Using Sparse Parts in Fused Information to Enhance Performance in Latent Low-Rank Representation-Based Fusion of Visible and Infrared Images.

Latent Low-Rank Representation (LatLRR) has emerged as a prominent approach for fusing visible and infrared images. In this approach, images are decomposed into three fundamental components: the base part, salient part, and sparse part. The aim is to blend the base and salient features to reconstruct images accurately. However, existing methods often focus more on combining the base and salient parts, neglecting the importance of the sparse component, whereas we advocate for the comprehensive inclusion of all three parts generated from LatLRR image decomposition into the image fusion process, a novel proposition introduced in this study. Moreover, the effective integration of Convolutional Neural Network (CNN) technology with LatLRR remains challenging, particularly after the inclusion of sparse parts. This study utilizes fusion strategies involving weighted average, summation, VGG19, and ResNet50 in various combinations to analyze the fusion performance following the introduction of sparse parts. The research findings show a significant enhancement in fusion performance achieved through the inclusion of sparse parts in the fusion process. The suggested fusion strategy involves employing deep learning techniques for fusing both base parts and sparse parts while utilizing a summation strategy for the fusion of salient parts. The findings improve the performance of LatLRR-based methods and offer valuable insights for enhancement, leading to advancements in the field of image fusion.

PM2.5 Concentration Prediction Model: A CNN-RF Ensemble Framework.

Although many machine learning methods have been widely used to predict PM2.5 concentrations, these single or hybrid methods still have some shortcomings. This study integrated the advantages of convolutional neural network (CNN) feature extraction and the regression ability of random forest (RF) to propose a novel CNN-RF ensemble framework for PM2.5 concentration modeling. The observational data from 13 monitoring stations in Kaohsiung in 2021 were selected for model training and testing. First, CNN was implemented to extract key meteorological and pollution data. Subsequently, the RF algorithm was employed to train the model with five input factors, namely the extracted features from the CNN and spatiotemporal factors, including the day of the year, the hour of the day, latitude, and longitude. Independent observations from two stations were used to evaluate the models. The findings demonstrated that the proposed CNN-RF model had better modeling capability compared with the independent CNN and RF models: the average improvements in root mean square error (RMSE) and mean absolute error (MAE) ranged from 8.10% to 11.11%, respectively. In addition, the proposed CNN-RF hybrid model has fewer excess residuals at thresholds of 10 µg/m3, 20 µg/m3, and 30 µg/m3. The results revealed that the proposed CNN-RF ensemble framework is a stable, reliable, and accurate method that can generate superior results compared with the single CNN and RF methods. The proposed method could be a valuable reference for readers and may inspire researchers to develop even more effective methods for air pollution modeling. This research has important implications for air pollution research, data analysis, model estimation, and machine learning.

Combination of VSLAM and a Magnetic Fingerprint Map to Improve Accuracy of Indoor Positioning.

With the continual advancement of positioning technology, people's use of mobile devices has increased substantially. The global navigation satellite system (GNSS) has improved outdoor positioning performance. However, it cannot effectively locate indoor users owing to signal masking effects. Common indoor positioning technologies include radio frequencies, image visions, and pedestrian dead reckoning. However, the advantages and disadvantages of each technology prevent a single indoor positioning technology from solving problems related to various environmental factors. In this study, a hybrid method was proposed to improve the accuracy of indoor positioning by combining visual simultaneous localization and mapping (VSLAM) with a magnetic fingerprint map. A smartphone was used as an experimental device, and a built-in camera and magnetic sensor were used to collect data on the characteristics of the indoor environment and to determine the effect of the magnetic field on the building structure. First, through the use of a preestablished indoor magnetic fingerprint map, the initial position was obtained using the weighted k-nearest neighbor matching method. Subsequently, combined with the VSLAM, the Oriented FAST and Rotated BRIEF (ORB) feature was used to calculate the indoor coordinates of a user. Finally, the optimal user's position was determined by employing loose coupling and coordinate constraints from a magnetic fingerprint map. The findings indicated that the indoor positioning accuracy could reach 0.5 to 0.7 m and that different brands and models of mobile devices could achieve the same accuracy.

Combining a Modified Particle Filter Method and Indoor Magnetic Fingerprint Map to Assist Pedestrian Dead Reckoning for Indoor Positioning and Navigation.

Although advancement has been observed in global navigation satellite systems and these systems are widely used, they cannot provide effective navigation and positioning services in covered areas and areas that lack strong signals, such as indoor environments. Therefore, in recent years, indoor positioning technology has become the focus of research and development. The magnetic field of the Earth is quite stable in an open environment. Due to differences in building and internal structures, this type of three-dimensional vector magnetic field is widely available indoors for indoor positioning. A smartphone magnetometer was used in this study to collect magnetic field data for constructing indoor magnetic field maps. Moreover, an acceleration sensor and a gyroscope were used to identify the position of a mobile phone and detect the number of steps travelled by users with the phone. This study designed a procedure for measuring the step length of users. All obtained information was input into a pedestrian dead reckoning (PDR) algorithm for calculating the position of the device. The indoor positioning accuracy of the PDR algorithm was optimised using magnetic gradients of magnetic field maps with a modified particle filter algorithm. Experimental results reveal that the indoor positioning accuracy was between 0.6 and 0.8 m for a testing area that was 85 m long and 33 m wide. This study effectively improved the indoor positioning accuracy and efficiency by using the particle filter method in combination with the PDR algorithm with the magnetic fingerprint map.

Low-Cost Indoor Positioning Application Based on Map Assistance and Mobile Phone Sensors.

Current mainstream navigation and positioning equipment, intended for providing accurate positioning signals, comprise global navigation satellite systems, maps, and geospatial databases. Although global navigation satellite systems have matured and are widespread, they cannot provide effective navigation and positioning services in covered areas or areas lacking strong signals, such as indoor environments. To solve the problem of positioning in environments lacking satellite signals and achieve cost-effective indoor positioning, this study aimed to develop an inexpensive indoor positioning program, in which the positions of users were calculated by pedestrian dead reckoning (PDR) using the built-in accelerometer and gyroscope in a mobile phone. In addition, the corner and linear calibration points were established to correct the positions with the map assistance. Distance, azimuth, and rotation angle detections were conducted for analyzing the indoor positioning results. The results revealed that the closure accuracy of the PDR positioning was enhanced by more than 90% with a root mean square error of 0.6 m after calibration. Ninety-four percent of the corrected PDR positioning results exhibited errors of <1 m, revealing a desk-level positioning accuracy. Accordingly, this study successfully combined mobile phone sensors with map assistance for improving indoor positioning accuracy.