Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (849)

Search Parameters:
Keywords = customer segmentation

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
30 pages, 28721 KB  
Article
Dual-Arm Robotic Textile Unfolding with Depth-Corrected Perception and Fold Resolution
by Tilla Egerhei Båserud, Joakim Johansen, Ajit Jha and Ilya Tyapin
Robotics 2026, 15(4), 78; https://doi.org/10.3390/robotics15040078 - 8 Apr 2026
Abstract
Reliable textile recycling requires automated unfolding to expose hidden hard components such as zippers, buttons, and metal fasteners, which otherwise risk damaging machinery and compromising downstream processes. This paper presents the design and implementation of an automated textile unfolding system based on a [...] Read more.
Reliable textile recycling requires automated unfolding to expose hidden hard components such as zippers, buttons, and metal fasteners, which otherwise risk damaging machinery and compromising downstream processes. This paper presents the design and implementation of an automated textile unfolding system based on a dual-arm robotic manipulation framework. The system uses two Interbotix WidowX 250s 6-DoF robotic arms and an Intel RealSense L515 LiDAR camera for visual perception. The unfolding process consists of three stages: initial dual-arm stretching to reduce major folds, refinement through a second stretch targeting the lower region, and a machine-learning stage that employs a YOLOv11 framework trained on depth-encoded textile images, followed by a depth-gradient-based estimator for fold direction. The system applies an extremity-based grasping strategy that selects leftmost and rightmost textile points from a custom error-corrected depth map, enabling robust grasp point selection, and a fold direction estimation method based on depth gradients around the detected fold. The most confident fold region is selected, an unfolding direction is determined using depth ranking, and the textile is manipulated until a flat state is confirmed through depth uniformity. Experiments show that depth correction significantly reduces spatial error in the robot frame, while segmentation and extremity detection achieve high accuracy across varied fold configurations, and the YOLOv11n-based model reaches 98.8% classification accuracy, while fold direction is estimated correctly in 87% of test cases. By enabling robust, largely autonomous textile unfolding, the system demonstrates a practical approach that could support safer and more efficient automated textile recycling workflows. Full article
(This article belongs to the Section Sensors and Control in Robotics)
Show Figures

Figure 1

35 pages, 4925 KB  
Article
Defect-Mask2Former: An Improved Semantic Segmentation Model for Precise Small-Sized Defect Detection on Large-Sized Timbers
by Mingming Qin, Hongxu Li, Yuxiang Huang, Xingyu Tong and Zhihong Liang
Sensors 2026, 26(7), 2254; https://doi.org/10.3390/s26072254 - 6 Apr 2026
Viewed by 38
Abstract
The precise segmentation of small-sized defects on wood surfaces is critical for the quality grading of glued laminated timber (GLT). Existing semantic segmentation models face core bottlenecks in this context: high miss rates, blurred boundary localization, and excessive size measurement errors. To address [...] Read more.
The precise segmentation of small-sized defects on wood surfaces is critical for the quality grading of glued laminated timber (GLT). Existing semantic segmentation models face core bottlenecks in this context: high miss rates, blurred boundary localization, and excessive size measurement errors. To address these issues, this paper proposes an improved Defect-Mask2Former model that integrates an Attention-Guided Pyramid Enhancement (AGPE) module and a Defect Boundary Calibration and Correction (DBCC) module. Through synergistic optimization, the model achieved pixel-level precise segmentation. To support model training and validation, a custom image acquisition device was designed, and the PlankDefSeg dataset was constructed, comprising 3500 pixel-level annotated images covering five defect types across six industrial wood species. Experimental results demonstrate that on the PlankDefSeg dataset, Defect-Mask2Former achieved a mean Intersection over Union (mIoU) of 85.34% for small-sized defects, a 17.84% improvement over the baseline Mask2Former. The miss rate was reduced from 20.78% to 5.83%, and the size measurement error was only 2.86%, strictly meeting the ≤3% accuracy requirement of the GB/T26899-2022 standard. The model achieved an inference speed of 27.6 FPS, satisfying real-time detection needs. By integrating the model into the GLT grading workflow, a grading accuracy of 94.3% was achieved, and the processing time per timber was reduced from 30 s to 1.5 s, a 20-fold efficiency improvement. This study provides reliable technical support for intelligent GLT quality grading and offers a reference solution for other industrial surface defect segmentation tasks. Full article
(This article belongs to the Section Smart Agriculture)
Show Figures

