Optimization Of Processing Research Articles

Recent Advances in Near‐β Titanium Alloys: Microstructure Control, Deformation Mechanisms, and Oxidation Behavior

Near‐β titanium alloys are used as promising structural materials for aerospace, biomedical, and other advanced applications due to their excellent combination of high specific strength and superior corrosion resistance. Precise control of the microstructure and mechanical properties through thermomechanical processing and heat treatment is paramount for exploiting the full potential of these alloys. This review article provides a comprehensive and critical assessment of the state‐of‐the‐art research on the microstructure evolution, deformation mechanisms, and oxidation behavior of near‐β titanium alloys. Furthermore, the challenges and emerging opportunities in the development of near‐β titanium alloys have also been identified, ranging from alloy design and processing optimization to multiscale characterization and integrated computational materials engineering. This review article provides a timely and comprehensive roadmap for the research and development of near‐β titanium alloys, paving the way for unlocking their full potential in critical industries.

Impact of morphology of hydrophilic and hydrophobic bentonites on improving the pour point in the recycling of waste cooking oils

Waste Cooking Oils (WCOs) are generated worldwide through industrial food processing and household use, posing environmental concerns upon disposal. Bentonites often showed to be effective in removing minor contaminants in vegetable oil refining. The present research focused on the processing of raw WCOs using four bentonites, two commercials and two obtained by ball milling of the latest. The different bentonites (hydrophobic and hydrophilic) were characterized before and after ball milling (BM) procedure, including an exhaustive analyses of crystal structure, morphology and surface area via x-ray diffraction (XRD), transmission electron microscopy (TEM), scanning electron microscopy (SEM), and N2-physisorption technique. Optimization of BM processing in terms of milling time was achieved within 60 min. The milled powders were then tested as adsorbents for recycling WCOs with different degrees of decomposition (expressed in terms of free fatty acids, FFAs, content). Employing a design of experiments approach, the impact of five parameters (FFAs content, temperature, specific surface area, stirring, BM time) on the resulting pour point (PP), taken as a quality benchmark for recycled oil, was assessed. Quantitative multivariate statistical analysis revealed temperature's negligible role and identified the significant impact of two characteristics of the bentonite (specific superficial area and ball milling time), as well as the relevant role of the stirring during the treatment. At the end, hydrophilic bentonite resulted able to improve the PP of waste oils with a low content of free fatty acids of about 10 °C.

An ecosystem of interconnected technologies to increase efficiencies in blood establishments: The example of the Blood and Tissue Bank of Aragón, Spain.

Blood establishments face environmental, financial, demographic and societal challenges that may impair sustainable blood supply to patients. This study presents the technologies (devices and software) assembled in a global ecosystem implemented by the Blood and Tissue Bank of Aragón (BTBA), Spain, over the last decade to overcome these challenges. Descriptive yearly activity data (2013-2023) of BTBA were retrospectively collected to evaluate the impact of different technologies on blood processing efficiency, focusing on the production of blood components (red blood cell concentrates [RCCs], platelet concentrates [PCs]) and plasma. Operator satisfaction about the technologies introduced in daily routine work was also monitored. Between 2013 and 2023, the annual production decreased by 16.0% for RCCs and increased by 13.3% for PCs. From 2020, all PCs were treated with pathogen reduction technology, and no inventory stock-out was reported. The lowest PC expiry rate (0.2%) was observed after the implementation of the software for blood processing and PC stock management. The deployment of this software also improved plasma recovery: on average, an extra plasma volume of 9 mL was collected per donation in 2023 compared to 2015. A survey confirmed staff satisfaction. The progressive implementation of automated and software-based solutions was key to increasing efficiencies in BTBA. This enabled the optimization of blood processing by maximizing productivity, enhancing traceability, reducing overproduction and wastage and increasing the yield of recovered plasma, while ensuring blood product safety and staff satisfaction.

