Search

In recent years, the wide application of deep neural network models has brought serious risks of intellectual property rights infringement. Embedding a watermark in a network model is an effective solution to protect intellectual property rights. Although researchers have proposed schemes to add watermarks to models, they cannot prevent attackers from adding and overwriting original information, and embedding rates cannot be quantified. Therefore, aiming at these problems, this paper designs a high embedding rate and tamper-proof watermarking scheme. We employ wet paper coding (WPC), in which important parameters are regarded as wet blocks and the remaining unimportant parameters are regarded as dry blocks in the model. To obtain the important parameters more easily, we propose an optimized probabilistic selection strategy (OPSS). OPSS defines the unimportant-level function and sets the importance threshold to select the important parameter positions and to ensure that the original function is not affected after the model parameters are changed. We regard important parameters as an unmodifiable part, and only modify the part that includes the unimportant parameters. We selected the MNIST, CIFAR-10, and ImageNet datasets to test the performance of the model after adding a watermark and to analyze the fidelity, robustness, embedding rate, and comparison schemes of the model. Our experiment shows that the proposed scheme has high fidelity and strong robustness along with a high embedding rate and the ability to prevent malicious tampering.

One of the most challenging issues in the routing protocols for underwater wireless sensor networks (UWSNs) is the occurrence of void areas (communication void). That is, when void areas are present, the data packets could be trapped in a sensor node and cannot be sent further to reach the sink(s) due to the features of the UWSNs environment and/or the configuration of the network itself. Opportunistic routing (OR) is an innovative prototype in routing for UWSNs. In routing protocols employing the OR technique, the most suitable sensor node according to the criteria adopted by the protocol rules will be elected as a next-hop forwarder node to forward the data packets first. This routing method takes advantage of the broadcast nature of wireless sensor networks. OR has made a noticeable improvement in the sensor networks’ performance in terms of efficiency, throughput, and reliability. Several routing protocols that utilize OR in UWSNs have been proposed to extend the lifetime of the network and maintain its connectivity by addressing void areas. In addition, a number of survey papers were presented in routing protocols with different points of approach. Our paper focuses on reviewing void avoiding OR protocols. In this paper, we briefly present the basic concept of OR and its building blocks. We also indicate the concept of the void area and list the reasons that could lead to its occurrence, as well as reviewing the state-of-the-art OR protocols proposed for this challenging area and presenting their strengths and weaknesses.

The introduction of fifth generation mobile networks is underway all over the world which makes many people think about the security of the network from any hacking. Over the past few years, researchers from around the world have raised this issue intensively as new technologies seek to integrate into many areas of business and human infrastructure. This paper proposes to implement an IDS (Intrusion Detection System) machine learning approach into the 5G core architecture to serve as part of the security architecture. This paper gives a brief overview of intrusion detection datasets and compares machine learning and deep learning algorithms for intrusion detection. The models are built on the basis of two network data CICIDS2017 and CSE-CIC-IDS-2018. After testing, the ML and DL models are compared to find the best fit with a high level of accuracy. Gradient Boost emerged as the top method when we compared the best results based on metrics, displaying 99.3% for a secure dataset and 96.4% for attacks on the test set.

Intelligent mechanical systems are a focused area nowadays. One of the requirements of intelligent mechanical systems is to achieve intelligent fault diagnosis through the real-time acquisition and analysis of data from various sensors installed on mechanical components. In this paper, a new fault diagnosis method is proposed to solve the problems of difficulty in integrating the fault diagnosis algorithm and locating fault parts due to the complexity of modern mechanical systems. The complexity of modern industrial intelligent systems is due to the fact that the systems are composed of multiple components and there are various connections between them. Common fault diagnosis is to design specialized fault identification algorithms for the physical characteristics of each component, and the integration of different algorithms is a major challenge for system performance. Therefore, this paper investigates a general algorithm for the fault diagnosis of complex systems using the timing characteristics of sensors and transfer entropy. The fault diagnosis algorithm is based on the prediction of multi-dimensional long time series using Autoformer, and fault identification is performed based on the deviation of the predicted value from the actual value. After fault identification, a root cause analysis method of faults based on transfer entropy is proposed. The method can locate the component where the fault occurs more accurately based on the analysis of the cause–effect relationship of each component and help maintenance personnel to troubleshoot the fault.

When the pulse current method is used for partial discharge (PD) monitoring of mining cables, the detected PD signals are seriously disturbed by the field noise, which are easily submerged in the noise and cannot be extracted. In order to realize the effective separation of the PD signal and the interference signal of the mining cable and improve the signal-to-noise ratio of the PD signal, a denoising method for the PD signal of the mining cable based on genetic algorithm optimization of variational mode decomposition (VMD) and wavelet threshold is proposed in this paper. Firstly, the genetic algorithm is used to optimize the VMD, and the optimal value of the number of modal components K and the quadratic penalty factor α is determined; secondly, the PD signal is decomposed by the VMD algorithm to obtain K intrinsic mode functions (IMF). Then, wavelet threshold denoising is applied to each IMF, and the denoised IMFs are reconstructed. Finally, the feasibility of the denoising method proposed in this paper is verified by simulation and experiment.

Surveillance video has been widely used in business, security, search, and other fields. Identifying and locating specific pedestrians in surveillance video has an important application value in criminal investigation, search and rescue, etc. However, the requirements for real-time capturing and accuracy are high for these applications. It is essential to build a complete and smooth system to combine pedestrian detection, tracking and re-identification to achieve the goal of maximizing efficiency by balancing real-time capture and accuracy. This paper combined the detector and Re-ID models into a single end-to-end network by introducing a new track branch to YOLOv5 architecture for tracking. For pedestrian detection, we employed the weighted bi-directional feature pyramid network (BiFPN) to enhance the network structure based on the YOLOv5-Lite, which is able to further improve the ability of feature extraction. For tracking, based on Deepsort, this paper enhanced the tracker, which uses the Noise Scale Adaptive (NSA) Kalman filter to track, and adds adaptive noise to strengthen the anti-interference of the tracking model. In addition, the matching strategy is further updated. For pedestrian re-identification, the network structure of Fastreid was modified, which can increase the feature extraction speed of the improved algorithm by leaps and bounds. Using the proposed unified network, the parameters of the entire model can be trained in an end-to-end method with the multi-loss function, which has been demonstrated to be quite valuable in some other recent works. Experimental results demonstrate that pedestrians detection can obtain a 97% mean Average Precision (mAP) and that it can track the pedestrians well with a 98.3% MOTA and a 99.8% MOTP on the MOT16 dataset; furthermore, high pedestrian re-identification performance can be achieved on the VERI-Wild dataset with a 77.3% mAP. The overall framework proposed in this paper has remarkable performance in terms of the precise localization and real-time detection of specific pedestrians across time, regions, and cameras.

