Standard Machine Research Articles

Biomechanical Test Setup for the Investigation of Forehead Suture Techniques

Abstract Wound healing can be delayed if the biomechanical stability of the wound closure is inadequate. Therefore, it is necessary to investigate different suturing techniques for their biomechanical stability. In this study, suturing techniques suitable for the forehead area were investigated. For this application, a special test setup was developed to simulate the curvature of the forehead and the corresponding physiological configuration. The average forehead curvature is 62.24 ± 4.11 mm in radius. To simulate this curvature, the skin specimens are subjected to tensile stress over the spherical surface using a standard uniaxial testing machine. For the evaluation, an automated evaluation tool for MATLAB was also developed. Three different suturing techniques (Straight, Lazy-S, Zigzag) were investigated and tested for their biomechanical stability. Of the three suturing techniques, the Zigzag suture proved to be the most stable with the highest stiffness of 44.23 ± 8.18 % and the highest final failure of 32.60 ± 4.95 % (relative to the control sample without incision). The study has shown that the test setup can be used to investigate different forehead suture techniques.

Classification and prediction of deformed steel and concrete bond-slip failure modes based on SSA-ELM model

Bond-slip failure modes between reinforcement and concrete can seriously affect the load-bearing performance and safety of reinforced concrete (RC) structures. The pull-out test is widely used to analyze RC bond-slip and failure modes because of its simplicity. Therefore, a prediction model based on Sparrow Search Algorithm (SSA) Optimized Extreme Learning Machine (SSA-ELM) is proposed in this study to quickly and effectively evaluate the failure forms of RC structures. The bond-slip test samples containing 399 sets of deformed bar and concrete deformation pull-out tests were first collected as a database, and the various characteristic parameters were preprocessed. Then, the features significantly influencing the failure pattern were screened out using random forest, and the plausibility tests were performed using the Pearson correlation coefficient and mutual information. Subsequently, a classification prediction model of the pull-out failure pattern was developed based on standard machine learning (ML) algorithms. In addition, nine well-known ML algorithms (LR, K-NN, DT, SVC, BPNN, NB, RF, AdaBoost, and XGBoost) are considered. This model's accuracy and generalization ability are compared based on the Precision and Recall confusion matrix. Finally, the optimized ELM was trained by SSA using the training set data with optimized ELM weights and thresholds. The results showed that the concrete protective layer thickness ratio to reinforcement diameter had the highest sensitivity to the failure pattern of RC-drawn specimens. The accuracy of the prediction results of the SSA-ELM model was better than other ML algorithms (Accuracy = 95.8%), such as BP Neural Network. In addition, SSA has better stability and higher accuracy than Gray Wolf Optimization (GWO) Algorithm, Particle Swarm Optimization (PSO) Algorithm, Genetic Algorithm (GA), Ant Colony Optimization (ACO), and other ML classification algorithms.

Fast Simulation of Analog Spiking Neural Network With Device Non-Idealites

We present a method for spiking neural network simulation with hardware realistic device non-idealities present in the neuron and synapse circuits as an alternative to time-consumingexpensive spice simulation. Neuromorphic machine learning algorithms for spiking neural networks are often simulatedtested with an ideal mathematical description of spiking neurons and synapses. However, silicon implementations of spiking neurons differ significantly from their ideal mathematical models because of device non-idealities and restrictions in the range of device operation. These non-idealities affect the performance of chip implementations of spiking networks. The dynamical system phase plane of the neuron and synapse circuit is used to create a compact representation of the neuron dynamics that captures device non-idealities for simulation of spiking neural networks. The proposed method would allow hardware-aware optimization of neuromorphic algorithms using standard machine learning tools and provide simulated network prediction close to what would be expected from a chip implementation.

