Demand prediction is a crucial task for e-commerce and physical retail businesses, especially during high-stake sales events. However, the limited availability of historical data from these peak periods poses a signif...
Demand prediction is a crucial task for e-commerce and physical retail businesses, especially during high-stake sales events. However, the limited availability of historical data from these peak periods poses a significant challenge for traditional forecasting methods. In this paper, we propose a novel approach that leverages proxy data from non-peak periods, enriched by features learned from a graph neural networks (GNNs) based forecasting model, to predict demand during peak events. We formulate the demand prediction as a meta-learning problem and introduce the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm, which adapts to new tasks by conditioning on the GNN-generated relational metadata. Empirical evaluations on large-scale industrial datasets demonstrate the superiority of our approach, with our model consistently outperforming state-of-the-art baselines in the demand prediction task, by 26.24% on the internal vending machine dataset and 8.7% on the public *** dataset over the Mean Absolute Error.
Healthcare professionals are quite concerned with constantly monitoring their patients. An Internet of Things (IoT) based wireless health monitoring station can be a viable option to reduce human labor. The design stu...
详细信息
Healthcare professionals are quite concerned with constantly monitoring their patients. An Internet of Things (IoT) based wireless health monitoring station can be a viable option to reduce human labor. The design study of a single-ended ring oscillator-based voltage-controlled oscillator (RO-VCO) optimized for implementation in an IoT-based wireless health monitoring system is presented in this paper. The schematic was created using a 50 nm CMOS process. By varying the control voltage from 0.9 V to 1.5 V the voltage-controlled oscillator can operate at 1.67 to 3.13 GHz. A supply voltage of 1 V was used to achieve the oscillation frequency of 2.4 GHz. Such a VCO will be an essential module for the proposed IoT-based patient monitoring station and other ISM band applications.
Performance of concatenated multilevel coding with probabilistic shaping (PS) and Voronoi constellations (VCs) is analysed over AWGN channel. Numerical results show that VCs provide up to 1.3 dB SNR gains over PS-QAM ...
详细信息
In minimally invasive telesurgery, obtaining accurate force information is difficult due to the complexities of in-vivo end effector force sensing. This constrains development and implementation of haptic feedback and...
详细信息
Knowledge Graph Embedding aims to advance the learning performance of knowledge graphs by deliberating the complexity of hierarchical data structures in a finite-dimensional space. Most traditional Euclidean models st...
详细信息
With the agile development process of most academic and corporate entities, designing a robust computational back-end system that can support their ever-changing data needs is a constantly evolving challenge. We propo...
详细信息
The paper provides detailed information about the design and implementation of the universal DSP module for simultaneous multiple RS232 communication with synchronous measurements reading capability. The hardware aspe...
The paper provides detailed information about the design and implementation of the universal DSP module for simultaneous multiple RS232 communication with synchronous measurements reading capability. The hardware aspect of the module includes the development of an electric scheme and PCB scheme, ensuring the proper functioning and connectivity of the RS232 devices. Additionally, the paper includes relevant pictures that visually depict the module's design and components. Furthermore, the software part of the module is described, focusing on the development of an application that facilitates the reception and processing of data from the connected RS232 devices. The paper provides a comprehensive description of the created application, outlining its features and functionalities. Overall, this research offers a comprehensive exploration of the hardware and software aspects of the universal DSP module, providing readers with valuable insights into its design, implementation, and application in facilitating simultaneous RS232 communication with synchronous measurements reading capability.
作者：
Zhang, YiXie, YajingWang, LijiaLiwang, MinghuiWang, XianbinXiamen University
Ministry of Education of China Department of Information and Communication Engineering Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen China Tongji University
Shanghai Research Institute for Intelligent Autonomous Systems Department of Control Science and Engineering Shanghai China Western University
Department of Electrical and Computer Engineering ON Canada
Recently, unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) have merged as important enabling technologies for localization coverage extension and localization accuracy improvement under s...
详细信息
The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, whic...
The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in multilingual speech recognition. Recent studies have attempted to address this setting by separating the modules for different languages to ensure distinct latent representations for languages. Some other methods considered the switching mechanism based on language identification. In this study, a new attention-guided adaptation is proposed to conduct parameter-efficient learning for bilingual ASR. This method selects those attention heads in a model which closely express language identities and then guided those heads to be correctly attended with their corresponding languages. The experiments on the Mandarin-English code-switching speech corpus show that the proposed approach achieves a 14.2% mixed error rate, surpassing state-of-the-art method, where only 5.6% additional parameters over Whisper are trained.
This paper introduces a novel magnet configuration for a radially magnetized trans-rotary magnetic gear (TROMAG) that offers higher shear stress per magnet volume and shear stress per gear mass. TROMAG is a type of ma...
This paper introduces a novel magnet configuration for a radially magnetized trans-rotary magnetic gear (TROMAG) that offers higher shear stress per magnet volume and shear stress per gear mass. TROMAG is a type of magnetic gear that converts linear motion to rotation and vice versa. The device is known for its high force density and high gear ratio. Different permanent magnet (PM) configurations have been introduced for the TROMAG; namely, radially-magnetized (RMT), axially-magnetized (AMT), and Halbach-magnetized (HMT) TROMAG. While RMT is the least challenging from a fabrication perspective, its conventional PM configuration has shear stress and shear stress per PM volume lower than that of HMT. The novel RMT configuration introduced in this paper, compared to the conventional RMT, offers up to ~47% higher shear stress per PM volume and up to ~26% higher shear stress per TROMAG’s mass.
暂无评论