As a key component of various machinery, rolling bearing’s running reliability performance has a significant impact on the whole system. However, it will become an extra challenge when facing few-shot data and severe noise interference. Recently, the Beluga Whale optimization (BWO) algorithm has been presented, which has caused widespread concerns due to its powerful optimization capability and fast convergence characteristic. The variational modal decomposition (VMD) has been proven by numerous scientific experiments to be a powerful tool for noise reduction; the wavelet synchronous extraction transformation (WSET) exhibits strong time-frequency aggregation performance. In addition, the CNN model has significant superiority in automatically extracting hidden features, and the LSSVM algorithm is highly effective in handling small sample pattern recognition problems. Integrating all of the advantages of the above-mentioned techniques, a novel intelligent fault diagnosis scheme using BWO-based VMD and LSSVM with WSET-CNN is introduced. This method includes three parts, which are BWO-based VMD for signal preprocessing, feature extraction based on WSET-CNN architecture, and fault identification using BWO-optimized LSSVM. At first, the VMD can extract various intrinsic mode components (IMFs) contained in the original signals so as to achieve noise reduction after selecting the optimal IMF. However, the effect is greatly influenced by its parameters. Therefore, during the signal preprocessing phase, the BWO algorithm is implemented to optimize key parameters of variation mode decomposition to achieve optimal noise-reduction results. Second, time-frequency characteristics are captured using the WSET technique during the feature-extraction stage, and subsequently, the time-frequency spectrum images are utilized as an input matrix for the CNN model to fulfill the feature mapping and dimension reduction through convolution and pooling operations, automatically extracting the hidden characteristics vectors. In the final stage, the BWO algorithm was once again utilized to search for the best parameters for the LSSVM model so that the classification results could be achieved. In the final section, a fault diagnosis experiment for bearing is conducted and the analysis results are obtained, from which it can be concluded that the newly-developed methodology has superiority with high accuracy even in small-sized sample intelligent fault diagnosis.

The rapidly-increasing computing power of GPUs has rendered the I/O subsystem a bottleneck for distributed deep learning (DL) training. Currently, substantial data preprocessing work (e.g., decoding) has to be conducted on CPUs for a wide range of training scenarios such as computer vision (CV) and audio. Unfortunately, the involvement of training nodes' host memory and/or CPUs on the critical path of loading data to GPUs incurs significant GPU stalls in modern RDMA training clusters, because CPUs are much slower than GPUs and the connection from PCIe switches to host memory tends to suffer from incast problems. Moreover, this also incurs high CPU usage and resource contention, which consequently causes data loading performance variation and stragglers. This paper presents KSpeed, a novel data provisioning framework for large-scale RDMA training clusters. As many data preprocessing tasks need to be done by CPUs, KSpeed organizes host memory and CPU resources in the cluster to build a disaggregated memory/CPU pool, where the nodes can read raw input data from backend storage to their host memory, preprocess the data by their CPUs if necessary, and write cached/preprocessed data (on demand) directly to the training workers' GPU memory to minimize GPU stalls. KSpeed leverages the multi-rail RDMA network to eliminate unnecessary memory copies, interference, and congestion. Evaluation on a 96-GPU cluster shows that KSpeed delivers$5.4 \times \sim 100 \times$higher data loading performance over the state-of-the-art designs (DPP and Alluxio). KSpeed achieves near-linear scalability as the GPU number increases from 8 to 512.

Dark silicon is a phenomenon of under-utilization in today's manycore systems due to power and thermal limitations. In order to improve the performance of dark silicon systems, it is necessary to adopt dynamic power constraints for different core mapping decisions. However, existing power budgeting methods are generally over pessimistic, e.g., Thermal Safe Power (TSP), or over optimistic, e.g., Greedy based Dynamic Power (GDP). This paper proposes a practical power budgeting method, called Combinational Optimization Power (COP). Different from existing methods, which ignore some actual factors, such as communication overhead and lifetime reliability, COP formulates the power budgeting problem as a thermal-constrained combinational optimization power problem. For the steady-state case, COP achieves the target fusion of optimized temperature and communication energy consumption by applying task priority ranking and task-to-core mapping. For the transient case, COP uses the rainflow counting algorithm to construct the reliability framework based on the thermal cycling failure mechanism, and then establishes a linear time-invariant transient temperature model to obtain the core mapping selection and the corresponding dynamic power budget. Experimental results demonstrate that COP is capable of providing an optimized core mapping decision, which can maximize power budget while ensuring the system performance.

A session-based news recommender system recommends the next news to a user by modeling the potential interests embedded in a sequence of news read/clicked by her/him in a session. Generally, a user’s interests are diverse, namely there are multiple interests corresponding to different types of news, e.g., news of distinct topics, within a session. However, most of existing methods typically overlook such important characteristic and thus fail to distinguish and model the potential multiple interests of a user, impeding accurate recommendation of the next piece of news. Therefore, this paper proposes multi-interest news sequence (MINS) model for news recommendation. In MINS, a news encoder based on self-attention is devised on learn an informative embedding for each piece of news, and then a novel parallel interest network is devised to extract the potential multiple interests embedded in the news sequence in preparation for the subsequent next-news recommendations. The experimental results on a real-world dataset demonstrate that our model can achieve better performance than the state-of-the-art compared models. Our source code is publicly available on GitHub1.

Intelligent human-device interfaces play key roles in fully automated vehicles (FAVs), ensuring smooth interactions and improving the driving experience. Listening to news is a popular method of relaxing during a journey; as a result, travelers require automatic recommendations of preferred news programs. Most existing news recommender systems usually learn topic-level representations of users and news for recommendations while neglecting to learn more informative aspect-level features, resulting in limited recommendation performance. To bridge this significant gap, we propose a novel Aspect-driven News Recommender System (ANRS) built on aspect-level user preferences and news representation learning. In ANRS, a news aspect-level encoder and a user aspect-level encoder are devised to learn the fine-grained aspect-level representations of users’ preferences and news characteristics respectively. These representations are subsequently fed into a click predictor to predict the probability of a given user clicking on the candidate news item. Extensive experiments demonstrate the superiority of our method over state-of-the-art baseline methods.