Search

Abstract In nature, coenzyme-independent oxidases have evolved in selective catalysis using isolated substrate-binding pockets. Single-atom nanozymes (SAzymes), an emerging type of non-protein artificial enzymes, are promising to simulate enzyme active centers, but owing to the lack of recognition sites, realizing substrate specificity is a formidable task. Here we report a metal-ligand dual-site SAzyme (Ni-DAB) that exhibited selectivity in uric acid (UA) oxidation. Ni-DAB mimics the dual-site catalytic mechanism of urate oxidase, in which the Ni metal center and the C atom in the ligand serve as the specific UA and O2 binding sites, respectively, characterized by synchrotron soft X-ray absorption spectroscopy, in situ near ambient pressure X-ray photoelectron spectroscopy, and isotope labeling. The theoretical calculations reveal the high catalytic specificity is derived from not only the delicate interaction between UA and the Ni center but also the complementary oxygen reduction at the beta C site in the ligand. As a potential application, a Ni-DAB-based biofuel cell using human urine is constructed. This work unlocks an approach of enzyme-like isolated dual sites in boosting the selectivity of non-protein artificial enzymes.

Abstract Highly efficient interconversion of different types of energy plays a crucial role in both science and technology. Among them, electrochemiluminescence, an emission of light excited by electrochemical reactions, has drawn attention as a powerful tool for bioassays. Nonetheless, the large differences in timescale among diverse charge-transfer pathways from picoseconds to seconds significantly limit the electrochemiluminescence efficiency and hamper their broad applications. Here, we report a timescale coordination strategy to improve the electrochemiluminescence efficiency of carbon nitrides by engineering shallow electron trap states via Au-N bond functionalization. Quantitative electrochemiluminescence kinetics measurements and theoretic calculations jointly disclose that Au-N bonds endow shallow electron trap states, which coordinate the timescale of the fast electron transfer in the bulk emitter and the slow redox reaction of co-reagent at diffusion layers. The shallow electron trap states ultimately accelerate the rate and kinetics of emissive electron-hole recombination, setting a new cathodic electrochemiluminescence efficiency record of carbon nitrides, and empowering a visual electrochemiluminescence sensor for nitrite ion, a typical environmental contaminant, with superior detection range and limit.

Abstract Existing monocular depth estimation driving datasets are limited in the number of images and the diversity of driving conditions. The images of datasets are commonly in a low resolution and the depth maps are sparse. To overcome these limitations, we produce a Synthetic Digital City Dataset (SDCD) which was collected under 6 different weather driving conditions, and 6 common adverse perturbations caused by the data transmission. SDCD provides a total of 930 K high-resolution RGB images and corresponding perfect observed depth maps. The evaluation shows that depth estimation models which are trained on SDCD provide a clearer, smoother, and more precise long-range depth estimation compared to those trained on one of the best-known driving datasets KITTI. Moreover, we provide a benchmark to investigate the performance of depth estimation models in different adverse driving conditions. Instead of collecting data from the real world, we generate the SDCD under severe driving conditions with perfect observed data in the digital world, enhancing depth estimation for autonomous driving.

Summary: Cooperative vehicle-infrastructure system (CVIS) is an important part of the intelligent transport system (ITS). Autonomous vehicles have the potential to improve safety, efficiency, and energy saving through CVIS. Although a few CVIS studies have been conducted in the transportation field recently, a comprehensive analysis of CVIS is necessary, especially about how CVIS is applied in autonomous vehicles. In this paper, we overview the relevant architectures and components of CVIS. After that, state-of-the-art research and applications of CVIS in autonomous vehicles are reviewed from the perspective of improving vehicle safety, efficiency, and energy saving, including scenarios such as straight road segments, intersections, ramps, etc. In addition, the datasets and simulators used in CVIS-related studies are summarized. Finally, challenges and future directions are discussed to promote the development of CVIS and provide inspiration and reference for researchers in the field of ITS.

