Machine Platform Research Articles

Advancing Hydrogel-Based 3D Cell Culture Systems: Histological Image Analysis and AI-Driven Filament Characterization.

Background: Machine learning is used to analyze images by training algorithms on data to recognize patterns and identify objects, with applications in various fields, such as medicine, security, and automation. Meanwhile, histological cross-sections, whether longitudinal or transverse, expose layers of tissues or tissue mimetics, which provide crucial information for microscopic analysis. Objectives: This study aimed to employ the Google platform "Teachable Machine" to apply artificial intelligence (AI) in the interpretation of histological cross-section images of hydrogel filaments. Methods: The production of 3D hydrogel filaments involved different combinations of sodium alginate and gelatin polymers, as well as a cross-linking agent, and subsequent stretching until rupture using an extensometer. Cross-sections of stretched and unstretched filaments were created and stained with hematoxylin and eosin. Using the Teachable Machine platform, images were grouped and trained for subsequent prediction. Results: Over six hundred histological cross-section images were obtained and stored in a virtual database. Each hydrogel combination exhibited variations in coloration, and some morphological structures remained consistent. The AI efficiently identified and differentiated images of stretched and unstretched filaments. However, some confusion arose when distinguishing among variations in hydrogel combinations. Conclusions: Therefore, the image prediction tool for biopolymeric hydrogel histological cross-sections using Teachable Machine proved to be an efficient strategy for distinguishing stretched from unstretched filaments.

A Review of Electroplastic Effect on Difficult‐to‐Machine Materials in Cutting Processing

Electroplastic effect refers to the role of pulsed current, material plasticity, and microstructural properties change, resulting in an increase in the plasticity of the material, the deformation resistance is reduced, and thus improves the processing performance of the phenomenon. This article summarizes the Joule thermal effect and a variety of nonthermal effects of the electrophysical effect mechanism, of which the nonthermal effects include pure electrophysical effect, magnetic field compression effect, and skin effect. The application of electroplastic‐assisted technology in cutting machining, such as turning, milling, drilling, and so on, and the potential application in other manufacturing processes are summarized. The limitations and shortcomings of the electroplastic‐assisted technology are analyzed, including the limitations of the required special equipment, machining platforms, and electric pulse parameters. The effects of different electric pulse parameters on the machinability of various types of difficult‐to‐machine metallic materials are summarized. The electric pulse parameters within a certain threshold range can promote the dynamic recrystallization of the workpiece, enhance the plastic deformation of the cutting zone, reduce the cutting force, improve the surface finish, and reduce tool wear. Finally, this article summarizes and looks forward to the electroplastic‐assisted cutting technology.

Anomaly detection in virtual machine logs against irrelevant attribute interference.

Virtual machine logs are generated in large quantities. Virtual machine logs may contain some abnormal logs that indicate security risks or system failures of the virtual machine platform. Therefore, using unsupervised anomaly detection methods to identify abnormal logs is a meaningful task. However, collecting accurate anomaly logs in the real world is often challenging, and there is inherent noise in the log information. Parsing logs and anomaly alerts can be time-consuming, making it important to improve their effectiveness and accuracy. To address these challenges, this paper proposes a method called LADSVM(Long Short-Term Memory + Autoencoder-Decoder + SVM). Firstly, the log parsing algorithm is used to parse the logs. Then, the feature extraction algorithm, which combines Long Short-Term Memory and Autoencoder-Decoder, is applied to extract features. Autoencoder-Decoder reduces the dimensionality of the data by mapping the high-dimensional input to a low-dimensional latent space. This helps eliminate redundant information and noise, extract key features, and increase robustness. Finally, the Support Vector Machine is utilized to detect different feature vector signals. Experimental results demonstrate that compared to traditional methods, this approach is capable of learning better features without any prior knowledge, while also exhibiting superior noise robustness and performance. The LADSVM approach excels at detecting anomalies in virtual machine logs characterized by strong sequential patterns and noise. However, its performance may vary when applied to disordered log data. This highlights the necessity of carefully selecting detection methods that align with the specific characteristics of different log data types.