Biaxial expansion due to compression experiments for measuring the failure strain of tubular samples

AbstractThe failure strain of a tube is a function of the biaxial strain ratio (axial strain/hoop strain) to which it is subjected. The relationship between failure strain and the strain ratio can be determined experimentally using expansion due to compression tests with a tensile load (EDCT), in which a ductile pellet placed inside the tube is compressed axially so it expands in diameter and imposes a hoop strain on the tube. At the same time, a tensile load on the ends of the tube creates an axial strain. This study investigates the capabilities and limitations of EDCT tests using two devices that allow experiments to be performed on a standard tensile testing machine. The first device applies an axial force on the ends of the sample, and the second device applies an axial displacement. Tests on zirconium alloy tubes confirmed that the failure strain is dependent on the strain ratio and the metallurgical state of the material. EDCT tests can produce a range of strain ratios, but there is an upper limit on the strain ratio that can be obtained, and it is dependent on the plastic behaviour of the sample and the friction conditions between the components.

Physics informed neural network for charged particles surrounded by conductive boundaries

Molecular dynamics of charged particles in porous conductive media have received considerable attention in recent years due to their application in cutting-edge technologies such as batteries and supercapacitors. Due to the presence of long-range electrical interactions, induced charges present at the boundary, and the influence of boundary conditions, the simulation of these systems is more challenging than the simulation of typical molecular dynamic systems. Simulating these kinds of systems typically involves using a numerical solver to solve the Poisson equation, which is a very time-consuming procedure. Recently, Physics-Informed Neural Networks (PINNs) have been introduced as an alternative to numerical solutions of PDEs. In this paper, we present a new PINN-based model for predicting the potential of point-charged particles surrounded by conductive walls. As a result of the proposed PINN model, the mean square error is less than 7% and R^{2} score is more than 90% for the corresponding example simulation. Results have been compared with typical neural networks and random forest as standard machine learning algorithms. The R^{2} score of the random forest model was 70%, and a standard neural network could not be trained well.

Identifying the Neurocognitive Difference Between Two Groups Using Supervised Learning


 
 
 Brain Imaging Analysis is a dynamic and exciting field within neuroscience. This study is conducted with two main objectives. First, to develop a classification framework to enhance predictive performance, and second, to conduct a comparative analysis of accuracy versus inference using brain imaging data. The dataset of chess masters and chess novices is utilized to identify neurocognitive differences between the two groups, based on their resting-state functional magnetic resonance imaging data. A network of connections between brain regions is created and analyzed. Standard statistical learning techniques and machine learning models are then applied to distinguish connectivity patterns between the groups. The trade-off between model precision and interpretability is also assessed. Finally, model performance measures, including accuracy, sensitivity, specificity, and AUC, are reported to demonstrate the effectiveness of the model framework.
 
 

DeepAmes: A deep learning-powered Ames test predictive model with potential for regulatory application

The Ames assay is required by the regulatory agencies worldwide to assess the mutagenic potential risk of consumer products. As well as this in vitro assay, in silico approaches have been widely used to predict Ames test results as outlined in the International Council for Harmonization (ICH) guidelines. Building on this in silico approach, here we describe DeepAmes, a high performance and robust model developed with a novel deep learning (DL) approach for potential utility in regulatory science. DeepAmes was developed with a large and consistent Ames dataset (>10,000 compounds) and was compared with other five standard Machine Learning (ML) methods. Using a test set of 1,543 compounds, DeepAmes was the best performer in predicting the outcome of Ames assay. In addition, DeepAmes yielded the best and most stable performance up to when compounds were >30% outside of the applicability domain (AD). Regarding the potential for regulatory application, a revised version of DeepAmes with a much-improved sensitivity of 0.87 from 0.47. In conclusion, DeepAmes provides a DL-powered Ames test predictive model for predicting the results of Ames tests; with its defined AD and clear context of use, DeepAmes has potential for utility in regulatory application.

Machine Learning Seams of Conical Intersection: A Characteristic Polynomial Approach.

