The Effect of Machine Learning Algorithms on the Prediction of Layer-by-Layer Coating Properties

Comparative study of ten machine learning algorithms for short-term forecasting in gas warning systems

This research aims to explore more efficient machine learning (ML) algorithms with better performance for short-term forecasting. Up-to-date literature shows a lack of research on selecting practical ML algorithms for short-term forecasting in real-time industrial applications. This research uses a quantitative and qualitative mixed method combining two rounds of literature reviews, a case study, and a comparative analysis. Ten widely used ML algorithms are selected to conduct a comparative study of gas warning systems in a case study mine. We propose a new assessment visualization tool: a 2D space-based quadrant diagram can be used to visually map prediction error assessment and predictive performance assessment for tested algorithms. Overall, this visualization tool indicates that LR, RF, and SVM are more efficient ML algorithms with overall prediction performance for short-term forecasting. This research indicates ten tested algorithms can be visually mapped onto optimal (LR, RF, and SVM), efficient (ARIMA), suboptimal (BP-SOG, KNN, and Perceptron), and inefficient algorithms (RNN, BP_Resilient, and LSTM). The case study finds results that differ from previous studies regarding the ML efficiency of ARIMA, KNN, LR, LSTM, and SVM. This study finds different views on the prediction performance of a few paired algorithms compared with previous studies, including RF and LR, SVM and RF, KNN and ARIMA, KNN and SVM, RNN and ARIMA, and LSTM and SVM. This study also suggests that ARIMA, KNN, LR, and LSTM should be investigated further with additional prediction error assessments. Overall, no single algorithm can fit all applications. This study raises 20 valuable questions for further research.

Protein-based layer-by-layer films for biomedical applications

The surface engineering of biomaterials is crucial for their successful (bio)integration by the body, i.e. the colonization by the tissue-specific cell, and the prevention of fibrosis and/or bacterial colonization. Performed at room temperature in an aqueous medium, the layer-by-layer (LbL) coating method is based on the alternating deposition of macromolecules. Versatile and simple, this method allows the functionalization of surfaces with proteins, which play a crucial role in several biological mechanisms. Possessing intrinsic properties (cell adhesion, antibacterial, degradable, etc.), protein-based LbL films represent a powerful tool to control bacterial and mammalian cell fate. In this article, after a general introduction to the LbL technique, we will focus on protein-based LbL films addressing different biomedical issues/domains, such as bacterial infection, blood contacting surfaces, mammalian cell adhesion, drug and gene delivery, and bone and neural tissue engineering. We do not consider biosensing applications or electrochemical aspects using specific proteins such as enzymes.

Recent Developments in Layer-by-Layer Assembly for Drug Delivery and Tissue Engineering Applications

Surfaces with biological functionalities are of great interest for biomaterials, tissue engineering, biophysics, and for controlling biological processes. The layer-by-layer (LbL) assembly is a highly versatile methodology introduced 30 years ago, which consists of assembling complementary polyelectrolytes or biomolecules in a stepwise manner to form thin self-assembled films. In view of its simplicity, compatibility with biological molecules, and adaptability to any kind of supporting material carrier, this technology has undergone major developments over the past decades. Specific applications have emerged in different biomedical fields owing to the possibility to load or immobilize biomolecules with preserved bioactivity, to use an extremely broad range of biomolecules and supporting carriers, and to modify the film's mechanical properties via crosslinking. In this review, the focus is on the recent developments regarding LbL films formed as 2D or 3D objects for applications in drug delivery and tissue engineering. Possible applications in the fields of vaccinology, 3D biomimetic tissue models, as well as bone and cardiovascular tissue engineering are highlighted. In addition, the most recent technological developments in the field of film construction, such as high-content liquid handling or machine learning, which are expected to open new perspectives in the future developments of LbL, are presented.