Pedestrian detection is an important research domain due to its relevance for autonomous and assisted driving, as well as its applications in security and industrial automation. Often, more than one type of sensor is used to cover a broader range of operating conditions than a single-sensor system would allow. However, it remains difficult to make pedestrian detection systems perform well in highly dynamic environments, often requiring extensive retraining of the algorithms for specific conditions to reach satisfactory accuracy, which, in turn, requires large, annotated datasets captured in these conditions. In this paper, we propose a probabilistic decision-level sensor fusion method based on naive Bayes to improve the efficiency of the system by combining the output of available pedestrian detectors for colour and thermal images without retraining. The results in this paper, obtained through long-term experiments, demonstrate the efficacy of our technique, its ability to work with non-registered images, and its adaptability to cope with situations when one of the sensors fails. The results also show that our proposed technique improves the overall accuracy of the system and could be very useful in several applications.

With the aim of solving the problem of coal congestion caused by big coal blocks in underground mine scraper conveyors, in this paper we proposed the use of a YOLO-BS (YOLO-Big Size) algorithm to detect the abnormal phenomenon of coal blocks on scraper conveyors. Given the scale of the big coal block targets, the YOLO-BS algorithm replaces the last layer of the YOLOv4 algorithm feature extraction backbone network with the transform module. The YOLO-BS algorithm also deletes the redundant branch which detects small targets in the PAnet module, which reduces the overall number of parameters in the YOLO-BS algorithm. As the up-sampling and down-sampling operations in the PAnet module of the YOLO algorithm can easily cause feature loss, YOLO-BS improves the problem of feature loss and enhances the convergence performance of the model by adding the SimAM space and channel attention mechanism. In addition, to solve the problem of sample imbalance in big coal block data, in this paper, it was shown that the YOLO-BS algorithm selects focal loss as the loss function. In view of the problem that the same lump coal in different locations on the scraper conveyor led to different congestion rates, we conducted research and proposed a formula to calculate the congestion rate. Finally, we collected 12,000 image datasets of coal blocks on the underground scraper conveyor in Daliuta Coal Mine, China, and verified the performance of the method proposed in this paper. The results show that the processing speed of the proposed method can reach 80 fps, and the correct alarm rate can reach 93%. This method meets the real-time and accuracy requirements for the detection of abnormal phenomena in scraper conveyors.

This paper proposes a three-computing-layer architecture consisting of Edge, Fog, and Cloud for remote health vital signs monitoring. The novelty of this architecture is in using the Narrow-Band IoT (NB-IoT) for communicating with a large number of devices and covering large areas with minimum power consumption. Additionally, the architecture reduces the communication delay as the edge layer serves the health terminal devices with initial decisions and prioritizes data transmission for minimizing congestion on base stations. The paper also investigates different authentication protocols for improving security while maintaining low computation and transmission time. For data analysis, different machine learning algorithms, such as decision tree, support vector machines, and logistic regression, are used on the three layers. The proposed architecture is evaluated using CloudSim, iFogSim, and ns3-NB-IoT on real data consisting of medical vital signs. The results show that the proposed architecture reduces the NB-IoT delay by 59.9%, the execution time by an average of 38.5%, and authentication time by 35.1% for a large number of devices. This paper concludes that the NB-IoT combined with edge, fog, and cloud computing can support efficient remote health monitoring for large devices and large areas.

In this paper, human step length is estimated based on the wireless channel properties and the received signal strength indicator (RSSI) method. The path loss between two ankles, called the on-ankle path loss, is converted from the RSSI, which is measured by our developed wearable hardware in indoor and outdoor ambulation scenarios. The human walking step length is estimated by a reliable range of RSSI values. The upper threshold and the lower threshold of this range are determined experimentally. This paper advances our previous step length measurement technique by proposing a novel exponential weighted moving average (EWMA) algorithm to update the upper and lower thresholds, and thus the step length estimation, recursively. The EWMA algorithm allows our measurement technique to process each shorter subset of the dataset, called a time window, and estimate the step length, rather than having to process the whole dataset at a time. The step length is periodically updated on the fly when the time window is “sliding” forwards. Thus, the EWMA algorithm facilitates the step length estimation in real-time. The impact of the EWMA parameter is analysed, and the optimal parameter is discovered for different experimental scenarios. Our experiments show that the EWMA algorithm could achieve comparable accuracy as our previously proposed technique with errors as small as 3.02% and 0.30% for the indoor and outdoor scenarios, respectively, while the processing time required to output an estimation of the step length could be significantly shortened by 53.96% and 60% for the indoor walking and outdoor walking, respectively.

A new approach to the estimation and classification of nonlinear frequency modulated (NLFM) signals is presented in the paper. These problems are crucial in electronic reconnaissance systems whose role is to indicate what signals are being received and recognized by the intercepting receiver. NLFM signals offer a variety of useful properties not available for signals with linear frequency modulation (LFM). In particular, NLFM signals can ensure the desired reduction of sidelobes of an autocorrelation (AC) function and desired power spectral density (PSD); therefore, such signals are more frequently used in modern radar and echolocation systems. Due to their nonlinear properties, the discussed signals are difficult to recognize and therefore require sophisticated methods of analysis, estimation and classification. NLFM signals with frequency content varying with time are mainly analyzed by time–frequency algorithms. However, the methods presented in the paper belong to time–chirp domain, which is relatively rarely cited in the literature. It is proposed to use polynomial approximations of nonlinear frequency and phase functions describing signals. This allows for applying the cubic phase function (CPF) as an estimator of phase polynomial coefficients. Originally, the CPF involved only third-order nonlinearities of the phase function. The extension of the CPF using nonuniform sampling is used to analyse the higher order polynomial phase. In this paper, a sixth order polynomial is considered. It is proposed to estimate the instantaneous frequency using a polynomial with coefficients calculated from the coefficients of the phase polynomial obtained by CPF. The determined coefficients also constitute the set of distinctive features for a classification task. The proposed CPF-based classification method was examined for three common NLFM signals and one LFM signal. Two types of neural network classifiers: learning vector quantization (LVQ) and multilayer perceptron (MLP) are considered for such defined classification problem. The performance of both the estimation and classification processes was analyzed using Monte Carlo simulation studies for different SNRs. The results of the simulation research revealed good estimation performance and error-free classification for the SNR range encountered in practical applications.