Navigating the depths of refuse-derived fuel in Canada: From heterogeneity to insightful analysis

ABSTRACT Refuse-derived fuel (RDF) presents inherent heterogeneity, encompassing diverse physical and chemical compositions. This study aims to comprehensively investigate the thermogravimetric characteristics of key RDF fractions and compare them with RDF compositions from Canada and other countries. A representative RDF sample was obtained using three ASTM standard procedures, including the quartering technique, manual sorting, and laboratory preparation. Five major RDF fractions – cardboard (46%), mixed papers (17%), mixed plastics (19%), other organics (3%), and fines (13%) – were manually separated and subjected to cryogenic grinding for characterization analysis. Thermogravimetric characterization at 20°C/min in a nitrogen atmosphere, along with proximate/ultimate analysis and heating value measurements, revealed significant variability in decomposition behavior. DTG analysis showed that LDPE exhibited the highest thermal stability, which peaks at 483.6°C, whereas cardboard and mixed paper underwent single-step decomposition, peaks at 361.4°C, and 359.3°C, respectively. In contrast, mixed plastics, other organics, fines, and raw RDF displayed complex, multi-step decomposition behaviors, underscoring the heterogeneous nature of RDF and informing thermal processing optimization. The Canadian RDF sample showed notably higher cardboard 45% and fines content 13% compared to other studies from different countries averaged 25% cardboard, and 8% fines. Additionally, sorting a 2 kg representative sample required 5 man-hours per kilogram, highlighting the labor-intensive nature of the process.

Bilateral Defect Cutting Strategy for Sawn Timber Based on Artificial Intelligence Defect Detection Model.

Solid wood is renowned as a superior material for construction and furniture applications. However, characteristics such as dead knots, live knots, piths, and cracks are easily formed during timber's growth and processing stages. These features and defects significantly undermine the mechanical characteristics of sawn timber, rendering it unsuitable for specific applications. This study introduces BDCS-YOLO (Bilateral Defect Cutting Strategy based on You Only Look Once), an artificial intelligence bilateral sawing strategy to advance the automation of timber processing. Grounded on a dual-sided image acquisition platform, BDCS-YOLO achieves a commendable mean average feature detection precision of 0.94 when evaluated on a meticulously curated dataset comprising 450 images. Furthermore, a dual-side processing optimization module is deployed to enhance the accuracy of defect detection bounding boxes and establish refined processing coordinates. This innovative approach yields a notable 12.3% increase in the volume yield of sawn timber compared to present production, signifying a substantial leap toward efficiently utilizing solid wood resources in the lumber processing industry.

State of art on evaluation of three- to six-dimensional novel additive manufacturing technology for biomedical applications

Additive manufacturing has evolved over the last few decades. Three-dimensional printing is a digital manufacturing technology that provides nearly endless options for the creation of an accessible instrument for all parts of various medical practices, including tissue engineering, through meticulous optimization of material, processing, and geometry for every point in an object. Three-dimensional printing has opened up a new, faster, and safer manufacturing process, despite its incapability to fabricate complex structures and objects. Recently, novel four-dimensional printing techniques have been developed for the transformation of typical stable three-dimensional printed parts into smart objects. The limitations of three-dimensional printing could be remedied with four-dimensional printing, by applying time as the fourth dimension. Self-repairing and speedy printing are two additional benefits of this technology's by using smart materials. By adapting this technology, numerous medical domains could be profited. Four-dimensional printing does not have the ability to produce curved complicated forms. However, five-dimensional printing overcomes the flaws seems in four-dimensional printing. Five-dimensional additive manufacturing relies on the rotation of both the print bed and the extruder head. Five-dimensional printing outlasts in terms of durability than three- and four-dimensional printing. Currently, a combination of the principles of four- and five-dimensional printing into a single process is called six-dimensional printing. In six-dimensional printing, the form changes over time due to the reaction of environmental factors, which is primarily used in biomedical applications. This paper summarizes extensive research on biomaterials in the field of biomedical science and discusses the present implications of three-, four-, five-, and six-dimensional printing techniques.

Complex Scene Understanding and Object Detection Algorithm Assisted by Artificial Intelligence

The purpose of this paper is to study the algorithm of object detection and scene understanding in complex scenes assisted by AI(Artificial Intelligence), so as to improve the machine's perception of the surrounding environment. Aiming at occlusion and dense scenes, this paper proposes a series of innovative algorithms by introducing technologies such as multi-scale detection, occlusion processing and real-time optimization. Experimental results show that the proposed algorithm has achieved excellent performance on several public data sets. Compared with the current mainstream object detection algorithm -YOLO, the method proposed in this paper has a significant improvement in accuracy. Especially in multi-scale object detection, occlusion and dense scene processing and real-time optimization, the proposed algorithm shows obvious advantages. The research results provide an effective solution for object detection and scene understanding in complex scenes, and promote the application of AI system in related fields.

