Abstract:Multivariant time series (MTS) data are usually incomplete in real scenarios, and imputing the incomplete MTS is practically important to facilitate various time series mining tasks. Recently, diffusion model-based MTS imputation methods have achieved promising results by utilizing CNN or attention mechanisms for temporal feature learning. However, it is hard to adaptively trade off the diverse effects of local and global temporal features by simply combining CNN and attention. To address this issue, we propose a Score-weighted Convolutional Diffusion Model (Score-CDM for short), whose backbone consists of a Score-weighted Convolution Module (SCM) and an Adaptive Reception Module (ARM). SCM adopts a score map to capture the global temporal features in the time domain, while ARM uses a Spectral2Time Window Block (S2TWB) to convolve the local time series data in the spectral domain. Benefiting from the time convolution properties of Fast Fourier Transformation, ARM can adaptively change the receptive field of the score map, and thus effectively balance the local and global temporal features. We conduct extensive evaluations on three real MTS datasets of different domains, and the result verifies the effectiveness of the proposed Score-CDM.
Abstract:Quantum density matrix represents all the information of the entire quantum system, and novel models of meaning employing density matrices naturally model linguistic phenomena such as hyponymy and linguistic ambiguity, among others in quantum question answering tasks. Naturally, we argue that applying the quantum density matrix into classical Question Answering (QA) tasks can show more effective performance. Specifically, we (i) design a new mechanism based on Long Short-Term Memory (LSTM) to accommodate the case when the inputs are matrixes; (ii) apply the new mechanism to QA problems with Convolutional Neural Network (CNN) and gain the LSTM-based QA model with the quantum density matrix. Experiments of our new model on TREC-QA and WIKI-QA data sets show encouraging results. Similarly, we argue that the quantum density matrix can also enhance the image feature information and the relationship between the features for the classical image classification. Thus, we (i) combine density matrices and CNN to design a new mechanism; (ii) apply the new mechanism to some representative classical image classification tasks. A series of experiments show that the application of quantum density matrix in image classification has the generalization and high efficiency on different datasets. The application of quantum density matrix both in classical question answering tasks and classical image classification tasks show more effective performance.
Abstract:Federated Learning (FL) over wireless network enables data-conscious services by leveraging the ubiquitous intelligence at network edge for privacy-preserving model training. As the proliferation of context-aware services, the diversified personal preferences causes disagreeing conditional distributions among user data, which leads to poor inference performance. In this sense, clustered federated learning is proposed to group user devices with similar preference and provide each cluster with a personalized model. This calls for innovative design in edge association that involves user clustering and also resource management optimization. We formulate an accuracy-cost trade-off optimization problem by jointly considering model accuracy, communication resource allocation and energy consumption. To comply with parameter encryption techniques in FL, we propose an iterative solution procedure which employs deep reinforcement learning based approach at cloud server for edge association. The reward function consists of minimized energy consumption at each base station and the averaged model accuracy of all users. Under our proposed solution, multiple edge base station are fully exploited to realize cost efficient personalized federated learning without any prior knowledge on model parameters. Simulation results show that our proposed strategy outperforms existing strategies in achieving accurate learning at low energy cost.
Abstract:Visual Simultaneous Localization and Mapping (v-SLAM) and navigation of multirotor Unmanned Aerial Vehicles (UAV) in an unknown environment have grown in popularity for both research and education. However, due to the complex hardware setup, safety precautions, and battery constraints, extensive physical testing can be expensive and time-consuming. As an alternative solution, simulation tools lower the barrier to carry out the algorithm testing and validation before field trials. In this letter, we customize the ROS-Gazebo-PX4 simulator in deep and provide an end-to-end simulation solution for the UAV v-SLAM and navigation study. A set of localization, mapping, and path planning kits were also integrated into the simulation platform. In our simulation, various aspects, including complex environments and onboard sensors, can simultaneously interact with our navigation framework to achieve specific surveillance missions. In this end-to-end simulation, we achieved click and fly level autonomy UAV navigation. The source code is open to the research community.
Abstract:The ability to determine if the brain is developing normally is a key component of pediatric neuroradiology and neurology. Brain magnetic resonance imaging (MRI) of infants demonstrates a specific pattern of development beyond simply myelination. While radiologists have used myelination patterns, brain morphology and size characteristics in determining if brain maturity matches the chronological age of the patient, this requires years of experience with pediatric neuroradiology. Due to the lack of standardized criteria, estimation of brain maturity before age three remains fraught with interobserver and intraobserver variability. An objective measure of brain developmental age estimation (BDAE) could be a useful tool in helping physicians identify developmental delay as well as other neurological diseases. We investigated a three-dimensional convolutional neural network (3D CNN) to rapidly classify brain developmental age using common MRI sequences. MRI datasets from normal newborns were obtained from the National Institute of Mental Health Data Archive from birth to 3 years. We developed a BDAE method using T1-weighted, as well as a fusion of T1-weighted, T2-weighted, and proton density (PD) sequences from 112 individual subjects using 3D CNN. We achieved a precision of 94.8% and a recall of 93.5% in utilizing multiple MRI sequences in determining BDAE.