Complex & Intelligent Systems最新文献

Abstract

To improve the accuracy of remote-sensing image semantic segmentation in complex scenario, an improved DeepLabv3+ lightweight neural network is proposed. Specifically, the lightweight network MobileNetv2 is used as the backbone network. In atrous spatial pyramid pooling (ASPP), to alleviate the gridding effect, the Dilated Convolution in original DeepLabv3+ network is replaced with the Hybrid Dilated Convolution (HDC) module. In addition, the traditional spatial mean pooling is replaced by the strip pooling module (SPN) to improve the local segmentation effect. In the decoder, to obtain the rich low-level target edge information, the ResNet50 residual network is added after the low-level feature fusion. To enhance the shallow semantic information, the efficient and lightweight Normalization-based Attention Module (NAM) is added to capture the feature information of small target objects. The results show that, under the INRIA Aerial Image Dataset and same parameter setting, the Mean Pixel Accuracy (MPA) and Mean Intersection over Union (MIoU) are generally best than DeepLabv3+ , U-Net, and PSP-Net, which are respectively improved by 1.22%, − 0.22%, and 2.22% and 2.17%, 1.35%, and 3.42%. Our proposed method has also a good performance on the small object segmentation and multi-object segmentation. What’s more, it significantly converges faster with fewer model parameters and stronger computing power while ensuring the segmentation effect. It is proved to be robust and can provide a methodological reference for high-precision remote-sensing image semantic segmentation.

Accurate target detection in complex orchard environments is the basis for automatic picking and pollination. The characteristics of small, clustered and complex interference greatly increase the difficulty of detection. Toward this end, we explore a detector in the orchard and improve the detection ability of complex targets. Our model includes two core designs to make it suitable for reducing the risk of error detection due to small and camouflaged object features. Multi-scale texture enhancement design focuses on extracting and enhancing more distinguishable features for each level with multiple parallel branches. Our adaptive region-aware feature fusion module extracts the dependencies between locations and channels, potential cross-relations among different levels and multi-types information to build distinctive representations. By combining enhancement and fusion, experiments on various real-world datasets show that the proposed network can outperform previous state-of-the-art methods, especially for detection in complex conditions.

The present-day globalized economy and diverse market demands have compelled an increasing number of manufacturing enterprises to move toward the distributed manufacturing pattern and the model of multi-variety and small-lot. Taking these two factors into account, this study investigates an extension of the distributed hybrid flowshop scheduling problem (DHFSP), called the distributed hybrid flowshop scheduling problem with consistent sublots (DHFSP_CS). To tackle this problem, a mixed integer linear programming (MILP) model is developed as a preliminary step. The NP-hard nature of the problem necessitates the use of the iterated F-Race (I/F-Race) as the automated algorithm design (AAD) to compose a metaheuristic that requires minimal user intervention. The I/F-Race enables identifying the ideal values of numerical and categorical parameters within a promising algorithm framework. An extension of the collaborative variable neighborhood descent algorithm (ECVND) is utilized as the algorithm framework, which is modified by intensifying efforts on the critical factories. In consideration of the problem-specific characteristics and the solution encoding, the configurable solution initializations, configurable solution decoding strategies, and configurable collaborative operators are designed. Additionally, several neighborhood structures are specially designed. Extensive computational results on simulation instances and a real-world instance demonstrate that the automated algorithm conceived by the AAD outperforms the CPLEX and other state-of-the-art metaheuristics in addressing the DHFSP_CS.