Small object detection has always been a difficult direction in the field of object detection, especially the detection of small objects in UAV aerial images. The images captured by UAVs have the characteristics of small objects and dense objects. In order to solve these two problems, this paper improves the performance of object detection from the aspects of data and network structure. In terms of data, the data augmentation strategy and image pyramid mechanism are mainly used. The data augmentation strategy adopts the method of image division, which can greatly increase the number of small objects, making it easier for the algorithm to be fully trained during the training process. Since the object is denser, the image pyramid mechanism is used. During the training process, the divided images are up-sampled into three different sizes, and then sent to three different detectors respectively. Finally, the detection results of the three detectors are fused to obtain the final detection results. The small object itself has few pixels and few features. In order to improve the detection performance, it is necessary to use context. This paper adds attention mechanism to the yolov5 network structure, while adding a detection head to the underlying feature map to make the network structure pay more attention to small objects. By using data augmentation and improved network structure, the detection performance of small objects can be significantly improved. The experiment in this paper is carried out on the Visdrone2019 dataset and DOTA dataset. Through experimental verification, our proposed method can significantly improve the performance of small object detection.

Target tracking algorithms based on deep learning have achieved good results in public datasets. Among them, the network tracking algorithm based on Siamese tracking has a high accuracy and fast speed, which has attracted significant attention. However, the Siamese tracker uses the AlexNet network as its backbone and the network layers are relatively shallow, so it does not make full use of the ability of the deep neural network. If only the backbones of target tracking are replaced, there will be no obvious improvement, such as in the cases of ResNet and Inception. Therefore, this paper designs a wider and deeper network structure. At a wider level, a mechanism that can adaptively adjust the receptive field (RF) size is designed. Firstly, multiple branches are divided by the split operator, and each branch has a different size of kernel corresponding to a different size of RF; then, the fuse operator is used to fuse the information of each branch to obtain the selection weights; and finally, according to the selection, the aggregation feature map is weighted. At a deeper level, a new kind of residual models is designed. The channel is simplified by pruning in order to improve the tracking speed. According to the above, a wider and deeper Siamese network was proposed in this paper. The experimental results show that the structure proposed in this paper achieves a good tracking effect and real-time performance on six kinds of datasets. The proposed tracker achieves an SUC and Prec of LaSOT of 0.569 and 0.571, respectively.

A systematic review on the topic of automatic detection of COVID-19 using audio signals was performed. A total of 48 papers were obtained after screening 659 records identified in the PubMed, IEEE Xplore, Embase, and Google Scholar databases. The reviewed studies employ a mixture of open-access and self-collected datasets. Because COVID-19 has only recently been investigated, there is a limited amount of available data. Most of the data are crowdsourced, which motivated a detailed study of the various pre-processing techniques used by the reviewed studies. Although 13 of the 48 identified papers show promising results, several have been performed with small-scale datasets (lt;200). Among those papers, convolutional neural networks and support vector machine algorithms were the best-performing methods. The analysis of the extracted features showed that Mel-frequency cepstral coefficients and zero-crossing rate continue to be the most popular choices. Less common alternatives, such as non-linear features, have also been proven to be effective. The reported values for sensitivity range from 65.0% to 99.8% and those for accuracy from 59.0% to 99.8%.

The history of Compton cameras began with the detection of radiation sources originally for applications in astronomy. A Compton camera is a promising γ-ray detector that operates in the wide energy range of a few tens of keV to MeV. The γ-ray detection method of a Compton camera is based on Compton scattering kinematics, which is used to determine the direction and energy of the γ-rays without using a mechanical collimator. Although the Compton camera was originally designed for astrophysical applications, it was later applied in medical imaging as well. Moreover, its application in environmental radiation measurements is also under study. Although a few review papers regarding Compton cameras have been published, they either focus very specifically on the detectors used in such cameras or the particular applications of Compton cameras. Thus, the aim of this paper is to review the features and types of Compton cameras and introduce their applications, associated imaging algorithms, improvement scopes, and their future aspects.

The synthesis between face sketches and face photos has important application values in law enforcement and digital entertainment. In cases of a lack of paired sketch-photo data, this paper proposes an unsupervised model to solve the problems of missing key facial details and a lack of realism in the synthesized images of existing methods. The model is built on the CycleGAN architecture. To retain more semantic information in the target domain, a multi-scale feature extraction module is inserted before the generator. In addition, the convolutional block attention module is introduced into the generator to enhance the ability of the model to extract important feature information. Via CBAM, the model improves the quality of the converted image and reduces the artifacts caused by image background interference. Next, in order to preserve more identity information in the generated photo, this paper constructs the multi-level cycle consistency loss function. Qualitative experiments on CUFS and CUFSF public datasets show that the facial details and edge structures synthesized by our model are clearer and more realistic. Meanwhile the performance indexes of structural similarity and peak signal-to-noise ratio in quantitative experiments are also significantly improved compared with other methods.

When a vehicle is being driven, it is excited by the road roughness and generates its own vibration. In order to improve the vehicle’s riding comfort and the physical–mental health of passengers in the vehicle, this paper proposes a formulation method for a comfortable speed strategy and the technical route of its application. According to international standard ISO 2631-1, the relationship between the weighted root-mean-square acceleration value and comfortable vehicle speed is analyzed. The simulation test platform of the road roughness signal and vehicle vibration signal is built by using the filtering white noise method and the second Lagrange equation through Matlab/Simulink. Combined with the simulation platform, this paper extracts seven characteristics with statistical properties from the time-domain signal and obtains 500 sample data. Random forest (RF), extreme learning machine (ELM), and radial basis function neural network (RBF-NN) are applied to identify roads. Two comfortable speed strategy formulation methods based on the improved simulated annealing (ISA) algorithm are proposed and compared according to the solution effect of each grade of comfortable speed. The results show that the simulated signals of each grade road roughness are accurate. Road recognition can be effectively carried out using the statistical characteristics of vehicle vibration acceleration signals. ELM has high recognition accuracy and fast execution speed. The ISA-II algorithm has a low solution error of comfortable speed and a low computation time. The comfortable speed of the research vehicle on different road grades showed a great difference.