Against the backdrop of urbanization and land use policy formulation, the accurate identification of changes is imperative for the effective monitoring and control of urban growth, conservation of natural resources, and environmental protection. Traditional remote sensing techniques for change detection, foundational to these applications, typically face significant challenges such as pronounced errors and inadequate parsing of complex environments. To surmount these obstacles, this study proposes a cutting-edge, deep learning-based strategy with a Siamese network framework, and utilizing a modified U-Net++ network (SIAM-CDNET) to improve change detection capabilities. This model integrates an attention mechanism to enhance the acuity and distinguishing features of remote sensing imagery, particularly for subtle variations and intricate structures in urban settings. Furthermore, an edge-detection component designed for multiscale feature amalgamation and a change detection-specific composite loss function are devised to increase the precision and generalizability of the model. Evaluations based on the LEVIR-CD,CDD and GZ-CD datasets indicate that the proposed SIAM-CDNET markedly surpasses existing methods in terms of accuracy and F1-score, with values of 90.50% and 90.82% (LEVIR-CD dataset),89.95% and 91.18% (CDD dataset) and 93.81% and 90.8%(GZ-CD dataset), respectively. These results confirm the exceptional performance of SIAM-CDNET in urban development and land use change detection, potentially making a significant technical contributions to the field.

Abstract Tumor cell-released LC3+ extracellular vesicles (LC3+ EVs) participate in immunosuppression during autophagy and contribute to the occurrence and development of breast cancer. In view of the strong association between the LC3+ EVs and breast cancer, developing an effective strategy for the quantitative detection of LC3+ EVs levels with high sensitivity to identify LC3+ EVs as new biomarkers for accurate diagnosis of breast cancer is crucial, but yet not been reported. Herein, an ultrasensitive electrochemical immunosensor is presented for the quantitative determination of LC3+ EVs using a three-dimensional graphene oxide hydrogel-methylene blue composite as a redox probe, showing a low detection limit and a wide linear range. With this immunosensor, the expression levels of LC3+ EVs in various practical sample groups including different cancer cell lines, the peripheral blood of tumor-bearing mice before and after immunotherapy, and the peripheral blood from breast cancer patients with different subtypes and stages were clearly distinguished. This study demonstrated that LC3+ EVs were superior as biomarkers for the accurate diagnosis of breast cancer compared to traditional biomarkers, particularly for cancer subtype discrimination. This work would provide a new noninvasive detection tool for the early diagnosis and prognosis assessment of breast cancer in clinics.

Abstract A series of carbon nitride (CN) materials represented by graphitic carbon nitride (g‐C3N4) have been widely used in bioimaging, biosensing, and other fields in recent years due to their nontoxicity, low cost, and high luminescent quantum efficiency. What is more attractive is that the luminescent properties such as wavelength and intensity can be regulated by controlling the structure at the molecular level. Hence, it is time to summarize the related research on CN structural evolution and make a prospect on future developments. In this review, we first summarize the research history and multiple structural evolution of CN. Then, the progress of improving the luminescence performance of CN through structural evolution was discussed. Significantly, the relationship between CN structure evolution and energy conversion in the forms of photoluminescence, chemiluminescence, and electrochemiluminescence was reviewed. Finally, key challenges and opportunities such as nanoscale dispersion strategy, luminous efficiency improving methods, standardization evaluation, and macroscopic preparation of CN are highlighted.

Abstract Vehicles in the platoon can sufficiently incorporate the information via V2X communication to plan ecological speed trajectories and pass the intersection smoothly. Most existing eco‐driving studies mainly focus on the optimal control of a single vehicle at an individual signalized intersection, while rarely involving the cooperative optimization of a group of vehicles at successive signalized intersections. In this study, a hierarchical cooperative eco‐driving control for a connected autonomous vehicle (CAV) platoon is proposed to enhance traffic mobility and energy efficiency, wherein the velocity trajectory of the leading vehicle at each isolated signalized intersection is planned using the pseudo‐spectral method, and then the cooperative optimization of following vehicles in the platoon is conducted via rolling optimization, with the aim of improving driving comfort, safety and energy economy for the platoon. The simulation results highlight that the proposed hierarchical cooperative eco‐driving strategy can lead to preferable vehicle‐following behaviours and platoon driving performance, and the overall energy consumption and trip time of vehicle platoon are respectively reduced by 26.10% and 2.83%, compared with that under manual driving. Furthermore, the overall energy economy is promoted by 4.95% and 4.60%, compared with cooperative adaptive cruise control and intelligent driver model‐based platoon control strategies.

