Semi-supervised object detection (SSOD) mitigates the annotation burden in object detection by leveraging unlabeled data, providing a scalable solution for modern perception systems. Concurrently, detection transformers (DETRs) have emerged as a popular end-to-end framework, offering advantages such as non-maximum suppression (NMS)-free inference. However, existing SSOD methods are predominantly designed for conventional detectors, leaving the exploration of DETR-based SSOD largely uncharted. This paper presents a systematic study to bridge this gap. We begin by identifying two principal obstacles in semi-supervised DETR training: (1) the inherent one-to-one assignment mechanism of DETRs is highly sensitive to noisy pseudo-labels, which impedes training efficiency; and (2) the query-based decoder architecture complicates the design of an effective consistency regularization scheme, limiting further performance gains. To address these challenges, we propose Semi-DETR++, a novel framework for efficient SSOD with DETRs. Our approach introduces a stage-wise hybrid matching strategy that enhances robustness to noisy pseudo-labels by synergistically combining one-to-many and one-to-one assignments while preserving NMS-free inference. Furthermore, based on our observation of the unique layer-wise decoding behavior in DETRs, we develop a simple yet effective re-decode query consistency training method to regularize the decoder. Extensive experiments demonstrate that Semi-DETR++ enables more efficient semi-supervised learning across various DETR architectures, outperforming existing methods by significant margins. The proposed components are also flexible and versatile, showing superior generalization by readily extending to semi-supervised segmentation tasks.

Robust altitude tracking and attitude stabilization of a quadrotor helicopter (QH) operating in dynamic and uncertain environments remain challenging due to unknown external disturbances, time-varying parametric uncertainties, and practical actuator and sensor constraints. To address these challenges, this article proposes a neural-enhanced sliding-mode control (NE-SMC) framework that integrates a lightweight multilayer perceptron neural network (MLP-NN) with an SMC backbone within a unified adaptive control architecture. The neural module employs a sliding-mode-inspired weight-update law to enable real-time compensation for disturbances and uncertainties without requiring explicit disturbance models or prior knowledge of system parameters, thereby strengthening system-level robustness and adaptability. A rigorous Lyapunov-based analysis guarantees closed-loop stability and finite-time convergence of the tracking errors. Extensive high-fidelity simulations, including deterministic scenarios and a 100-run Monte Carlo study, are conducted under severe wind disturbances and turbulent conditions, up to 25% mass and inertia variations, actuator saturation, and sensor constraints. Comparative results demonstrate that the proposed NE-SMC achieves substantially improved tracking accuracy and robustness compared with standard SMC and conventional hybrid SMC (H-SMC) schemes. Specifically, the root-mean-square error (RMSE) is reduced by 83.3%–88.9% relative to standard SMC and by 75%–87.5% relative to conventional H-SMC. These results confirm that the proposed framework provides a robust, constraint-aware, and computationally efficient control solution suitable for real-time QH applications, aligning with the requirements of intelligent systems in complex, uncertain environments.

Conversational recommender systems (CRSs) aim to proactively capture user preferences through natural language dialogue and recommend high-quality items. To achieve this, CRS gathers user preferences via a dialog module and builds user profiles through a recommendation module to generate appropriate recommendations. However, existing CRS faces challenges in capturing the deep semantics of user preferences and dialogue context. In particular, the efficient integration of external knowledge graph (KG) information into dialogue generation and recommendation remains a pressing issue. Traditional approaches typically combine KG information directly with dialogue content, which often struggles with complex semantic relationships, resulting in recommendations that may not align with user expectations.

Personalized recommendation systems play a critical role in helping users discover relevant content amidst information overload. This paper proposes DisenRec, a novel sequential recommendation framework that addresses key limitations in existing approaches. By constructing a heterogeneous graph that incorporates multidimensional contextual information, we first learn initial user/item representations using a Heterogeneous Graph Attention Network. We then disentangle user preferences into dynamic interest preferences (modeling temporal behavioral patterns) and static attribute preferences (capturing stable trait-based inclinations) through causal decomposition and orthogonal constraints. A context-aware fusion module dynamically balances these components during prediction. Experiments on Amazon-Books and MovieLens-1M datasets demonstrate that DisenRec significantly outperforms state-of-the-art baselines in HR@10 and NDCG@10 metrics. Our model reduces representation entanglement, enhances preference modeling granularity, and improves both recommendation accuracy and interpretability by uncovering the causal mechanisms driving user decisions.

