Crack detection is vital for maintaining hydraulic engineering infrastructure. However, achieving a balance between real-time processing and high precision in semantic segmentation models presents a significant challenge, especially given the intricate details of cracks and complex backgrounds. To tackle this issue, this paper proposes a real-time, high-precision crack segmentation model. Initially, a four-branch feature extraction structure is devised to capture the edge details of cracks, with a focus on enhancing segmentation accuracy. Subsequently, an image pyramid is constructed at the input end to feed small-scale samples into high-dimensional feature extraction branches, thereby reducing computational costs and improving segmentation speed. Finally, an effective feature fusion module is designed for the feature extraction structure to capture sufficient crack features and achieve precise crack localization. Extensive experiments validate the superior performance of the proposed method, with Pixel Accuracy, Recall, Intersection over Union, and F1 score reaching 68.45 % , 67.04 % , 51.22 % , and 67.74 % , respectively, while maintaining a modest parameter count of 13.12M. This model provides a reliable and efficient solution for the health monitoring and maintenance of hydraulic engineering.

Timely detection of defects is essential for ensuring safe and stable operation of concrete buildings. Automatic segmentation of concrete buildings’ surfaces is challenging due to the high diversity of crack appearance, the detailed information, and the unbalanced proportion of crack pixels and background pixels. In this work, the Double Feature Pyramid Network is designed for high-precision crack segmentation. Our work reached the state-of-the-art level in crack segmentation, with key contributions outlined as follows: firstly, considering the diversity of crack shapes, the network constructs a feature pyramid containing three feature extraction backbones to extract the global feature map with three scale input images. In particular, due to the biggest challenge being too much single-pixel crack area, the targeted feature pyramid based on the high-resolution is added to extract adequate shallow semantic information. Lastly, designing a cascade feature fusion unit to aggregate the extracted multi-dimensional feature maps and obtain the final prediction. Compared with existing crack detection methods, the superior performance of this method has been verified based on extensive experiments, with Pixel Accuracy of 65.99%, Intersection over Union of 44.71%, and Recall of 62.95%, providing a reliable and efficient solution for the health monitoring and maintenance of concrete structures. This work contributes to the advancement of research and practical applications in related fields, offering robust support for the monitoring and maintenance of concrete structures.

Purpose - This study aims to understand households' adoption of small-scale solar energy to reduce carbon dioxide emissions that cause due to conventional energy consumptions. Design/methodology/approach - This study is quantitative in nature and households were selected as unit of analysis. Online data has been collected from seven main cities of Pakistan to understand households' intention to use small-scale solar energy for domestic consumption. A total of 370 valid data were analyzed through partial least square structural equation modeling. Findings - The study findings reveal that publicity information, attitude green norm and perceived behavioral control are the strongest predictors of households' intention to use small-scale solar energy. Practical implications - The considered model practically contributes to the literature by understanding households intention to adopt solar technologies that are viable means to conserve conventional energy and preserve the environment through less emission of carbon dioxide. In addition to this, understanding the green norm of households is imperative in a developing country, Pakistan where climate risk is high. Understanding household' green norms would help marketers and practitioners to design and introduce new and more efficient renewable technologies that maintain environmental sustainability. Originality/value - This study has contributed to theory of planned behavior (TPB) by the inclusion of publicity information and green norms. Previous studies focused on the environmental benefits of using renewable energy sources. This study added novel antecedents into TPB that help to understand the adoption of small-scale solar energy for domestic consumption.

Vehicular ad hoc networks (VANETs) are self-organizing, open-structure inter-vehicle communication networks, along with wireless communication technology and transportation. Vehicle communication aims to improve the driver’s response-ability and ensure traffic safety when encountering traffic accidents. The 5G NR on V2V communication, compared to fourth-generation (4G) long-term evolution (LTE), is more sophisticated and has ultra-high reliability. This research proposes intelligent driver model-lane changes (IDM-LC) and intelligent driver model-avoidance (IDM-A) models, which enhance the performance accuracy of the V2V communication through the 5G NR system. In this case, the authenticity of the vehicle movement models is tested on different road scenarios, i.e., square, hexagon, heptagon and triangle. In these scenarios, the vehicles’ movements over the 5G networks receive widespread coverage whenever the vehicles receive signals from the roadside unit (RSU). Hence, the flexibility of VANET is used to improve the device-to-device (D2D) or vehicle-to-vehicle (V2V) communication efficiency in the fifth-generation (5G) new radio (NR) system. In addition, the VANET simulation platform, i.e., simulation of urban mobility (SUMO) and network simulator-3 (NS-3), simulate and evaluate the comparison of V2V through the 5G networks, which receives widespread coverage in 15 to 20 m/s. The simulation results and analysis show that the V2V communication through the 5G system performs better on the IDM models.