Abstract Self-adaptability is highly envisioned for artificial devices such as robots with chemical noses. For this goal, seeking catalysts with multiple and modulable reaction pathways is promising but generally hampered by inconsistent reaction conditions and negative internal interferences. Herein, we report an adaptable graphitic C6N6-based copper single-atom catalyst. It drives the basic oxidation of peroxidase substrates by a bound copper-oxo pathway, and undertakes a second gain reaction triggered by light via a free hydroxyl radical pathway. Such multiformity of reactive oxygen-related intermediates for the same oxidation reaction makes the reaction conditions capable to be the same. Moreover, the unique topological structure of CuSAC6N6 along with the specialized donor-π-acceptor linker promotes intramolecular charge separation and migration, thus inhibiting negative interferences of the above two reaction pathways. As a result, a sound basic activity and a superb gain of up to 3.6 times under household lights are observed, superior to that of the controls, including peroxidase-like catalysts, photocatalysts, or their mixtures. CuSAC6N6 is further applied to a glucose biosensor, which can intelligently switch sensitivity and linear detection range in vitro.

The escalating environmental concerns and energy crisis caused by internal combustion engines (ICE) have become unacceptable under environmental regulations and the energy crisis. As a promising alternative solution, multi-power source electric vehicles (MPS-EVs) integrate various clean energy systems to enhance the powertrain efficiency. The energy management strategy (EMS) is plays a pivotal role for MPS-EVs to maximize efficiency, fuel economy, and range. Reinforcement Learning (RL) has emerged as an effective methodology for EMS development, attracting continuous attention and research. However, a systematic analysis of the design elements of RL-based EMS is currently lacking. This paper addresses this gap by presenting a comprehensive analysis of current research on RL-based EMS (RL-EMS) and summarizing its design elements. This paper first summarizes the previous applications of RL in EMS from five aspects: algorithm, perception scheme, decision scheme, reward function, and innovative training method. It highlights the contributions of advanced algorithms to training effectiveness, provides a detailed analysis of perception and control schemes, classifies different reward function settings, and elucidates the roles of innovative training methods. Finally, by comparing the development routes of RL and RL-EMS, this paper identifies the gap between advanced RL solutions and existing RL-EMS. Potential development directions are suggested for implementing advanced artificial intelligence (AI) solutions in EMS.

Summary: Severe weather conditions pose a significant challenge for computer vision algorithms in autonomous driving applications, particularly regarding robustness. Image rain-removal algorithms have emerged as a potential solution by leveraging the power of neural networks to restore rain-free backgrounds in images. However, existing research overlooks the vulnerability concerns in neural networks, which exposes a potential threat to the intelligent perception of autonomous vehicles in rainy conditions. This paper proposes a universal rain-removal attack (URA) that exploits the vulnerability of image rain-removal algorithms. By generating a non-additive spatial perturbation, URA significantly diminishes scene restoration similarity and image quality. The imperceptible and generic perturbation employed by URA makes it a crucial tool for vulnerability detection in image rain-removal algorithms and a potential real-world AI attack method. Experimental results demonstrate that URA can reduce scene repair capability by 39.5% and image generation quality by 26.4%, effectively targeting state-of-the-art rain-removal algorithms.

Abstract Background Carbon dot has been widely used in biomedical field as a kind of nanomaterial with low toxicity and high biocompatibility. CDs has demonstrated its unique advantages in assisted drug delivery, target diagnosis and targeted therapy with its small size and spontaneous fluorescence. However, the potential biosafety of CDs cannot be evaluated. Therefore, we focused on the study of liver, the target organ involved in CDs metabolism, to evaluate the risk of CDs in vitro. Methods and results Liver macrophage KUP5 cells and normal liver cells AML12 cells were incubated in CDs at the same concentration for 24 h to compare the different effects under the same exposure conditions. The study found that both liver cell models showed ATP metabolism disorder, membrane damage, autophagosome formation and lysosome damage, but the difference was that, KUP5 cells exhibited more serious damage than AML12 cells, suggesting that immunogenic cell type is particularly sensitive to CDs. The underlying mechanism of CDs-induced death of the two hepatocyte types were also assessed. In KUP5 cells, death was caused by inhibition of autophagic flux caused by autophagosome accumulation, this process that was reversed when autophagosome accumulation was prevented by 3-MA. AML12 cells had no such response, suggesting that the accumulation of autophagosomes caused by CDs may be specific to macrophages. Conclusion Activation of the TFEB-lysosome pathway is important in regulating autophagy and apoptosis. The dual regulation of ERK and mTOR phosphorylation upstream of TFEB influences the death outcome of AML12 cells. These findings provide a new understanding of how CDs impact different liver cells and contribute to a more complete toxicological safety evaluation of CDs.