In Partial Multi-Label Learning (PML), each instance is associated with a candidate label set containing multiple relevant labels along with other false positive labels. Currently, most PML methods directly extract instance correlation from instance features while ignoring the candidate labels, which may contain more discriminative instance-related information. This paper argues that, with a well-designed model, more accurate instance correlation can be mined from the candidate labels to facilitate label disambiguation. To this end, we propose a novel PML method based on pseudo-label reconstruction (PML-PLR). Specifically, we first propose a novel orthogonal candidate label reconstruction method, which jointly optimizes with instance features to extract more consistent instance correlation. Then, we use instance correlation as reconstruction coefficient to reconstruct pseudo-labels. Subsequently, through local manifold learning, the reconstructed pseudo-labels are leveraged to propagate the consistency relationship between labels and instances, thereby improving the accuracy of pseudo-labels. Extensive experiments and analyses demonstrate that the proposed PML-PLR outperforms state-of-the-art methods.

Supervised cross-modal hashing has achieved remarkable progress in retrieving related items across different modalities. However, in practical applications, a significant portion of data remains unlabeled, such as online data on websites, which must be included for effective retrieval. To address this challenge, while maintaining the high accuracy and efficiency of supervised methods, few works have attempted to adapt existing supervised techniques to handle unsupervised tasks through a general modular approach. To this end, we introduce a novel cross-modal hashing method, termed Label Prediction Inherited Hashing (LPIH). Initially, LPIH leverages labeled data to learn high-quality general label functions using supervised methods. Subsequently, it inherits the existing hash codes from existing supervised methods to further refine the pseudo-label information. Finally, LPIH integrates the refined pseudo-label information with the existing hash functions to learn new hash functions specifically tailored for unsupervised tasks. Extensive experimental results on three public datasets demonstrate the superior performance of LPIH compared to state-of-the-art (SOTA) cross-modal hashing methods. Specifically, LPIH achieves an average precision improvement of 5% over SOTA methods, highlighting its effectiveness in bridging the gap between supervised and unsupervised learning in the context of cross-modal retrieval.

Autonomous driving has become an inevitable trend in automotive development. Reinforcement Learning (RL) is extensively used in autonomous vehicle motion planning, demonstrating good generalization but facing challenges of long training times and lack of consideration of uncertainty. To address these challenges, an Adaptive Heuristic Reinforcement Learning (AHRL) approach is proposed. First, this study improves upon the Dueling Double Deep Q Network (D3QN) algorithm by proposing the Adaptive Heuristic Dueling Double Deep Q Network (Adapt-HD3QN) algorithm. Specifically, heuristic functions from search-based planning algorithms are incorporated into the RL reward terms to guide heuristic learning and enhance learning efficiency. Additionally, considering the uncertainties in real-world driving environments, such as the movement of other traffic participants and building occlusions, a Mixed Artificial Potential Field (Mix-APF) is implemented to address static and dynamic obstacle avoidance. Furthermore, potential collisions between the autonomous vehicle and other vehicles in occluded areas are modeled as a zero-sum game, with a Dynamic Bayesian Network (DBN) used for prior modeling of potential vehicles, aiding in constructing the potential vehicle’s forward hidden set. Finally, a signal-free intersection scenario, a typical crash-prone road type, is constructed on CARLA, incorporating static obstacles and other traffic participants. Experimental results demonstrate that the proposed Adapt-HD3QN algorithm exhibits superior safety, training efficiency, and traffic efficiency in scenarios with road environment perception uncertainties caused by occlusion.