A rapidly spreading epidemic, COVID-19 had a serious effect on millions and took many lives. Therefore, for individuals with COVID-19, early discovery is essential for halting the infection's progress. To quickly and accurately diagnose COVID-19, imaging modalities, including computed tomography (CT) scans and chest X-ray radiographs, are frequently employed. The potential of artificial intelligence (AI) approaches further explored the creation of automated and precise COVID-19 detection systems. Scientists widely use deep learning techniques to identify coronavirus infection in lung imaging. In our paper, we developed a novel light CNN model architecture with watershed-based region-growing segmentation on Chest X-rays. Both CT scans and X-ray radiographs were employed along with 5-fold cross-validation. Compared to earlier state-of-the-art models, our model is lighter and outperformed the previous methods by achieving a mean accuracy of 98.8% on X-ray images and 98.6% on CT scans, predicting the rate of 0.99% and 0.97% for PPV (Positive predicted Value) and NPV (Negative predicted Value) rate of 0.98% and 0.99%, respectively.

Environment mapping is an essential prerequisite for mobile robots to perform different tasks such as navigation and mission planning. With the availability of low-cost 2-D LiDARs, there are increasing applications of such 2-D LiDARs in industrial environments. However, environment mapping in an unknown and featureless environment with such low-cost 2-D LiDARs remains a challenge. The challenge mainly originates from the short range of LiDARs and complexities in performing scan matching in these environments. In order to resolve these shortcomings, we propose to fuse the ultrawideband (UWB) with 2-D LiDARs to improve the mapping quality of a mobile robot. The optimization-based approach is utilized for the fusion of UWB ranging information and odometry to first optimize the trajectory. Then, the LiDAR-based loop closures are incorporated to improve the accuracy of the trajectory estimation. Finally, the optimized trajectory is combined with the LiDAR scans to produce the occupancy map of the environment. The performance of the proposed approach is evaluated in an indoor featureless environment with a size of 20 × 20 m. Obtained results show that the mapping error of the proposed scheme is 85.5% less than that of the conventional GMapping algorithm with short-range LiDAR (for example, Hokuyo URG-04LX in our experiment with a maximum range of 5.6 m).

A single technological advancement in the business sector tremendously changed customers’ lifestyles and consumption behavior. Drone technology is one of the main revolutions that increase business efficiency at a lower cost. However, the acceptance of emerging technologies is not rapid in developing markets. Therefore, this study aims to evaluate customers’ adoption of drone technology in the context of food delivery services. This study has used an extended technology acceptance model (TAM) to assess customers’ behavior. Product processing innovativeness, information processing innovativeness, and subjective norms have been added as additional constructs into TAM. The data of 354 customers from five different cities of Pakistan have been collected and analyzed through partial least square structural equation modeling (PLS-SEM). The results of the study revealed that all proposed hypotheses, except the positive influence of perceived ease of use on perceived usefulness, were accepted. Further, the results depict that perceived usefulness, subjective norms, and attitude were the major predictors of customers’ adoption of drone food delivery services. In addition to this, customers’ word of mouth has a greater influence and reach than other forms of marketing communication. Therefore, practitioners and marketers may consider hosting competition programs to experiment with drone food delivery systems to enhance the acceptance of this technology among the masses.