Fault diagnosis for multi-axis carving machine systems with Gaussian mixture hidden Markov models: A data-model interactive perspective

This paper is concerned with sensor fault diagnosis problems for multi-axis carving machine systems (MACMSs) with repetitive machining tasks. A novel fault diagnosis method that combines the multi-feature fusion technology and Gaussian mixture hidden Markov models (GMHMMs) is proposed, which is inspired by a data- and model-driven collaborative perspective. With fault-sensitive features first extracted from both the time domain and time–frequency domain, the composite health index (CHI) is constructed to facilitate the understanding of the time-varying evolution. Then, GMHMMs are established to characterize the probabilistic relationship between the hidden states and CHI. To achieve high-precision fault classification, a well-designed global objective function is adopted to dynamically optimize both the CHI construction and classifier model training in a closed-loop feedback mechanism. Specifically, the fusion coefficients with range and equality constraints are integrated as part of the model parameters into the global optimization objective function, thereby reducing the search range and improving convergence speed. Besides, the well-trained GMHMMs interact with each other to capture the correlation information between different faults, and are utilized for online fault diagnosis. Finally, experiments are conducted on a self-developed multi-axis carving machine platform. The results exhibit outstanding performance in comparison with existing methods, particularly attaining a diagnostic accuracy of 95.37%.

Design of adaptive barrier function-based backstepping finite time guidance control for interceptor-target systems

This study introduces an optimal finite-time backstepping sliding mode guidance law, leveraging an adaptive continuous barrier function to examine the interceptor-target system’s motion in cylindrical coordinates. The integration of sliding mode and backstepping controllers enhances the robustness and performance of the proposed guidance method amidst external disturbances and model uncertainties. This combination also improves transient response, reduces chattering, and lowers control efforts. The adaptive continuous barrier function employed in this method eliminates the need for prior knowledge of the upper bounds of uncertainties and disturbances. Additionally, it ensures that adaptation gains are not overestimated, leading to more accurate performance and complete elimination of chattering. The Lyapunov stability theory is used to prove the finite-time convergence of the state trajectories of the interceptor-target system to a predefined neighborhood around the origin, despite external disturbances and uncertainties. A genetic optimization algorithm is utilized to optimally select the parameters of the guidance method. The efficacy of the proposed technique is validated through simulation results and real-time experiments on the Baseline Speedgoat Real-Time Target Machine platform. The method’s effectiveness and performance are further demonstrated through analysis and simulation in the MATLAB/Simulink environment.

Milling and Grinding to Single-Figure Micron Accuracy on One Machining Platform

Gerhard Rauch utilises high-tech 5-axis machine tools that enable it to machine to extremely tight tolerances and produce the high standards expected from its customers

Vision-based planting position selection system for an unmanned reforestation machine

Abstract Research on automated seedling planting systems in forestry is a crucial aspect of forestry automation. This paper introduces the development of a vision-based automated seedling planting position selection system, integrated with hardware and software components on an unmanned forest machine platform. Developed around object detection as the core, this research presents a comprehensive system consisting of two main functionalities: (i) A vision system that performs obstacle detection and localization, providing estimated obstacle types, sizes, and positions to the plant planner function. (ii) A plant planner function utilizes this information to plan the plantable areas and selects suitable planting locations. The integrated system has been tested in the field and we found it to effectively determine suitable planting locations on the ground of a clear-cut. The implementation of this system lays the foundation for subsequent automated planting operations. Furthermore, the automation of forest seedling planting reduces the need for manual labor and enhances planting precision, contributing to improved forest health and ecological balance. Looking ahead, this research offers insights into the future development of unmanned forestry operations, making strides in automating forest management, achieving cost-effectiveness, and facilitating ecological restoration.