Chip pad inspection is of great practical importance for chip alignment inspection and correction. It is one of the key technologies for automated chip inspection in semiconductor manufacturing. When applying deep learning methods for chip pad inspection, the main problem to be solved is how to ensure the accuracy of small target pad detection and, at the same time, achieve a lightweight inspection model. The attention mechanism is widely used to improve the accuracy of small target detection by finding the attention region of the network. However, conventional attention mechanisms capture feature information locally, which makes it difficult to effectively improve the detection efficiency of small targets from complex backgrounds in target detection tasks. In this paper, an OCAM (Object Convolution Attention Module) attention module is proposed to build long-range dependencies between channel features and position features by constructing feature contextual relationships to enhance the correlation between features. By adding the OCAM attention module to the feature extraction layer of the YOLOv5 network, the detection performance of chip pads is effectively improved. In addition, a design guideline for the attention layer is proposed in the paper. The attention layer is adjusted by network scaling to avoid network characterization bottlenecks, balance network parameters, and network detection performance, and reduce the hardware device requirements for the improved YOLOv5 network in practical scenarios. Extensive experiments on chip pad datasets, VOC datasets, and COCO datasets show that the approach in this paper is more general and superior to several state-of-the-art methods.

The incidence of maritime accidents can be significantly reduced by identifying the deck officer’s fatigue levels. The development of car driver fatigue detectors has employing electroencephalogram (EEG)-based technologies in recent years and made it possible to swiftly and accurately determine the level of a driver’s fatigue. However, individual variability and the sensitivity of EEG signals reduce the detection precision. Recently, another type of video-based technology for detecting driver fatigue by recording changes in the drivers’ eye characteristics has also been explored. In order to improve the classification performance of EEG-based approaches, this paper introduces the ADTIDO (Automatic Detect the TIred Deck Officers) algorithm, an EEG-based classification method of deck officers’ fatigue level, which combines a video-based approach to record the officer’s eye closure time for each time window. This paper uses a Discrete Wavelet Transformer (DWT) and decomposes the EEG signals into six sub-signals, from which we extract various EEG-based features, e.g., MAV, SD, and RMS. Unlike the traditional video-based method of calculating the Eyelid Closure Degree (ECD), this paper then obtains the ECD values from the EEG signals. The ECD-EEG fusion features are then created and used as the inputs for a classifier by combining the ECD and EEG feature sets. In addition, the present work develops the definition of “fatigue” at the individual level based on the real-time operational reaction time of the deck officer. To verify the efficacy of this research, the authors conducted their trials by using the EEG signals gathered from 21 subjects. It was found that Bidirectional Gated Recurrent Unit (Bi-GRU) networks outperform other classifiers, reaching a classification accuracy of 90.19 percent, 1.89 percent greater than that of only using EEG features as inputs. By combining the ADTIDO channel findings, the classification accuracy of deck officers’ fatigue levels finally reaches 95.74 percent.

In recent years, image segmentation based on deep learning has been widely used in medical imaging, automatic driving, monitoring and security. In the fields of monitoring and security, the specific location of a person is detected by image segmentation, and it is segmented from the background to analyze the specific actions of the person. However, in low-illumination conditions, it is a great challenge to the traditional image-segmentation algorithms. Unfortunately, a scene with low light or even no light at night is often encountered in monitoring and security. Given this background, this paper proposes a multi-modal fusion network based on the encoder and decoder structure. The encoder, which contains a two-branch swin-transformer backbone instead of the traditional convolutional neural network, fuses the RGB and depth features with a multiscale fusion attention block. The decoder is also made up of the swin-transformer backbone and is finally connected via the encoder with several residual connections, which are proven to be beneficial in improving the accuracy of the network. Furthermore, this paper first proposes the low light–human segmentation (LLHS) dataset of portrait segmentation, with aligned depth and RGB images with fine annotation under low illuminance, by combining the traditional monocular camera and a depth camera with active structured light. The network is also tested in different levels of illumination. Experimental results show that the proposed network has good robustness in the scene of human segmentation in a low-light environment with varying illumination. The mean Intersection over Union (mIoU), which is often used to evaluate the performance of image segmentation model, of the Swin-MFA in the LLHS dataset is 81.0, is better than those of ACNet, 3DGNN, ESANet, RedNet and RFNet at the same level of depth in a mixed multi-modal network and is far ahead of the segmentation algorithm that only uses RGB features, so it has important practical significance.

This paper presents a real-time object-based 3D change detection method that is built around the concept of semantic object maps. The algorithm is able to maintain an object-oriented metric-semantic map of the environment and can detect object-level changes between consecutive patrol routes. The proposed 3D change detection method exploits the capabilities of the novel ZED 2 stereo camera, which integrates stereo vision and artificial intelligence (AI) to enable the development of spatial AI applications. To design the change detection algorithm and set its parameters, an extensive evaluation of the ZED 2 camera was carried out with respect to depth accuracy and consistency, visual tracking and relocalization accuracy and object detection performance. The outcomes of these findings are reported in the paper. Moreover, the utility of the proposed object-based 3D change detection is shown in real-world indoor and outdoor experiments.

Due to the recent increasing utilization of deep learning models on edge devices, the industry demand for Deep Learning Model Optimization (DLMO) is also increasing. This paper derives a usage strategy of DLMO based on the performance evaluation through light convolution, quantization, pruning techniques and knowledge distillation, known to be excellent in reducing memory size and operation delay with a minimal accuracy drop. Through experiments regarding image classification, we derive possible and optimal strategies to apply deep learning into Internet of Things (IoT) or tiny embedded devices. In particular, strategies for DLMO technology most suitable for each on-device Artificial Intelligence (AI) service are proposed in terms of performance factors. In this paper, we suggest a possible solution of the most rational algorithm under very limited resource environments by utilizing mature deep learning methodologies.

The ball screw is the core component of the CNC machine tool feed system, and its health plays an important role in the feed system and even in the entire CNC machine tool. This paper studies the fault diagnosis and health assessment of ball screws. Aiming at the problem that the ball screw signal is weak and susceptible to interference, using a wavelet convolution structure to improve the network can improve the mining ability of signal time domain and frequency domain features; aiming at the challenge of ball screw sensor installation position limitation, a transfer learning method is proposed, which adopts the domain adaptation method as jointly distributed adaptation (JDA), and realizes the transfer diagnosis across measurement positions by extracting the diagnosis knowledge of different positions of the ball screw. In this paper, the adaptive batch normalization algorithm (AdaBN) is introduced to enhance the proposed model so as to improve the accuracy of migration diagnosis. Experiments were carried out using a self-made lead screw fatigue test bench. Through experimental verification, the method proposed in this paper can extract effective fault diagnosis knowledge. By collecting data under different working conditions at the bearing seat of the ball screw, the fault diagnosis knowledge is extracted and used to identify and diagnose the position fault of the nut seat. In this paper, some background noise is added to the collected data to test the robustness of the proposed network model.

