Nonlinear vibratory energy harvesters often exhibit multiple coexisting attractors, making their control challenging and energy-intensive. Ensuring an effective transition between these attractors while minimizing con...
详细信息
Nonlinear vibratory energy harvesters often exhibit multiple coexisting attractors, making their control challenging and energy-intensive. Ensuring an effective transition between these attractors while minimizing control effort is crucial for maximizing power generation and maintaining system stability. This paper introduces a differentiable data-driven control strategy that optimizes energy harvester performance by leveraging a neural network (NN)-based control framework. Unlike traditional fixed-gain or surrogate modeling approaches, the proposed method directly integrates system dynamics and control power consumption into the gain adaptation process, ensuring real-time adaptability. By exploiting the differentiability of neural networks, the controller employs gradient-based optimization to continuously refine control parameters in response to changes in operating conditions. The control framework consists of an offline training phase, where the neural network learns an energy-efficient control strategy through differentiable simulations. During this phase, the neural network is trained using a large dataset of system responses to different control inputs, allowing it to learn the most energy-efficient control strategy. This trained network is then used in the online deployment phase, where the trained controller dynamically adjusts control parameters in real-time. The proposed approach minimizes control energy consumption and efficiently guides the system toward the high-energy attractor, avoiding unnecessary control effort. Our approach significantly outperforms conventional PID-based sliding mode controllers. Simulation results confirm that the differentiable controller considerably enhances energy harvesting efficiency and reduces chattering, ensuring a smooth transition to the high-energy orbit while maintaining robust system stability. The study also highlights the necessity of an adaptive control strategy, stressing the urgency of its implementation for o
Infectious diseases like the novel Coronavirus (COVID-19) affect millions of individuals if not managed well in time. Thus, to reduce the transmission rate, effective diagnostic techniques must be identified. Early de...
详细信息
This article investigates the role of multi-oriented photovoltaic (PV) systems in enhancing energy self-sufficiency and reducing greenhouse gas emissions. Focusing on the evaluation of energy production prediction per...
详细信息
Discrete compartmental epidemiological models are widely used in epidemiological modeling because they allow the study of relationships between microscopic dynamics and macroscopic properties of the epidemic. They can...
详细信息
Contextualized embeddings of words (such as BLOOM and BERT) outperform static embeddings (such as Word2vec, Fasttext, and GloVe) for many natural language processing tasks. In this article, an exploration is conducted...
详细信息
ISBN:
(数字)9798331531836
ISBN:
(纸本)9798331531843
Contextualized embeddings of words (such as BLOOM and BERT) outperform static embeddings (such as Word2vec, Fasttext, and GloVe) for many natural language processing tasks. In this article, an exploration is conducted of the use of contextualized embeddings for the purposes of searching for C++ code and classifying the algorithms that are utilized. Furthermore, a novel approach is proposed for reducing the dimensionality of the resulting embeddings, leveraging a multilayer perceptron trained with Multi Similarity Loss. The experiments performed for the methods of multilabel classification of algorithms and for the code similarity search show that the proposed method not only effectively reduces the dimension of embeddings, but also increases their representativeness.
The quantum alternating operator ansatz (QAOA) represents a branch of quantum algorithms for solving combinatorial optimization problems. A specific variant, the Grover-mixer (GM) QAOA, ensures uniform amplitude acros...
详细信息
The quantum alternating operator ansatz (QAOA) represents a branch of quantum algorithms for solving combinatorial optimization problems. A specific variant, the Grover-mixer (GM) QAOA, ensures uniform amplitude across states that share equivalent objective values. This property makes the algorithm independent of the problem structure, focusing instead on the distribution of objective values within the problem. In this work we provide an alternative proof for the upper bound on the probability of measuring a computational basis state from a GM QAOA circuit with a given depth, which is a critical factor in QAOA cost. Using this, we derive the upper bounds for the probability of sampling an optimal solution and for the approximation ratio of maximum optimization problems, both dependent on the objective value distribution. Through numerical analysis, we link the distribution to the problem size and build the regression models that relate the problem size, QAOA depth, and performance upper bound. Our results suggest that the GM QAOA provides a quadratic enhancement in sampling probability and requires circuit depth that scales exponentially with problem size to maintain consistent performance.
With the rapid evolution of artificial intelligence (AI) and computer vision, assistive technologies have become increasingly adept at supporting individuals with special needs. This paper provides a comprehensive exa...
详细信息
ISBN:
(数字)9798331523657
ISBN:
(纸本)9798331523664
With the rapid evolution of artificial intelligence (AI) and computer vision, assistive technologies have become increasingly adept at supporting individuals with special needs. This paper provides a comprehensive examination of two critical areas: AI-powered visual assistance systems for the visually impaired and sign language recognition and generation frameworks for the Deaf and hard-of-hearing communities. We review the latest research trends, algorithms, and tools, highlighting emerging deep learning architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Transformers in both domains. We then propose a unified framework that leverages edge computing, multimodal learning, and advanced human-computer interaction (HCI) techniques to address challenges such as real-time object recognition, complex gesture capture, data scarcity, and cultural variations in sign languages. We further detail an experimental design and set of results that demonstrate the feasibility and benefits of these approaches, followed by a discussion of ethical considerations, limitations, and future directions. Our goal is to illustrate a path toward more inclusive AI systems that offer robust solutions for accessibility, ultimately bridging communication gaps and fostering independence for individuals with special needs [1]–[11].
Loss functions are at the heart of deep learning, shaping how models learn and perform across diverse tasks. They are used to quantify the difference between predicted outputs and ground truth labels, guiding the opti...
详细信息
Social media serve as a crucial platform for expressing opinions and perspectives. Its texts often characterised by code-switching or mixed languages in multilingual setting. This results in a diverse and complex ling...
详细信息
暂无评论