarised and issues to consider addressing in future research on HMT in healthcare are identified.

Design of N-11-Azaartemisinins Potentially Active against Plasmodium falciparum by Combined Molecular Electrostatic Potential, Ligand-Receptor Interaction and Models Built with Supervised Machine Learning Methods

N-11-azaartemisinins potentially active against Plasmodium falciparum are designed by combining molecular electrostatic potential (MEP), ligand-receptor interaction, and models built with supervised machine learning methods (PCA, HCA, KNN, SIMCA, and SDA). The optimization of molecular structures was performed using the B3LYP/6-31G* approach. MEP maps and ligand-receptor interactions were used to investigate key structural features required for biological activities and likely interactions between N-11-azaartemisinins and heme, respectively. The supervised machine learning methods allowed the separation of the investigated compounds into two classes: cha and cla, with the properties εLUMO+1 (one level above lowest unoccupied molecular orbital energy), d(C6-C5) (distance between C6 and C5 atoms in ligands), and TSA (total surface area) responsible for the classification. The insights extracted from the investigation developed and the chemical intuition enabled the design of sixteen new N-11-azaartemisinins (prediction set), moreover, models built with supervised machine learning methods were applied to this prediction set. The result of this application showed twelve new promising N-11-azaartemisinins for synthesis and biological evaluation.

Integrated Simulation Method for Interaction between Manufacturing Process and Machine Tool

The interaction between the machining process and the machine tool （IMPMT） plays an important role on high precision components manufacturing. However, most researches are focused on the machining process or the machine tool separately, and the interaction between them has been always overlooked. In this paper, a novel simplified method is proposed to realize the simulation of IMPMT by combining use the finite element method and state space method. In this method, the transfer function of the machine tool is built as a small state space. The small state space is obtained from the complicated finite element model of the whole machine tool. Furthermore, the control system of the machine tool is integrated with the transfer function of the machine tool to generate the cutting trajectory. Then, the tool tip response under the cutting force is used to predict the machined surface. Finally, a case study is carried out for a fly-cutting machining process, the dynamic response analysis of an ultra-precision fly-cutting machine tool and the machined surface verifies the effectiveness of this method. This research proposes a simplified method to study the IMPMT, the relationships between the machining process and the machine tool are established and the surface generation is obtained.

Research on menu-typed man-machine interaction system of digital TIG welding machine

A digital man-machine interaction system controlled by communications between two processors of TMS320F240 and AT98C2051 was researched in the paper. The system is easy to set and modify welding process parameters by keyboards, and display information of welding site by LCD (Liquid Crystal Display). As one part of multi-task system about TIG welding machine, the coordination of man-machine interaction system with other tasks is the main point to the stability and reliability of its operation. Experiments result indicates that the system is stable, operation-flexible, high precision, and anti-interfering.

BLIND SPEECH SEPARATION FOR ROBOTS WITH INTELLIGENT HUMAN-MACHINE INTERACTION

Speech recognition rate will deteriorate greatly in human-machine interaction when the speaker's speech mixes with a bystander's voice. This paper proposes a time-frequency approach for Blind Source Seperation (BSS) for intelligent Human-Machine Interaction(HMI). Main idea of the algorithm is to simultaneously diagonalize the correlation matrix of the pre-whitened signals at different time delays for every frequency bins in time-frequency domain. The prososed method has two merits: (1) fast convergence speed; (2) high signal to interference ratio of the separated signals. Numerical evaluations are used to compare the performance of the proposed algorithm with two other deconvolution algorithms. An efficient algorithm to resolve permutation ambiguity is also proposed in this paper. The algorithm proposed saves more than 10% of computational time with properly selected parameters and achieves good performances for both simulated convolutive mixtures and real room recorded speeches.

