Temporal knowledge graph reasoning (TKGR) excels at inferring missing event‐centric facts within a timeline, thereby mitigating the inherent incompleteness of real‐world data. Existing TKGR methods predominantly exploit intrasnapshot structural patterns and intersnapshot temporal dependencies. However, they often fail to incorporate valuable time‐invariant factual knowledge about events and struggle to jointly model entity–relation evolution dynamics. To address these challenges, we propose CKE 3 , a novel contrastive knowledge‐enhanced event evolution model that integrates time‐invariant entity background knowledge with time‐variant structural information for enhanced reasoning. Specifically, CKE 3 improves the learning of expressive entity and relation representations through an adaptive knowledge retrieval strategy, which constructs descriptive common sense knowledge associated with each entity to provide richer contextual information. Moreover, we introduce a knowledge‐aware hierarchical structural–temporal modeling module that jointly captures entity–relation structural interactions as well as sequential and periodic temporal patterns across knowledge graph snapshots. To further mitigate the impact of knowledge noise, we design a self‐supervised augmentation task that promotes the fusion of relevant information while alleviating noise. Extensive experiments on four public TKGR datasets demonstrate that CKE 3 consistently surpasses state‐of‐the‐art baselines, highlighting its effectiveness in accurate entity forecasting for the TKGR task.

Traffic flow prediction plays a crucial role in the construction of smart cities. Although numerous models already exist for traffic flow prediction, they neither extracted the spatio-temporal features at different scales nor precisely considered the deviation between the traffic signals collected by the sensors and the trend signals at different scales. This leads to their inaccurate prediction results. To address the aforementioned issues, this paper proposes a multi-layer structure to extract spatio-temporal features at different scales and designs an information decomposition module to separate abnormal signals in traffic data. Furthermore, based on the above structure and modules, this paper constructs a new traffic flow prediction modelMulti-scaleAnomalyDecompositionGraphNeuralNetwork (MADGNN) for feature extraction and information decomposition at different scales. Firstly, the model encodes the input data to fully capture spatio-temporal dependencies. Then, this paper extracts spatio-temporal features at multiple scales based on a multi-layer structure containing multiple GRUs and subtracts the learned abnormal information from the input signal to achieve abnormal signal decomposition. Finally, we use multiple spatio-temporal hidden states for further information extraction and traffic prediction. The final prediction result of the model is obtained by adding up the prediction outputs of each layer. The experimental results show that, compared with DDGCRN, on the Railway datasets, the MAE and RMSE metrics are improved by an average of 3.92% and 2.30% respectively, and on the public dataset PEMSD8, the MAE and MAPE metrics are improved by 2.92% and 2.23% respectively.

Low rank tensor ring based data recovery algorithms have been widely used in data-driven consumer electronics to recover missing data entries in the collecting data pre-processing stage for providing stable and reliable service. However, traditional recovery methods often fail to utilize the abundant prior knowledge of data and the non-local self-similarity of the data, thus leading to the failure to effectively capture the spatial relationships within high-dimensional data to recover them accurately. To address these problems, we present a novel Non-local Self-similarity and Low-rank Prior Knowledge based tensor ring completion method. Firstly, we incorporate the BM3D denoising operator within a Plug-and-Play framework to exploit the self-similarity in the data. Then a logarithmic determinant function is integrated to distinguish singular values in the cyclic unfolding matrix of the tensor and adopts a tensor ring completion approach based on weighted nuclear norms. Finally, in order to evaluate the effectiveness of our proposed method, we conducted a series of experiments by using the missing image dataset and the missing traffic data dataset respectively, and the experimental results show that our method achieves the highest level in terms of data recovery accuracy.

Electroencephalogram (EEG) signals, as a reliable biological indicator, have been widely used in fatigue driving detection due to their capacity to reflect a driver's cognitive and neural response state. However, EEG signals have problems such as imbalanced data distribution, significant differences between subjects, and complex scenes, which affect the detection effect. Small commonalities between input objects can be interpreted as important information about an entire sample. Therefore, to retain as much information as possible, We design a new approach for integrating fuzzy features, comprehensive adaptive interpretable TSK fuzzy classifier(CAI-TSK-FC). It not only captures the features of multiple subclassifiers more efficiently and alleviates the dataset imbalance problem. Also, it can reduce the accumulation of error information by randomly retaining fuzzy rules as well as normalization. Finally, we linearly combine the results of multiple subclassifiers to comprehensively consider the learning effect of multiple subclassifiers to adapt to different subjects and datasets. Experiments conducted on both self-made and public datasets (SEED-VIG) show that CAI-TSK-FC has good performance and interpretability on different EEG fatigue driving datasets. In comparison to existing methods, it achieves an accuracy improvement of 3.15% and 1.52%, respectively, as well as a specificity improvement of 4.72% and 0.91%, respectively.

