Adaptive Node Research Articles

Research on Trajectory Planning of Autonomous Vehicles in Constrained Spaces.

This paper addresses the challenge of trajectory planning for autonomous vehicles operating in complex, constrained environments. The proposed method enhances the hybrid A-star algorithm through back-end optimization. An adaptive node expansion strategy is introduced to handle varying environmental complexities. By integrating Dijkstra's shortest path search, the method improves direction selection and refines the estimated cost function. Utilizing the characteristics of hybrid A-star path planning, a quadratic programming approach with designed constraints smooths discrete path points. This results in a smoothed trajectory that supports speed planning using S-curve profiles. Both simulation and experimental results demonstrate that the improved hybrid A-star search significantly boosts efficiency. The trajectory shows continuous and smooth transitions in heading angle and speed, leading to notable improvements in trajectory planning efficiency and overall comfort for autonomous vehicles in challenging environments.

From emotional arousal to executive action. Role of the prefrontal cortex.

Emotional arousal is caused by the activity of two parallel ascending systems targeting mostly the subcortical limbic regions and the prefrontal cortex. The aversive, negative arousal system is initiated by the activity of the mesolimbic cholinergic system and the hedonic, appetitive, arousal is initiated by the activity of the mesolimbic dopaminergic system. Both ascending projections have a diffused nature and arise from the rostral, tegmental part of the brain reticular activating system. The mesolimbic cholinergic system originates in the laterodorsal tegmental nucleus and the mesolimbic dopaminergic system in the ventral tegmental area. Cholinergic and dopaminergic arousal systems have converging input to the medial prefrontal cortex. The arousal system can modulate cortical EEG with alpha rhythms, which enhance synaptic strength as shown by an increase in long-term potentiation (LTP), whereas delta frequencies are associated with decreased arousal and a decrease in synaptic strength as shown by an increase in long-term depotentiation (LTD). It is postulated that the medial prefrontal cortex is an adaptable node with decision making capability and may control the switch between positive and negative affect and is responsible for modifying or changing emotional state and its expression.

CAG-NSPDE: Continuous adaptive graph neural stochastic partial differential equations for traffic flow forecasting

Traffic flow forecasting, which aims to predict future traffic flow given historical data, is crucial for the planning and construction of urban transportation infrastructure. Existing methods based on discrete dynamic graphs are unable to model the smooth evolution of spatial relationships and usually have high computational cost. In addition, they ignore the effect of stochastic noise on the modeling of temporal dependencies, which lead to poor predictive performance on complex intelligent transportation systems. To address these issues, we propose continuous adaptive graph neural stochastic partial differential equation (CAG-NSPDE). A continuous graph is constructed based on learnable continuous adaptive node embeddings for the modeling of evolution of spatial dependencies. To explicitly model the effect of noise, a novel architecture based on stochastic partial differential equation (SPDE) is proposed. It can simultaneously extract features from the temporal and frequency domains by reducing SPDEs to a system of ODEs in Fourier space. We perform extensive experiments on four real-world datasets and the results demonstrate the superiority of CAG-NSPDE compared with state-of-the-arts.

Adaptive node feature extraction in graph-based neural networks for brain diseases diagnosis using self-supervised learning

Electroencephalography (EEG) has demonstrated significant value in diagnosing brain diseases. In particular, brain networks have gained prominence as they offer additional valuable insights by establishing connections between EEG signal channels. While brain connections are typically delineated by channel signal similarity, there lacks a consistent and reliable strategy for ascertaining node characteristics. Conventional node features such as temporal and frequency domain properties of EEG signals prove inadequate for capturing the extensive EEG information. In our investigation, we introduce a novel adaptive method for extracting node features from EEG signals utilizing a distinctive task-induced self-supervised learning technique. By amalgamating these extracted node features with fundamental edge features constructed using Pearson correlation coefficients, we showed that the proposed approach can function as a plug-in module that can be integrated to many common GNN networks (e.g., GCN, GraphSAGE, GAT) as a replacement of node feature selections module. Comprehensive experiments are then conducted to demonstrate the consistently superior performance and high generality of the proposed method over other feature selection methods in various of brain disorder prediction tasks, such as depression, schizophrenia, and Parkinson’s disease. Furthermore, compared to other node features, our approach unveils profound spatial patterns through graph pooling and structural learning, shedding light on pivotal brain regions influencing various brain disorder prediction based on derived features.