Improving mechanical and electrical properties of Cu-Ni-Si alloy via machine learning assisted optimization of two-stage aging processing

Recent studies have shown that synergistic precipitation of continuous precipitates (CPs) and discontinuous precipitates (DPs) is a promising method to simultaneously improve the strength and electrical conductivity of Cu-Ni-Si alloy. However, the complex relationship between precipitates and two-stage aging process presents a significant challenge for the optimization of process parameters. In this study, machine learning models were established based on orthogonal experiment to mine the relationship between two-stage aging parameters and properties of Cu-5.3Ni-1.3Si-0.12Nb alloy with preferred formation of DPs. Two-stage aging parameters of 400 °C/75 min + 400 °C/30 min were then obtained by multi-objective optimization combined with an experimental iteration strategy, resulting in a tensile strength of 875 MPa and a conductivity of 41.43 %IACS, respectively. Such an excellent comprehensive performance of the alloy is attributed to the combined precipitation of DPs and CPs (with a total volume fraction of 5.4% and a volume ratio of CPs to DPs of 6.7). This study could provide a new approach and insight for improving the comprehensive properties of the Cu-Ni-Si alloys.

Evaluating fine tuned deep learning models for real-time earthquake damage assessment with drone-based images

Earthquakes pose a significant threat to life and property worldwide. Rapid and accurate assessment of earthquake damage is crucial for effective disaster response efforts. This study investigates the feasibility of employing deep learning models for damage detection using drone imagery. We explore the adaptation of models like VGG16 for object detection through transfer learning and compare their performance to established object detection architectures like YOLOv8 (You Only Look Once) and Detectron2. Our evaluation, based on various metrics including mAP, mAP50, and recall, demonstrates the superior performance of YOLOv8 in detecting damaged buildings within drone imagery, particularly for cases with moderate bounding box overlap. This finding suggests its potential suitability for real-world applications due to the balance between accuracy and efficiency. Furthermore, to enhance real-world feasibility, we explore two strategies for enabling the simultaneous operation of multiple deep learning models for video processing: frame splitting and threading. In addition, we optimize model size and computational complexity to facilitate real-time processing on resource-constrained platforms, such as drones. This work contributes to the field of earthquake damage detection by (1) demonstrating the effectiveness of deep learning models, including adapted architectures, for damage detection from drone imagery, (2) highlighting the importance of evaluation metrics like mAP50 for tasks with moderate bounding box overlap requirements, and (3) proposing methods for ensemble model processing and model optimization to enhance real-world feasibility. The potential for real-time damage assessment using drone-based deep learning models offers significant advantages for disaster response by enabling rapid information gathering to support resource allocation, rescue efforts, and recovery operations in the aftermath of earthquakes.

Raman Spectroscopic Analysis of Steviol Glycosides: Spectral Database and Quality Control Algorithms

Besides all sharing an extraordinary high (i.e., up to ~450 times) sweetening power as compared to sucrose and while presenting strong similarities in their molecular structures, molecules belonging to the family of diterpene glycosides (i.e., the secondary metabolites of Stevia rebaudiana) differ in specific structural details that strongly impact on their levels of sweetness and bitter aftertaste. Given the nutritional and pharmacological benefits of steviol secondary metabolites as natural dietetic and anti-diabetic remedies, extraction and purification of steviol glycosides from plant material are nowadays widely spread among many countries. However, an unpleasant bitter aftertaste, which is linked to a genetic variation in human bitter taste receptors, hampers the full exploitation of such benefits and calls for a prompt improvement in organoleptic property control of stevia products. A deeper understanding of the molecular structure of different steviol glycosides and the consequent development of promptly measurable criteria for the organoleptic performance of their mixtures will support processing optimization and control of taste profiles within desired yields. The present research aimed at establishing Raman spectroscopic algorithms for quantitative characterizations of raw stevia-based sweetener products. First, a series of twelve high-purity diterpene glycosides were analyzed by high spectrally resolved Raman spectroscopy and their spectra analyzed in order to establish a complete Raman library of molecular structures. Then, quantitative spectroscopic parameters were built up and applied to characterize the organoleptic property of five different commercially available samples including the recently developed Rebaudioside M isoform. Raman spectroscopy was confirmed as a versatile analytical technique that could be used for quantitative quality control tasks on the production line and for prompt in situ characterizations of purchased products.

Artificial intelligence and machine learning applications for cultured meat.