Thrust Ripple Suppression Strategy for Precision Machining Platform by Using Predicted Current Sliding Control

Thrust Ripple Suppression Strategy for Precision Machining Platform by Using Predicted Current Sliding Control

The Role of ArtificiaI Intelligence in Brain Tumor Diagnosis: An Evaluation of a Machine Learning Model.

This research study explores of the effectiveness of a machine learning image classification model in the accurate identification of various types of brain tumors. The types of tumors under consideration in this study are gliomas, meningiomas, and pituitary tumors. These are some of the most common types of brain tumors and pose significant challenges in terms of accurate diagnosis and treatment. The machine learning model that is the focus of this study is built on the Google Teachable Machine platform (Alphabet Inc., Mountain View, CA). The Google Teachable Machine is a machine learning image classification platform that is built from Tensorflow, a popular open-source platform for machine learning. The Google Teachable Machine model was specifically evaluated for its ability to differentiate between normal brains and the aforementioned types of tumors in MRI images. MRI images are a common tool in the diagnosis of brain tumors, but the challenge lies in the accurate classification of the tumors. This is where the machine learning model comes into play. The model is trained to recognize patterns in the MRI images that correspond to the different types of tumors. The performance of the machine learning model was assessed using several metrics. These include precision, recall, and F1 score. These metrics were generated from a confusion matrix analysis and performance graphs. A confusion matrix is a table that is often used to describe the performance of a classification model. Precision is a measure of the model's ability to correctly identify positive instances among all instances it identified as positive. Recall, on the other hand, measures the model's ability to correctly identify positive instances among all actual positive instances. The F1 score is a measure that combines precision and recall providing a single metric for model performance. The results of the study were promising. The Google Teachable Machine model demonstrated high performance, with accuracy, precision, recall, and F1 scores ranging between 0.84 and 1.00. This suggests that the model is highly effective in accurately classifying the different types of brain tumors. This study provides insights into the potential of machine learning models in the accurate classification of brain tumors. The findings of this study lay the groundwork for further research in this area and have implications for the diagnosis and treatment of brain tumors. The study also highlights the potential of machine learning in enhancing the field of medical imaging and diagnosis. With the increasing complexity and volume of medical data, machine learning models like the one evaluated in this study could play a crucial role in improving the accuracy and efficiency of diagnoses. Furthermore, the study underscores the importance of continued research and development in this field to further refine these models and overcome any potential limitations or challenges. Overall, the study contributes to the field of medical imaging and machine learning and sets the stage for future research and advancements in this area.

Design and Simulation of Mobile Multi-Robot Machining Platform

Design and Simulation of Mobile Multi-Robot Machining Platform

Optimizing dynamic measurement accuracy for machine tools and industrial robots with unscented Kalman filter and particle swarm optimization methods

The telescoping ballbar is widely utilized for diagnosing accuracy and identifying faults in machine tools and industrial robots. Currently, there are no established standards for determining the optimal feed rate for ballbar tests. This lack of clear guidelines results in time inefficiency in measurements and inconsistencies in dynamic measurements, which complicates the comparison of ballbar test results under various conditions or across different machine platforms. To mitigate dynamic variations in ballbar results, an updated ballbar data processing method that integrates the unscented Kalman filter (UKF) and particle swarm optimization (PSO) was developed and validated using real ballbar data measured at multiple feed rates and simulated data with varying vibration magnitudes generated through the Renishaw ballbar simulator. Experimental results revealed that the dynamic components extracted from the ballbar results were observed to increase in correlation with the vibration measured at different feed rates and from the simulations. Moreover, the variations in the results measured at different feed rates after PSO-UKF processing were significantly reduced. The findings confirm the effectiveness of the proposed method in minimizing the dynamics of the ballbar results. Ultimately, this approach enhances the efficiency and accuracy of ballbar testing and offers a general method for improved diagnostics.

Microbiome Sex-Related Diversity in Non-Muscle-Invasive Urothelial Bladder Cancer.