In current piece of writing, we bring in the new notion of induced bipolar neutrosophic (BN) AOs by utilizing Einstein operations as the foundation for aggregation operators (AOs), as well as to endow having a real-world problem-related application. The neutrosophic set can rapidly and more efficiently bring out the partial, inconsistent, and ambiguous information. The fundamental definitions and procedures linked to the basic bipolar neutrosophic (BN) set as well as the neutrosophic set (NS), are presented first. Our primary concern is the induced Einstein AOs, like, induced bipolar neutrosophic Einstein weighted average (I-BNEWA), induced bipolar neutrosophic Einstein weighted geometric (I-BNEWG), as well as their different types and required properties. The main advantage of employing the offered methods is that they give decision-makers a more thorough analysis of the problem. These strategies whenever compare to on hand methods, present complete, progressively precise, and accurate result. Finally, utilizing a numerical representation of an example for selection of robot, for a problem involving multi-criteria community decision making, we propose a novel solution. The suitability ratings are then ranked to select the most suitable robot. This demonstrates the practicality as well as usefulness of these novel approaches.

Activities of daily living (ADLs) relate to people’s daily self-care activities, which reflect their living habits and lifestyle. A prior study presented a neural network model called STADLART for ADL routine learning. In this paper, we propose a cognitive model named Spatial-Temporal Episodic Memory for ADL (STEM-ADL), which extends STADLART to encode event sequences in the form of distributed episodic memory patterns. Specifically, STEM-ADL encodes each ADL and its associated contextual information as an event pattern and encodes all events in a day as an episode pattern. By explicitly encoding the temporal characteristics of events as activity gradient patterns, STEM-ADL can be suitably employed for activity prediction tasks. In addition, STEM-ADL can predict both the ADL type and starting time of the subsequent event in one shot. A series of experiments are carried out on two real-world ADL data sets: Orange4Home and OrdonezB, to estimate the efficacy of STEM-ADL. The experimental results indicate that STEM-ADL is remarkably robust in event retrieval using incomplete or noisy retrieval cues. Moreover, STEM-ADL outperforms STADLART and other state-of-the-art models in ADL retrieval and subsequent event prediction tasks. STEM-ADL thus offers a vast potential to be deployed in real-life healthcare applications for ADL monitoring and lifestyle recommendation.

Deep learning demonstrates impressive performance in many medical image analysis tasks. However, its reliability builds on the labeled medical datasets and the assumption of the same distributions between the training data (source domain) and the test data (target domain). Therefore, some unsupervised medical domain adaptation networks transfer knowledge from the source domain with rich labeled data to the target domain with only unlabeled data by learning domain-invariant features. We observe that conventional adversarial-training-based methods focus on the global distributions alignment and may overlook the class-level information, which will lead to negative transfer. In this paper, we attempt to learn the robust features alignment for the cross-domain medical image analysis. Specifically, in addition to a discriminator for alleviating the domain shift, we further introduce an auxiliary classifier to achieve robust features alignment with the class-level information. We first detect the unreliable target samples, which are far from the source distribution via diverse training between two classifiers. Next, a cross-classifier consistency regularization is proposed to align these unreliable samples and the negative transfer can be avoided. In addition, for fully exploiting the knowledge of unlabeled target data, we further propose a within-classifier consistency regularization to improve the robustness of the classifiers in the target domain, which enhances the unreliable target samples detection as well. We demonstrate that our proposed dual-consistency regularizations achieve state-of-the-art performance on multiple medical adaptation tasks in terms of both accuracy and Macro-F1-measure. Extensive ablation studies and visualization results are also presented to verify the effectiveness of each proposed module. For the skin adaptation results, our method outperforms the baseline and the second-best method by around 10 and 4 percentage points. Similarly, for the COVID-19 adaptation task, our model achieves consistently the best performance in terms of both accuracy (96.93%) and Macro-F1 (86.52%).

The dynamics of swarm robotic systems are complex and often nonlinear. One key issue is to design the controllers of a large number of simple, low-cost robots so that emergence can be observed. This paper presents a sensor and computation-friendly controller for swarm robotic systems inspired by the mechanisms observed in algae. The aim is to achieve uniform dispersion of robots by mimicking the circular movement observed in marine algae systems. The proposed controller utilizes binary sensory information (i.e., see or not see) to guide the robots’ motion. By moving circularly and switching the radii based on the perception of other robots in their line of sight, the robots imitate the repulsion behavior observed in algae. The controller relies solely on binary-state sensory input, eliminating the need for additional memory or communication. Up to 1024 simulated robots are used to validate the effectiveness of the dispersion controller, while experiments with 30 physical robots demonstrate the feasibility of the proposed approach.