Cultured meat has the potential to provide a complementary meat industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time-and resource-intensive research and development efforts. Machine learning has the potential to accelerate cultured meat technology by streamlining experiments, predicting optimal results, and reducing experimentation time and resources. However, the use of machine learning in cultured meat is in its infancy. This review covers the work available to date on the use of machine learning in cultured meat and explores future possibilities. We address four major areas of cultured meat research and development: establishing cell lines, cell culture media design, microscopy and image analysis, and bioprocessing and food processing optimization. In addition, we have included a survey of datasets relevant to CM research. This review aims to provide the foundation necessary for both cultured meat and machine learning scientists to identify research opportunities at the intersection between cultured meat and machine learning.

Postoperative rehabilitation after knee arthroplasty

Postoperative rehabilitation after knee arthroplasty plays adecisive role in restoring the function and mobility of the affected joint. However, there is still disagreement regarding the setting, structure and content of rehabilitation after knee arthroplasty, and the evidence on the individual measures is largely unclear. The aim of this article is to provide an evidence-based overview of the current status of rehabilitation after knee arthroplasty and to critically discuss the points that are still unclear. In view of the increasing prevalence of knee osteoarthritis and the rising number of knee endoprosthesis implantations, the optimization and scientific processing of postoperative rehabilitation is more important than ever in order to be able to offer scientifically sound, practice-oriented and cost-effective rehabilitation measures in the future. This review is based on asystematic literature search in Medline, Cochrane Library and Web of Science databases on the topic of postoperative rehabilitation after knee arthroplasty. Regarding specific treatment components, duration and frequency after knee arthroplasty, the evidence is unclear. Passive therapies should only be used supportive to active interventions. Educational programmes before and after knee arthroplasty can play acrucial role in outcome and patient satisfaction. Regular strength training should always be combined with centrally oriented components, such as motor imagery, to achieve better movement visualization and central anchoring. There is still afrequent lack of scientific evidence regarding individual therapeutic measures, their intensity, frequency, duration, exercise selection and their specific implementation in rehabilitation after knee arthroplasty. In the future, digital diagnostic and training tools will become established in both inpatient and outpatient therapy, supporting the urgently needed data collection for the scientific analysis of individual therapeutic measures.

Optimization of High-Pressure Processing for Microbial Inactivation in Pigmented Rice Grass Juice and Quality Impact Assessment during Refrigerated Storage.

Pigmented rice grass juice (RGJ) is a good source of bioactive compounds, but fresh juice has a relatively short shelf life of only 7 days at 4 °C. The objectives of this study were to determine the optimal growth stage of pigmented rice grass, investigate the optimal condition of high-pressure processing (HPP) for bacterial inactivation in inoculated RGJ using response surface methodology (RSM), and evaluate quality changes in uninoculated HPP-treated juice during storage at 4 °C compared with heat-treated (85 °C/10 min) and untreated samples. Results revealed that the optimal growth stage of rice grass was 9 days with the highest total anthocyanin content of 158.92 mg/L. The optimal condition of HPP was determined to be 612 MPa, 11 min, and 36 °C, and inactivated Escherichia coli K12 and Listeria innocua with 6.43 and 5.02 log reductions, respectively, meeting FDA regulations. The lethality of bacteria after HPP treatment can be explained by damage to the cell membrane and the leakage of intracellular constituents such as protein and nucleic acid. During 12 weeks of storage at 4 °C, total plate counts and yeast and mold counts in uninoculated HPP-treated juice were not detected. Moreover, HPP did not significantly change phytochemical properties (p < 0.05), caused a minor impact on physicochemical properties of RGJ, and maintained the durability of juice samples during storage. Analysis of the phytochemical profile revealed that HPP treatment could preserve most of the phenolic compounds in RGJ and especially increase the contents of protocatechuic acid, 4-hydroxybenzoic acid, syringic acid, transcinnamic acid, isorhamnetin-3-o-glucoside, quercetin, and cyanidin-3-glucoside (p < 0.05). Overall, HPP is a potential pasteurization technique for microbial inactivation and nutritional preservation for rice grass juice.

A review of the botany, metabolites, pharmacology, toxicity, industrial applications, and processing of Polygalae Radix: the "key medicine for nourishing life".

