Search Results (23,976)

Knee arthroplasty, commonly performed to treat osteoarthritis, necessitates precise surgical techniques for optimal outcomes. The introduction of systems such as the Persona Knee System (Zimmer Biomet, Warsaw, IN, USA) has revolutionized knee arthroplasty, promising enhanced precision and better patient outcomes. This study investigates the application of robotic planning specifically in knee prosthetic surgeries, with a focus on Persona Knee System prostheses. We conducted a retrospective analysis of 300 patients who underwent knee arthroplasty using the Persona Knee System between January 2020 and November 2023, including demographic data, surgical parameters, and preoperative imaging. Robotic planning was employed to simulate surgical procedures. The planning process integrated preoperative imaging data from a specific program adopted for conducting digital preoperative planning, and statistical analyses were conducted to assess correlations between patient characteristics and surgical outcomes. Out of 300 patients, 85% presented with minor deformities, validating the feasibility of robotic planning. Robotic planning demonstrated precise prediction of optimal arthroplasty sizes and alignment, closely aligning with preoperative imaging data. This study highlights the potential benefits of robotic planning in knee arthroplasty surgeries, particularly in cases with minor deformities. By leveraging preoperative imaging data and integrating advanced robotic technologies, surgeons can improve precision and efficacy in knee arthroplasty. Moreover, robotic technology allows for a reduced level of constraint in the intraoperative choice between Posterior-Stabilized and Constrained Posterior-Stabilized liners compared with an imageless navigated procedure. Full article

The air void system in concrete significantly affects its mechanical, thermal, and frost durability properties. This study explored the use of ChatGPT, an AI tool, to generate Python code for analyzing air void parameters in hardened concrete, such as total air void content (A), specific surface (α), and air void spacing factor (L). Initially, Python scripts were created by requesting ChatGPT-3.5 to convert MATLAB scripts developed by Fonseca and Scherer in 2015. The results from Python closely matched those from MATLAB when applied to polished sections of seven different concrete mixes, demonstrating ChatGPT’s effectiveness in code conversion. However, generating accurate code without referencing the original MATLAB scripts required detailed prompts, highlighting the need for a strong understanding of the test method. Finally, a Python script was applied to modify void reconstruction in 2D images into 3D by stereology, and comparing this with (3D) CT scanner results, showing comparable results. Full article

The Internet of Things (IoT) has emerged as a popular topic in both industrial and academic research. IoT devices are often equipped with rapid response capabilities to ensure seamless communication and interoperability, showing significant potential for IoT-based maritime traffic monitoring and navigation safety tasks. However, this also presents major challenges for maritime surveillance systems. The diversity of IoT devices and variability in collected data are substantial. Visual image ship detection is crucial for maritime tasks, yet it must contend with environmental challenges such as haze and waves that can obscure ship details. To address these challenges, we propose an adaptive query selection transformer (AQSFormer) that utilizes two-dimensional rotational position encoding for absolute positioning and integrates relative positions into the self-attention mechanism to overcome insensitivity to the position. Additionally, the introduced deformable attention module focuses on ship edges, enhancing the feature space resolution. The adaptive query selection module ensures a high recall rate and a high end-to-end processing efficiency. Our method improves the mean average precision to 0.779 and achieves a processing speed of 31.3 frames per second, significantly enhancing both the real-time capabilities and accuracy, proving its effectiveness in ship detection. Full article

Artificial Intelligence (AI) is poised to revolutionize numerous aspects of human life, with healthcare among the most critical fields set to benefit from this transformation. Medicine remains one of the most challenging, expensive, and impactful sectors, with challenges such as information retrieval, data organization, diagnostic accuracy, and cost reduction. AI is uniquely suited to address these challenges, ultimately improving the quality of life and reducing healthcare costs for patients worldwide. Despite its potential, the adoption of AI in healthcare has been slower compared to other industries, highlighting the need to understand the specific obstacles hindering its progress. This review identifies the current shortcomings of AI in healthcare and explores its possibilities, realities, and frontiers to provide a roadmap for future advancements. Full article