Sustainable supply chain management (SSCM) in sharing economy platforms supports resource management and achieves environmental sustainability. Corporate social responsibility (CSR) is an essential pillar of sustainability, but the link between CSR and SSCM has been missing in the literature. Therefore, the current study intends to examine the connection between CSR and SSCM practices in sharing economy-based platforms. This study has applied the means-end theory to understand customer intention in the sharing economy. The data of 379 respondents from five main cities of Pakistan have been collected through convenience sampling. Partial least square structural equation modeling (PLS-SEM) has been used to test the proposed conceptual model. The study results show that the corporate social responsibility approach adopted by the sharing economy platforms improves internal supply chain management that drives customers' intention to use sharing economy platforms. Green concern has a significant moderating effect on customers' tendency toward environmental issues and solutions. However, findings revealed that eco-design in the sustainable supply chain does not affect customer purchase intention in sharing economy platforms. The study findings provide practical implications to organizations focusing on sustainable supply chain management practices in the sharing economy.

This paper describes a method in an indoor environment for the estimation and position, using an Unscented Kalman Filter (UKF). The UKF algorithm applied for the position estimation proposing a new measurement uncertainty model that fixes the error covariance according to the distance measurement. In addition, this approach sets the non-diagonal component of the error covariance matrix for the uncertainty of the speed information and the measurement uncertainty to a value other than zero. This method is evaluated through an experiment using a wheel-type mobile robot with an LRF sensor in an indoor environment. In this experiment, we differentiate the estimation execution of the proposed approach with a conventional method that does not employ an adaptive uncertainty model. Moreover, the results improved the estimation performance by setting the non-diagonal component of the error covariance to a value other than zero. The main emphasis of this paper is to implement a practical UKF method for location estimation of a mobile robot and analyze it with better performance.

This paper aims to improve the performance and positioning accuracy of a robot by using the particle filter method. The laser range information is a wireless navigation system mainly used to measure, position, and control autonomous robots. Its localization is more flexible to control than wired guidance systems. However, the navigation through the laser range finder occurs with a large positioning error while it moves or turns fast. For solving this problem, the paper proposes a method to improve the positioning accuracy of a robot in an indoor environment by using a particle filter with robust characteristics in a nonlinear or non-Gaussian system. In this experiment, a robot is equipped with a laser range finder, two encoders, and a gyro for navigation to verify the positioning accuracy and performance. The positioning accuracy and performance could improve by approximately 85.5% in this proposed method.

Ultra-wideband (UWB) and inertial measurement unit (IMU) fusion is an efficient method to resolve the uncertainties of UWB in non-line-of-sight (NLOS) situations because of signals refraction, the effect of multipath and inertial positioning error accumulation in indoor environments. Existing systems, however, are focused only on foot-mounted IMUs that restrict the system’s implementation to particular real situations. In this research, using foot-mounted IMU, we suggest combining UWB ranging and IMU pedestrian dead reckoning (PDR), which can provide a generic indoor positioning solution. The issues such as position and orientation drift, interferences and divergence in strap-down inertial navigation system (SINS) based orientation estimates could be addressed by a UWB ranging sensor fusing with an IMU using the extended Kalman filter (EKF). The main goal of this research is to investigate and compare two different sensor data fusion techniques. For instance, adaptive Kalman filter (AKF) and least-squares (LSs) incorporate a foot-mounted IMU tightly coupled to a 2D pedestrian positioning solution derived from UWB signals. Moreover, we consider the UWB NLOS and IMU error identification. A real-time ranging error compensation model based on the LS method and AKF positioning algorithm are used for fixing such problems. We propose a new tightly coupled inertial navigation system (INS) with a two-way ranging (TWR) fusion positioning algorithm to improve accuracy, integrating UWB and IMU sensors based on the EKF in pedestrian navigation. Experiments in dynamic indoor environment validate the effectiveness of the proposed approach that uses EKF to combine AKF and LS for error minimization.

Object identification and localization in indoor and outdoor environments are paramount issues in object–human interaction. Recent advancements in the data fusion capabilities of multi-sensor systems have paved the way for research on emerging object identification and positioning techniques. This review describes techniques and methods used in positioning technologies. State-of-the-art localization technologies are classified into range-based, range-free and AI-based categories. An in-depth analysis of localization approaches based on laser range finder, radio-frequency identification, ultra-wideband, inertial measurement unit, etc., are presented by providing a detailed comparison based on range, accuracy, measurement method, advantages, disadvantages, and their applications. Furthermore, we investigate state-of-the-art multimodal data fusion techniques that utilize probabilistic methods for the precise estimation of object identification in motion and its localization.

