The brain-inspired collaborative Simultaneous Localization And Mapping technology simulates the spatial navigation cells of biological brains to process the detection information of leader-follower Autonomous Underwater Vehicles (AUVs), which can obtain global map of underwater world. However, the capacity of underwater acoustic communication is limited, and the communication content is affected by environmental noise, which can affect the performance of collaborative navigation. To address the above issues, inspired by the granule cells and time cells of biological brains, this paper proposes a Bio-inspired Collaborative Navigation Method of leader-follower AUVs based on composite spatial navigation cells (BCNM). Firstly, this method discusses a brain-inspired collaborative navigation scenario of AUVs. Next, this method designs a granular cell based on Spiking Neural Networks (SNN) to achieve feature point selection and the compression and aggregation of local descriptors, which are used for data transmission and loop closure detection of AUVs. In addition, this method designs a time cell based on sliding window Gaussian Process Regression (GPR) and Improved Walrus Optimizer algorithm (IWO) to correct the position information of AUVs and obtain the transition matrix of local maps, which are used to achieve the map fusion of AUVs. Finally, the pose cells are used to encode the motion postures of AUVs, and the experience map is used to represent the paths of AUVs. To validate the performance of BCNM, this paper establishes an underwater collaborative SLAM dataset. Experimental results show that BCNM has good adaptability in the underwater SLAM datasets, and outperforms other methods in terms of trajectory error.

The brain-inspired Simultaneous Localization And Mapping technology (SLAM) in Internet of Underwater Things enables real-time location of multi-Autonomous Underwater Vehicle (AUV) with low computational overhead. However, in actual scenarios, the movement of AUV swarm interferes with visual images, which affects the performance of SLAM seriously. To deal with the above problem, a Brain-inspired Navigation Method based on Composite Spatial Navigation Cell model is proposed to achieve the autonomous navigation of AUVs, which is inspired from the speed cell and boundary cell of biological brain. Firstly, this method establishes a brain-inspired navigation scene of multi-AUV, where the stereo camera of AUVs is used to collect environmental information. Next, this method establishes speed cells based on Spiking Neural Network (SNN) to obtain semantic information, the location, score, and descriptor of feature points, which helps to estimate the motion information of AUVs such as displacement changes and heading angle changes) accurately. In addition, based on the distance information and angle information from stereo camera of AUVs to static obstacles, the proposed method calculates the activity value of boundary cells to assist in the loop-closure detection of local view cells. Finally, this method uses pose cells to represent the motion posture of AUVs, and applies experience map to record the movement trajectory of AUVs. To measure the performance of proposed method, this paper establishes an underwater SLAM dataset and a land SLAM dataset respectively, which are affected by dynamic entities. Extensive experimental results show that this method has good adaptability in different SLAM datasets, and is better than other methods in terms of trajectory error.

In Internet of Underwater Things (IoUT), multiautonomous underwater vehicles (AUVs) can hunt specific targets by performing collaborative hunting tasks. Collaborative hunting task refers to multi-AUV hunts underwater target through collaborative hunting algorithm, which includes target searching, tracking path planning, and encirclement keeping. However, in actual scenarios, this task requires hunter AUVs to search targets independently, and encircle targets continuously, which poses a huge challenge to the collaborative hunting algorithm. To solve this challenge, this article proposes a collaborative hunting algorithm for dynamic ocean targets to ensure collaborative hunting effects. First, this algorithm models the collaborative hunting of hunter AUVs, and designs the kinematic model and detection model of hunter AUVs. According to the 3-D encirclement of hunter AUVs, this algorithm establishes a tracking encirclement metric to evaluate the encirclement keeping of hunter AUVs. In addition, this algorithm adjusts divide areas based on robots initial position (DARP) and bio-inspired neural network (BINN) to achieve collaborative searching in 3-D environment. Then, this algorithm designs an improve crayfish optimization algorithm (ICOA) to obtain tracking paths and hunting actions of hunter AUVs. Specifically, ICOA uses planning space and cubic map to initialize populations, and performs the optimization operation through Levy flight. Extensive simulation results show that the proposed algorithm can complete the collaborative hunting task, and is better than other algorithms in terms of encirclement keeping and tracking path planning.

As one of the important tools for exploring the ocean, multiple autonomous underwater vehicles (multi-AUVs) system can complete complex tasks in complex Internet of Underwater Things. Collaborative target search, as a typical application of multiple autonomous underwater vehicle (AUV) systems, has been applied in the fields of territorial sea security and marine biology research. Among them, hunting task allocation is a key issue determining the effective application of multiple AUV systems. Therefore, this article proposes a hunting task assignment framework based on contract network (CN) to assign hunting tasks. In the investigated framework, the tenderee AUV (TAUV) is responsible for setting the task reward and assigning hunting tasks, while bidder AUVs (BAUVs) set the working time as bidding information. Combining the mobile energy consumption and communication energy consumption of hunter AUVs, we establish the revenue optimization model of BAUVs and the TAUV. Based on the above model, we model the interaction process of hunting task allocation process between BAUVs and the TAUV as a Stackelberg game, and use the backward induction method to prove that there is a unique Stackelberg equilibrium (SE) in the game. In addition, this article proposes a strategy search algorithm based on the steepest descent method (SSA_SDM) to obtain the optimal strategy of BAUVs and the TAUV, which can achieve SE. Finally, experimental results show that SSA_SDM can reach the SE and outperform other algorithms.