Open-Set Graph Domain Adaptation via Separate Domain Alignment

Domain adaptation has become an attractive learning paradigm, as it can leverage source domains with rich labels to deal with classification tasks in an unlabeled target domain. A few recent studies develop domain adaptation approaches for graph-structured data. In the case of node classification task, current domain adaptation methods only focus on the closed-set setting, where source and target domains share the same label space. A more practical assumption is that the target domain may contain new classes that are not included in the source domain. Therefore, in this paper, we introduce a novel and challenging problem for graphs, i.e., open-set domain adaptive node classification, and propose a new approach to solve it. Specifically, we develop an algorithm for efficient knowledge transfer from a labeled source graph to an unlabeled target graph under a separate domain alignment (SDA) strategy, in order to learn discriminative feature representations for the target graph. Our goal is to not only correctly classify target nodes into the known classes, but also classify unseen types of nodes into an unknown class. Experimental results on real-world datasets show that our method outperforms existing methods on graph domain adaptation.

Heterogeneous Graph Neural Network for Power Allocation in Multicarrier-Division Duplex Cell-Free Massive MIMO Systems

In order to maximize the spectral efficiency (SE) in multicarrier-division duplex (MDD) enabled cell-free massive MIMO (CF-mMIMO), a heterogeneous graph neural network (HGNN), referred to as CF-HGNN, is specifically introduced to optimize the power allocation (PA). To efficiently manage the interference invoked, a meta-path based mechanism is applied in CF-HGNN to enable individual access point (AP) and mobile station (MS) nodes to aggregate information from the interfering and communication paths with different priorities during message passing. Moreover, the proposed CF-HGNN employs the adaptive node embedding layer and adaptive output layer to make it scalable to the various numbers of APs, MSs and subcarriers. For comparison, a quadratic transform and successive convex approximation (QT-SCA) algorithm is proposed to solve the PA problem in classic way. Numerical results show that CF-HGNN is capable of achieving 99% of the SE achievable by QT-SCA but using only 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-4</sup> times of its operation time, and it can outperform the conventional learning-based and greedy unfair methods in terms of SE performance. Furthermore, CF-HGNN exhibits good scalability to the CF networks with various numbers of nodes and subcarriers, and also to the large-scale CF networks when assisted by user-centric clustering.

Enhancing anomaly detection with adaptive node inspection in large-scale networks with binary sensors

Maintaining the stability and reliability of large-scale networks and graph structures is a practical challenge, particularly in sensor-intensive systems. One critical task in such networks is to identify anomalies and the origin of disturbances in a timely manner. However, successful anomaly detection requires sufficient and accurate data from sensors across the network. This work aims to develop an innovative framework to improve the accuracy of anomaly detection tasks with binary sensor data through intelligent node selection and inspection. Instead of relying only on stochastic insights obtained from network sensors, we explore how a specific small set of nodes can be inspected using a Bayesian framework so that the anomaly detection performance is improved. We demonstrate the effectiveness of the proposed model with a set of numerical experiments.

Enhancing Smart Building Surveillance Systems in Thin Walls: An Efficient Barrier Design.

This paper introduces an efficient barrier model for enhancing smart building surveillance in harsh environment with thin walls and structures. After the main research problem of minimizing the total number of wall-recognition surveillance barriers, we propose two distinct algorithms, Centralized Node Deployment and Adaptation Node Deployment, which are designed to address the challenge by strategic placement of surveillance nodes within the smart building. The Centralized Node Deployment aligns nodes along the thin walls, ensuring consistent communication coverage and effectively countering potential disruptions. Conversely, the Adaptation Node Deployment begins with random node placement, which adapts over time to ensure efficient communication across the building. The novelty of this work is in designing a novel barrier system to achieve energy efficiency and reinforced surveillance in a thin-wall environment. Instead of a real environment, we use an ad hoc server for simulations with various scenarios and parameters. Then, two different algorithms are executed through those simulation environments and settings. Also, with detailed discussions, we provide the performance analysis, which shows that both algorithms deliver similar performance metrics over extended periods, indicating their suitability for long-term operation in smart infrastructure.

Graph Pooling Inference Network for Text-based VQA

Effectively leveraging objects and optical character recognition (OCR) tokens to reason out pivotal scene text is critical for the challenging Text-based Visual Question Answering (TextVQA) task. Graph-based models can effectively capture the semantic relationship among visual entities (objects and tokens) and report remarkable performance in TextVQA. However, previous efforts usually leverage all visual entities and ignore the negative effect of superfluous entities. This article presents a Graph Pooling Inference Network (GPIN), which is an evolutionary graph learning method to purify the visual entities and capture the core semantics. It is observed that the dense distribution of reduplicative objects and the crowd of semantically dependent OCR tokens usually co-exist in the image. Motivated by this, GPIN adopts an adaptive node dropping strategy to dynamically downscale semantically closed nodes for graph evolution and update. To deepen the comprehension of scene text, GPIN is a dual-path hierarchical graph architecture that progressively aggregates the evolved object graph and the evolved token graph semantics into a graph vector that serves as visual cues to facilitate the answer reasoning. It can effectively eliminate object redundancy and enhance the association of semantically continuous tokens. Experiments conducted on TextVQA and ST-VQA datasets show that GPIN achieves promising performance compared with state-of-the-art methods.