This paper presents an energy optimization approach to applying electrical impedance tomography (EIT) for medical diagnostics, particularly in detecting lung diseases. The designed Lung Electrical Tomography System (LETS) incorporates 102 electrodes and advanced image reconstruction algorithms. Energy efficiency is achieved through the use of modern electronic components and high-efficiency DC/DC converters that reduce the size and weight of the device without the need for additional cooling. Special attention is given to minimizing energy consumption during electromagnetic measurements and data processing, significantly improving the system’s overall performance. Research studies confirm the device’s high energy efficiency while maintaining the accuracy of the classification of lung disease using the LightGBM algorithm. This solution enables long-term patient monitoring and precise diagnosis with reduced energy consumption, marking a key step towards sustainable medical diagnostics based on EIT technology. Full article

As a crucial stage in the processing of black tea, rolling plays a significant role in both the color transformation and the quality development of the tea. In this process, the production of theaflavins, thearubigins, and theabrownins is a primary factor contributing to the alteration in color of rolled leaves. Herein, tea pigments are selected as the key quality indicators during rolling of black tea, aiming to establish rapid detection methods for them. A machine vision system is employed to extract nine color feature variables from the images of samples subjected to varying rolling times. Then, the tea pigment content in the corresponding samples is determined using a UV-visible spectrophotometer. In the meantime, the correlation between color variables and tea pigments is discussed. Additionally, Z-score and PCA are used to eliminate the magnitude difference and redundant information in original data. Finally, the quantitative prediction models of tea pigments based on the images’ color features are established by using PLSR, SVR, and ELM. The data show that the Z-score–PCA–ELM model has the best prediction effect for tea pigments. The Rp values for the model prediction sets are all over 0.96, and the RPD values are all greater than 3.50. In this study, rapid determination methods for tea pigments during rolling of black tea are established. These methods offer significant technical support for the digital production of black tea. Full article

This article explores the challenges of integrating two deep learning neural networks, YOLOv5 and RT-DETR, to enhance the recognition of unmanned aerial vehicles (UAVs) within the optical-electronic channels of Sensor Fusion systems. The authors conducted an experimental study to test YOLOv5 and Faster RT-DETR in order to identify the average accuracy of UAV recognition. A dataset in the form of images of two classes of objects, UAVs, and birds, was prepared in advance. The total number of images, including augmentation, amounted to 6337. The authors implemented training, verification, and testing of the neural networks exploiting PyCharm 2024 IDE. Inference testing was conducted using six videos with UAV flights. On all test videos, RT-DETR-R50 was more accurate by an average of 18.7% in terms of average classification accuracy (Pc). In terms of operating speed, YOLOv5 was 3.4 ms more efficient. It has been established that the use of RT-DETR as the only module for UAV classification in optical-electronic detection channels is not effective due to the large volumes of calculations, which is due to the relatively large number of parameters. Based on the obtained results, an algorithm for combining two neural networks is proposed, which allows for increasing the accuracy of UAV and bird classification without significant losses in speed. Full article

This review provides an in-depth analysis of current hardware acceleration approaches for image processing and neural network inference, focusing on key operations involved in these applications and the hardware platforms used to deploy them. We examine various solutions, including traditional CPU–GPU systems, custom ASIC designs, and FPGA implementations, while also considering emerging low-power, resource-constrained devices. Full article