This study proposes a novel framework based on an entropy-informed graph neural network (EIGNN) integrated with Gaussian distribution (GD) to assess the driving risk of intelligent vehicles in typical traffic scenarios. Existing research often overlooks comprehensive spatiotemporal modeling of vehicle interaction characteristics and the quantification of uncertainty in dynamic risk assessments. In this work, vehicle speed and acceleration are probabilistically modeled using GD, while entropy theory is introduced to quantify risk uncertainty. A risk assessment model based on graph neural networks (GNNs) is then designed to capture the spatiotemporal dynamics of multivehicle interactions and predict the potential risk levels of driving strategies. The results demonstrate that the framework accurately quantifies collision risks in multivehicle interactions in complex traffic scenarios, with high accuracy and robustness across typical situations such as cruising, cut-ins, lane changes, overtaking, and different density traffic. By thoroughly analyzing traffic risk characteristics and incorporating them into intelligent driving decision-making, this study provides significant technical insights and theoretical support for enhancing the safety and decision-making efficiency of autonomous driving systems.

This study explores the effect of takeover time (TOT) on decision-making for Level-3 autonomous vehicles (L3-AVs). The existing research on L3-AV lacks an in-depth analysis of the mechanisms affecting TOT, ignores the importance of spatial and temporal variations in features for TOT prediction, and also lacks consideration of TOT in downstream trajectory planning tasks. This study proposed an exponential smoothing transformers (ETS) former model for TOT prediction, and then, the spatial-temporal predictive transformer (ST-Preformer) was employed to forecast the trajectories of surrounding vehicles, assess lane availability, and determine lane-changing probabilities. Ultimately, these evaluations contribute to the decision-making process of L3-AVs. The findings showed that the ETSformer was able to explain more than 83% of the characteristics of the TOT distribution in the TOT prediction task, effectively reducing the absolute percentage error by 0.7%, based on which the decision-making framework was able to make safe and comfortable optimal decisions. Decision-making is closely related to driving conditions and the surrounding traffic state, and TOT has a critical impact on the safety and stability of decision-making. A comprehensive understanding the impact of TOT on decision-making can help improve the safety of autonomous driving and provide guidance for improving decision-making techniques.

The path tracking control problem for autonomous vehicle with uncertain dynamics requires simultaneous consideration of control optimality and safety-based performance constraints. In this paper, an adaptive optimal control method with prescribed performance is proposed to solve this problem, which contains two contributions: 1) by introducing a prescribed performance function (PPF) into adaptive dynamic programming (ADP), the controller can constrain the tracking error of the system within a specified performance boundary while optimizing the control cost; 2) the critic-only ADP is used for the controller design, which simplifies the commonly used actor-critic ADP scheme, and the convergence of the estimation error is guaranteed under FE conditions. On this basis, the neural network identification technique is introduced to deal with the unknown dynamic parameters of the vehicle system. The control scheme is able to strictly guarantee user-defined vehicle performance specifications with approximately optimal control performance. The stability of the closed-loop system is rigorously demonstrated by the Lyapunov method. In addition, the controller also embeds a radial basis function neural network (RBFNN) compensator to approximate the nonlinear external disturbances of the autonomous vehicle. Finally, the efficiency of the controller to achieve autonomous vehicle path tracking is verified by CarSim-Simulink simulation.

Hashing-based techniques present appealing solutions for cross-modal retrieval due to its low storage requirements and excellent query efficiency. The majority of cross-modal hashing methods typically adopt equal-length encoding scheme to represent multimodal data and achieve cross-modal similarity search. However, such scheme can be regarded as a relatively strict limitation, because it sacrifices the flexible representation of multimodal data in reality and cannot always guarantee the optimal retrieval performance. To address the challenge, this paper focuses on encoding heterogeneous data with varying hash lengths. To achieve this purpose, we propose a flexible cross-modal hashing approach, named Two-stage Asymmetric Similarity Preserving Hashing, TASPH for short, which can be applied to both unequal-length and equal-length retrieval scenarios. Specifically, in the first stage, TASPH designs a novel discrete asymmetric strategy to learn the modality-specific hash codes with varying lengths, enabling a flexible representation of heterogeneous data. Simultaneously, TASPH utilizes two semantic transformation matrices to establish the semantic correlations between varying hash codes. Different from most of the existing approaches that employ relaxation solutions, TASPH satisfies the discrete constraints without any relaxation. In the second stage, the learned semantic transformation matrices are employed to alleviate cross-modal heterogeneity, which guarantees that TASPH can learn more powerful hash functions to improve the discriminative ability of hash codes. Abundant experiments conducted on three benchmark datasets demonstrate encouraging results compared with the state-of-the-art approaches under different retrieval scenarios.