Sex-specific discrepancies in bladder cancer (BCa) are reported, and new studies imply that microbiome may partially explain the diversity. We aim to provide characterization of the bladder microbiome in both sexes diagnosed with non-muscle-invasive BCa with specific insight into cancer grade. In our study, 16S rRNA next-generation sequencing was performed on midstream urine, bladder tumor sample, and healthy-appearing bladder mucosa. Bacterial DNA was isolated using QIAamp Viral RNA Mini Kit. Metagenomic analysis was performed using hypervariable fragments of the 16S rRNA gene on Ion Torrent Personal Genome Machine platform. Of 41 sample triplets, 2153 taxa were discovered: 1739 in tumor samples, 1801 in healthy-appearing bladder mucosa and 1370 in midstream urine. Women were found to have smaller taxa richness in Chao1 index than men (p = 0.03). In comparison to low-grade tumors, patients with high-grade lesions had lower bacterial diversity and richness in urine. Significant differences between sexes in relative abundance of communities at family level were only observed in high-grade tumors.

A neural network model for point defect microcavities of two-dimensional GaAs media background photonic crystals

This paper aims to address the challenge of constructing, training, and optimizing a neural network model for the point defect microcavity of a two-dimensional GaAs media background photonic crystal. The objective is to achieve more accurate predictions and analyses of photon modes, thereby enhancing the performance of the microcavity. Due to the structural complexity and multi-parameter nature of point defect microcavities, traditional analysis methods often fail to capture their optical behavior adequately. Consequently, there is a need for a novel approach to establishing an optical model for point defect microcavities, enabling precise predictions of their optical properties and optimal design. In this study, the MPB computing tool developed by MIT, in conjunction with the programming language Scheme, MATLAB, and the Ubuntu virtual machine platform, was utilized for data acquisition. The neural network model was employed to process the input data of the photonic crystal point defect microcavity, leading to predictions and analyses. This interdisciplinary approach results in a high-precision model of the microcavity. The neural network model is capable of nonlinear mapping and prediction by learning the patterns and features of the data. Additionally, this combination holds the promise of enabling more efficient optical information processing and increased data transfer rates. The relationship between the energy band data and the structure of photonic crystals exhibits a high degree of nonlinearity. The neural network model proposed in this paper can infer the structure of photonic crystals based on the photon energy band (dispersion relation ω-K) of micro-cavity structures with point defects in different photonic crystals. This provides a valuable reference for more accurate predictions and analyses of photon modes in complex photonic crystal micro-cavities, ultimately leading to improved micro-cavity performance.

Predictive process diagram for parameters selection in laser powder bed fusion to achieve high-density and low-cracking built parts

The laser powder bed fusion process (LPBF) has been widely used in many industrial sectors, including automotive, aerospace, and biomedical devices. With the fast development of new materials designed for critical applications, the conventional design of experiments for determining an optimal LPBF process window is a time and material-consuming activity. This can impose difficulties on small-to-medium industrial businesses where investing resources are limited. To address these challenges, this study draws inspiration from a reliable diagram used in laser welding to construct a similar diagram for the LPBF process. The objective is to enable the "right-first-time" selection of parameters that achieve a minimum of 99% density, regardless of the metallic materials and machine platforms. The diagram is established based on dimensionless beam power and velocity, derived from multiple LPBF process parameters (e.g., laser power, scan speed, hatch spacing) and the thermophysical properties of materials (e.g., melting point, density, thermal diffusivity). Furthermore, hot cracking susceptibility is considered by a strain-rate approach incorporated with the dimensionless thermal strain factor, which benefits when processing hard-to-weld alloys. The diagram shows high reliability in determining parameters corresponding to lack of fusion, keyhole porosity and 99% dense parts when plotting against literature data of LPBF for several metallic materials. Similar results were observed when applying to a novel material ABD-900AM Ni-based alloy, for which no previously published data were available. Moreover, the diagram proved effective in selecting parameters to process the high-cracking susceptible CM247LC Ni-based alloy, resulting in significant mitigation of hot cracking in the as-fabricated parts.