Humanoid Intelligent Display Platform for Audiovisual Interaction and Sound Identification

This study proposes a rational strategy for the design,fabrication and system integration of the humanoid intelligent display platform(HIDP)to meet the requirements of highly humanized mechanical properties and intelligence for human-machine interfaces.The platform’s sandwich structure comprises a middle lightemitting layer and surface electrodes,which consists of silicon elastomer embedded with phosphor and silk fibroin ionoelastomer,respectively.Both materials are highly stretchable and resilient,endowing the HIDP with skin-like mechanical properties and applicability in various extreme environments and complex mechanical stimulations.Furthermore,by establishing the numerical correlation between the amplitude change of animal sounds and the brightness variation,the HIDP realizes audiovisual interaction and successful identification of animal species with the aid of Internet of Things(IoT)and machine learning techniques.The accuracy of species identification reaches about 100%for 200 rounds of random testing.Additionally,the HIDP can recognize animal species and their corresponding frequencies by analyzing sound characteristics,displaying real-time results with an accuracy of approximately 99%and 93%,respectively.In sum,this study offers a rational route to designing intelligent display devices for audiovisual interaction,which can expedite the application of smart display devices in human-machine interaction,soft robotics,wearable sound-vision system and medical devices for hearing-impaired patients.

Personalized assessment and training of neurosurgical skills in virtual reality:An interpretable machine learning approach

Background Virtual reality technology has been widely used in surgical simulators,providing new opportunities for assessing and training surgical skills.Machine learning algorithms are commonly used to analyze and evaluate the performance of participants.However,their interpretability limits the personalization of the training for individual participants.Methods Seventy-nine participants were recruited and divided into three groups based on their skill level in intracranial tumor resection.Data on the use of surgical tools were collected using a surgical simulator.Feature selection was performed using the Minimum Redundancy Maximum Relevance and SVM-RFE algorithms to obtain the final metrics for training the machine learning model.Five machine learning algorithms were trained to predict the skill level,and the support vector machine performed the best,with an accuracy of 92.41%and Area Under Curve value of 0.98253.The machine learning model was interpreted using Shapley values to identify the important factors contributing to the skill level of each participant.Results This study demonstrates the effectiveness of machine learning in differentiating the evaluation and training of virtual reality neurosurgical performances.The use of Shapley values enables targeted training by identifying deficiencies in individual skills.Conclusions This study provides insights into the use of machine learning for personalized training in virtual reality neurosurgery.The interpretability of the machine learning models enables the development of individualized training programs.In addition,this study highlighted the potential of explanatory models in training external skills.

Stock Type Prediction Based on Multiple Machine Learning Methods

Stocks in the Chinese stock market can be divided into ST stocks and normal stocks, so to prevent investors from buying potential ST stocks, this paper first performs SMOTEENN oversampling data preprocessing for the ST stock category, and selects 139 financial indicators and technical factor as predictive features. Then, it combines the Boruta algorithm and Copula entropy method for feature selection, effectively improving the machine learning model’s performance in ST stock classification, with the AUC values of the two models reaching 98% on the test set. In the model selection and optimization, this paper uses six major models, including logistic regression, XGBoost, AdaBoost, LightGBM, Catboost, and MLP, for modeling and optimizes them using the Optuna framework. Ultimately, XGBoost model is selected as the best model because its AUC value exceeds 95% and its running time is less. Finally, the XGBoost model is explained using the SHAP theory and the interaction between features is discovered, further improving the model’s accuracy and AUC value by about 0.6%, verifying the effectiveness of the model.

Support vector machine for predicting protein interactions using domain scores

Protein-protein interactions play a crucial role in the cellular processsuch as metabolic pathways and immunological recognition. This paper presents a new domain score-based support vector machine （SVM） to infer protein interactions, which can be used not only to explore all possible domain interactions by the kernel method, but also to reflect the evolutionary conservation of domains in proteins by using the domain scores of proteins. The experimental result on the Saccharomyces cerevisiae dataset demonstrates that this approach can predict protein-protein interactions with higher performances compared to the existing approaches.