Hashing techniques have been extensively studied in cross-modal retrieval due to their advantages in high computational efficiency and low storage cost. However, existing methods unconsciously ignore the complementary information of multimodal data, thus failing to consider learning discriminative hash codes from the perspective of information complementarity while often involving time-consuming training overhead. To tackle the above issues, we propose an efficient discriminative hashing (EDH) with information complementarity consideration. Specifically, we reckon that multimodal features and their corresponding semantic labels describe heterogeneous data viewed from low-and high-level structures, which owns complementarity. To this end, low-level latent representation and high-level semantics representation are simply derived. Then, a joint learning strategy is formulated to simultaneously exploit the above two representations for generating discriminative hash codes, which is quite computationally efficient. Besides, EDH decomposes hash learning into two steps. To obtain powerful hash functions which are conductive to retrieval, a regularization term considering pairwise semantic similarity is introduced into hash functions learning. In addition, an efficient optimization algorithm is designed to solve the optimization problem in EDH. Extensive experiments conducted on benchmark datasets demonstrate the superiority of our EDH in terms of retrieval performance and training efficiency. The source code is available at https://github.com/hjf-hjf/EDH.

This article presents an interacting multiple model (IMM) for short-term prediction and long-term trajectory prediction of an intelligent vehicle. This model is based on vehicle's physics model and maneuver recognition model. The long-term trajectory prediction is challenging due to the dynamical nature of the system and large uncertainties. The vehicle physics model is composed of kinematics and dynamics models, which could guarantee the accuracy of short-term prediction. The maneuver recognition model is realized by means of hidden Markov model, which could guarantee the accuracy of long-term prediction, and an IMM is adopted to guarantee the accuracy of both short-term prediction and long-term prediction. The experiment results of a real vehicle are presented to show the effectiveness of the prediction method.

This special issue of the IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (T-ASE) focuses on how the state-of-the-art achievements and applications in the general area of artificial intelligence in automation for autonomous unmanned systems applications. As Guest Editors, we are very pleased to present the selected 16 articles, whose topics are specifically related to artificial intelligence real-time object detection, recognition, localization, control optimization, motion planning, formation control, adaptive control, and autonomous decision-making.

This article presents a structure constraint matrix factorization framework for different behavior segmentation of the human behavior sequential data. This framework is based on the structural information of the behavior continuity and the high similarity between neighboring frames. Due to the high similarity and high dimensionality of human behavior data, the high-precision segmentation of human behavior is hard to achieve from the perspective of application and academia. By making the behavior continuity hypothesis, first, the effective constraint regular terms are constructed. Subsequently, the clustering framework based on constrained non-negative matrix factorization is established. Finally, the segmentation result can be obtained by using the spectral clustering and graph segmentation algorithm. For illustration, the proposed framework is applied to the Weiz dataset, Keck dataset, mo_86 dataset, and mo_86_9 dataset. Empirical experiments on several public human behavior datasets demonstrate that the structure constraint matrix factorization framework can automatically segment human behavior sequences. Compared to the classical algorithm, the proposed framework can ensure consistent segmentation of sequential points within behavior actions and provide better performance in accuracy.

Robotic grasping ability lags far behind human skills and poses a significant challenge in the robotics research area. According to the grasping part of an object, humans can select the appropriate grasping postures of their fingers. When humans grasp the same part of an object, different poses of the palm will cause them to select different grasping postures. Inspired by these human skills, in this article, we propose new grasping posture prediction networks (GPPNs) with multiple inputs, which acquire information from the object image and the palm pose of the dexterous hand to predict appropriate grasping postures. The GPPNs are further combined with grasping rectangle detection networks (GRDNs) to construct multilevel convolutional neural networks (ML-CNNs). In this study, a force-closure index was designed to analyze the grasping quality, and force-closure grasping postures were generated in the GraspIt! environment. Depth images of objects were captured in the Gazebo environment to construct the dataset for the GPPNs. Herein, we describe simulation experiments conducted in the GraspIt! environment, and present our study of the influences of the image input and the palm pose input on the GPPNs using a variable-controlling approach. In addition, the ML-CNNs were compared with the existing grasp detection methods. The simulation results verify that the ML-CNNs have a high grasping quality. The grasping experiments were implemented on the Shadow hand platform, and the results show that the ML-CNNs can accurately complete grasping of novel objects with good performance.