This research analyzes the design and simulation of a mobile robot using Extended Kalman Filter (EKF) and Unscented Kalman filter (UKF). The mobile platform has a differential configuration, where each track of a wheel is associated with an encoder. The EKF and UKF methods are used to integrate the measurements of a novel odometric system based on the optical mice and the measurements of a localization system based on a map of geometric beacons. Two different types of simulations have been performed for validating the results, either using the mouse-based odometric system or using the conventional wheel encoder-based odometric system, to compare and evaluate the errors made by each system.

This work is proposed to improve the security and privacy issues in real-time database system, such as the military departments, public organizations and the other private organizations. These institutions are associated with the database system environments that shows controlled retrieving of data and information with their operation. In fact, the huge volumes of data and information are supervised by the today’s real-time database system. For security purpose a concurrency control algorithm (OPT) is used, a simulation is written in C+ + for the real-time databases and timing constraints is also used in this research. Hence, this work consistently tackles, improves and identifies the solutions of different challenges such as security and privacy of database, such as security measures objectives, security threats to database and the database security maintenance process. The paper presents the mechanism of scheduling called as “timing” and access control “timing” in real-time.

In an indoor environment, object identification and localization are paramount for human-object interaction. Visual or laser-based sensors can achieve the identification and localization of the object based on its appearance, but these approaches are computationally expensive and not robust against the environment with obstacles. Radio Frequency Identification (RFID) has a unique tag ID to identify the object, but it cannot accurately locate it. Therefore, in this paper, the data of RFID and laser range finder are fused for the better identification and localization of multiple dynamic objects in an indoor environment. The main method is to use the laser range finder to estimate the radial velocities of objects in a certain environment, and match them with the object’s radial velocities estimated by the RFID phase. The method also uses a fixed time series as “sliding time window” to find the cluster with the highest similarity of each RFID tag in each window. Moreover, the Pearson correlation coefficient (PCC) is used in the update stage of the particle filter (PF) to estimate the moving path of each cluster in order to improve the accuracy in a complex environment with obstacles. The experiments were verified by a SCITOS G5 robot. The results show that this method can achieve an matching rate of 90.18% and a localization accuracy of 0.33m in an environment with the presence of obstacles. This method effectively improves the matching rate and localization accuracy of multiple objects in indoor scenes when compared to the Bray-Curtis (BC) similarity matching-based approach as well as the particle filter-based approach.

Vehicle to Vehicle (V2V) communication plays a significant role in the Intelligent Transportation System (ITS) in Vehicular Ad hoc Networks (VANET) for which the usage of IOT in vehicles is increasing rapidly. Vehicles communicate with each other through wireless networks. However, the deployment of new generation of mobile networks 5G needs a major upgradation of its existing systems such as 4G, LTE and other infrastructure. Therefore, it is proposed to introduce advanced technology of 5G networks upgradation in Vehicle to Vehicle communication. Massive MIMO have the important role for the DSRC (Dedicated Short Range Communication) wireless technology. This mechanism works on the vehicle-to-vehicle communication such as the vehicle relative speed, range transmission etc., base station (tower) and RSU control and monitor of the vehicle to vehicle communication. In this research, the road styles such as square, straight, triangle and any other are designed and tested through simulation program using MATLAB 2017. The upcoming 5G technology for driverless V2V communication makes the journey easier and safer with full control.

Amongst all the design modules employed in aircraft design process, weight module is the most significant one. Evaluating aircraft performance is dependent on a suitable aircraft weight in order to carry out its intended mission. In interactive design process, the weight design engineers usually follow one particular published methodology such as that proposed by Roskam or Torenbeek or etc. The main drawback of these methodologies is their limited accuracy to be applied to the vast variation of civilian aircraft. Furthermore, the non-availability of component-weight data, which may be used in evaluating maximum take-off weight, makes the design process difficult. Hence, new weight module has been applied to interactive design process. It suggests that many equations of different methodologies are applied to each aircraft component instead of applying one analyst’s methodology. Simultaneously, any formula that has secondary variables, which may not be available in the early stages of aircraft design, is rejected. The equation that gives the lowest average value is selected. The new module results show that the accuracy of the estimated operating empty weight and the maximum take-off weight is better than 5%.