Central Nervous System (CNS) tumors represent a significant public health concern due to their high morbidity and mortality rates. Magnetic Resonance Imaging (MRI) has emerged as a critical non-invasive modality for the detection, diagnosis, and management of brain tumors, offering high-resolution visualization of anatomical structures. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), have shown potential in augmenting MRI-based diagnostic accuracy for brain tumor detection. In this study, we evaluate the diagnostic performance of six fundamental MRI sequences in detecting tumor-involved brain slices using four distinct CNN architectures enhanced with transfer learning techniques. Our dataset comprises 1646 MRI slices from the examinations of 62 patients, encompassing both tumor-bearing and normal findings. With our approach, we achieved a classification accuracy of 98.6%, underscoring the high potential of CNN-based models in this context. Additionally, we assessed the performance of each MRI sequence across the different CNN models, identifying optimal combinations of MRI modalities and neural networks to meet radiologists’ screening requirements effectively. This study offers critical insights into the integration of deep learning with MRI for brain tumor detection, with implications for improving diagnostic workflows in clinical settings. Full article

This paper presents a method for detecting holes and grooves made by wood-boring pests. As part of the production process automation, wood delivered from sawmills is checked for defects visible on its surface. One of the critical defects that disqualifies wood from further processing is the presence of feeding marks left by various types of pests on its surface. This paper proposes a method for detecting this type of damage based on analysis of three-dimensional images of the wood surface. Three-dimensional imaging methods and the image resolutions resulting from the adopted imaging system’s configurations are discussed. An analysis of the advantages and disadvantages of the methods investigated is presented, together with an assessment of their potential use in the implementation of the assigned control task, i.e., the detection of holes and grooves made by pests. Three-dimensional image parameters and interferences affecting the quality of the recorded image are described, along with the designed algorithm for identifying holes and grooves and the parametric description of the identified defect. The imaging effects for selected surfaces bearing signs of pest damage and the parameters describing the effectiveness of the present industrial solution are also presented. This paper demonstrates that it is possible to build a three-dimensional image to identify damage effectively within a minimum diameter of 1mm. It makes it possible to observe the damage carried out by most wood-boring pests. Full article

Background/Objectives: Neovascular age-related macular degeneration (nAMD) is a retinal disorder leading to irreversible central vision loss. The pro-re-nata (PRN) treatment for nAMD involves frequent intravitreal injections of anti-VEGF medications, placing a burden on patients and healthcare systems. Predicting injections needs at each monitoring session could optimize treatment outcomes and reduce unnecessary interventions. Methods: To achieve these aims, machine learning (ML) models were evaluated using different combinations of clinical variables, including retinal thickness and volume, best-corrected visual acuity, and features derived from macular optical coherence tomography (OCT). A “Leave Some Subjects Out” (LSSO) nested cross-validation approach ensured robust evaluation. Moreover, the SHapley Additive exPlanations (SHAP) analysis was employed to quantify the contribution of each feature to model predictions. Results: Results demonstrated that models incorporating both structural and functional features achieved high classification accuracy in predicting injection necessity (AUC = 0.747 ± 0.046, MCC = 0.541 ± 0.073). Moreover, the explainability analysis identified as key predictors both subretinal and intraretinal fluid, alongside central retinal thickness. Conclusions: These findings suggest that session-by-session prediction of injection needs in nAMD patients is feasible, even without processing the entire OCT image. The proposed ML framework has the potential to be integrated into routine clinical workflows, thereby optimizing nAMD therapeutic management. Full article

With Japan facing workforce shortages and the need for enhanced recycling systems due to an aging population and increasing environmental challenges, automation in recycling facilities has become a key component for advancing sustainability goals. This study presents the development of an automated sorting robot to replace manual processes in beverage container recycling, aiming to address environmental, social, and economic sustainability by optimizing resource efficiency and reducing labor demands. Using artificial intelligence (AI) for image recognition and high-speed suction-based grippers, the robot effectively sorts various container types, including PET bottles and clear and colored glass bottles, demonstrating a pathway toward more sustainable waste management practices. The findings indicate that stabilizing items on the sorting line may enhance acquisition success, although clear container detection remains an AI challenge. This research supports the United Nation’s 2030 Agenda for Sustainable Development by advancing recycling technology to improve waste processing efficiency, thus contributing to reduced pollution, resource conservation, and a sustainable recycling infrastructure. Further development of gripper designs to handle deformed or liquid-containing containers is required to enhance the system’s overall sustainability impact in the recycling sector. Full article