Figure 1

37 pages, 1919 KB  
Article
LLMs for Integrated Business Intelligence: A Big Data-Driven Framework Integrating Marketing Optimization, Financial Performance, and Audit Quality
by Leonidas Theodorakopoulos, Aristeidis Karras, Alexandra Theodoropoulou and Christos Klavdianos
Big Data Cogn. Comput. 2026, 10(4), 110; https://doi.org/10.3390/bdcc10040110 - 5 Apr 2026
Viewed by 163
Abstract
Enterprise decision making in marketing, finance, and audit remains fragmented, leading to inefficient budget allocation and incomplete risk assessment. This study proposes an integrated, Big Data-driven decision-support framework that unifies Large Language Models (LLMs), attention-based marketing mix modeling, and multi-agent, game-theoretic optimization to [...] Read more.
Enterprise decision making in marketing, finance, and audit remains fragmented, leading to inefficient budget allocation and incomplete risk assessment. This study proposes an integrated, Big Data-driven decision-support framework that unifies Large Language Models (LLMs), attention-based marketing mix modeling, and multi-agent, game-theoretic optimization to coordinate cross-functional decisions. The architecture combines five modules: LLM-enhanced customer segmentation and customer lifetime value prediction, attention-weighted marketing mix modeling, multi-agent LLM systems for hierarchical budget optimization, attention-informed Markov multi-touch attribution, and LLM-augmented audit quality assessment. Empirical validation on a large-scale e-commerce dataset with 2.8 million customers and USD 156 million in marketing expenditure shows that marketing return on investment increases from 4.2 to 6.78 (61.4% relative improvement), financial forecasting error (MAPE) decreases from 12.8% to 4.7% (63.3% reduction), fraud detection accuracy improves by 29.8%, the Audit Quality Index reaches 0.951, and customer lifetime value prediction accuracy improves from 76.4% to 91.3%. By operationalizing the convergence of LLMs, attention mechanisms, and game-theoretic reasoning within a unified and empirically validated framework, the study delivers both theoretical advances and practically deployable tools for integrated business intelligence in digital economies. Full article
(This article belongs to the Section Large Language Models and Embodied Intelligence)
Show Figures

Figure 1

28 pages, 7908 KB  
Article
PLYS-Longan: A Picking Point Localization Model for Longan in Natural Environments
by Yingyu Liao, Guogang Huang, Junlong Li, Xue Zhou, Chunyin Wu and Changyu Liu
Agriculture 2026, 16(7), 789; https://doi.org/10.3390/agriculture16070789 - 2 Apr 2026
Viewed by 189
Abstract
Longan is an important economic fruit in tropical and subtropical regions, whose harvesting primarily relies on manual labor. Automated longan harvesting is key to improving the industry’s economic benefits but faces core challenges: mature pericarp is highly similar in color to fruiting mother [...] Read more.
Longan is an important economic fruit in tropical and subtropical regions, whose harvesting primarily relies on manual labor. Automated longan harvesting is key to improving the industry’s economic benefits but faces core challenges: mature pericarp is highly similar in color to fruiting mother branches, plus dense branches and severe leaf occlusion, leading to difficult cluster detection and fruiting branch segmentation. Herein, we propose a picking point localization method named PLYS-Longan integrating three customized core modules: Dynamic Convolution, Convolutional Gated Linear Unit (CGLU), and Dynamic Hyperbolic Tangent Activation (DYT) are introduced into YOLongan module to enhance the model’s ability to detect longan clusters. For SELongan module, Depthwise Over-parameterized Convolution (DO-Conv) and Ultra-light Subspace Attention (ULSA) are adopted to improve main branch segmentation precision. The PCLongan module then performs morphological erosion on the segmentation masks and calculates centroids to precisely determine the picking points. Experimental results show that the improved model achieves a mAP@50 of 90.1% (3.3% higher than baseline model) in object detection and a mIoU of 77.24% (1.75% improvement) in semantic segmentation, outperforming the various model significantly. This study provides an efficient and robust solution for longan picking point localization, laying a solid foundation for subsequent automated harvesting. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