In order to reduce the influence of redundant features on the performance of the model in the process of accelerometer behavior recognition, and to improve the recognition accuracy of the model, this paper proposes an improved Whale Optimization algorithm with mixed strategy (IWOA) combined with the extreme gradient boosting algorithm (XGBoost) as a preferred method for chicken behavior identification features. A nine-axis inertial sensor was used to obtain the chicken behavior data. After noise reduction, the sliding window was used to extract 44 dimensional features in the time domain and frequency domain. To improve the search ability of the Whale Optimization algorithm for optimal solutions, the introduction of the good point set improves population diversity and expands the search range; the introduction of adaptive weight balances the search ability of the optimal solution in the early and late stages; the introduction of dimension-by-dimension lens imaging learning based on the adaptive weight factor perturbs the optimal solution and enhances the ability to jump out of the local optimal solution. This method’s effectiveness was verified by recognizing cage breeders’ feeding and drinking behaviors. The results show that the number of feature dimensions is reduced by 72.73%. At the same time, the behavior recognition accuracy is increased by 2.41% compared with the original behavior feature dataset, which is 95.58%. Compared with other dimensionality reduction methods, the IWOA–XGBoost model proposed in this paper has the highest recognition accuracy. The dimension reduction results have a certain degree of universality for different classification algorithms. This provides a method for behavior recognition based on acceleration sensor data.

Time-space four-dimensional motion target localization is a fundamental and challenging task in the field of intelligent driving, and an important part of achieving the upgrade in existing target localization technologies. In order to solve the problem of the lack of localization of moving targets in a spatio-temporal four-dimensional environment in the existing spatio-temporal data model, this paper proposes an optical imaging model in the four-dimensional time-space system and a mathematical model of the object-image point mapping relationship in the four-dimensional time-space system based on the central perspective projection model, combined with the one-dimensional “time” and three-dimensional “space”. After adding the temporal dimension, the imaging system parameters are extended. In order to solve the nonlinear mapping problem of complex systems, this paper proposes to construct a time-space four-dimensional object-image mapping relationship model based on a BP artificial neural network and demonstrates the feasibility of the joint time-space four-dimensional imaging model theory. In addition, indoor time-space four-dimensional localization prediction experiments verify the performance of the model in this paper. The maximum relative error rates of the predicted motion depth values, time values, and velocity values of this localization method compared with the real values do not exceed 0.23%, 2.03%, and 1.51%, respectively

The use of multi-connectivity has become a useful tool to manage the traffic in heterogeneous cellular network deployments, since it allows a device to be simultaneously connected to multiple cells. The proper exploitation of this technique requires to adequately configure the traffic sent through each cell depending on the experienced conditions. This motivates this work, which tackles the problem of how to optimally split the traffic among the cells when the multi-connectivity feature is used. To this end, the paper proposes the use of a deep reinforcement learning solution based on a Deep Q-Network (DQN) in order to determine the amount of traffic of a device that needs to be delivered through each cell, making the decision as a function of the current traffic and radio conditions. The obtained results show a near-optimal performance of the DQN-based solution with an average difference of only 3.9% in terms of reward with respect to the optimum strategy. Moreover, the solution clearly outperforms a reference scheme based on Signal to Interference Noise Ratio (SINR) with differences of up to 50% in terms of reward and up to 166% in terms of throughput for certain situations. Overall, the presented results show the promising performance of the DQN-based approach that establishes a basis for further research in the topic of multi-connectivity and for the application of this type of techniques in other problems of the radio access network This paper is part of ARTIST project (ref. PID2020-115104RB-I00) funded by MCIN/AEI/10.13039/501100011033. The work is also funded by the Spanish Ministry of Science and Innovation under grant ref. PRE2018-084691.

Infrared target detection is often disrupted by a complex background, resulting in a high false alarm and low target recognition. This paper proposes a robust principal component decomposition model with joint spatial and temporal filtering and L1 norm regularization to effectively suppress the complex backgrounds. The model establishes a new anisotropic Gaussian kernel diffusion function, which exploits the difference between the target and the background in the spatial domain to suppress the edge contours. Furthermore, in order to suppress the dynamically changing background, we construct an inversion model that combines temporal domain information and L1 norm regularization to globally constrain the low rank characteristics of the background, and characterize the target sparse component with L1 norm. Finally, the overlapping multiplier method is used for decomposition and reconstruction to complete the target detection.Through relevant experiments, the proposed background modeling method in this paper has a better background suppression effect in different scenes. The average values of the three evaluation indexes, SSIM, BSF and IC, are 0.986, 88.357 and 18.967, respectively. Meanwhile, the proposed detection method obtains a higher detection rate compared with other algorithms under the same false alarm rate.

This paper considers the problem of finding the position of a passive target using noisy time difference of arrival (TDOA) measurements, obtained from multiple transmitters and a single receiver. The maximum likelihood (ML) estimator’s objective function is extremely nonlinear and non-convex, making it impossible to use traditional optimization techniques. In this regard, this paper proposes the chaos-enhanced adaptive hybrid butterfly particle swarm optimization algorithm, named CAHBPSO, as the hybridization of butterfly optimization (BOA) and particle swarm optimization (PSO) algorithms, to estimate passive target position. In the proposed algorithm, an adaptive strategy is employed to update the sensory fragrance of BOA algorithm, and chaos theory is incorporated into the inertia weight of PSO algorithm. Furthermore, an adaptive switch probability is employed to combine global and local search phases of BOA with the PSO algorithm. Additionally, the semidefinite programming is employed to convert the considered problem into a convex one. The statistical comparison on CEC2014 benchmark problems shows that the proposed algorithm provides a better performance compared to well-known algorithms. The CAHBPSO method surpasses the BOA, PSO and semidefinite programming (SDP) algorithms for a broad spectrum of noise, according to simulation findings, and achieves the Cramer–Rao lower bound (CRLB).