Optimization and control of synchrotron emission in ultraintense laser–solid interactions using machine learning – CORRIGENDUM

Due to an isolated error in the 3D simulation parameters,the laser energy and intensity(calculated using the energy)values were incorrectly stated as 10.9 J and 3×10^(22) W cm^(−2),respectively,in Sections 3.3,7 and 8.The correct values are 39.8 J and 1.1×10^(23) W cm^(−2).Similarly,the values stated for the higher energy case,109 J and 3×10^(23) W cm^(−2) in Section 7,should be 398 J and 1.1×10^(24) W cm^(−2),respectively.

Understanding Nonverbal Communication Cues of Human Personality Traits in Human-Robot Interaction

With the increasing presence of robots in our daily life,there is a strong need and demand for the strategies to acquire a high quality interaction between robots and users by enabling robots to understand users’mood,intention,and other aspects.During human-human interaction,personality traits have an important influence on human behavior,decision,mood,and many others.Therefore,we propose an efficient computational framework to endow the robot with the capability of understanding the user’s personality traits based on the user’s nonverbal communication cues represented by three visual features including the head motion,gaze,and body motion energy,and three vocal features including voice pitch,voice energy,and mel-frequency cepstral coefficient(MFCC).We used the Pepper robot in this study as a communication robot to interact with each participant by asking questions,and meanwhile,the robot extracts the nonverbal features from each participant’s habitual behavior using its on-board sensors.On the other hand,each participant’s personality traits are evaluated with a questionnaire.We then train the ridge regression and linear support vector machine(SVM)classifiers using the nonverbal features and personality trait labels from a questionnaire and evaluate the performance of the classifiers.We have verified the validity of the proposed models that showed promising binary classification performance on recognizing each of the Big Five personality traits of the participants based on individual differences in nonverbal communication cues.

Multi‑Crack Interaction and Influence on the Spherical Pressure Hull for a Deep‑Sea Manned Submersible

This study investigates the interaction and influence of surface cracks on the spherical pressure hull of a deep-sea manned submersible.The finite element model of the spherical hull is established,and a semi-elliptical surface crack is inserted in the welding toe of the spherical hull as the main crack.Considering the combined effect of external uniform pressure and welding residual stress at the weld toe,the stress intensity factor(SIF)is obtained based on the M-integral method.Inserting disturbing cracks at different positions on the spherical hull surface,the interaction and influence between multi-cracks are revealed by numerical calculation.The results show that the existence of the disturbing crack has a great influence on the stress intensity factor of the main crack,and the influence is different with the different location of disturbing crack.The study of the interaction of multiple cracks under different interference factors and the influence of disturbing cracks on the main crack can provide some reference for future engineering applications.

Lateral interaction by Laplacian‐based graph smoothing for deep neural networks

Lateral interaction in the biological brain is a key mechanism that underlies higher cognitive functions.Linear self‐organising map(SOM)introduces lateral interaction in a general form in which signals of any modality can be used.Some approaches directly incorporate SOM learning rules into neural networks,but incur complex operations and poor extendibility.The efficient way to implement lateral interaction in deep neural networks is not well established.The use of Laplacian Matrix‐based Smoothing(LS)regularisation is proposed for implementing lateral interaction in a concise form.The authors’derivation and experiments show that lateral interaction implemented by SOM model is a special case of LS‐regulated k‐means,and they both show the topology‐preserving capability.The authors also verify that LS‐regularisation can be used in conjunction with the end‐to‐end training paradigm in deep auto‐encoders.Additionally,the benefits of LS‐regularisation in relaxing the requirement of parameter initialisation in various models and improving the classification performance of prototype classifiers are evaluated.Furthermore,the topologically ordered structure introduced by LS‐regularisation in feature extractor can improve the generalisation performance on classification tasks.Overall,LS‐regularisation is an effective and efficient way to implement lateral interaction and can be easily extended to different models.