Attribute reduction is a crucial research area within concept lattices. However, the existing works are mostly limited to either increment or decrement algorithms, rather than considering both. Therefore, dealing with large-scale streaming attributes in both cases may be inefficient. Convolution calculation in deep learning involves a dynamic data processing method in the form of sliding windows. Inspired by this, we adopt slide-in and slide-out windows in convolution calculation to update attribute reduction. Specifically, we study the attribute changing mechanism in the sliding window mode of convolution and investigate five attribute variation cases. These cases consider the respective intersection of slide-in and slide-out attributes, i.e., equal to, disjoint with, partially joint with, containing, and contained by. Then, we propose an updated solution of the reduction set for simultaneous sliding in and out of attributes. Meanwhile, we propose the CLARA-DC algorithm, which aims to solve the problem of inefficient attribute reduction for large-scale streaming data. Finally, through the experimental comparison on four UCI datasets, CLARA-DC achieves higher efficiency and scalability in dealing with large-scale datasets. It can adapt to varying types and sizes of datasets, boosting efficiency by an average of 25%.

Plug-in hybrid electric vehicles (PHEVs) have been validated as a preferable solution to transportation due to its great advantages in fuel economy promotion, harmful emission reduction and mileage anxiety mitigation. While, designing an effective energy management strategy to allocate the power between battery and engine is critical to improve the performance of powertrain in PHEVs. To this end, a real-time energy management strategy is proposed via incorporating double-delay Q-Learning and model predictive control (MPC). First, the energy management for PHEV is transformed into a nonlinear optimal control problem, and the vehicle speed predictor based on convolutional neural network is proposed to forecast vehicle speed in MPC. Then, based on the predicted vehicle speed, the double-delay Q-Learning algorithm is implemented to solve the receding horizon optimal problem in the MPC module. The simulation is conducted to verify the performance of the proposed strategy, and the results showcase that incorporating the double-delay Q-Learning into MPC can effectively improve the adaptability of energy management to dynamic environment, and meanwhile achieve a similar fuel consumption of the offline stochastic dynamic programming-based strategy. In addition, the single-step computation time of the proposed strategy is less than 23 milliseconds, highlighting its significant potential in online implementation.

Abstract In this paper, a novel energy management strategy with the improved adaptability to various conditions for plug‐in hybrid electric vehicle (PHEV) is proposed. The control parameters, derived from the benchmark test, are optimized offline for different driving conditions. The optimized parameters are implemented according to different driving behaviours identified online. The offline and online cooperation improves performance of energy management strategy in different driving conditions. Three main efforts have been made: Firstly, the valuable features that describe different driving conditions are extracted by random forest (RF) and the features are used for determining driving condition categories, utilized for online driving condition identification by support vector machine (SVM). Secondly, the control thresholds in the developed control strategy are optimized by whale optimization algorithm (WOA) under different driving conditions. The optimal control thresholds for different driving conditions will be called online after certain traffic condition is categorized. At last, simulation‐based evaluation is performed, validating the enhanced performance of the proposed methods in energy‐saving in different driving conditions.

Summary: Accurate estimates of State of Health (SoH) are critical for characterizing the aging of lithium-ion batteries. This protocol combines feature extraction and a representative machine learning algorithm (i.e., least-squares support vector machine) for SoH prediction of lithium-ion batteries. We detail the step-by-step estimation process, followed by validation of the constructed model with a maximum absolute error of 1.62%. Overall, the proposed approach can efficiently track the aging trajectory and ensure precise SoH prediction.For complete details on the use and execution of this protocol, please refer to Shu et al. (2021b).