Internet availability and its integration with smart technologies have favored everyday objects and things and offered new areas, such as the Internet of Things (IoT). IoT refers to a concept where smart devices or things are connected and create a network. This new area has suffered from big data handling and security issues. There is a need to design a data analytics model by using new 5G technologies, architecture, and a security model. Reliable data communication in the presence of legitimate nodes is always one of the challenges in these networks. Malicious nodes are generating inaccurate information and breach the user’s security. In this paper, a data analytics model and self-organizing architecture for IoT networks are proposed to understand the different layers of technologies and processes. The proposed model is designed for smart environmental monitoring systems. This paper also proposes a security model based on an authentication, detection, and prediction mechanism for IoT networks. The proposed model enhances security and protects the network from DoS and DDoS attacks. The proposed model evaluates in terms of accuracy, sensitivity, and specificity by using machine learning algorithms.

Most machine learning algorithms only have a good recognition rate on balanced datasets. However, in the field of malicious traffic identification, benign traffic on the network is far greater than malicious traffic, and the network traffic dataset is imbalanced, which makes the algorithm have a low identification rate for small categories of malicious traffic samples. This paper presents a traffic sample synthesizing model named Conditional Tabular Traffic Generative Adversarial Network (CTTGAN), which uses a Conditional Tabular Generative Adversarial Network (CTGAN) algorithm to expand the small category traffic samples and balance the dataset in order to improve the malicious traffic identification rate. The CTTGAN model expands and recognizes feature data, which meets the requirements of a machine learning algorithm for training and prediction data. The contributions of this paper are as follows: first, the small category samples are expanded and the traffic dataset is balanced; second, the storage cost and computational complexity are reduced compared to models using image data; third, discrete variables and continuous variables in traffic feature data are processed at the same time, and the data distribution is described well. The experimental results show that the recognition rate of the expanded samples is more than 0.99 in MLP, KNN and SVM algorithms. In addition, the recognition rate of the proposed CTTGAN model is better than the oversampling and undersampling schemes.

This paper outlines challenges and opportunities in operating underwater robots (so-called AUVs) on a seaweed farm. The need is driven by an emerging aquaculture industry on the Swedish west coast where large-scale seaweed farms are being developed. In this paper, the operational challenges are described and key technologies in using autonomous systems as a core part of the operation are developed and demonstrated. The paper presents a system and methods for operating an AUV in the seaweed farm, including initial localization of the farm based on a prior estimate and dead-reckoning navigation, and the subsequent scanning of the entire farm. Critical data from sidescan sonars for algorithm development are collected from real environments at a test site in the ocean, and the results are demonstrated in a simulated seaweed farm setup.

Electro-oculography (EOG)-based brain–computer interface (BCI) is a relevant technology influencing physical medicine, daily life, gaming and even the aeronautics field. EOG-based BCI systems record activity related to users’ intention, perception and motor decisions. It converts the bio-physiological signals into commands for external hardware, and it executes the operation expected by the user through the output device. EOG signal is used for identifying and classifying eye movements through active or passive interaction. Both types of interaction have the potential for controlling the output device by performing the user’s communication with the environment. In the aeronautical field, investigations of EOG-BCI systems are being explored as a relevant tool to replace the manual command and as a communicative tool dedicated to accelerating the user’s intention. This paper reviews the last two decades of EOG-based BCI studies and provides a structured design space with a large set of representative papers. Our purpose is to introduce the existing BCI systems based on EOG signals and to inspire the design of new ones. First, we highlight the basic components of EOG-based BCI studies, including EOG signal acquisition, EOG device particularity, extracted features, translation algorithms, and interaction commands. Second, we provide an overview of EOG-based BCI applications in the real and virtual environment along with the aeronautical application. We conclude with a discussion of the actual limits of EOG devices regarding existing systems. Finally, we provide suggestions to gain insight for future design inquiries.

Energy and security are major challenges in a wireless sensor network, and they work oppositely. As security complexity increases, battery drain will increase. Due to the limited power in wireless sensor networks, options to rely on the security of ordinary protocols embodied in encryption and key management are futile due to the nature of communication between sensors and the ever-changing network topology. Therefore, machine learning algorithms are one of the proposed solutions for providing security services in this type of network by including monitoring and decision intelligence. Machine learning algorithms present additional hurdles in terms of training and the amount of data required for training. This paper provides a convenient reference for wireless sensor network infrastructure and the security challenges it faces. It also discusses the possibility of benefiting from machine learning algorithms by reducing the security costs of wireless sensor networks in several domains; in addition to the challenges and proposed solutions to improving the ability of sensors to identify threats, attacks, risks, and malicious nodes through their ability to learn and self-development using machine learning algorithms. Furthermore, this paper discusses open issues related to adapting machine learning algorithms to the capabilities of sensors in this type of network.

The filtered-x recursive least square (FxRLS) algorithm is widely used in the active noise control system and has achieved great success in some complex de-noising environments, such as the cabin in vehicles and aircraft. However, its performance is sensitive to some user-defined parameters such as the forgetting factor and initial gain. Once these parameters are not selected properly, the de-noising effect of FxRLS will deteriorate. Moreover, the tracking performance of FxRLS for mutation is still restricted to a certain extent. To solve the above problems, this paper proposes a new proportional FxRLS (PFxRLS) algorithm. The forgetting factor and initial gain sensitivity are successfully reduced without introducing new turning parameters. The de-noising level and tracking performance have also been improved. Moreover, the momentum technique is introduced in PFxRLS to further improve its robustness and de-noising level. To ensure stability, its convergence condition is also discussed in this paper. The effectiveness of the proposed algorithms is illustrated by simulations and experiments with different user-defined parameters and time-varying noise environments.

Precise motor control requires high accuracy of the rotor position through the incremental encoder. The speed and accuracy of the acquisition equipment (microcontroller) play an important element in terms of cost and efficiency. In this paper, the author presents alternative methods for speed acquisition from an incremental encoder. In the first stage of research, the main performances of the STM32 microcontroller, connected with an incremental encoder, will be analyzed and compared with two different acquisition systems, i.e., ELVIS II and a Unidrive M701 power inverter. Using the LabVIEW graphical programming language, a user-friendly, convenient, and flexible human–machine interface is designed. Due to the advantages provided by the STM32 microcontroller in terms of processing power, cost, and programming interface, the obtained results are accurate and consistent. Through experimental testing and analysis, the speed acquisition is stable for both developed software algorithms used for ELVIS II and STM32 platforms. It is the aim of the paper to propose a useful speed acquisition tool in low-cost, high-accuracy prototyping applications.

Agricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligence of robots. Agricultural robots must have intelligent control functions in agricultural scenarios and be able to autonomously decide paths to complete agricultural tasks. In response to this requirement, this paper proposes a Residual-like Soft Actor Critic (R-SAC) algorithm for agricultural scenarios to realize safe obstacle avoidance and intelligent path planning of robots. In addition, in order to alleviate the time-consuming problem of exploration process of reinforcement learning, this paper proposes an offline expert experience pre-training method, which improves the training efficiency of reinforcement learning. Moreover, this paper optimizes the reward mechanism of the algorithm by using multi-step TD-error, which solves the probable dilemma during training. Experiments verify that our proposed method has stable performance in both static and dynamic obstacle environments, and is superior to other reinforcement learning algorithms. It is a stable and efficient path planning method and has visible application potential in agricultural robots.

In recent years, image segmentation techniques based on deep learning have achieved many applications in remote sensing, medical, and autonomous driving fields. In space exploration, the segmentation of spacecraft objects by monocular images can support space station on-orbit assembly tasks and space target position and attitude estimation tasks, which has essential research value and broad application prospects. However, there is no segmentation network designed for spacecraft targets. This paper proposes an end-to-end spacecraft image segmentation network using the semantic segmentation network DeepLabv3+ as the basic framework. We develop a multi-scale neural network based on sparse convolution. First, the feature extraction capability is improved by the dilated convolutional network. Second, we introduce the channel attention mechanism into the network to recalibrate the feature responses. Finally, we design a parallel atrous spatial pyramid pooling (ASPP) structure that enhances the contextual information of the network. To verify the effectiveness of the method, we built a spacecraft segmentation dataset on which we conduct experiments on the segmentation algorithm. The experimental results show that the encoder+ attention+ decoder structure proposed in this paper, which focuses on high-level and low-level features, can obtain clear and complete masks of spacecraft targets with high segmentation accuracy. Compared with DeepLabv3+, our method is a significant improvement. We also conduct an ablation study to research the effectiveness of our network framework.

Level 5 autonomy, as defined by the Society of Automotive Engineers, requires the vehicle to function under all weather and visibility conditions. This sensing problem becomes significantly challenging in weather conditions that include events such as sudden changes in lighting, smoke, fog, snow, and rain. No standalone sensor currently in the market can reliably perceive the environment in all conditions. While regular cameras, lidars, and radars will suffice for typical driving conditions, they may fail in some edge cases. The goal of this paper is to demonstrate that the addition of Long Wave Infrared (LWIR)/thermal cameras to the sensor stack on a self-driving vehicle can help fill this sensory gap during adverse visibility conditions. In this paper, we trained a machine learning-based image detector on thermal image data and used it for vehicle detection. For vehicle tracking, Joint Probabilistic Data association and Multiple Hypothesis Tracking approaches were explored where the thermal camera information was fused with a front-facing radar. The algorithms were implemented using FLIR thermal cameras on a 2017 Lincoln MKZ operating in College Station, TX, USA. The performance of the tracking algorithm has also been validated in simulations using Unreal Engine.

It is possible to construct cost-efficient three-dimensional (3D) or four-dimensional (4D) scanning systems using multiple affordable off-the-shelf RGB-D sensors to produce high-quality reconstructions of 3D objects. However, the quality of these systems’ reconstructions is sensitive to a number of factors in reconstruction pipelines, such as multi-view calibration, depth estimation, 3D reconstruction, and color mapping accuracy, because the successive pipelines to reconstruct 3D meshes from multiple active stereo sensors are strongly correlated with each other. This paper categorizes the pipelines into sub-procedures and analyze various factors that can significantly affect reconstruction quality. Thus, this paper provides analytical and practical guidelines for high-quality 3D reconstructions with off-the-shelf sensors. For each sub-procedure, this paper shows comparisons and evaluations of several methods using data captured by 18 RGB-D sensors and provide analyses and discussions towards robust 3D reconstruction. Through various experiments, it has been demonstrated that significantly more accurate 3D scans can be obtained with the considerations along the pipelines. We believe our analyses, benchmarks, and guidelines will help anyone build their own studio and their further research for 3D reconstruction.

This paper addresses the problem of real-time model predictive control (MPC) in the integrated guidance and control (IGC) of missile systems. When the primal-dual interior point method (PD-IPM), which is a convex optimization method, is used as an optimization solution for the MPC, the real-time performance of PD-IPM degenerates due to the elevated computation time in checking the Karush–Kuhn–Tucker (KKT) conditions in PD-IPM. This paper proposes a graphics processing unit (GPU)-based method to parallelize and accelerate PD-IPM for real-time MPC. The real-time performance of the proposed method was tested and analyzed on a widely-used embedded system. The comparison results with the conventional PD-IPM and other methods showed that the proposed method improved the real-time performance by reducing the computation time significantly.

In the field of biometric recognition, finger vein recognition has received widespread attention by virtue of its advantages, such as biopsy, which is not easy to be stolen. However, due to the limitation of acquisition conditions such as noise and illumination, as well as the limitation of computational resources, the discriminative features are not comprehensive enough when performing finger vein image feature extraction. It will lead to such a result that the accuracy of image recognition cannot meet the needs of large numbers of users and high security. Therefore, this paper proposes a novel feature extraction method called principal component local preservation projections (PCLPP). It organically combines principal component analysis (PCA) and locality preserving projections (LPP) and constructs a projection matrix that preserves both the global and local features of the image, which will meet the urgent needs of large numbers of users and high security. In this paper, we apply the Shandong University homologous multi-modal traits (SDUMLA-HMT) finger vein database to evaluate PCLPP and add “Salt and pepper” noise to the dataset to verify the robustness of PCLPP. The experimental results show that the image recognition rate after applying PCLPP is much better than the other two methods, PCA and LPP, for feature extraction.

The adverse impacts of using conventional batteries in the Internet of Things (IoT) devices, such as cost-effective maintenance, numerous battery replacements, and environmental hazards, have led to an interest in integrating energy harvesting technology into IoT devices to extend their lifetime and sustainably effectively. However, this requires improvements in different IoT protocol stack layers, especially in the MAC layer, due to its high level of energy consumption. These improvements are essential in critical applications such as IoT medical devices. In this paper, we simulated a dense solar-based energy harvesting Wi-Fi network in an e-Health environment, introducing a new algorithm for energy consumption mitigation while maintaining the required Quality of Service (QoS) for e-Health. In compliance with the upcoming Wi-Fi amendment 802.11be, the Access Point (AP) coordination-based optimization technique is proposed, where an AP can request dynamic resource rescheduling along with its nearby APs, to reduce the network energy consumption through adjustments within the standard MAC protocol. This paper shows that the proposed algorithm, alongside using solar energy harvesting technology, increases the energy efficiency by more than 40% while maintaining the e-Health QoS requirements. We believe this research will open new opportunities in IoT energy harvesting integration, especially in QoS-restricted environments.