Sleep stage classification is essential in evaluating sleep quality. Sleep disorders disrupt the periodicity of sleep stages, especially the common obstructive sleep apnea (OSA). Many methods only consider how to effectively extract features from physiological signals to classify sleep stages, ignoring the impact of OSA on sleep staging. We propose a structured sleep staging network (SSleepNet) based on OSA to solve the above problem. This research focused on the effect of sleep apnea patients with different severity on sleep staging performance and how to reduce this effect. Considering that the transfer relationship between sleep stages of OSA subjects is different, SSleepNet learns comprehensive features and transfer relationships to improve the sleep staging performance. First, the network uses the multi-scale feature extraction (MSFE) module to learn rich features. Second, the network uses a structured learning module (SLM) to understand the transfer relationship between sleep stages, reducing the impact of OSA on sleep stages and making the network more universal. We validate the model on two datasets. The experimental results show that the detection accuracy can reach 84.6% on the Sleep-EDF-2013 dataset. The detection accuracy decreased slightly with the increase of OSA severity on the Sleep Heart Health Study (SHHS) dataset. The accuracy of healthy subjects to severe OSA subjects ranged from 79.8 to 78.4%, with a difference of only 1.4%. It shows that the SSleepNet can perform better sleep staging for healthy and OSA subjects.

Despite the ability of 3D convolutional methods to extract spatio-temporal information simultaneously, they also increase parameter redundancy and computational and storage costs. Previous work that has utilized the 2D convolution method has approached the problem in one of two ways: either using the entire body sequence as input to extract global features or dividing the body sequence into several parts to extract local features. However, global information tends to overlook detailed information specific to each body part, while local information fails to capture relationships between local regions. Therefore, this study proposes a new framework for constructing spatio-temporal representations, which involves extracting and fusing features in a novel manner. To achieve this, we introduce the multi-feature extraction-fusion (MFEF) module, which includes two branches: each branch extracts global features or local features individually, after which they are fused using multiple strategies. Additionally, as gait is a periodic action and different body parts contribute unequally to recognition during each cycle, we propose the periodic temporal feature modeling (PTFM) module, which extracts temporal features from adjacent frame parts during the complete gait cycle, based on the fused features. Furthermore, to capture fine-grained information specific to each body part, our framework utilizes multiple parallel PTFMs to correspond with each body part. We conducted a comprehensive experimental study on the widely used public dataset CASIA-B. Results indicate that the proposed approach achieved an average rank-1 accuracy of 97.2% in normal walking conditions, 92.3% while carrying a bag during walking, and 80.5% while wearing a jacket during walking.

With the continuous advancement of deep space exploration missions, the solar system boundary exploration mission is established as one of the China's most important deep space scientific exploration missions. The mission of the solar system boundary exploration has many challenges such as ultra-remote detection distance, ultra-long operation time, and ultra-long communication delay. Therefore, the problem of high-precision autonomous navigation needs to be solved urgently. This paper designs an autonomous intelligent navigation method based on X-ray pulsars in the cruise phase, which estimate the motion state of the probe in real time. The proposed navigation method employs the Q-learning Extended Kalman filter (QLEKF) to improve navigation accuracy during long periods of self-determining running. The QLEKF selects automatically the error covariance matrix parameter of the process noise and the measurement noise by the reward mechanism of reinforcement learning. Compared to the traditional EKF and AEKF, the QLEKF improves the estimation accuracy of position and velocity. Finally, the simulation result demonstrates the effectiveness and the superiority of the intelligent navigation algorithm based on QLEKF, which can satisfy the high-precision navigation requirements in the cruise phase of the solar system boundary exploration.