Adaptive Hard Parameter Sharing Method Based on Multi-Task Deep Learning

Multi-task learning (MTL) improves the performance achieved on each task by exploiting the relevant information between tasks. At present, most of the mainstream deep MTL models are based on hard parameter sharing mechanisms, which can reduce the risk of model overfitting. However, negative knowledge transfer may occur, which hinders the performance improvement achieved for each task. In this paper, for situations when multiple tasks are jointly trained, we propose the adaptive hard parameter sharing method. On the basis of the adaptive hard parameter sharing method, the number of nodes in the network is dynamically updated by setting a continuous gradient difference-based sign threshold and a warm-up training iteration threshold through the relationships between the parameters and the loss function. After each task fully utilizes the shared information, adaptive nodes are used to further optimize each task, reducing the impact of negative migration. By using simulation studies and instance analyses, we demonstrate theoretical proof that the performance of the proposed method is better than that of the competing method.

Attention based adaptive spatial–temporal hypergraph convolutional networks for stock price trend prediction

Stock price trend prediction is an important and challenging issue, and accurate forecasting will effectively improve investment decisions and contribute to investment returns. Improving prediction accuracy by exploring stock correlations has received much attention in recent studies. However, there are still some issues that have not been fully considered, such as the impact of invalid correlations, low sensitivity to minor price fluctuations and dependence on priors expert information. To solve the above issues, we propose a novel spatial–temporal framework, which has several characteristics: (1) the noise-aware spatial–temporal attention that dynamically filters out invalid associations from traditional spatial attention and combines temporal attention to capture the spatial–temporal patterns of different stock series; (2) the adaptive stock hypergraph generation maps the intrinsic associations of stocks into a trainable dense matrix via adaptive node embedding; (3) the adaptive graph convolution extends the graph convolution operation from static graphs to adaptive hypergraphs for exploring the dynamic correlations. (4) Multiple stacked attention-based adaptive spatial–temporal Blocks form the end-to-end prediction framework, which uses time-aware cascaded convolution to extract fine-grained temporal features. Convincing experimental results on two stock datasets, studies on the performance on various simulation investments and the model interpretability confirm the advantages of our approach.

Clustering-based dragonfly optimization algorithm for underwater wireless sensor networks

Communication and monitoring of the undersea environment have numerous applications, including marine environment studies, offshore research, and mineral extraction. However, factors like as the presence of an underwater current, a limited bandwidth, high water pressure, propagation lag, and error probability make these applications more difficult to implement. Underwater communication might be challenging due to the surroundings. As a clustering approach for sensor nodes in underwater wireless sensor networks (UWSNs), we present a clustering-based dragonfly optimisation (CDFO) algorithm with decentralised forwarding over wireless networks. The CDFO-UWSN approach is used to determine how many clusters should be used for routing. Analogous algorithms have been found to be connected to the proposed method, including the Ant Colony Optimizer (ACO), Adaptive Node Clustering for UWSN (ANC-UWSN), Grey Wolf Optimizer (GWO), and Moth Flame Optimizer (MFO). During the simulation, a performance matrix will be used to account for a variety of parameters such as grid size, transmission range, and node density. The results show that CDFO-UWSN outperforms all other algorithms tested. By establishing more clusters than competing systems, it improves overall routing and boosts network lifetime. This enables a network to run for an extended amount of time. The proposed CDFO-UWSN algorithm outperforms the GWO, ACO, MFO, and DFO algorithms in terms of number of nodes, with a percentage improvement of 78.13 % for 1500*1500 m grid size, and a percentage improvement of 64.71 % in terms of transmission range for 1500*1500 m grid size.