22 pages, 1479 KB  
Article
Gate Management in Free Port Context: A Case Study of the Port of Trieste
by Valentina Boschian, Caterina Caramuta, Alessia Grosso and Giovanni Longo
Sustainability 2026, 18(7), 3433; https://doi.org/10.3390/su18073433 - 1 Apr 2026
Viewed by 205
Abstract
Ports play a central role in global trade and act as key hubs for both maritime and land transport. Free ports, characterized by special customs regimes and fiscal advantages, represent a distinctive segment of this landscape. Despite their relevance, the literature on port [...] Read more.
Ports play a central role in global trade and act as key hubs for both maritime and land transport. Free ports, characterized by special customs regimes and fiscal advantages, represent a distinctive segment of this landscape. Despite their relevance, the literature on port gate management and on free ports has developed disconnected research streams, leaving the operational implications of special customs regimes largely unexplored. This study addresses this gap by investigating how gate procedures in free ports can be managed more efficiently, using the Port of Trieste as a case study. The analysis combines Business Process Model and Notation (BPMN) with discrete event simulation: BPMN served as the logical foundation for capturing the procedural complexity of free port gate operations, while simulation provided the quantitative framework for scenario evaluation. The model was calibrated on real gate access data and validated against observed vehicle volumes. Nine scenarios were evaluated, covering managerial, technological, infrastructural, and disruption-related interventions. The results show that no single measure produces significant improvements across all performance indicators and the integrated approaches consistently outperform standalone measures. Infrastructure interventions, while more costly, prove particularly valuable in improving port resilience under severe disruption conditions. Full article
(This article belongs to the Section Sustainable Transportation)
Show Figures

Figure 1

23 pages, 809 KB  
Article
Corporate Sustainability Systems Development Framework for Comfort Socks, Hosiery and Bodywear Textiles Production: Türkiye Case Study
by Saliha Karadayi-Usta
Sustainability 2026, 18(7), 3326; https://doi.org/10.3390/su18073326 - 30 Mar 2026
Viewed by 227
Abstract
The socks, hosiery, bodywear (SHB) industry is a critical segment of the textile sector, characterized by high-volume production and rapid delivery requirements, making efficiency and resource optimization essential. A corporate sustainability system is needed to minimize environmental impact, ensure long-term competitiveness, and align [...] Read more.
The socks, hosiery, bodywear (SHB) industry is a critical segment of the textile sector, characterized by high-volume production and rapid delivery requirements, making efficiency and resource optimization essential. A corporate sustainability system is needed to minimize environmental impact, ensure long-term competitiveness, and align operations with global sustainability standards. Thus, this research aims to propose an integrated Corporate Sustainability System (CSS) framework that synergizes Lean Manufacturing (LM), Digital Transformation (DT), and sustainability transition through a methodological triangulation of (1) a narrative review, (2) in-depth expert interviews, and (3) a comprehensive Turkish case study. The proposed framework integrates foundational lean principles such as 5S, TPM, and Value Stream Mapping with Industry 4.0 technologies, including RFID traceability, real-time ERP integration and machine vision systems. Empirical demonstration through the case study reveals that establishing foundational lean maturity is a critical foundation for successful digital adoption. Furthermore, the study demonstrates that transitioning from manual tracking to integrated digital platforms resolves data silos and enhances the transparency of customer revisions and warehouse accuracy. The framework also incorporates human-centric Lean 5.0 improvements, proving that ergonomic interventions such as rail-mounted cable systems are vital for operational sustainability. Ultimately, the CSS provides a scalable model that aligns SHB production with global mandates like the EU Green Deal and CBAM, positioning the sector for long-term competitive advantage in an increasingly eco-conscious global market. Full article
(This article belongs to the Special Issue Sustainable Manufacturing Systems in the Context of Industry 4.0)
Show Figures