The machine learning of potential energy surfaces (PESs) has undergone rapid progress in recent years. The vast majority of this work, however, has been focused on the learning of ground state PESs. To reliably extend machine learning protocols to excited state PESs, the occurrence of seams of conical intersections between adiabatic electronic states must be correctly accounted for. This introduces a serious problem, for at such points, the adiabatic potentials are not differentiable to any order, complicating the application of standard machine learning methods. We show that this issue may be overcome by instead learning the coordinate-dependent coefficients of the characteristic polynomial of a simple decomposition of the potential matrix. We demonstrate that, through this approach, quantitatively accurate machine learning models of seams of conical intersection may be constructed.

An adaptive semi-supervised deep learning-based framework for the detection of Android malware

Positive developments in smartphone usage have led to an increase in malicious attacks, particularly targeting Android mobile devices. Android has been a primary target for malware exploiting security vulnerabilities due to the presence of critical applications, such as banking applications. Several machine learning-based models for mobile malware detection have been developed recently, but significant research is needed to achieve optimal efficiency and performance. The proliferation of Android devices and the increasing threat of mobile malware have made it imperative to develop effective methods for detecting malicious apps. This study proposes a robust hybrid deep learning-based approach for detecting and predicting Android malware that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). It also presents a creative machine learning-based strategy for dealing with unbalanced datasets, which can mislead the training algorithm during classification. The proposed strategy helps to improve method performance and mitigate over- and under-fitting concerns. The proposed model effectively detects Android malware. It extracts both temporal and spatial features from the dataset. A well-known Drebin dataset was used to train and evaluate the efficacy of all creative frameworks regarding the accuracy, sensitivity, MAE, RMSE, and AUC. The empirical finding proclaims the projected hybrid ConvLSTM model achieved remarkable performance with an accuracy of 0.99, a sensitivity of 0.99, and an AUC of 0.99. The proposed model outperforms standard machine learning-based algorithms in detecting malicious apps and provides a promising framework for real-time Android malware detection.

Learning-Informed Parameter Identification in Nonlinear Time-Dependent PDEs

We introduce and analyze a method of learning-informed parameter identification for partial differential equations (PDEs) in an all-at-once framework. The underlying PDE model is formulated in a rather general setting with three unknowns: physical parameter, state and nonlinearity. Inspired by advances in machine learning, we approximate the nonlinearity via a neural network, whose parameters are learned from measurement data. The latter is assumed to be given as noisy observations of the unknown state, and both the state and the physical parameters are identified simultaneously with the parameters of the neural network. Moreover, diverging from the classical approach, the proposed all-at-once setting avoids constructing the parameter-to-state map by explicitly handling the state as additional variable. The practical feasibility of the proposed method is confirmed with experiments using two different algorithmic settings: A function-space algorithm based on analytic adjoints as well as a purely discretized setting using standard machine learning algorithms.

Enhanced breast mass mammography classification approach based on pre-processing and hybridization of transfer learning models.

The second most prevalent cause of death among women is now breast cancer, surpassing heart disease. Mammography images must accurately identify breast masses to diagnose early breast cancer, which can significantly increase the patient's survival percentage. Although, due to the diversity of breast masses and the complexity of their microenvironment, it is still a significant issue. Hence, an issue that researchers need to continue searching into is how to establish a reliable breast mass detection approach in an effective factor application to increase patient survival. Even though several machine and deep learning-based approaches were proposed to address these issues, pre-processing strategies and network architectures were insufficient for breast mass detection in mammogram scans, which directly influences the accuracy of the proposed models. Aiming to resolve these issues, we propose a two-stage classification method for breast mass mammography scans. First, we introduce a pre-processing stage divided into three sub-strategies, which include several filters for Region Of Interest (ROI) extraction, noise removal, and image enhancements. Secondly, we propose a classification stage based on transfer learning techniques for feature extraction, and global pooling for classification instead of standard machine learning algorithms or fully connected layers. However, instead of using the traditional fine-tuning feature extraction phase, we proposed a hybrid model where we concatenate two recent pre-trained CNNs to assist the feature extraction phase, rather than using one. Using the CBIS-DDSM dataset, we managed to increase mainly each of the accuracy, sensitivity, and specificity reaching the highest accuracy of 98,1% using the Median filter for noise removal. Followed by the Gaussian filter trial with 96% accuracy, meanwhile, the winner filter attained the lowest accuracy of 94.13%. Moreover, the usage of global average pooling as a classifier is suitable in our case better than global max pooling. The experimental findings demonstrate that the suggested strategy of breast Mass detection in mammography can outperform the top-ranked methods currently in use in terms of classification performance.