Accurate and reliable prediction of bearing remaining useful life (RUL) is crucial to the prognostics and health management of rotation machinery. Despite the rapid progress of data-driven methods, the generalizability of data-driven models remains an open issue to be addressed. In this article, we tackle this challenge by resolving the feature misalignment problem that arises in extracting features from the raw vibration signals. Toward this goal, we introduce a logarithmic cumulative transformation (LCT) operator consisting of cumulative, logarithmic, and another cumulative transformation for feature extraction. In addition, we propose a novel method to estimate the reliability associated with each RUL prediction by integrating a linear regression model and an auxiliary exponential model. The linear regression model rectifies bias from neural network's point predictions while the auxiliary exponential model fits the differential slopes of the linear models and generates the upper and lower bounds for building the reliability indicator. The proposed approach comprised of LCT, an attention GRU-based encoder–decoder network, and reliability evaluation is validated on the FEMETO-ST dataset. Computational results demonstrate the superior performance of the proposed approach several other state-of-the-art methods.

OBJECTIVE: Intracranial electroencephalogram (iEEG) signals are generally recorded using multiple channels, and channel selection is therefore a significant means in studying iEEG-based seizure prediction. For n channels, [Formula: see text] channel cases can be generated for selection. However, by this means, an increase in n can cause an exponential increase in computational consumption, which may result in a failure of channel selection when n is too large. Hence, it is necessary to explore reasonable channel selection strategies under the premise of controlling computational consumption and ensuring high classification accuracy. Given this, we propose a novel method of channel reordering strategy combined with dual CNN-LSTM for effectively predicting seizures. METHOD: First, for each patient with n channels, interictal and preictal iEEG samples from each single channel are input into the CNN-LSTM model for classification. Then, the F1-score of each single channel is calculated, and the channels are reordered in descending order according to the size of F1-scores (channel reordering strategy). Next, iEEG signals with an increasing number of channels are successively fed into the CNN-LSTM model for classification again. Finally, according to the classification results from n channel cases, the channel case with the highest classification rate is selected. RESULTS: Our method is evaluated on the three iEEG datasets: the Freiburg, the SWEC-ETHZ and the American Epilepsy Society Seizure Prediction Challenge (AES-SPC). At the event-based level, the sensitivities of 100%, 100% and 90.5%, and the false prediction rates (FPRs) of 0.10/h, 0/h and 0.47/h, are achieved for the three datasets, respectively. Moreover, compared to an unspecific random predictor, our method also shows a better performance for all patients and dogs from the three datasets. At the segment-based level, the sensitivities-specificities-accuracies-AUCs of 88.1%-94.0%-93.5%-0.9101, 99.1%-99.7%-99.6%-0.9935, and 69.2%-79.9%-78.2%-0.7373, are attained for the three datasets, respectively. CONCLUSION: Our method can effectively predict seizures and address the challenge of an excessive number of channels during channel selection.

Autonomous underwater vehicle (AUV) system has played an important role in complex Internet of Underwater Things (IoUT). As we know, single AUV is inefficient in collecting data in large-scale IoUT. In order to improve the timeliness of data, this article uses multiple AUVs with specific formation shape to collect sensory data. However, the intermittent and unreliable characteristics of underwater acoustic communication between AUVs seriously affects the performance of formation control. To solve this issue, this article mainly investigates formation control problem of leade–follower structured AUVs with state prediction estimation under the condition of unreliable underwater acoustic channel. First, a novel formation control law derived from backstepping sliding mode method is proposed, and then, a suitable Lyapunov functional is constructed to prove sufficient stability conditions. Second, Gaussian prediction model considering time delay and packet dropout has been designed to estimate the intermittent communication channel. Moreover, a new metric named formation uniform degree (FUD) is proposed to measure the degree of queue uniformity in a quantitative manner. Finally, extensive simulation results compared with traditional methods based on ideal channel model demonstrate the effectiveness of proposed formation control method.

Deep understanding the special nature of underwater topography plays an important role for Internet of Underwater Things (IoUT). Nowadays, underwater topography scanning with autonomous underwater vehicle (AUV) has been becoming the chief methodology of knowing seabed topography and geomorphology. How to design topography scanning trajectory can be mathematically described as a full coverage path planning (CPP) problem. In this article, facing the complete CPP problem of mobile AUV, a new strategy based on bio-inspired neural network (BINN) algorithm with improved activity value of each neuron is discussed in detail. The original activity value function in BINN is instead of a piecewise linear function to reduce computational complexity. In addition, to overcome traditional dead-zone problem, an A* path planning-based dead-zone escape method along the shorter path as early as possible to the recently uncovered area is described in deep. Extensive simulation results and practical experiments verify the performance of proposed Improved BINN (IBINN in short)-based algorithm.