Radar and camera information fusion sensing methods are used to solve the inherent shortcomings of the single sensor in severe weather. Our fusion scheme uses radar as the main hardware and camera as the auxiliary hardware framework. At the same time, the Mahalanobis distance is used to match the observed values of the target sequence. Data fusion based on the joint probability function method. Moreover, the algorithm was tested using actual sensor data collected from a vehicle, performing real-time environment perception. The test results show that radar and camera fusion algorithms perform better than single sensor environmental perception in severe weather, which can effectively reduce the missed detection rate of autonomous vehicle environment perception in severe weather. The fusion algorithm improves the robustness of the environment perception system and provides accurate environment perception information for the decision-making system and control system of autonomous vehicles.

In intelligent driving, situational assessment (SA) is an important technology, which helps to improve the cognitive ability of intelligent vehicles in the environment. Uncertainty analysis is very significant in situation assessment. This article proposes an SA method based on uncertainty risk analysis. Under uncertain conditions, according to the random environment model and Gaussian distribution model, the collision probability between multiple vehicles is estimated by comprehensive trajectory prediction. The proposed method considers collision probabilities of different prediction points within and outside the prediction range and obtains long-term accurate prediction results. The method is suitable for the situation risk assessment of sensor systems in the presence of unexpected dynamic obstacles, sensor failures or communication losses in traffic, and different environmental sensing accuracy. The experimental results show that in the dynamic traffic environment, the proposed scenario assessment method can not only accurately predict and assess the situation risks within the prediction range, but also provide accurate scenario risk assessment outside the prediction range.

More natural and intuitive control is expected to maximize the auxiliary effect of the powered prosthetic leg for lower limb amputees. In order to realize the stable and flexible walking of prosthetic legs in different terrains according to human intention, a brain-computer interface (BCI) based on motor imagery (MI) is developed. For the raw electroencephalogram (EEG) signals, discrete wavelet transform (DWT) is utilized to extract the time-frequency domain features, which are used as the input signals of the common spatial pattern (CSP) to obtain the time-frequency-space domain features of EEG signals. Then, a support vector machine (SVM) classifier and a directed acyclic graph (DAG) structure are combined to classify multiclass imaginary tasks. According to the result of human intention recognition, the prosthetic leg performs the corresponding gait trajectory generated by coding the ground reaction force (GRF). In addition, a sensory feedback loop is established by functional electrical stimulation (FES), which feeds back the movement of the prosthetic leg to human in real time. The effectiveness and feasibility of the developed EEG-based volitional control of powered prosthetic legs have been validated by three subjects, all of whom were able to fulfill smoothly walking on the floor, ascending stairs, and descending stairs according to their own intentions using prosthetic legs.

Singularity issue has long been a concern of the task-space control design for Euler-Lagrange systems. In classical task-space controls, robots are often assumed to operate in the task space, where singularities do not exist. Such an assumption limits their potential applications in various workspaces. To address the potential singularity issue associated with Euler-Lagrange systems, this article proposes an adaptive fuzzy-region-based control for Euler-Lagrange systems with kinematically singular configurations. Singular regions are described by the potential energy function. The proposed controller includes a joint-space control, which is active when the system approaches singular regions, and a task-space control, which is used to track the desired trajectory. Therefore, the system can smoothly transit from singular regions to nonsingular regions or can achieve singularity avoidance during the tracking task. In order to achieve singularity avoidance while reducing control effort, the coefficients of the potential energy function are adjusted dynamically based on the designed fuzzy system. Rigorous analysis shows that singularity issues can be properly handled, and the asymptotic stability of the system is ensured. Experiments are conducted to demonstrate the effectiveness of the proposed controller.