Development of a Genetic Algorithm Based Geodesic Active Contour for Iris Based Ethnicity Prediction System

The developments in science and technology have made it possible to use biometrics in applications where it is required to establish or confirm the identity of individuals. Among all possible biometric characteristics, the use of iris texture for recognition of individuals has been proven to be highly reliable. However, existing iris prediction systems have suffered from inability to handle more constrained acquisition (processing non-ideal iris images), high processing time and inappropriate parameter settings which usually results in inaccurate segmentation and poor classification results. This research therefore developed an improved segmentation and classification algorithms for iris-based ethnicity prediction system featuring the three major tribes in Nigeria. Six hundred (600) iris images from three major tribes in Nigeria (Yoruba, Hausa and Ibo) were locally captured for the database. Genetic Algorithm based Geodesic Active Contour (GAGAC) and standard Geodesic Active Control (GAC) were used for iris segmentation while Standard Support Vector Machine (SVM) and Galactic Swarm Optimisation SVM (GSOSVM) was used for iris classification. GAGAC and GSOSVM were used in the designing of the iris-based ethnicity prediction system at segmentation and classification stage. The developed iris-based ethnicity prediction system gave an improved predictive performance over the conventional one. The developed system can be used in different areas where higher security authentication is required.

NFSDense201: microstructure image classification based on non-fixed size patch division with pre-trained DenseNet201 layers

In the field of nanoscience, the scanning electron microscope (SEM) is widely employed to visualize the surface topography and composition of materials. In this study, we present a novel SEM image classification model called NFSDense201, which incorporates several key components. Firstly, we propose a unique nested patch division approach that divides each input image into four patches of varying dimensions. Secondly, we utilize DenseNet201, a deep neural network pretrained on ImageNet1k, to extract 2920 deep features from the last fully connected and global average pooling layers. Thirdly, we introduce an iterative neighborhood component analysis function to select the most discriminative features from the merged feature vector, which is formed by concatenating the four feature vectors extracted per input image. This process results in a final feature vector of optimal length 698. Lastly, we employ a standard shallow support vector machine classifier to perform the actual classification. To evaluate the performance of NFSDense201, we conducted experiments using a large public SEM image dataset. The dataset consists of 972, 162, 326, 4590, 3820, 3925, 4755, 181, 917, and 1624.jpeg images belonging to the following microstructural categories: “biological,” “fibers,” “film-coated surfaces,” “MEMS devices and electrodes,” “nanowires,” “particles,” “pattern surfaces,” “porous sponge,” “powder,” and “tips,” respectively. For both four-class and ten-class classification tasks, we evaluated NFSDense201 using subsets of the dataset containing 5080 and 21,272 images, respectively. The results demonstrate the superior performance of NFSDense201, achieving a four-class classification accuracy rate of 99.53% and a ten-class classification accuracy rate of 97.09%. These accuracy rates compare favorably against previously published SEM image classification models. Additionally, we report the performance of NFSDense201 for each class in the dataset.

SUPPORT VECTOR MACHINE MODELS FOR DIABETIC RETINOPATHY DIAGNOSIS AND GRADING

This work applies five variants of the support vector machine to the classification of the various stages of nonproliferative diabetic retinopathy. Four hundred eye fundus images from the Messidor repository are preprocessed and thirteen features extracted. The features best suited as inputs for support vector machine classification are identified. Initially, binary classification of severe nonproliferative diabetic retinopathy alone versus a normal eye is performed, achieving an accuracy of 97.44% using the standard support vector machine with Gaussian kernel and when optimized for accuracy. When optimized for sensitivity, the twin bounded support vector machine achieves the highest sensitivity of 99.06%. Then multiclass grading into all four stages of nonproliferative diabetic retinopathy is performed. Best performance with regards to four performance metrics, namely accuracy, sensitivity, specificity, and precision is achieved with the twin bounded support vector machine variant, when one-versus-one decision configuration is used in combination with a novel decision strategy that includes accumulated distances from the decision hyperplanes in the decision algorithm. The results compare favorably with data published in the literature.