Quantum circuit mapping (QCM) is a crucial preprocessing step for executing a logical circuit (LC) on noisy intermediate-scale quantum (NISQ) devices. Balancing the introduction of extra gates and the efficiency of preprocessing poses a significant challenge for the mapping process. To address this challenge, we propose the mutual-influence-aware (MIA) heuristic method by integrating an initial mapping search framework, an initial mapping generator, and a heuristic circuit mapper. Initially, the framework utilizes the generator to obtain a favorable starting point for the initial mapping search. With this starting point, the search process can efficiently discover a promising initial mapping within a few bidirectional iterations. The circuit mapper considers mutual influences of SWAP gates and is invoked once per iteration. Ultimately, the best result from all iterations is considered the QCM outcome. The experimental results on extensive benchmark circuits demonstrate that, compared to the iterated local search (ILS) method, which represents the current state-of-the-art, our MIA method introduces a similar number of extra gates while achieving nearly 95 times faster execution.

In recent years, the blockchain technology has been widely used in the Internet of Things (IoT). One of the major concerns is how to adopt a smart contract to process data from IoT devices flexibly. While plenty of smart contract-based methods can be used, smart contracts are required to be deployed previously. This requires an additional step (to deploy a smart contract) and makes a smart contract separate from its data (transactions to trigger its interface), which generates limitations in IoT scenarios. In this article, we developed an approach to embed the smart contract and its data into the same transaction, eliminating the need for a predeployment step. Data is employed as parameters to invoke the interface of a smart contract, and the smart contract is used to process the data inside the transaction. With this method, a smart contract does not need other transactions from the user. Results indicate that the proposed method can eliminate the requirement of a separately deployed smart contract, saving costs, and waiting time for the predeployment.

Computation offloading has become popular in recent years as it is an effective way to reduce the energy consumption and enhance the performance of smartphones. To deal with the heterogeneous architectures between the smartphone and the server, and to simplify deployment of the server, we propose and implement a lightweight offloading framework which supports offloading of compute-intensive tasks and deploying the server efficiently. Based on this framework, generic and developer-customized offloading services could be provided for different third-party applications. Furthermore, we design a multi-task offloading tactic for the framework to deal with intensive offloading requests from various mobile devices. When receiving an offloading request, the master node in server-side determines whether this task should be offloaded or not and which VM should handle this task, so that the overall execution time and energy consumption are optimized. We implement this framework and evaluate it by comparing the execution time, energy consumption and CPU utilization rate among three execution modes with three applications. We also conduct experiments of the multi-task offloading tactic in simulation environment. Experimental results indicate that this framework effectively reduces energy consumption and boosts performance for compute-intensive tasks, and the multi-task offloading tactic is valid for intensive offloading requests.

Temporal action detection is a challenging task in video understanding, due to the complexity of the background and rich action content impacting high-quality temporal proposals generation in untrimmed videos. Capsule networks can avoid some limitations of the invariance caused by pooling and inability from convolutional neural networks, which can better understand the temporal relations for temporal action detection. However, because of the extremely computationally expensive procedure, capsule network is difficult to be applied to the task of temporal action detection. To address this issue, this paper proposes a novel U-shaped capsule network framework with a k-Nearest Neighbor (k-NN) mechanism of 3D convolutional dynamic routing, which we named U-BlockConvCaps. Furthermore, we build a Capsules Boundary Network (CapsBoundNet) based on U-BlockConvCaps for dense temporal action proposal generation. Specifically, the first module is one 1D convolutional layer for fusing the two-stream with RGB and optical flow video features. The sampling module further processes the fused features to generate the 2D start-end action proposal feature maps. Then, the multi-scale U-Block convolutional capsule module with 3D convolutional dynamic routing is used to process the proposal feature map. Finally, the feature maps generated from the CapsBoundNet are used to predict starting, ending, action classification, and action regression score maps, which help to capture the boundary and intersection over union features. Our work innovatively improves the dynamic routing algorithm of capsule networks and extends the use of capsule networks to the temporal action detection task for the first time in the literature. The experimental results on benchmarks THUMOS14 show that the performance of CapsBoundNet is obviously beyond the state-of-the-art methods, e.g., the mAP@tIoU = 0.3, 0.4, 0.5 on THUMOS14 are improved from 63.6% to 70.0%, 57.8% to 63.1%, 51.3% to 52.9%, respectively. We also got competitive results on the action detection dataset of ActivityNet1.3.