Figure 1

27 pages, 7774 KB  
Article
From Ethnobotanical Resource to Functional Food: Research Trends, Value Networks, and Market Prospects of Brosimum alicastrum Swartz in Mexico
by Javier E. Vera-López, Alberto Santillán-Fernández, Arely del R. Ireta-Paredes, Iban Vázquez-González, Alfredo E. Tadeo-Noble, Guillermo García-García and Jaime Bautista-Ortega
Forests 2026, 17(4), 433; https://doi.org/10.3390/f17040433 - 29 Mar 2026
Viewed by 276
Abstract
Brosimum alicastrum Swartz is a forest species with substantial potential for animal and human nutrition. However, its nutritional attributes and commercial applications are poorly disseminated and structurally underdeveloped. This study examines the relationship between scientific research and the commercialization of Brosimum alicastrum products [...] Read more.
Brosimum alicastrum Swartz is a forest species with substantial potential for animal and human nutrition. However, its nutritional attributes and commercial applications are poorly disseminated and structurally underdeveloped. This study examines the relationship between scientific research and the commercialization of Brosimum alicastrum products in Mexico, integrating bibliometric analysis with a value network approach to identify market constraints and opportunities. Scientific publications indexed in Scopus from 1961 to 2024 were analyzed to characterize research trends, documented uses, and the geographic distribution of knowledge production. In parallel, companies commercializing Brosimum alicastrum-based products in Mexico were surveyed during 2024 using a value network approach (suppliers, customers, complementors, and competitors). A SWOT analysis was conducted to assess the structural strengths and vulnerabilities affecting market development. The results show that research in Mexico has primarily focused on the species’ properties as a functional food. At the same time, limited attention has been given to silviculture, commercialization strategies, and value-chain governance. Although Brosimum alicastrum products are currently positioned within premium market segments, business continuity is constrained by unstable supply systems that rely almost exclusively on seasonal wild collection from natural distribution areas. Both the value network and the SWOT analysis identified supply instability as the main factor limiting market expansion. Therefore, advancing research on the silviculture of Brosimum alicastrum is essential to support the establishment of managed production systems and commercial plantations capable of ensuring a stable, year-round supply of raw material. These developments would facilitate access to new market niches and enhance the biocultural and ethnobotanical value of Brosimum alicastrum as a functional and medicinal food resource within Mexico’s emerging bioeconomy. Full article
Show Figures

Figure 1

16 pages, 5371 KB  
Article
Histological Study of a Novel 3D-Printed Hydroxyapatite/PLGA Bone Graft in the Regeneration of Critical-Sized Long Bone Defects
by Marijana Popović Bajić, Smiljana Paraš, Milutin Mićić, Božana Petrović, Vladimir Biočanin, Slavoljub Živković, Marija Živković, Damjana Drobne and Vukoman Jokanović
Bioengineering 2026, 13(4), 394; https://doi.org/10.3390/bioengineering13040394 - 28 Mar 2026
Viewed by 418
Abstract
Critical-sized bone defects pose significant challenges in orthopedic surgery. The introduction of 3D printing technology in bone grafting offers a promising solution by creating customized grafts that mimic the natural bone structure. This study aimed to reconstruct long-segment bone defects in the rabbit [...] Read more.
Critical-sized bone defects pose significant challenges in orthopedic surgery. The introduction of 3D printing technology in bone grafting offers a promising solution by creating customized grafts that mimic the natural bone structure. This study aimed to reconstruct long-segment bone defects in the rabbit radius using a 3D-printed material composed of hydroxyapatite (HAP) and poly(lactide-co-glycolide) (PLGA), referred to as ALBO-OS, and to evaluate its potential to support bone healing without the use of stem cells or growth factors. Six rabbits underwent computed tomography scanning to create patient-specific 3D models of the radius. Custom-designed ALBO-OS implants were 3D-printed and used to fill segmental defects corresponding to one-third of the bone length in each rabbit, created by osteotomy. Over a 12-week observation period, graft integration, osteointegration, and overall bone regeneration were assessed through histological and histomorphometric analyses. The implanted scaffolds demonstrated encouraging bone healing, with significant bone regeneration observed within the defect areas. Histological evaluation revealed significant new bone formation and vascularization, with minimal inflammatory response. The findings demonstrated the potential of 3D-printed HAP/PLGA-based materials as a promising strategy for the reconstruction of large bone defects, eliminating the need for exogenous biological agents. Full article
Show Figures