Systems and methods for authenticating manufacturing Machines through an unobservable fingerprinting system

Digital transformation leads to the inevitable change in the security paradigm for machines on a factory production floor. A unified namespace for machines in an Industrial Internet of Things (IIoT) network is only reliable when machine assets can trust and verify the identity of assets connected to the IIoT system. Current methods of asset authentication do not consider physical unclonable functions (PUFs) and can easily be spoofed or misused. Our work proposes using PUFs for industrial equipment such as CNC machines, robots, and 3D printers for identifying machines on a network and providing authentication procedures. In this work, we chose to use the vibration associated with machines and its embedded moving parts as a means to identify machine assets on a network. It is hypothesized that the vibrations associated with specific machine movements will be unique to each machine even when machines look exactly the same. The moving parts within a machine may produce a unique vibration pattern that can be used for machine identification throughout the working cycle. Our method requires light computing and relatively cheap measuring devices to capture the ‘fingerprints’ of machines and verify the signal's integrity. An adequate number of equipment has been tested for the worst-case scenario, i.e. when two machines look exactly the same with the same moving parts and produce exactly similar motion to generate the vibration signal. Data preprocessing and standard machine learning techniques like RF, LASSO, and SVM show great performance on raw time series data, enabling 100% TPR and more than 94% TNR in detecting the false class of the machines.

Spam review detection with Metapath-aggregated graph convolution network

The large flux of online products in today’s world makes business reviews a valuable source for consumers for making sound decisions before making online purchases. Reviews are useful for readers in learning more about the product and gauge its quality. Fake reviews and reviewers form the bulk of the review corpus, making review spamming an open research challenge. These spam reviews require detection to nullify their contribution to product recommendations. In the past, researchers and communities have taken spam detection problems as a matter of serious concern. Yet, for all that, there is space for the performance of exploration on large-scale complex datasets. The work contributes towards robust feature selection with derived features that provide more details on malicious reviews and spammers. Ensemble and other standard machine learning techniques are trained and evaluated over optimal feature sets. In addition, the Metapath-based Graph Convolution Network (M-GCN) framework is proposed, which is an implicit knowledge extraction method to automatically capture the complex semantic meaning of reviews from the heterogeneous network. It makes analysis of triplet (users, reviews, and products) relationships in e-commerce sites through examination of Top-n feature sets in a mutually reinforcing manner. The proposed model is demonstrated on Yelp and Amazon benchmark datasets for evaluation of efficacy and it is shown outperforming state-of-the-art techniques with and without graph-utilization, providing an accuracy of 96% in the prediction task.

Five-axis parallel mechanism system (PMS) CNC partial link control system based on modified inverse kinematic of 6-DOF UPS parallel manipulator

This paper presents a control system algorithm for a five-axis parallel mechanism system (PMS) CNC milling machine based on a 6-DOF Stewart platform parallel manipulator with a universal-prismatic-spherical (UPS) configuration. The control system reads the G-Code commands as standard CNC machine language, then extract data points and interpolates them to generate the robot trajectory patterns as motion references. Then, the control system uses the modified inverse kinematic equation to determine the length of each link to move the end effector to track the trajectory patterns from the previous G-code extraction process. The inverse kinematic equation is modified especially for the five-axis PMS CNC milling machine by including machine-offset and tools-offset parameters so it will be easier for the control system to implement the kinematic equation. As expected, the system simulation results successfully followed the G-Code program moving commands. The average error of the length control system is 0,1 mm, while the average error of the length change rate control system is 1,8 mm/s. The maximum error is 26.9 mm was caused by the system's inability to follow the motion profile in transient. It can be concluded that 6-DOF Stewart platform parallel structures,which provide better performance than serial structures, can be implemented as a new concept for the motion mechanism of five-axis CNC milling machines. The five-axis PMS CNC milling machine also promises better performance than conventional five-axis gantry structures CNC.

