Road infrastructure is a key public asset because it benefits the social and economic development of any country. It plays an important role in the development of the industrial complex and the production sector, and the surfaces of transport roads should be of high quality and have a long service life. Road infrastructure, like all infrastructure, requires preservation, maintenance and repair. There are special requirements for roadways that must be observed during construction or repair. The uncertainty of the composition, temperature sensitivity and viscoelastic characteristics of road materials make the structural analysis of pavement very difficult compared to other civil structures, such as bridges, tunnels and buildings. For this reason, the question of how to improve fiber sensors based on fiber Bragg grating (FBG) arose. The novelty of this study is to modernize fiber sensors based on FBG so that they display deformation, stress and displacement, temperature and other parameters with much greater accuracy, which would provide a reliable scientific basis for modifying the theory, as well as the use of a fiber sensor based on FBG for simultaneous measurement of deformation and temperature when monitoring the road surface. This article is devoted to a detailed study of the use of fiber-optic sensors (FOS) based on fiber Bragg grating for road surface monitoring. Such a fiber sensor, consisting of a fiber Bragg grating and a pair of grids, can offer the possibility of simultaneous measurement of deformation and temperature for monitoring the pavement. Temperature and deformation measurements were carried out by installing a sensor on the surface of a made asphalt sample. The built-in fiber sensor based on FBG provides important information about how the pavement structure can withstand the load and subsidence of soil and implement road safety and stability measures in a timely manner to evaluate and predict the service life of the pavement. The results of the study showed that the synchronicity, repeatability and linearity of the characteristics of the fiber sensor are excellent. The difference between the experimental and theoretical results was about 7%. Thus, based on the results of the obtained data, the fiber sensor on the FBG can be used for monitoring and designing road surfaces and in general transport infrastructure.

In many fields, data-driven decision making has become essential due to machine learning (ML), which provides insights that improve productivity and quality of life. A basic machine learning approach called clustering helps find comparable data points. Clustering plays a critical role in the identification of patient subgroups and the customisation of treatment in the context of tuberculosis (TB) research. While prior studies have recognized its utility, a comprehensive comparative analysis of multiple clustering methods applied to TB data is lacking. Using TB data, this study thoroughly assesses and contrasts four well-known machine learning clustering algorithms: spectral clustering, DBSCAN, hierarchical clustering, and k-means. To evaluate the quality of a cluster, quantitative measures such as the silhouette score, Davies–Bouldin index, and Calinski–Harabasz index are utilised. The results provide quantitative insights that enhance comprehension of clustering and guide future research.

Colorectal cancer is the third most prevalent type of cancer globally, and it typically progresses unnoticed, making early detection via effective screening methods crucial. This study presents the TASPP-UNet, an advanced deep learning model that integrates Atrous Spatial Pyramid Pooling (ASPP) blocks and a ResNet-50 encoder to enhance polyp boundary delineation accuracy in colonoscopy images. We utilized augmented datasets from Kvasir-SEG and CVC Clinic-DB, which included up to 2000 images, to enrich the training examples’ variability. The TASPP-UNet achieved a superior IOU of 0.9276, compared to 0.9128 by the ResNet50-UNet and 0.8607 by the standard U-Net, demonstrating its efficacy in precise segmentation tasks. Notably, this model exhibited impressive computational efficiency with a processing speed of 151.1 frames per second (FPS), underscoring its potential for real-time clinical applications aimed at early and accurate colorectal cancer detection. This performance highlights the model’s capability not only to improve diagnostic accuracy but also to enhance clinical workflows, potentially leading to better patient outcomes.

Road infrastructure is a key public asset because it benefits the social and economic development of any country. It plays an important role for the development of the industrial complex, the production sector and the road surfaces of transport roads should be of high quality, have a long service life. Road infrastructure, as well as all infrastructure, requires preservation, maintenance and repair. There are special requirements for the roadway that must be observed during construction or repair. This article is devoted to a detailed study of the use of fiber optics sensors (FOS) based on the fiber Bragg grating (FBG) for road surface monitoring. Such a fiber sensor consisting of a fiber Bragg grid and a pair of grids can offer the possibility of simultaneous measurement of deformation and temperature for monitoring the pavement. Temperature and deformation measurements were carried out by installing a sensor on the surface of a made asphalt sample. The built-in fiber sensor based on FBG provides important information about how the pavement structure can withstand the load, subsidence of soil, timely implement road safety and stability measures evaluate and predict the service life of the pavement. The results of the study showed that the synchronicity, repeatability and linearity of the characteristics of the fiber sensor are excellent. The difference between the experimental and theoretical results is about 7%. Thus, based on the results of the obtained data, the fiber sensor on the FBG can be used for monitoring, designing road surfaces and in general transport infrastructure.

This research focuses on developing an artificial vision system for a flexible delta robot manipulator and integrating it with machine-to-machine (M2M) communication to optimize real-time device interaction. This integration aims to increase the speed of the robotic system and improve its overall performance. The proposed combination of an artificial vision system with M2M communication can detect and recognize targets with high accuracy in real time within the limited space considered for positioning, further localization, and carrying out manufacturing processes such as assembly or sorting of parts. In this study, RGB images are used as input data for the MASK-R-CNN algorithm, and the results are processed according to the features of the delta robot arm prototype. The data obtained from MASK-R-CNN are adapted for use in the delta robot control system, considering its unique characteristics and positioning requirements. M2M technology enables the robot arm to react quickly to changes, such as moving objects or changes in their position, which is crucial for sorting and packing tasks. The system was tested under near real-world conditions to evaluate its performance and reliability.

This paper presents the implementation, trajectory planning, kinematics, and experimental validation of an open-source 3D-printed delta robot manipulator. The robot’s hardware consists of three servo motors, an Arduino Uno microcontroller, and a Pulse Width Modulation (PWM) servo module. The software includes a trapezoidal velocity profile planner and an inverse and forward kinematics solver to calculate the motor angles required to achieve a desired end-effector position in task space. The 3D printed parts were obtained from an open-source Thingiverse project and assembled to form the robot’s kinematic structure. The robot’s performance was evaluated in terms of its accuracy, repeatability, and maximum speed for a pick-and-place task. Experimental results show that the robot can achieve a positioning accuracy of 2.2 mm, with a top speed of 0.4 m/s, 30 picks per minute, and load carrying capacity up to 200 g. These results are satisfactory, considering the ease of assembly and the cost-effectiveness of the robot. The comparison of the calculated motor angles with actual motor angles obtained through additional potentiometer wires soldering shows promising results. The proposed robot’s cost-effective characteristics, utilization of open-source additive manufacturing, and motion planning algorithms make it suitable for various applications, including education, research, and small-scale industrial applications.