Figure 1

20 pages, 1938 KB  
Article
Interpretable Photoplethysmography Feature Engineering for Multi-Class Blood Pressure Staging
by Souhair Msokar, Roman Davydov and Vadim Davydov
Computers 2026, 15(4), 209; https://doi.org/10.3390/computers15040209 - 27 Mar 2026
Viewed by 255
Abstract
Hypertension is a leading global health risk and requires accurate and continuous monitoring for effective management. Although photoplethysmography (PPG) is a promising non-invasive modality for cuffless blood pressure (BP) assessment, many existing approaches (especially raw-signal deep learning) are vulnerable to data leakage, overfitting [...] Read more.
Hypertension is a leading global health risk and requires accurate and continuous monitoring for effective management. Although photoplethysmography (PPG) is a promising non-invasive modality for cuffless blood pressure (BP) assessment, many existing approaches (especially raw-signal deep learning) are vulnerable to data leakage, overfitting on small datasets, limited interpretability, and poor performance on minority BP stages. To address these limitations, we propose a robust and physiologically grounded framework for multi-class BP stage classification based on interpretable PPG features. Our approach centers on a comprehensive multi-domain feature engineering pipeline that extracts 124 PPG features, including demographic, morphological, functional decomposition, spectral, nonlinear dynamics, and clinical composite indices. We apply rigorous preprocessing and feature selection prior to model training. We validate the framework on two datasets: PPG-BP dataset (657 segments, 4 classes) for benchmarking and PulseDB (283,773 segments, 3 classes) to assess scalability. We evaluate the proposed framework using a segment-level train/test split, appropriate for assessing intra-subject BP tracking after initial personalization. For the PulseDB dataset, this follows the protocol established by the dataset creators, while for the PPG-BP dataset, it enables direct comparison with prior work given practical dataset constraints. On PPG-BP, LightGBM trained on the selected features achieved macro-F1 = 0.78 and accuracy = 0.74, outperforming comparable deep-learning models. On the PulseDB, a custom Residual MLP achieved accuracy = 0.81 and macro-F1 = 0.79, supporting generalization at scale. These results show that the proposed feature-based approach can outperform complex end-to-end deep-learning models on small datasets while providing improved interpretability. This work establishes a reliable and transparent pathway toward clinically viable continuous BP staging, moving beyond black-box models toward physiologically grounded decision support. Ablation analysis reveals that engineered features provide most of the predictive power (F1 = 0.911), while raw PPG features alone achieve modest performance (F1 = 0.384). For the minority hypertension stage 2 (HT-2) class, a bootstrap 95% confidence interval of [0.762, 1.000] is reported, reflecting uncertainty due to limited sample size. Full article
Show Figures