Real-World Implementation and Performance Analysis of Distributed Learning Frameworks for 6G IoT Applications

This paper explores the practical implementation and performance analysis of distributed learning (DL) frameworks on various client platforms, responding to the dynamic landscape of 6G technology and the pressing need for a fully connected distributed intelligence network for Internet of Things (IoT) devices. The heterogeneous nature of clients and data presents challenges for effective federated learning (FL) techniques, prompting our exploration of federated transfer learning (FTL) on Raspberry Pi, Odroid, and virtual machine platforms. Our study provides a detailed examination of the design, implementation, and evaluation of the FTL framework, specifically adapted to the unique constraints of various IoT platforms. By measuring the accuracy of FTL across diverse clients, we reveal its superior performance over traditional FL, particularly in terms of faster training and higher accuracy, due to the use of transfer learning (TL). Real-world measurements further demonstrate improved resource efficiency with lower average load, memory usage, temperature, power, and energy consumption when FTL is implemented compared to FL. Our experiments also showcase FTL’s robustness in scenarios where users leave the server’s communication coverage, resulting in fewer clients and less data for training. This adaptability underscores the effectiveness of FTL in environments with limited data, clients, and resources, contributing valuable information to the intersection of edge computing and DL for the 6G IoT.

Adaptive prescribed performance based on recursive nonsingular terminal sliding mode control for quad-rotor systems under uncertainty and disturbance: Real-time validation

In this paper, at the aim of the fast trajectory-following control of the Unmanned Aerial Vehicle (UAV) systems subject to uncertainty and disturbance, the adaptive prescribed performance control based recursive nonsingular terminal sliding mode control is suggested. Afterward, for the fast trajectory-following control of the uncertain and perturbed quad-rotor system, a recursive nonsingular terminal sliding mode strategy is recommended. Since the better transient and steady-state response of the sliding mode surface is of the utmost importance in the design of the controller, the prescribed performance control scheme is proposed in which the transformed prescribed form of the previously proposed recursive nonsingular terminal sliding surface is obtained to prove that the recursive nonsingular terminal sliding surface can converge to a preset region. Whereas unknown bounded uncertainty and disturbance always exist in the UAV system's dynamical model which decreases its performance and efficiency, the adaptive mechanism is applied to approximate uncertain bounds of uncertainty and disturbance to advance the implementation of the UAV system. Later, quick reachability of the prescribed form switching surface is demonstrated using Lyapunov concept. Ultimately, simulation results using MATLAB/Simulink over a quad-rotor system and real-time simulation using the Speedgoat Real-Time Target Machine platform are conducted to validate the feasibility and performance of the proposed method.

Optimization of HIV Sequencing Method Using Vela Sentosa Library on Miseq Ilumina Platform.

Genotypic testing is often recommended to improve the management of patients infected with human immunodeficiency virus (HIV). To help combat this major pandemic, next-generation sequencing (NGS) techniques are widely used to analyse resistance to antiretroviral drugs. In this study, we used a Vela Sentosa kit (Vela Diagnostics, Kendall, Singapore), which is usually used for the Ion Torrent personal genome machine (PGM) platform, to sequence HIV using the Illumina Miseq platform. After RNA extraction and reverse transcriptase-polymerase chain reaction (RT-PCR), minor modifications were applied to the Vela Sentosa kit to adapt it to the Illumina Miseq platform. Analysis of the results showed the same mutations present in the samples using both sequencing platforms. The total number of reads varied from 185,069 to 752,343 and from 642,162 to 2,074,028 in the Ion Torrent PGM platform and the Illumina Miseq platform, respectively. The average depth was 21,955 and 46,856 for Ion Torrent PGM and Illumina Miseq platforms, respectively. The cost of sequencing a run of eight samples was quite similar between the two platforms (about USD 1790 for Illumina Miseq and about USD 1833 for Ion Torrent PGM platform). We have shown for the first time that it is possible to adapt and use the Vela Sentosa kit for the Illumina Miseq platform to obtain high-quality results with a similar cost.