Programmable Energy-Efficient Analog Multilayer Perceptron Architecture Suitable for Future Expansion to Hardware Accelerators

A programmable, energy-efficient analog hardware implementation of a multilayer perceptron (MLP) is presented featuring a highly programmable system that offers the user the capability to create an MLP neural network hardware design within the available framework. In addition to programmability, this implementation provides energy-efficient operation via analog/mixed-signal design. The configurable system is made up of 12 neurons and is fabricated in a standard 130 nm CMOS process occupying approximately 1 mm2 of on-chip area. The system architecture is analyzed in several different configurations with each achieving a power efficiency of greater than 1 tera-operations per watt. This work offers an energy-efficient and scalable alternative to digital configurable neural networks that can be built upon to create larger networks capable of standard machine learning applications, such as image and text classification. This research details a programmable hardware implementation of an MLP that achieves a peak power efficiency of 5.23 tera-operations per watt while consuming considerably less power than comparable digital and analog designs. This paper describes circuit elements that can readily be scaled up at the system level to create a larger neural network architecture capable of improved energy efficiency.

Multi-proximity based embedding scheme for learning vector quantization-based classification of biochemical structured data

In this paper, we propose a data embedding technique for structured data that allows for the direct application of standard vector-based machine learning models without the need for explicit feature extraction. Our approach relies on multiple notions of data proximity, making it suitable for handling mixed data types or incorporating domain knowledge. Our method also reduces the computational costs of pairwise proximity calculations, resulting in improved efficiency and scalability. We demonstrate the effectiveness of our technique on graph and sequence datasets from the biochemical domain. In particular, we show that the method can efficiently be combined with interpretable machine learning approaches like relevance-based learning vector quantization for sophisticated classification learning.

Does the Protrusion of Corticobasal Implants in the Maxillary Sinuses Affect Sinus Health? A Retrospective Study.

The aim of this retrospective study is to investigate the effect of corticobasal implant penetration in the nasal and maxillary sinuses on sinus health and implant survival rate in cases of severely atrophid ridges. This retrospective study was conducted on thirty patients with 172 implants who underwent corticobasal implant treatment between 2014 and 2018. Implants were divided into two groups according to the penetration depths (Group A, <4 mm; Group B, 4 mm). Inclusion criteria for the study included: (A) patients with severe maxillary ridge resorption with an immediately loaded corticobasal implant-supported prosthesis that showed implant protrusion inside the maxillary sinus on cone-beam computed tomography (CBCT); and (B) patients with a preoperative and postoperative follow-up CBCT scan using the same standard technique and machine. (C) Patients without any history of sinusitis before implant insertion patients who fulfilled the inclusion criteria were recalled for follow-up. The presence of sinus complications was clinically assessed according to the clinical practice guidelines for adult sinusitis of the American Academy of Otolaryngology-Head and Neck Surgery and Radiologically using CBCT. Moreover, patient satisfaction was evaluated using yes-or-no questions. The result was statistically analyzed using Fisher's Exact test. Despite the differences in implant penetration depths, no clinical signs of sinusitis were evident in any patient. One patient presented with transient epistaxis after the surgery, and 2 patients with nine implants revealed nonsignificant thickening of the sinus membrane radiologically (p = 0.055). All implants showed optimum bone-implant contact with a 100% survival rate. A significant relationship was reported between the thickness of the membrane and the patient's gender, hypertension, and smoking habits. (p = 0.001*, p = 0.002*, and p = 0.034*, respectively). Penetration of corticobasal implants in the maxillary sinus did not compromise the health of the maxillary sinus or implant survival rate. Limited posterior maxillary bony support and maxillary sinus pneumatization present challenges in implant dentistry and increase the possibility of implant protrusion inside the maxillary and nasal cavities. Hence, studying the effect of this protrusion on the maxillary sinuses' health and implant survival is highly significant.