In this paper, an improved online particle swarm optimization (PSO) is proposed to optimize the traditional search controller for improving the operating efficiency of the permanent magnet synchronous motor (PMSM). This algorithm combines the advantages of the attraction and repulsion PSO and the distributed PSO that can help the search controller to find the optimal d - axis air gap current quickly and accurately under non-stationary operating conditions, thereby minimizing the air gap flux and then improving the motor efficiency. To verify the effectiveness and stability of this proposed algorithm, the operating efficiency of PMSM as using this proposed algorithm is compared with that of traditional search controller under non-stationary operating conditions. The results show that the proposed algorithm can improve the operating efficiency of PMSM by 6.03% on average under non-stationary operation conditions. This indicates that the search controller based on the improved PSO has a better adaptation to the variation of external operating conditions, and can improve the operation efficiency of PMSM under non-stationary condition.

The acquisition of critical roles of each molecular constituent in carbon nitrides for photocatalysis remains elusive. Here the authors synthesize carbon nitrides with distinguishable units and reveal the roles of the different units in light absorption and charge separation.

Summary: In the intelligent transportation system (ITS), speed prediction plays a significant role in supporting vehicle routing and traffic guidance. Recently, a considerable amount of research has been devoted to a single-level (e.g., traffic or vehicle) prediction. However, a systematic review of speed prediction in and between different levels is still missing. In this article, existing research is comprehensively analyzed and divided into three levels, i.e. macro traffic, micro vehicles, and meso lane. In addition, this article summarizes the influencing factors and reviews the prediction methods based on how those methods utilize the available information to meet the challenges of the prediction at different levels. This is followed by a summary of evaluation metrics, public datasets, and open-source codes. Finally, future directions in this field are discussed to inspire and guide readers. This article aims to draw a complete picture of speed prediction and promote the development of ITS.

This work presents the control strategies for the configuration involving an open-end winding induction motor (OW-IM) fed by dual two-level inverters, which can realize the controllable power sharing between two isolated power sources without using the DC/DC converter. Based on the mathematical model of the OW-IM and the principles of the voltage vector distribution, two rotor flux calculation algorithms, namely the motor loss minimization (MLM) algorithm and the maximum power sharing capability (MPSC) algorithm are proposed and compared, with their selection strategy to select the suitable algorithm depending on the operating condition. The MLM algorithm has the optimal efficiency performance, while the MPSC algorithm can maximize the power sharing capability of the dual inverter while holding the widest operation range of the motor. Based on the dual space vector pulse-width modulation (SVPWM) control scheme, the golden section (GS) search method is introduced to allocate the stator voltage vector to the dual inverter for the power sharing demand, with a flexible iteration number to obtain a stable and efficient computational performance, which fully utilizes the power sharing capability via the voltage vector distribution. Simulation results prove the validity and the advantages of the proposed strategy. This system also lays a foundation for energy management function of the dual-power electric vehicles.

Capacity prediction of lithium-ion batteries represents an important function of battery management systems. Conventional machine learning-based methods for capacity prediction are inefficient to learn long-term dependencies during capacity degradations. This paper investigates the deep learning method for lithium-ion battery's capacity prediction based on long short-term memory recurrent neural network, which is employed to capture the latent long-term dependence of degraded capacity. The neural network is adaptively optimized by the Adam optimization algorithm, and the dropout technique is exploited to prevent overfitting. Based on the offline cycling aging data of batteries, the capacity prediction performance is validated and evaluated. The experimental results demonstrate that the proposed algorithm can accurately track the nonlinear degradation trend of capacity within the whole lifespan with a maximum error of only 2.84%.

Summary: Accurate state of health (SOH) prediction is significant to guarantee operation safety and avoid latent failures of lithium-ion batteries. With the development of communication and artificial intelligence technologies, a body of researches have been performed toward precise and reliable SOH prediction method based on machine learning (ML) techniques. In this paper, the conception of SOH is defined, and the state-of-the-art prediction methods are classified based on their primary implementation procedure. As an essential step in ML-based SOH algorithms, the health feature extraction methods reported in the literature are comprehensively surveyed. Next, an exhausted comparison is conducted to elaborate the development of ML-based SOH prediction techniques. Not only their advantages and disadvantages of the application in SOH prediction are reviewed but also their accuracy and execution process are fully discussed. Finally, pivotal challenges and corresponding research directions are provided for more reliable and high-fidelity SOH prediction.