Layer adaptive node selection in Bayesian neural networks: Statistical guarantees and implementation details

Sparse deep neural networks have proven to be efficient for predictive model building in large-scale studies. Although several works have studied theoretical and numerical properties of sparse neural architectures, they have primarily focused on the edge selection. Sparsity through edge selection might be intuitively appealing; however, it does not necessarily reduce the structural complexity of a network. Instead pruning excessive nodes leads to a structurally sparse network with significant computational speedup during inference. To this end, we propose a Bayesian sparse solution using spike-and-slab Gaussian priors to allow for automatic node selection during training. The use of spike-and-slab prior alleviates the need of an ad-hoc thresholding rule for pruning. In addition, we adopt a variational Bayes approach to circumvent the computational challenges of traditional Markov Chain Monte Carlo (MCMC) implementation. In the context of node selection, we establish the fundamental result of variational posterior consistency together with the characterization of prior parameters. In contrast to the previous works, our theoretical development relaxes the assumptions of the equal number of nodes and uniform bounds on all network weights, thereby accommodating sparse networks with layer-dependent node structures or coefficient bounds. With a layer-wise characterization of prior inclusion probabilities, we discuss the optimal contraction rates of the variational posterior. We empirically demonstrate that our proposed approach outperforms the edge selection method in computational complexity with similar or better predictive performance. Our experimental evidence further substantiates that our theoretical work facilitates layer-wise optimal node recovery.

Multitarget Real-Time Path Planning Using Double Adaptive A Algorithm

Multi-target real-time path planning (MTRT) is an extension of path planning that aims to traverse multiple targets in an unknown environment at the lowest cost. The MTRT is gov-erned by the “multi-target” demand leading to a rather extensive search space and the “real-time” requirement that imposes fast planning. However, the traditional path planning algorithm A* is notoriously inefficient in large spaces. Therefore, spurred by the low efficiency of A* for MTRT, this paper proposes the double adaptive A algorithm (DAA), which implements an adaptive multi-target heuristic function and an adaptive node expansion method to accelerate planning. The suggested method is evaluated utilizing two approaches to establishing the search space, i.e., decompose MTRT into traditional path planning problems and involve one target at a time, and consider all unsearched targets while planning. Simulations in discrete grid maps demonstrate that DAA provides at least equivalent searching paths to A* and other algorithms, but at much less running time.

HiGRN: A Hierarchical Graph Recurrent Network for Global Sea Surface Temperature Prediction

Sea surface temperature (SST) is one critical parameter of global climate change, and accurate SST prediction is important to various applications, e.g., weather forecasting, fishing directions, and disaster warnings. The global ocean system is unified and complex, and the SST patterns in different oceanic regions are highly diverse and correlated. However, existing data-driven SST prediction methods mainly consider the local patterns within a certain oceanic region, e.g., El Nino region and the Black sea. It is challenging but necessary to model the global SST correlations rather than that in a specific region to enhance the prediction accuracy of SST. In this work, we proposed a new method called Hierarchical Graph Recurrent Network (HiGRN) to address the issue. First, to learn the dynamic and diverse local SST patterns of specific locations, we design an adaptive node embedding with self-learned parameters to learn various SST patterns. Then we develop a hierarchical cluster generator to aggregate the locations with similar patterns into regional clusters and utilize a graph convolution network to learn the spatial correlations among these clusters. Finally, we introduce a multi-level attention mechanism to fuse the local patterns and regional correlations, and the output is fed into a recurrent network to achieve SST predictions. Extensive experiments on two real-world datasets show that our method largely outperforms the state-of-the-art SST prediction methods. The source code is available at https://github.com/Neoyanghc/HiGRN .

Path planning algorithm of robot arm based on improved RRT* and BP neural network algorithm

To address the issues of slow motion planning, low efficiency, and high path calculation cost of the six-degrees of freedom manipulator in three dimensional multi-obstacle narrow space, a path planning method of the manipulator based on Back Propagation (BP) neural network and improved Rapidly expanding Random Tree* (RRT*) algorithm is proposed (referred to as BP-RRT*). Due to the spherical envelope of the obstacle, this method evaluates the connection between the path and obstacle in space using the triangular function and identifies the collision-free path in 3D space. Then, using the sampling space division, obstacles discretization, and distance weight function, the adaptive node sampling probability method of RRT* algorithm in space is proposed, to reduce unnecessary sampling nodes and optimize the sampling efficiency; because the sampling nodes might fall into the area with dense obstacles, which results in significant increase in the search time. A stepwise sampling method is proposed to modify the global search into a phased local search, train the BP neural network model, forecast the number of node samples in the local search at each stage, automatically guide the algorithm into the next stage to complete the search, and improve the path optimization efficiency. Finally, the simulation experiment of the improved BP-RRT* algorithm is executed on the Python and Robot Operating System, and the physical experiment is done on the Baxter manipulator. The effectiveness and superiority of the improved algorithm are determined by comparing it with the existing algorithms.