To solve the problem of inflexibility of offline hand–eye calibration in “eye-in-hand” modes, an online hand–eye calibration method based on the ChArUco board is proposed in this paper. Firstly, a hand–eye calibration model based on the ChArUco board is established, by analyzing the mathematical model of hand–eye calibration, and the image features of the ChArUco board. According to the advantages of the ChArUco board, with both the checkerboard and the ArUco marker, an online hand–eye calibration algorithm based on the ChArUco board is designed. Then, the online hand–eye calibration algorithm, based on the ChArUco board, is used to realize the dynamic adjustment of the hand–eye position relationship. Finally, the hand–eye calibration experiment is carried out to verify the accuracy of the hand–eye calibration based on the ChArUco board. The robustness and accuracy of the proposed method are verified by online hand–eye calibration experiments. The experimental results show that the accuracy of the online hand–eye calibration method proposed in this paper is between 0.4 mm and 0.6 mm, which is almost the same as the offline hand–eye calibration accuracy. The method in this paper utilizes the advantages of the ChArUco board to realize online hand–eye calibration, which improves the flexibility and robustness of hand–eye calibration.

Social media platforms have many users who share their thoughts and use these platforms to organize various events collectively. However, different upsetting incidents have occurred in recent years by taking advantage of social media, raising significant concerns. Therefore, considerable research has been carried out to detect any disturbing event and take appropriate measures. This review paper presents a thorough survey to acquire in-depth knowledge about the current research in this field and provide a guideline for future research. We systematically review 67 articles on event detection by sensing social media data from the last decade. We summarize their event detection techniques, tools, technologies, datasets, performance metrics, etc. The reviewed papers mainly address the detection of events, such as natural disasters, traffic, sports, real-time events, and some others. As these detected events can quickly provide an overview of the overall condition of the society, they can significantly help in scrutinizing events disrupting social security. We found that compatibility with different languages, spelling, and dialects is one of the vital challenges the event detection algorithms face. On the other hand, the event detection algorithms need to be robust to process different media, such as texts, images, videos, and locations. We outline that the event detection techniques compatible with heterogeneous data, language, and the platform are still missing. Moreover, the event and its location with a 24 × 7 real-time detection system will bolster the overall event detection performance.

Navigating safely in complex marine environments is a challenge for submarines because proper path planning underwater is difficult. This paper decomposes the submarine path planning problem into global path planning and local dynamic obstacle avoidance. Firstly, an artificial potential field ant colony algorithm (APF-ACO) based on an improved artificial potential field algorithm and improved ant colony algorithm is proposed to solve the problem of submarine underwater global path planning. Compared with the Optimized ACO algorithm proposed based on a similar background, the APF-ACO algorithm has a faster convergence speed and better path planning results. Using an inflection point optimization algorithm greatly reduces the number and length of inflection points in the path. Using the Clothoid curve fitting algorithm to optimize the path results, a smoother and more stable path result is obtained. In addition, this paper uses a three-dimensional dynamic obstacle avoidance algorithm based on the velocity obstacle method. The experimental results show that the algorithm can help submarines to identify threatening dynamic obstacles and avoid collisions effectively. Finally, we experimented with the algorithm in the submarine underwater semi-physical simulation system, and the experimental results verified the effectiveness of the algorithm.

Deep learning-based methods, especially convolutional neural networks, have been developed to automatically process the images of concrete surfaces for crack identification tasks. Although deep learning-based methods claim very high accuracy, they often ignore the complexity of the image collection process. Real-world images are often impacted by complex illumination conditions, shadows, the randomness of crack shapes and sizes, blemishes, and concrete spall. Published literature and available shadow databases are oriented towards images taken in laboratory conditions. In this paper, we explore the complexity of image classification for concrete crack detection in the presence of demanding illumination conditions. Challenges associated with the application of deep learning-based methods for detecting concrete cracks in the presence of shadows are elaborated on in this paper. Novel shadow augmentation techniques are developed to increase the accuracy of automatic detection of concrete cracks.

Speech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imaginary speech recognition system to obtain the best performance according to the developed method that can be applied to a low-cost system with limited resources. In developing the system, we used signals from the Kara One database containing recordings acquired for seven phonemes and four words. We used in the feature extraction stage a method based on covariance in the frequency domain that performed better compared to the other time-domain methods. Further, we observed the system performance when using different window lengths for the input signal (0.25 s, 0.5 s and 1 s) to highlight the importance of the short-term analysis of the signals for imaginary speech. The final goal being the development of a low-cost system, we studied several architectures of convolutional neural networks (CNN) and showed that a more complex architecture does not necessarily lead to better results. Our study was conducted on eight different subjects, and it is meant to be a subject’s shared system. The best performance reported in this paper is up to 37% accuracy for all 11 different phonemes and words when using cross-covariance computed over the signal spectrum of a 0.25 s window and a CNN containing two convolutional layers with 64 and 128 filters connected to a dense layer with 64 neurons. The final system qualifies as a low-cost system using limited resources for decision-making and having a running time of 1.8 ms tested on an AMD Ryzen 7 4800HS CPU.

The use of autonomous underwater vehicles (AUV) has increased in a wide range of sectors, including the oil and gas industry, military, and marine research. The AUV capabilities to operate without a direct human operator and untethered to a support vessel are features that have aroused interest in the marine environment. The localization of AUV is significantly affected by the initial alignment and the calibration of the navigation sensors. In this sense, this paper proposes a thorough observability analysis applied to the latter problem. The observability analysis is carried out considering three types of sensor fusion integration and a set of maneuvers, and the results are validated through numerical simulations. As main contribution of this paper, it is shown how the addition of position errors in the observation vector can decouple some gyro and accelerometer biases from the latitude and altitude errors, particularly in the stationary observability analysis. The influence of oscillations in the diving plane and typical AUV maneuvers are analyzed, showing their relative impacts on the degree of observability of the inertial measurement unit (IMU)/Doppler velocity log (DVL) misalignment and DVL scale factor error. Finally, the state’s estimation accuracy is also analyzed, showing the limitation of the degree of observability as an assessment tool for the estimability of the states.