One of the most important characteristics porphyry copper deposits (PCDs) is type and distribution pattern alteration zones which can be used for screening recognizing these deposits. Hydrothermal minerals with diagnostic spectral absorption properties in visible near-infrared (VNIR) through shortwave infrared (SWIR) regions identified by multispectral hyperspectral remote sensing data. Six Advanced Spaceborne Thermal Emission Reflection Radiometer (ASTER) bands SWIR have been shown to...

Although many researchers of recommender systems have noted that encoding user-item interactions based on DNNs promotes the performance collaborative filtering, they ignore embedding latent features collected from external sources, e.g., knowledge graphs (KGs), is able to produce more precise recommendation results. Furthermore, CF-based models are still vulnerable scenarios sparse known interactions. In this paper, towards movie recommendation, we propose a novel knowledge-enhanced deep...

This work presents a novel ensemble of Bayesian Neural Networks for control safety-critical systems. Decision making systems is challenging due to performance requirements with significant consequences in the event failure. In practice, failure such can be avoided by introducing redundancies control. are generally not used as they behave unexpected ways response inputs. addition, there may any indication when will fail. BNNs have been recognized their ability produce only viable outputs but...

Self-supervised graph representation learning has driven significant advancements in domains such as social network analysis, molecular design, and electronics design automation (EDA). However, prior works EDA have mainly focused on the of gate-level digital circuits, failing to capture analog mixed-signal circuits. To address this gap, we introduce DICE: Device-level Integrated Circuits Encoder, first self-supervised pretrained neural (GNN) model for any circuit expressed at device level....

With the informatization development and digital construction in healthcare industry, electronic medical records Internet medicine facilitate people's treatment. However, current data storage method has risk of loss, leakage, tampering, can't support extensive secure sharing data. To realize effective among offline institutions platforms, this study used a combined private blockchain consortium to design double-chain system (MBDS). This can store encrypted distributed mode systematically...

With the development of autonomous driving, precise positioning capabilities are becoming increasingly important. GNSS (Global Navigation Satellite System) is normally utilized for vehicle positioning, but susceptible to factors such as urban canyons, especially in urbanized scenario nowadays. The interpretation relative information by means multi-source sensors LiDAR (Light Detection And Ranging) or camera, has also been widely investigated, there deficiencies precision and reliability due...

Information fusion is one of the key technologies in airborne multisource navigation, where federated filter widely used due to its simple structure. However, sensor measurement navigation system will become unreliable some interferential environment, which leads state and noise covariance matrix (MNCM) change over time estimate difficultly. Inaccurate matrices cause loss positioning accuracy traditional filter. To address problems, this article puts forward an adaptive federal Kalman...

Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some studies implicitly show that many generic techniques or ``tricks'', such as data augmentation, pre-training, knowledge distillation, self-supervision, may greatly boost the performance of a learning method. Moreover, different works employ software platforms, backbone architectures input sizes, making fair comparisons difficult practitioners...

Recently, many researchers in recommender systems have realized that encoding user-item interactions based on deep neural networks (DNNs) promotes collaborative-filtering (CF)'s performance. Nonetheless, those DNN-based models' performance is still limited when observed are very less because the training samples distilled from these critical for learning models. To address this problem, we resort to plenty features knowledge graphs (KGs), profile users and items precisely sufficiently rather...

We propose a sampling-based trajectory optimization methodology for constrained problems. extend recent works on stochastic search to deal with box control constraints, as well nonlinear state constraints discrete dynamical systems. Regarding the former, our strategy is optimize over truncated parameterized distributions inputs. Furthermore, we show how non-smooth penalty functions can be incorporated into framework handle constraints. Simulations cartpole and quadcopter that approach...

In this paper, we propose a novel elastic demand function that captures the price elasticity of in hotel occupancy prediction. We develop prediction model (PEM) with competitive representation module and multi-sequence fusion to learn dynamic from complex set affecting factors. Moreover, multi-task framework consisting room- hotel-level tasks is introduced PEM alleviate data sparsity issue. Extensive experiments on real-world datasets show outperforms other state-of-the-art methods for both...

Effective psychotherapy should satisfy the client, but that satisfaction depends on many factors. We do not fully understand factors affect client with and how these synergistically a client's experience.This study aims to use machine learning predict Chinese clients' analyze potential outcome contributors.In this cross-sectional investigation, self-compiled online questionnaire was delivered through WeChat app. The information of 791 participants who had received used in study. A series...

This paper proposes an improved whale optimization algorithm with chaotic mapping and adaptive iteration strategy (CMAIS-WOA). addresses the issues of WOA that is prone to local optimal solutions low stability. CMAIS-WOA utilizes enhance diversity coverage initial population. Also, it adaptively adjusts weight values based on current distribution populations fitness search agents. In addition, uses nonlinear convergence factor adjust breadth-first depth-first during process. The performance...

We investigate into the problem of joint direction-of-departure (DOD) and direction-ofarrival (DOA) estimation in a multiple-input multiple-output radar, novel covariance tensor-based quadrilinear decomposition algorithm is derived this paper. By taking account multidimensional structure matched array data, fourth-order tensor formulated, which links DOD DOA to model. A alternating least squares (QALSs) technique applied estimate loading matrices, thereafter automatically paired DODs DOAs...

In this paper, we present a novel maximum entropy formulation of the Differential Dynamic Programming algorithm and derive two variants using unimodal multimodal value functions parameterizations. By combining Bellman equations with particular approximation cost function, are able to obtain new which is escape from local minima via exploration policy. To demonstrate efficacy proposed algorithm, provide experimental results four systems on tasks that represented by multiple compare them...