Venous blood collection is a widely used medical diagnostic technique, and with rapid advancements in robotics, robotic venous blood collection has the potential to replace traditional manual methods. The success of this robotic approach is heavily dependent on the quality of vein imaging. In this paper, we develop a vein imaging device based on the simulation analysis of vein imaging parameters and propose a U-Net+ResNet18 neural network for vein image segmentation. The U-Net+ResNet18 neural network integrates the residual blocks from ResNet18 into the encoder of the U-Net to form a new neural network. ResNet18 is pre-trained using the Bootstrap Your Own Latent (BYOL) framework, and its encoder parameters are transferred to the U-Net+ResNet18 neural network, enhancing the segmentation performance of vein images with limited labelled data. Furthermore, we optimize the AD-Census stereo matching algorithm by developing a variable-weight version, which improves its adaptability to image variations across different regions. Results show that, compared to U-Net, the BYOL+U-Net+ResNet18 method achieves an 8.31% reduction in Binary Cross-Entropy (BCE), a 5.50% reduction in Hausdorff Distance (HD), a 15.95% increase in Intersection over Union (IoU), and a 9.20% increase in the Dice coefficient (Dice), indicating improved image segmentation quality. The average error of the optimized AD-Census stereo matching algorithm is reduced by 25.69%, and the improvement of the image stereo matching performance is more obvious. Future research will explore the application of the vein imaging system in robotic venous blood collection to facilitate real-time puncture guidance. Full article

Synthetic aperture radar is widely applied to ship detection due to generating high-resolution images under diverse weather conditions and its penetration capabilities, making SAR images a valuable data source. However, detecting multi-scale ship targets in complex backgrounds leads to issues of false positives and missed detections, posing challenges for lightweight and high-precision algorithms. There is an urgent need to improve accuracy of algorithms and their deployability. This paper introduces LH-YOLO, a YOLOv8n-based, lightweight, and high-precision SAR ship detection model. We propose a lightweight backbone network, StarNet-nano, and employ element-wise multiplication to construct a lightweight feature extraction module, LFE-C2f, for the neck of LH-YOLO. Additionally, a reused and shared convolutional detection (RSCD) head is designed using a weight sharing mechanism. These enhancements significantly reduce model size and computational demands while maintaining high precision. LH-YOLO features only 1.862 M parameters, representing a 38.1% reduction compared to YOLOv8n. It exhibits a 23.8% reduction in computational load while achieving a mAP50 of 96.6% on the HRSID dataset, which is 1.4% higher than YOLOv8n. Furthermore, it demonstrates strong generalization on the SAR-Ship-Dataset with a mAP50 of 93.8%, surpassing YOLOv8n by 0.7%. LH-YOLO is well-suited for environments with limited resources, such as embedded systems and edge computing platforms. Full article

Human activity recognition (HAR) technology is related to human safety and convenience, making it crucial for it to infer human activity accurately. Furthermore, it must consume low power at all times when detecting human activity and be inexpensive to operate. For this purpose, a low-power and lightweight design of the HAR system is essential. In this paper, we propose a low-power and lightweight HAR system using point-cloud data collected by radar. The proposed HAR system uses a pillar feature encoder that converts 3D point-cloud data into a 2D image and a classification network based on depth-wise separable convolution for lightweighting. The proposed classification network achieved an accuracy of 95.54%, with 25.77 M multiply–accumulate operations and 22.28 K network parameters implemented in a 32 bit floating-point format. This network achieved 94.79% accuracy with 4 bit quantization, which reduced memory usage to 12.5% compared to existing 32 bit format networks. In addition, we implemented a lightweight HAR system optimized for low-power design on a heterogeneous computing platform, a Zynq UltraScale+ ZCU104 device, through hardware–software implementation. It took 2.43 ms of execution time to perform one frame of HAR on the device and the system consumed 3.479 W of power when running. Full article