Zooming in on Urban Life in Early Modern Amsterdam. Time Machine as a Tool for Researching Everyday Urban Experience Across Space and Time

How do we make sense of urban life in the past? What do we do when we study urban history, and to what extent do our methods fully capture the complexities of historical city living? These are crucial questions for any scholar interested in the historical dimensions of urban experience. Notwithstanding the interest of most urban historians in the relationship between the physical form of urban space and its experience by inhabitants and visitors, very few scholars have written histories that systematically integrate these two areas of inquiry. In this article the authors argue that such research requires a method and an accompanying digital tool that can analyze historical urban life in a more integrated, holistic way. The authors propose a way forward by introducing the Time Machine platform as a scalable data visualization and analysis tool for researching everyday urban experience across space and time. To illustrate the potential, the authors focus on a case study: the area of the Bloemstraat in early modern Amsterdam. Unpacking a section of the Bloemstraat, house by house and room by room, this case shows how the Time Machine forms an instrument to connect spatial layouts to the arrangement of objects and to the practical and social use of the space by the inhabitants and visitors. The authors also sketch how this tool illuminates more dynamic spatial and temporal practices such as how people, goods and activities are connected to locations in the wider city and beyond.

Cross-domain tool wear condition monitoring via residual attention hybrid adaptation network

Intelligent models for tool wear condition monitoring (TWCM) have been extensively researched. However, in industrial scenarios, limited acquired monitoring signals and variations of machining parameters lead to insufficient training samples and data distribution shifts for the models. To address the issues, this research presents a novel residual attention hybrid adaptation network (RAHAN) model based on a residual attention network (ResAttNet) and a hybrid adaptation strategy. In the RAHAN model, by integrating a channel attention mechanism and deep residual modules, ResAttNet is designed as a feature extractor to acquire features from monitoring signals for tool wear conditions. Embedding subdomain adaptation into a condition recognizer while establishing separate adversarial learning in a domain obfuscator, the hybrid adaptation strategy is developed to eliminate global distribution shifts and align local distributions of each tool wear phase simultaneously. Six migration tasks under a laboratory and two factory machining platforms were conducted to evaluate the effectiveness of the RAHAN model. Compared with a baseline model, four ablation models, and six state-of-the-art transfer learning models, the RAHAN model achieved the highest average accuracy of 92.70% on six migration tasks. Furthermore, the RAHAN model shows clearer feature representations of each tool wear condition than other compared models. The comparative results demonstrate that the RAHAN model has superior transferability and therefore can be considered as a good potential solution to support cross-domain TWCM under different machining processes.

Implementation Model Prototyping In Application Design of Halal Food Product Detection For Overseas Muslim Students

In the age of globalization, the production and trading of food have become more widespread, and consumers, particularly those who follow the Islamic faith, require access to information about the halal status of the products they consume. It is crucial to provide accurate and relevant information to them regarding the halal nature of the products they buy. To cater to this need, many people are using barcode scanners via mobile platforms to obtain product information. These barcode scanners use optical scanners called code readers, and they are popular as they provide a quick and efficient way of obtaining information. Creating a barcode application using the prototyping method is an effective solution that involves several steps, such as gathering and analyzing requirements, rapid design, building a prototype, user evaluation, and refining the prototype. The programming language Kotlin is used to create these applications, which support building Android applications on the Java Virtual Machine Platform (JVM). The use of Kotlin, which is statically expressed and executed, makes the process of developing these applications efficient and straightforward. In summary, developing a barcode application using the prototyping method and Kotlin is an excellent solution to provide consumers with accurate and accessible information about the halal status of food products they consume.