Polygalae radix (PR) is the dried root of Polygala tenuifolia Willd. and Polygala sibirica L. and enjoys the reputation as the "key medicine for nourishing life." In this study, information about "Polygala tenuifolia Willd.," "Polygala sibirica L.," and "Yuanzhi" was retrieved from scientific databases, including Google Scholar, Baidu Scholar, Web of Science, PubMed, CNKI, and Wan Fang Data. Information from Chinese herbal medicine classics, Yaozhi Data, and the Gaide Chemical Network was also collected. Information related to botany, phytochemistry, pharmacology, toxicity, industrial applications, and processing is summarized in this paper to tap its potentialities and promote its further development and clinical application. More than 320 metabolites have been isolated from PR; saponins, xanthones, and oligosaccharide esters are the main functional metabolites. Pharmacological research shows that its pharmacological action mainly focuses on resisting nervous system diseases, and it also has the functions of anti-oxidation, anti-inflammation, anti-tumor, anti-pathogenic microorganisms and others. The gastrointestinal irritation of its saponins impeded its application, but this irritation can be reduced by controlling the dosage, compatibility with other herbs, or processing. The future progress of PR faces opportunities and challenges. More attention should be paid to the traditional application and processing methods of PR recorded in ancient books. The lack of safety and clinical studies has limited its application and transformation of achievements. Moreover, it is one-sided to take the content of only a few metabolites as the index of processing optimization and quality control, which cannot reflect the full pharmacological and toxicological activities of PR.

Quantifying laser irradiation-induced temperature field of particle reinforced metal matrix composites

While particle-reinforced metal matrix composites (PMMCs) are composed of particles and matrix with distinctly different thermomechanical properties, the thermal differences and coupled interactions between individual phases greatly determine the thermal characteristics of PMMCs under laser irradiation. In this work, we quantify the temperature evolution characteristics within SiCp/Al under laser irradiation by microstructural thermal finite element simulations and experimental investigation. Specifically, a 2D thermophysical FE model of laser-SiCp/Al interaction for the two-phase PMMCs material under laser irradiation is developed, which incorporates the temperature-dependent thermophysical properties of particles, matrix and interfaces, along with the considerations of the shape and distribution characteristics of particles, as well as the comprehensive thermal conditions. Furthermore, a 3D equivalent thermal FE model for experimental validation of predicted laser-induced temperature of SiCp/Al is developed, based on the derived equivalent properties. Meanwhile, an in-situ temperature measurement system is constructed for exploring temperature evolution characteristics during the on-going laser irradiation process, which validates a derivation of 1.7 % of predicted temperature by the equivalent thermal FE model. Finally, the impact of laser processing parameters on the temperature field of SiCp/Al is addressed. These findings provide valuable insights for understanding the thermal mechanisms of PMMCs under laser irradiation, and also the parameter optimization for laser processing of PMMCs.

Control factor optimization for friction stir processing of AA8090/SiC surface composites

Friction Stir Processing is a state-of-the-art technology for microstructure refinement, material property enhancement, and surface composites fabrication. This investigation concentrates on AA8090/SiC surface composites produced via friction stir processing. Experiments were conducted by varying the following friction stir processing parameters: Tool rotational speed (800–1400 rpm), Tool traverse speed (25–75 mm/min), and Groove width (1.0–1.8 mm). Response measures encompassed Ultimate Tensile Strength and surface roughness. Central Composite Design of Response Surface Methodology designed the experiments and mathematical relationships established between input parameters and ultimate tensile strength and surface roughness. Analysis of variance was used to test the model's adequacy. The models examined individual and interaction effects of input factors on ultimate tensile strength and surface roughness of surface composites. A combinations of input parameters was identified that yields the maximum ultimate tensile strength and minimum surface roughness. The current work employs the friction stir processing approach to synthesis near-net-shaped surface composites without additional machining by systematically optimizing process parameters. Results indicate that increasing tool rotational speed produces well-finished AA8090/SiC surface composites with decreased strength. In contrast, increased tool traverse speed and groove width generate surface composites with rougher surfaces and higher strength. Surface and contour plots further explored the influence of parameter interactions on responses.

Study on the interstitial oxygen diffusion to understand the reduction of cryogenic RF loss for the superconducting radio-frequency niobium cavities

Abstract Medium-temperature baking (Mid-T baking) is an innovative method employed to enhance the unloaded quality factor Q0 of superconducting radio-frequency (SRF) niobium (Nb) cavities at cryogenic temperatures. This study presents an interstitial oxygen diffusion model based on the decomposition of the natural oxide to clarify the improved performance of the Nb cavities after undergoing Mid-T baking. Additionally, the correlation between the interstitial oxygen within the RF penetration depth and the surface resistance of the Nb cavities has been explored. The parameter for the oxide decomposition was determined using in-situ X-ray photoelectron spectroscopy (XPS), where the thickness of the oxide/carbide layer was calculated from the peak fitting of Nb 3d spectra and the attenuation law of the photoelectron beam. The interstitial oxygen diffusion model, validated by the semi-quantitative distribution along the depth determined by Time of Flight Secondary Ion Mass Spectrometry (ToF-SIMS), quantifies the oxygen atomic concentration within the RF penetration depth in Mid-T baked Nb material. In the baking temperature range of 300~400 ℃, the calculated oxygen concentration from the interstitial oxygen diffusion model demonstrates a more pronounced dependence on the baking temperature than the baking time. This suggests that more precise control of the interstitial oxygen concentration can be achieved by adjusting the baking temperature. Furthermore, it has been observed that maintaining a uniform and moderate oxygen concentration throughout the depth is essential for optimal BCS resistance. This study paves the way for more efficient processing optimization and enhancing understanding of the mechanism behind RF loss in Nb cavities.