In the study of braking force distribution of trucks, the accurate estimation of the state parameters of the vehicle is very critical. However, during the braking process, the state parameters of the vehicle present a highly nonlinear relationship that is difficult to estimate accurately and that seriously affects the accuracy of the braking force distribution strategy. To solve this problem, this paper proposes a machine-learning-based state-parameter estimation method to provide a solid data base for the braking force distribution strategy of the vehicle. Firstly, the actual collected complete vehicle information is processed for data; secondly, random forest is applied for the feature screening of data to reduce the data dimensionality; subsequently, the generalized regression neural network (GRNN) model is trained offline, and the vehicle state parameters are estimated online; the estimated parameters are used to implement the four-wheel braking force distribution strategy; finally, the effectiveness of the method is verified by joint simulation using MATLAB/Simulink and TruckSim.

The current research on ensemble clustering mainly focuses on integration strategies, but the attention regarding the measurement and optimization of basic cluster is less emphasized. Based on the information entropy theory, this paper proposes a quality metric of basic cluster, and the clusterings are further selected by incorporating two-branch decisions and three-way decisions respectively. Determined by preset threshold(s), mechanism of two-branch based basic clustering filtering (BCF2BD) and three-way based basic clustering filtering (BCF3WD) are developed. Concretely, the basic clustering in BCF2BD is deleted if the quality metric of it is less than the preset threshold ξ, and the new clustering member is added to maintain the basic cluster set count. The basic clustering in BCF3WD is deleted if the quality metric of it is less than the preset threshold β, retained if the quality metric of it is greater than the preset threshold α, recalculated if the quality metric of it is greater than β and less than α. Both mechanism executed repeatedly until either non-decrement of basic clusters occurred or maximum iteration count reached. Contrastive experiments show that both methods of filtering algorithms can effectively improve the performance of ensemble clustering, and the three-way decisions filtering algorithm get less time consumption.

The vehicle-environment cooperative (VEC) control has shown a great potential to improve vehicle performance. Consequently, it is desirable to further investigate the incorporation of the VEC control. In this context, a novel method is proposed to predict the velocity profile; meanwhile, the potential of the proposed method is exploited to improve energy management performance of plug-in hybrid electric vehicles (PHEVs). In particular, a specific VEC control framework is first introduced based on the mobile edge computation (MEC). On this basis, a compound velocity profile prediction (CVPP) algorithm is developed, which merges the cloud server (CS), MEC servers, and on-board vehicle control unit (VCU), and provides more accurate and reasonable prediction results. Finally, a case study is conducted that applies the proposed CVPP method to energy management of PHEVs. The simulation results manifest that the performance of the proposed energy management strategy (EMS) is dramatically improved after incorporating the forecasted velocity profile information given by the proposed CVPP method.

This paper presents a prescient energy management strategy based on the model predictive control (MPC) for the parallel plug-in hybrid electric vehicles (PHEVs). In this hierarchical strategy, dynamic programming (DP), with its improved calculation speed, is chosen as the solution algorithm to calculate the optimal power distribution combinations in the predicted receding horizon and under the given terminal battery state-of-charge (SOC) terminal constraint. A synthesized velocity profile prediction (SVPP) method is adopted. The macroscopically and microcosmically predicted velocities obtained by the participatory sensing data (PSD)-based method and the Markov chain (MC), respectively, are synthesized by the linear regression method, obtaining the final velocity profile. In the linear regression step, a particle filter (PF) is implemented for the parameter estimation. According to the characteristics of the driving conditions and components, the terminal battery SOC in each control horizon is constrained by a novel method. Finally, we demonstrate the capability of the proposed scheme in terms of fuel economy improvement by comparing the value of this metric with those of other strategies through simulation.

Multi-label classification deals with the determination of instance-label associations for unseen instances. Although many margin-based approaches are delicately developed, the uncertainty classifications for those with smaller separation margins remain unsolved. The intuitionistic fuzzy set is an effective tool to characterize the concept of uncertainty, yet it has not been examined for multi-label cases. This paper proposed a novel model called intuitionistic fuzzy three-way label enhancement (IFTWLE) for multi-label classification. The IFTWLE combines label enhancement with an intuitionistic fuzzy set under the framework of three-way decisions. For unseen instances, we generated the pseudo-label for label uncertainty evaluation from a logical label-based model. An intuitionistic fuzzy set-based instance selection principle seamlessly bridges logical label learning and numerical label learning. The principle is hierarchically developed. At the label level, membership and non-membership functions are pair-wisely defined to measure the local uncertainty and generate candidate uncertain instances. After upgrading to the instance level, we select instances from the candidates for label enhancement, whereas they remained unchanged for the remaining. To the best of our knowledge, this is the first attempt to combine logical label learning with numerical label learning into a unified framework for minimizing classification uncertainty. Extensive experiments demonstrate that, with the selectively reconstructed label importance, IFTWLE achieves statistically superior over the state-of-the-art multi-label classification algorithms in terms of classification accuracy. The computational complexity of this algorithm is On2mk, where n, m, and k denote the unseen instances count, label count, and average label-specific feature size, respectively.