Research on Dynamic Mathematical Resource Screening Methods Based on Machine Learning

The current digital educational resources are of many kinds and large quantities, to solve the problems existing in the existing dynamic resource selection methods, a dynamic resource selection method based on machine learning is proposed. Firstly, according to the knowledge structure and concepts of mathematical resources, combined with the basic components of dynamic mathematical resources, the knowledge structure graph of mathematical resources is constructed;according to the characteristics of mathematical resources, the interaction between users and resources is simulated, and the graph of the main body of the resources is identified, and the candidate collection of mathematical knowledge is selected;finally, according to the degree of matching between mathematical literature and the candidate collection, machine learning is utilized, and the mathematical resources are screened.

Construction of gene/protein interaction networks and enrichment pathway analysis for paroxysmal nocturnal hemoglobinuria and aplastic anemia

Background:To develop a protein-protein interaction network of Paroxysmal nocturnal hemoglobinuria(PNH)and Aplastic anemia(AA)based on genetic genes and to predict pathways underlying the molecular complexes in the network.Methods:In this research,the PNH and AA-related genes were screened through Online Mendelian Inheritance in Man(OMIM).The plugins and Cytoscape were used to search literature and build a protein-protein interaction network.Results:The protein-protein interaction network contains two molecular complexes that are five higher than the correlation integral values.The target genes of this study were obtained:CD59,STAT3,TERC,TNF,AKT1,C5AR1,EPO,IL6,IL10 and so on.We also found that many factors regulate biological behaviors:neutrophils,macrophages,vascular endothelial growth factor,immunoglobulin,interleukin,cytokine receptor,interleukin-6 receptor,tumor necrosis factor,and so on.This research provides a bioinformatics foundation for further explaining the mechanism of common development of both.Conclusion:This indicates that the PNH and AA is a complex process regulated by many cellular pathways and multiple genes.

Human Interaction Dynamics for Its Use in Mobile Robotics:Impedance Control for Leader-follower Formation

A complete characterization of the behavior in human-robot interactions(HRI) includes both: the behavioral dynamics and the control laws that characterize how the behavior is regulated with the perception data. In this way, this work proposes a leader-follower coordinate control based on an impedance control that allows to establish a dynamic relation between social forces and motion error. For this, a scheme is presented to identify the impedance based on fictitious social forces, which are described by distance-based potential fields.As part of the validation procedure, we present an experimental comparison to select the better of two different fictitious force structures. The criteria are determined by two qualities: least impedance errors during the validation procedure and least parameter variance during the recursive estimation procedure.Finally, with the best fictitious force and its identified impedance,an impedance control is designed for a mobile robot Pioneer 3AT,which is programmed to follow a human in a structured scenario.According to results, and under the hypothesis that moving like humans will be acceptable by humans, it is believed that the proposed control improves the social acceptance of the robot for this kind of interaction.

Stability and Bifurcation Analysis of Man-machine System with Time Delay

A mathematical model of man-machine system is considered.Based on the reference [4],the direction and stability of the Hopf bifurcation are determined using the normal form method and the center manifold theory.Furthermore,the existence of Hopf-zero bifurcation is discussed.In the end,some numerical simulations are carried out to illustrate the results found.

An Approach for Evaluating Reliability of Man－Machine System in Evolving Environment

ＡｎＡｐｐｒｏａｃｈｆｏｒＥｖａｌｕａｔｉｎｇＲｅｌｉａｂｉｌｉｔｙｏｆＭａｎ┐ＭａｃｈｉｎｅＳｙｓｔｅｍｉｎＥｖｏｌｖｉｎｇＥｎｖｉｒｏｎｍｅｎｔ＊ＷａｎｇＷｕｈｏｎｇＺｈａｎｇＤｉａｎｙｅＣａｏＱｉＳｃｈｏｏｌｏｆＥｃｏｎｏｍｉｃｓａｎｄＭａｎａ...

Analysis of Drivers＇Burden and Man－Machine Interfaces in High－Speed Locomotive Driving Cab

With the introduction of high-speed trains into chinese railway system, closeattention should be paid to the aspects of safety in hish-speed railways. Thereare many interfaces which are very important and directly related to drivmgsafety. This paper focuses on features of design and analyses the principles ofsafety.