Dumpy: A Compact and Adaptive Index for Large Data Series Collections

Data series indexes are necessary for managing and analyzing the increasing amounts of data series collections that are nowadays available. These indexes support both exact and approximate similarity search, with approximate search providing high-quality results within milliseconds, which makes it very attractive for certain modern applications. Reducing the pre-processing (i.e., index building) time and improving the accuracy of search results are two major challenges. DSTree and the iSAX index family are state-of-the-art solutions for this problem. However, DSTree suffers from long index building times, while iSAX suffers from low search accuracy. In this paper, we identify two problems of the iSAX index family that adversely affect the overall performance. First, we observe the presence of a proximity-compactness trade-off related to the index structure design (i.e., the node fanout degree), significantly limiting the efficiency and accuracy of the resulting index. Second, a skewed data distribution will negatively affect the performance of iSAX. To overcome these problems, we propose Dumpy, an index that employs a novel multi-ary data structure with an adaptive node splitting algorithm and an efficient building workflow. Furthermore, we devise Dumpy-Fuzzy as a variant of Dumpy which further improves search accuracy by proper duplication of series. Experiments with a variety of large, real datasets demonstrate that the Dumpy solutions achieve considerably better efficiency, scalability and search accuracy than its competitors.

PeerRemove: An adaptive node removal strategy for P2P botnet based on deep reinforcement learning

Botnets have become one of the major intrusion threats to cybersecurity. P2P botnets have high concealment and resilience because of their distributed structure, which are difficult to be completely dismantled and destroyed. Existing methods based on traffic statistics and vulnerability tracing cannot effectively solve the problem of P2P botnet disintegration. Although P2P networks emphasize that each node is peer-to-peer, the difference in processing power, resource distribution, and node bandwidth can lead to a certain heterogeneity. The critical nodes bridge the underlying bot nodes and the upper control server. Traditional methods for ranking the importance of nodes mainly relies on classical graph-theoretic feature statistics method, such as degree, betweenness, clustering coefficient, feature vector centrality, PageRank, etc. In this paper, botnet defense strategies are investigated from the perspective of complex network graph theory, and graph embedding and deep reinforcement learning combination optimization methods are adopted to handle the critical nodes identification problem of P2P botnets. Then, a novel adaptive node removal model called PeerRemove is proposed. The model uses Structure2vec graph embedding to characterize the network structure information as a low-dimensional embedding space, and it uses n-step Q-learning to train the model to learn complex topological patterns to find the critical nodes that effectively disintegrate the network. To evaluate the effectiveness of the proposed method, the Area Under the Curve (AUC) of the Largest Connected Component (LCC) size during node removal is used as an evaluation indicator, and six different types real or synthetic P2P botnets are selected, namely Sality, ZeroAccess, NSIS, Mozi, Gnutella, and Peer sampling service. Experiments are conducted on many real and model networks with node sizes reaching thousands and tens of thousands, and our method is compared with five classical static or dynamic node attack methods of HAD, PageRank, CI, BPD, and HPRA. The experimental results show that the overall AUC curve of the PeerRemove method is lower than that of the benchmark method, which can minimize botnet resiliency at a small cost. The proposed method is superior to the existing node removal methods and shows good robustness and feasibility. To demonstrate the generality of this method, it is tested on a centralized topological dataset and good experimental results are obtained.

A Novel Dynamic Transmission Power of Cluster Heads Based Clustering Scheme

Clustering methods are promising tools for ensuring the network scalability and maintainability of large-scale flying ad hoc networks (FANETs). However, due to the high mobility and limited energy resources of unmanned aerial vehicles (UAVs), it is difficult to maintain the network reliability and extend the network life of FANETs. In this paper, a new K-means algorithm is developed, and a dynamic transmission power of the cluster heads based clustering (DTPCH-C) scheme is proposed. The goal of this scheme is presented for FANETs to improve the reliability and lifetime of FANETs. Firstly, the optimal number of clusters is calculated and the initial UAV clusters are set up by a K-means algorithm. Then, using a weighted clustering algorithm, the adaptive node degree, the node energy and the distance from the cluster head are weighted and summed for the cluster head election. In the process of inter-cluster communication, the cluster head adjusts its transmit power in real-time through meshing and mobile prediction, thus saving the energy consumption and improving the network lifetime. The proposed DTPCH-C simultaneously optimizes the cluster number, the cluster head energy consumption, the selected cluster head, and the cluster maintenance process. The simulation results show that compared with traditional clustering methods, the proposed DTPCH-C has obvious advantages in terms of the network reliability, network life, and energy consumption.

Performance Improvement through Novel Adaptive Node and Container Aware Scheduler with Resource Availability Control in Hadoop YARN

Performance Improvement through Novel Adaptive Node and Container Aware Scheduler with Resource Availability Control in Hadoop YARN