Graphical abstract

23 pages, 320 KB  
Article
Distributed Teaching Agency–AI in the University: A Typology Based on Student Voice
by Tomás Fontaines-Ruiz, Antonio Ponce-Rojo, Paolo Fabre Merchán, Walther Casimiro Urcos and Liliana Cánquiz Rincón
Multimodal Technol. Interact. 2026, 10(4), 34; https://doi.org/10.3390/mti10040034 - 27 Mar 2026
Viewed by 293
Abstract
Generative AI is reshaping university teaching and creating tension around authority, evidence, and accountability when decisions are made using algorithms. From a student perspective, this study constructed a typology of distributed teacher–AI agency (TAI) and examined the discursive mechanisms that produce the illusion [...] Read more.
Generative AI is reshaping university teaching and creating tension around authority, evidence, and accountability when decisions are made using algorithms. From a student perspective, this study constructed a typology of distributed teacher–AI agency (TAI) and examined the discursive mechanisms that produce the illusion of teacher autonomy. A non-experimental, cross-sectional, explanatory study was conducted: a lexicometric analysis of the ALCESTE (IRAMUTEQ) questionnaire, using open-ended responses from 3120 students (Mexico, n = 2051; Ecuador, n = 1069), segmented into 1077 units, and analyzed using positioning theory. Co-agency was operationalized using Teacher Agency (A), Delegation to AI (D), Governance (G: disclosure, criteria, verification), and the Illusion Index (II = A/(D + G + 1)). Three configurations emerged: Immediate Customizer (28.8%) with very high A and minimal D/G (II = 25.4); Technological Literacy Facilitator (27.3%) with visible delegation and safeguards (II ≈ 2.0); and Operational Optimizer (43.9%) oriented toward accelerating tasks with moderate governance (II ≈ 2.7). The illusion was associated with the agentive erasure of AI and a rhetoric of immediacy/efficiency that replaced verifiable criteria. These findings transform the student voice into a criteria-based diagnostic tool for strengthening traceability, minimal verification, and responsible orchestration of AI in higher education. Full article
22 pages, 4435 KB  
Article
Semantic Mapping in Public Indoor Environments Using Improved Instance Segmentation and Continuous-Frame Dynamic Constraint
by Yumin Lu, Xueyu Feng, Zonghuan Guo, Jianchao Wang, Lin Zhou and Yingcheng Lin
Electronics 2026, 15(7), 1392; https://doi.org/10.3390/electronics15071392 - 26 Mar 2026
Viewed by 312
Abstract
Reliable semantic perception is crucial for service robots operating in complex public indoor environments. However, existing semantic mapping approaches often face the dual challenges of high computational overhead and semantic redundancy in maps. To address these limitations, this paper proposes a low-resource semantic [...] Read more.
Reliable semantic perception is crucial for service robots operating in complex public indoor environments. However, existing semantic mapping approaches often face the dual challenges of high computational overhead and semantic redundancy in maps. To address these limitations, this paper proposes a low-resource semantic mapping framework based on improved instance segmentation and dynamic constraints from consecutive frames. First, we design the lightweight model MS-YOLO, which adopts MobileNetV4 as its backbone network and incorporates the SHViT neck module, effectively optimizing the balance between detection accuracy and computational cost. Second, we propose a consecutive frame dynamic constraint method that eliminates redundant object annotations through consecutive frame stability verification. Experimental results relating to both fusion and custom datasets demonstrate that compared to YOLOv8n-seg, MS-YOLO achieves improvements in accuracy, recall, and mAP@0.5, while reducing the number of parameters by 11.7% and floating-point operations (FLOPs) by 32.2%. Furthermore, compared to YOLOv11n-seg and YOLOv5n-seg, its FLOPs are reduced by 17.2% and 25.5%, respectively. Finally, the successful deployment and field validation of this system on the Jetson Orin NX platform demonstrate its real-time capability and engineering practicality for edge computing in public indoor service robots. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