Data representation is of significant importance in minimizing multi-label ambiguity. While most researchers intensively investigate label correlation, the research on enhancing model robustness is preliminary. Low-quality data is one of the main reasons that model robustness degrades. Aiming at the cases with noisy features and missing labels, we develop a novel method called robust global and local label correlation (RGLC). In this model, subspace learning reconstructs intrinsic latent features immune from feature noise. The manifold learning ensures that outputs obtained by matrix factorization are similar in the low-rank latent label if the latent features are similar. We examine the co-occurrence of global and local label correlation with the constructed latent features and the latent labels. Extensive experiments demonstrate that the classification performance with integrated information is statistically superior over a collection of state-of-the-art approaches across numerous domains. Additionally, the proposed model shows promising performance on multi-label when noisy features and missing labels occur, demonstrating the robustness of multi-label classification.

Vehicle speed prediction can obtain the future driving status of a vehicle in advance, which helps to make better decisions for energy management strategies. We propose a novel deep learning neural network architecture for vehicle speed prediction, called VSNet, by combining convolutional neural network (CNN) and long-short term memory network (LSTM). VSNet adopts a fake image composed of 15 vehicle signals in the past 15 s as model input to predict the vehicle speed in the next 5 s. Different from the traditional series or parallel structure, VSNet is structured with CNN and LSTM in series and then in parallel with two other CNNs of different convolutional kernel sizes. The unique architecture allows for better fitting of highly nonlinear relationships. The prediction performance of VSNet is first examined. The prediction results show a RMSE range of 0.519–2.681 and a R2 range of 0.997–0.929 for the future 5 s. Finally, an energy management strategy combined with VSNet and model predictive control (MPC) is simulated. The equivalent fuel consumption of the simulation increases by only 4.74% compared with DP-based energy management strategy and decreased by 2.82% compared with the speed prediction method with low accuracy.

Community detection is a challenging task in attributed networks, due to the data inconsistency between network topological structure and node attributes. The problem of how to effectively and robustly fuse multi-source heterogeneous data plays an important role in community detection algorithms. Although some algorithms taking both topological structure and node attributes into account have been proposed in recent years, the fusion strategy is simple and usually adopts the linear combination method. As a consequence of this, the detected community structure is vulnerable to small variations of the input data. In order to overcome this challenge, we develop a novel two-layer representation to capture the latent knowledge from both topological structure and node attributes in attributed networks. Then, we propose a weighted co-association matrix-based fusion algorithm (WCMFA) to detect the inherent community structure in attributed networks by using multi-layer fusion strategies. It extends the community detection method from a single-view to a multi-view style, which is consistent with the thinking model of human beings. Experiments show that our method is superior to the state-of-the-art community detection algorithms for attributed networks.

Relieving the adverse effects of automobiles on the environment and natural resources has drawn the attention of numerous researchers. This paper seeks a new path to reach a target by focusing on the synergy of the vehicle and the environment. A real-time economical route planning method for a plug-in hybrid electric vehicle (PHEV) is proposed. Three main contributions have been made. Firstly, a real comparison test is performed to provide rudimentary understanding of the difference in energy usage and route planning between PHEVs and conventional vehicles. Secondly, an approach to obtain PHEV customized data is developed for road weight calculation, which is the essential step in route planning. This method incorporates traffic data from conventional vehicles with the PHEV simulation model, obtaining the required data. Thirdly, the travel expense estimation model (TEEM) is designed. The TEEM could be applied to calculate the road weight of each road segment considering the impact on energy consumption with respect to environmental factors, providing the grounds for route planning. The proposed method to plan an economical route is evaluated, and the results justify its validation and ability to improve fuel economy.