Peptide Hydrogels as Immunomaterials and Their Use in Cancer Immunotherapy Delivery

Peptide-based hydrogel biomaterials have emerged as an excellent strategy for immune system modulation. Peptide-based hydrogels are supramolecular materials that self-assemble into various nanostructures through various interactive forces (i.e., hydrogen bonding and hydrophobic interactions) and respond to microenvironmental stimuli (i.e., pH, temperature). While they have been reported in numerous biomedical applications, they have recently been deemed promising candidates to improve the efficacy of cancer immunotherapies and treatments. Immunotherapies seek to harness the body's immune system to preemptively protect against and treat various diseases, such as cancer. However, their low efficacy rates result in limited patient responses to treatment. Here, the immunomaterial's potential to improve these efficacy rates by either functioning as immune stimulators through direct immune system interactions and/or delivering a range of immune agents is highlighted. The chemical and physical properties of these peptide-based materials that lead to immuno modulation and how one may design a system to achieve desired immune responses in a controllable manner are discussed. Works in the literature that reports peptide hydrogels as adjuvant systems and for the delivery of immunotherapies are highlighted. Finally, the future trends and possible developments based on peptide hydrogels for cancer immunotherapy applications are discussed.

Preclinical in vitro evaluation of implantable materials: conventional approaches, new models and future directions

Nowadays, implants and prostheses are widely used to repair damaged tissues or to treat different diseases, but their use is associated with the risk of infection, inflammation and finally rejection. To address these issues, new antimicrobial and anti-inflammatory materials are being developed. Aforementioned materials require their thorough preclinical testing before clinical applications can be envisaged. Although many researchers are currently working on new in vitro tissues for drug screening and tissue replacement, in vitro models for evaluation of new biomaterials are just emerging and are extremely rare. In this context, there is an increased need for advanced in vitro models, which would best recapitulate the in vivo environment, limiting animal experimentation and adapted to the multitude of these materials. Here, we overview currently available preclinical methods and models for biological in vitro evaluation of new biomaterials. We describe several biological tests used in biocompatibility assessment, which is a primordial step in new material's development, and discuss existing challenges in this field. In the second part, the emphasis is made on the development of new 3D models and approaches for preclinical evaluation of biomaterials. The third part focuses on the main parameters to consider to achieve the optimal conditions for evaluating biocompatibility; we also overview differences in regulations across different geographical regions and regulatory systems. Finally, we discuss future directions for the development of innovative biomaterial-related assays: in silico models, dynamic testing models, complex multicellular and multiple organ systems, as well as patient-specific personalized testing approaches.

Analysis of the Frictional Performance of AW-5251 Aluminium Alloy Sheets Using the Random Forest Machine Learning Algorithm and Multilayer Perceptron

This paper is devoted to the determination of the coefficient of friction (COF) in the drawbead region in metal forming processes. As the test material, AW-5251 aluminium alloys sheets fabricated under various hardening conditions (AW-5251-O, AW-5251-H14, AW-5251-H16 and AW-5251H22) were used. The sheets were tested using a drawbead simulator with different countersample roughness and different orientations of the specimens in relation to the sheet rolling direction. A drawbead simulator was designed to model the friction conditions when the sheet metal passed through the drawbead in sheet metal forming. The experimental tests were carried out under conditions of dry friction and lubrication of the sheet metal surfaces with three lubricants: machine oil, hydraulic oil, and engine oil. Based on the results of the experimental tests, the value of the COF was determined. The Random Forest (RF) machine learning algorithm and artificial neural networks (ANNs) were used to identify the parameters affecting the COF. The R statistical package software version 4.1.0 was used for running the RF model and neural network. The relative importance of the inputs was analysed using 12 different activation functions in ANNs and nine different loss functions in the RF. Based on the experimental tests, it was concluded that the COF for samples cut along the sheet rolling direction was greater than for samples cut in the transverse direction. However, the COF's most relevant input was oil viscosity (0.59), followed by the average counter sample roughness Ra (0.30) and the yield stress Rp0.2 and strength coefficient K (0.05 and 0.06, respectively). The hard sigmoid activation function had the poorest R2 (0.25) and nRMSE (0.30). The ideal run was found after training and testing the RF model (R2 = 0.90 ± 0.028). Ra values greater than 1.1 and Rp0.2 values between 105 and 190 resulted in a decreased COF. The COF values dropped to 9-35 for viscosity and 105-190 for Rp0.2, with a gap between 110 and 130 when the oil viscosity was added. The COF was low when the oil viscosity was 9-35, and the Ra was 0.95-1.25. The interaction between K and the other inputs, which produces a relatively limited range of reduced COF values, was the least relevant. The COF was reduced by setting the Rp0.2 between 105 and 190, the Ra between 0.95 and 1.25, and the oil viscosity between 9 and 35.