36 pages, 1048 KB  
Review
Patient-Specific 3D-Printed Porous Metal Implants in Orthopedics: A Narrative Review of Current Applications and Future Prospects
by Connor P. McCloskey, Anoop Sunkara, Siddhartha Kalala, Jack T. Peterson, Michael O. Sohn, Austin R. Chen, Arun K. Movva and Albert T. Anastasio
Appl. Sci. 2026, 16(7), 3192; https://doi.org/10.3390/app16073192 - 26 Mar 2026
Viewed by 306
Abstract
Atypical joint spaces, such as those encountered in complex segmental bone loss and large structural defects, remain challenging to manage with conventional implants within divisions across orthopedics, including arthroplasty, tumor reconstruction, trauma, and spine. Additive manufacturing advances have made patient-specific implants a possibility, [...] Read more.
Atypical joint spaces, such as those encountered in complex segmental bone loss and large structural defects, remain challenging to manage with conventional implants within divisions across orthopedics, including arthroplasty, tumor reconstruction, trauma, and spine. Additive manufacturing advances have made patient-specific implants a possibility, and this promising solution has enabled the creation of implants with customized geometry and controlled surface porosity to enhance osseointegration, reduce rejection rates, optimize biomechanics, and promote longevity. Despite its potential, patient-specific implants are still eclipsed in use by conventional, “off-the-shelf” implants due to their lower cost, documented long-term durability, insurance coverage, and the strength of available clinical evidence supporting their use. This narrative review summarizes current materials and manufacturing approaches for additively manufactured metal porous implants, including imaging and design workflows, lattice and pore architecture, and how the printing process influences implant stiffness, fatigue strength, surface roughness, and porosity. We also discuss the experimental and preclinical data on mechanical performance, fatigue resistance, and osseointegration for new developments in the field. Emerging trends such as material innovation, streamlined digital planning-to-implant workflows, 4D printing and other advanced additive manufacturing concepts, and cost-reduction efforts are examined in the context of clinical practicality. In this review, the integration of engineering principles with early clinical outcomes will provide orthopedic surgeons with a realistic understanding of the benefits and limitations of the future utilization of additive manufacturing in clinical practice. Full article
Show Figures

Figure 1

26 pages, 3329 KB  
Article
Multi-Class Weed Quantification Based on U-Net Convolutional Neural Networks Using UAV Imagery
by Lucía Sandoval-Pillajo, Marco Pusdá-Chulde, Jorge Pazos-Morillo, Pedro Granda-Gudiño and Iván García-Santillán
Appl. Sci. 2026, 16(7), 3149; https://doi.org/10.3390/app16073149 - 25 Mar 2026
Viewed by 561
Abstract
Weed identification and quantification are processes that are usually manual, subjective, and error-prone. Weeds compete with crops for nutrients, minerals, physical space, sunlight, and water. Thus, weed identification is a crucial component of precision agriculture for autonomous removal and site-specific treatments, efficient weed [...] Read more.
Weed identification and quantification are processes that are usually manual, subjective, and error-prone. Weeds compete with crops for nutrients, minerals, physical space, sunlight, and water. Thus, weed identification is a crucial component of precision agriculture for autonomous removal and site-specific treatments, efficient weed control, and sustainability. Convolutional Neural Networks (CNNs) are very common in weed identification. This work implemented CNN models for semantic segmentation based on the U-Net architecture for automatically segmenting and quantifying weeds in potato crops using RGB images acquired by a drone at 9–10 m height, flying at 1 m/s. Remote sensing images are affected by factors that degrade image quality and the model’s accuracy. Five U-Net variants were evaluated: the original U-Net, Residual U-Net, Double U-Net, Modified U-Net, and AU-Net. The models were trained using the TensorFlow/Keras frameworks on Google Colab Pro+, following the Knowledge Discovery in Databases (KDD) methodology for image analysis. Each model was trained using a diverse custom dataset in uncontrolled environments, considering six classes: background, Broadleaf dock (Rumex obtusifolius), Dandelion (Taraxacum officinale), Kikuyu grass (Cenchrus clandestinum), other weed species, and the crop potato (Solanum tuberosum L.). The models’ segmentation was widely assessed using Mean Dice Coefficient, Mean IoU, and Dice Loss metrics. The results showed that the Residual U-Net model performed the best in multi-class segmentation, achieving a Mean IoU of 0.8021, a performance comparable to or superior to that reported by other authors. Additionally, a Student’s t-test was applied to complement the data analysis, suggesting that the model is reliable for weed quantification. Full article
(This article belongs to the Collection Agriculture 4.0: From Precision Agriculture to Smart Agriculture)
Show Figures