This article investigates the integrated lane-keeping and roll control for autonomous ground vehicles (AGVs) considering the transient performance and system disturbances. The robust integral of the sign of error (RISE) control strategy is proposed to achieve the lane-keeping control purpose with rollover prevention, by guaranteeing the asymptotic stability of the closed-loop system, attenuating systematic disturbances, and maintaining the controlled states within the prescribed performance boundaries. Three contributions have been made in this article: 1) a new prescribed performance function (PPF) that does not require accurate initial errors is proposed to guarantee the tracking errors restricted within the predefined asymptotic boundaries; 2) a modified neural network (NN) estimator which requires fewer adaptively updated parameters is proposed to approximate the unknown vertical dynamics; and 3) the improved RISE control based on PPF is proposed to achieve the integrated control objective, which analytically guarantees both the controller continuity and closed-loop system asymptotic stability by integrating the signum error function. The overall system stability is proved with the Lyapunov function. The controller effectiveness and robustness are finally verified by comparative simulations using two representative driving maneuvers, based on the high-fidelity CarSim-Simulink simulation.

For human-robot co-manipulation by robotic exoskeletons, the interaction forces provide a communication channel through which the human and the robot can coordinate their actions. In this article, an optimization approach for reshaping the physical interactive trajectory is presented in the co-manipulation tasks, which combines impedance control to enable the human to adjust both the desired and the actual trajectories of the robot. Different from previous studies, the proposed method significantly reshapes the desired trajectory during physical human-robot interaction (pHRI) based on force feedback, without requiring constant human guidance. The proposed scheme first formulates a quadratically constrained programming problem, which is then solved by neural dynamics optimization to obtain a smooth and minimal-energy trajectory similar to the natural human movement. Then, we propose an adaptive neural-network controller based on the barrier Lyapunov function (BLF), which enables the robot to handle the uncertain dynamics and the joint space constraints directly. To validate the proposed method, we perform experiments on the exoskeleton robot with human operators for co-manipulation tasks. The experimental results demonstrate that the proposed controller could complete the co-manipulation tasks effectively.

To achieve better results on object detection for autonomous vehicle under complex outdoor conditions, we attempt to integrated the sensor-fusion, hierarchical multi-view networks and traditional heuristical method together. The most significant environmental perception sensors for autonomous vehicles are camera and LIDAR. The 2D RGB image and 3D point cloud from camera and LIDAR respectively are utilized. The hierarchical multi-view proposal network (HMVPN) is proposed in this paper, which can effectively fuse the multi-modal information of the camera with LIDAR. As there are several hierarchical network layers in HMVPN, image becomes the input of the primary network for object detection. Moreover, LIDAR data is divided into four projection image (HBV, IBV, HCV, DCV), and then combines its original 3D point cloud into hierarchical second network to generate candidate proposals using machine learning and heuristic methods. Several simulations on the famous autonomous vehicle benchmark of KITTI show that our approach obtains about 20% higher AP than the state-of-the-art methods.

In this paper, we first extract three different kinds of high-level features from LIDAR point cloud, and combine them into the DHA (Depth, Height and Angle) channels. Integrated with the traditional RGB image from camera, we build a rich feature-based road object classifier by training a deep convolutional neural network model with six-channel (RGBDHA) data. Subsequently, this deep convolution neural network is fed by the integration of spacial and RGB information. With additional upsampled LIDAR data, the classifier reaches higher accuracy than single RGB image base methods. Several simulations on the famous autonomous vehicle benchmark of KITTI show that our fusion-based classifier outperforms RGB-based approaches about 15% and reaches average accuracy of 96%.

This paper presents an object classification method for vision and light detection and ranging (LIDAR) fusion of autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image upsampling theory. By creating a point cloud of LIDAR data upsampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is also adopted to guarantee both object classification accuracy and minimal loss. Experimental results are presented and show the effectiveness and efficiency of object classification strategies.

In this work, we address a novel problem about tag co-occurrence relationship prediction across heterogeneous networks. Although tag co-occurrence has recently become a hot research topic, many studies mainly focus on how to produce the personalized recommendation leveraging the tag co-occurrence relationship and most of them are considered in a homogeneous network. So far, few studies pay attention to how to predict tag co-occurrence relationship across heterogeneous networks. In order to solve the aforementioned problem, we propose a novel two-step prediction approach. First, weight path-based topological features are systematically extracted from the network. Then, a supervised model is used to learn the best weights associated with different topological features in deciding the co-occurrence relationships. Experiments are performed on real-world dataset, the Flickr network, with comprehensive measurements. Experimental results demonstrate that weight path-based heterogeneous topological features have substantial advantages over commonly used link prediction approaches in predicting co-occurrence relations in information networks.