Knowledge representation learning (knowledge graph embedding) plays a critical role in the application of knowledge graph construction. The multi-source information knowledge representation learning, which is one class of the most promising knowledge representation learning at present, mainly focuses on learning a large number of useful additional information of entities and relations in the knowledge graph into their embeddings, such as the text description information, entity type information, visual information, graph structure information, etc. However, there is a kind of simple but very common information — the number of an entity’s relations which means the number of an entity’s semantic types has been ignored. This work proposes a multi-source knowledge representation learning model KRL-NER, which embodies information of the number of an entity’s relations between entities into the entities’ embeddings through the attention mechanism. Specifically, first of all, we design and construct a submodel of the KRL-NER LearnNER which learns an embedding including the information on the number of an entity’s relations; then, we obtain a new embedding by exerting attention onto the embedding learned by the models such as TransE with this embedding; finally, we translate based onto the new embedding. Experiments, such as related tasks on knowledge graph: entity prediction, entity prediction under different relation types, and triple classification, are carried out to verify our model. The results show that our model is effective on the large-scale knowledge graphs, e.g. FB15K.

Bitcoin mining consumes tremendous amounts of electricity to solve the hash problem. At the same time, large-scale applications of artificial intelligence (AI) require efficient and secure computing. There are many computing devices in use, and the hardware resources are highly heterogeneous. This means a cooperation mechanism is needed to realize cooperation among computing devices, and a good calculation structure is required in the case of data dispersion. In this paper, we propose an architecture where devices (also called nodes) can reach a consensus on task results using off-chain smart contracts and private data. The proposed distributed computing architecture can accelerate computing-intensive and data-intensive supervised classification algorithms with limited resources. This architecture can significantly increase privacy protection and prevent leakage of distributed data. Our proposed architecture can support heterogeneous data, making computing on each device more efficient. We used mathematical formulas to prove the correctness and robustness of our system and deduced the condition to stop a given task. In the experiments, we transformed Bitcoin hash collision into distributed computing on several nodes and evaluated the training and prediction accuracy for handwritten digit images (MNIST). The experimental results demonstrate the effectiveness of the proposed method.

Smart contracts are required to be instantiated in the predeployed stage, which consumes computation resources from then on. It is a big waste in the blockchain whose nodes are composed of IoT devices, as those devices often have limited resources (such as limited power supplies or a limited number of processes to run). Meanwhile, IoT devices are heterogeneous and different smart contracts are required. If those smart contracts are instantiated previously, numerous meaningless addresses are required. In this paper, we propose to delay the instantiation of a smart contract when used and terminate it when not used, which is similar to the life cycle of a variable. Then, a new kind of variable (the wrapping variable) is used to hide details of the instantiation and the address. The smart contract is instantiated in the construction function of the wrapping variable, or even it is delayed to the time when there are requests for it. The smart contract terminates when the variable is out of its scope. Then, different instantiation methods are proposed. Finally, we perform the qualitative comparison between the proposed approach and the predeployment method, and it demonstrates that the proposed methods optimize the life cycle of the smart contract and save calculation resources.

Blockchain technology has emerged as a novel distributed ledger technology, facilitating data sharing and system management securely and efficiently without interventions from a central authority. However, blockchain technology alone is not suitable for enterprise-class applications, mainly due to the limitations in capacity expansion and verification speed of blockchain systems. This paper proposes a secure and effective construction scheme for blockchain networks to improve performance and address the effective management concerns of blockchain data based on transaction categories. We designed a network link protocol to construct a directed acyclic graph (DAG) blockchain network and used a sharding protocol to divide the DAG blockchain into multiple category shards to process transactions in parallel. We then extensively evaluated our proposed design on local clusters. The experimental results show that our link and shard protocols achieved high throughput and the category-based sharded DAG blockchain demonstrated high scalability.

Several privacy protection technologies have been designed for protecting individuals’ privacy information in data publishing. It is often easy to make additional information loss of a dataset without measuring the strength of privacy protection it required. To apply appropriate strength of privacy preservation, the authors put forward privacy score, a new metric for making a comprehensive evaluation of the privacy information contained in the pre‐published dataset. Using this measure, publishers can apply the privacy techniques to the pre‐published dataset in accordance with the privacy level it belongs to. The privacy score is determined by the amount as well as the quality of privacy information in which the pre‐published dataset is contained. Furthermore, the authors present a data sensitivity model based on analytic hierarchy process for assigning a sensitivity score to each possible value of a sensitive attribute. The reasonability and effectiveness of the proposed approach are verified by using the Adult dataset.

Now, mobile applications grow at an exponential speed and their evolution activities are very active, while there is little research on the evolution of mobile apps. To have a better understanding of the evolution of mobile apps and find similarities or patterns in their evolution process, we conduct an empirical study on long spans in the lifetime of 8 typical open-source mobile apps, which covers 348 official releases. First, we try to verify whether Lehman's laws still apply to mobile apps or not, extract a variety of metrics of the apps, and use statistical hypothesis testing to validate these laws. We find enough data that support a subset of Lehman's laws, while the rest do not. Second, we make some novel observations, eg, the growth of mobile apps is nonsmooth, and some versions of the apps have a great growth in their evolution. Enough data confirming that software instability increases great with the addition of third-party method invocations, and automatic build and manage tool based on contract is introduced into project as apps continue evolving.