Thin, Uniform, and Highly Packed Multifunctional Structural Carbon Fiber Composite Battery Lamina Informed by Solid Polymer Electrolyte Cure Kinetics.

Multifunctional structural batteries promise advancements in structural energy storage technologies by seamlessly integrating load-bearing and energy-storage functions within a single material, reducing weight, and enhancing safety. Yet, commercialization faces challenges in materials processing, assembly, and design optimization. Here, we report a systematic approach to develop a carbon fiber (CF)-based structural battery impregnated with epoxy-based solid polymer electrolyte (SPE) via robust vacuum-assisted compression molding (VACM). Informed by cure kinetics, SPE processing enhances the multifunctional performance with no fillers or additives. The thin flexible CF-based laminae impregnated under high pressure achieved a substantial enhancement of ∼160% in the fiber volume fraction (FVF) as although thin and strip-shaped, the fibers were optimally packed with low void. A CF/SPE-based battery was fabricated, with a hybrid layered ionic liquid (IL)/ carbonate electrolyte (CE) showing enhanced safety and multifunctional performance. Enhanced by thin, uniform, and stiff CF-based composites, this study propels the development of advanced multifunctional structures, thereby expediting sustainable commercialization.

Optimization of the automotive millimeter-wave radar data processing using the modified MFNN neural network

BACKGROUND: Recognition and representation of the road scene is a relevant task in the field of autonomous driving. One of the ways to improve the characteristics of the existing sensory hardware is the use of neural networks for signal processing. AIM: To conduct an experimental study of the possibilities of using the modified MFNN neural network to increase the resolution of a radar with a small number of channels, to compare it with the classical algorithm based on the fast Fourier transform (FFT), and, in addition, to compare the results with the data obtained from other types of sensors (lidars). METHODS: The algorithm of the road scene representation, in particular, the detection of pedestrians and cars, is used with a millimeter-range automotive radar and a method for determining data components in relation to the DOA problem, based on the MFNN neural network, modified for the case of representing signals taking complex values in the form of excessive basis coefficients minimizing these coefficients according to the L1 norm. The algorithm based on the fast Fourier transform (FFT) is used for comparative analysis. RESULTS: As a result of the conducted research, confirmation of the practical feasibility of the developed modifications of the MFNN method was obtained, and the advantage of using a neural network, consisting in increasing the degree of detail of objects, the accuracy of determining their shape and position using a radar with a small number of channels, was demonstrated. CONCLUSION: The obtained results can be used to develop solutions to improve the efficiency of detecting obstacles on the way of transport, automatic vehicle control, continuous environmental monitoring, and so on, which helps to improve the safety and efficiency of highly automated and autonomous systems.

DiSA-CF: A distance-integrated self-attention model for collaborative filtering in web service recommendation

The ubiquity of the Internet of Things (IoT) across diverse applications underscore its pivotal role in seamlessly integrating physical devices to facilitate efficient data collection, analysis, and automation. Consequently, ensuring the Quality of Service (QoS) emerges as a critical imperative. While numerous studies have proposed methodologies focusing on resource optimization, network management, and data processing techniques, several previous approaches to QoS prediction may face constraints in the Internet of Things (IoT) environment, where the dynamic nature of IoT environments demands predictive models capable of adapting to varying conditions. Integrating user and service location data into QoS prediction models is paramount, as it enables personalized service delivery tailored to the user’s specific context, thus enhancing the user experience and overall system performance. This paper presents a novel approach to QoS prediction in IoT, harnessing self-attention and collaborative filtering (CF) techniques while incorporating location-based features such as distance from the user to the service. Experimental evaluations on benchmark datasets reveal that our proposed model improves prediction accuracy by up to 7 % compared to existing methods, underscoring its efficacy in enhancing QoS provisioning in IoT environments.