Figure 1

23 pages, 7102 KB  
Article
Detection of Uniform Corrosion in Steel Pipes Using a Mobile Artificial Vision System
by Rafael Antonio Rodríguez Ospino, Cristhian Manuel Durán Acevedo and Jeniffer Katerine Carrillo Gómez
Corros. Mater. Degrad. 2026, 7(1), 21; https://doi.org/10.3390/cmd7010021 - 20 Mar 2026
Viewed by 315
Abstract
Corrosion in steel pipelines can cause critical failures in industrial systems, while conventional inspection methods such as radiography and ultrasonic testing are costly and require specialized personnel. This study presents a mobile computer vision system for automated corrosion detection inside steel pipes using [...] Read more.
Corrosion in steel pipelines can cause critical failures in industrial systems, while conventional inspection methods such as radiography and ultrasonic testing are costly and require specialized personnel. This study presents a mobile computer vision system for automated corrosion detection inside steel pipes using deep learning-based visual analysis. The proposed system consists of a Raspberry Pi 4-based mobile robot equipped with a high-resolution camera for internal inspection. Acquired images were processed using color-space transformations (RGB–HSV), filtering, and segmentation. Convolutional neural networks and semantic segmentation models, including YOLOv8-seg (Instance segmentation) and DeepLabV3 (Semantic segmentation), were trained on a custom corrosion image dataset to identify corroded regions. Real-time visualization was implemented via Flask-based video streaming. Experimental results demonstrated high detection accuracy for uniform corrosion, achieving a mean Intersection over Union (mIoU) above 0.98 and a precision of 0.99 with the YOLOv8-seg model. These results indicate that the proposed system enables reliable and automated corrosion inspection, with the potential to reduce inspection costs and improve operational efficiency. Future work will focus on enhancing real-time performance through hardware optimization. Full article
Show Figures

Figure 1

25 pages, 2773 KB  
Article
A Segmented Machine Learning Approach to Predicting and Mitigating Churn in the Gig Economy
by Saranya Shanmugam, Einiyaselvi Elavarasan, Narassima Madhavarao Seshadri, Dharun Ashokkumar, Santhoshkumar Senthilkumar and Thenarasu Mohanavelu
J. Theor. Appl. Electron. Commer. Res. 2026, 21(3), 93; https://doi.org/10.3390/jtaer21030093 - 19 Mar 2026
Viewed by 330
Abstract
The highly competitive nature of the online food delivery (OFD) market faces a serious retention problem, with acquiring new users typically being much more expensive than retaining existing users. Traditional prediction methods that rely primarily upon static transactional metrics such as recency and [...] Read more.
The highly competitive nature of the online food delivery (OFD) market faces a serious retention problem, with acquiring new users typically being much more expensive than retaining existing users. Traditional prediction methods that rely primarily upon static transactional metrics such as recency and frequency are often unable to capture the psychological ‘disconfirmation’ which occurs prior to churn. To fill this gap, this study proposes a framework based on Expectation-Confirmation Theory (ECT). Unsupervised K-Means clustering was employed to classify a simulated and filtered dataset with 1500 customer records containing behaviour, geography, etc. This framework also couples sentiment analysis from BERT, allowing it to identify psychological “silent” attrition. Heterogeneous cohorts, which exhibit different psychological antecedents (utilitarian versus hedonic), were identified. The empirical results of our analyses demonstrated that Random Forest Classifiers with segment-specific features outperform baseline transactional models (F1 = 0.76) with an F1 Score of 0.89. The visual analytic interface developed provides a holistic view of the consumption process than traditional prediction models, including prescriptive, automated segment-based mitigation strategies. Our findings contradict the assumption that the “frequency–loyalty” model applies to all users. High-frequency discretionary users are found to be elastic in terms of retention and will experience significant churn. By utilising the automated action log, managers can plan targeted, highly efficient retention strategies rather than blanket discounting approaches. Full article
(This article belongs to the Section Data Science, AI, and e-Commerce Analytics)
Show Figures

Figure 1

Back to TopTop