Article
Computer Science, Artificial Intelligence
Yanying Liang, Wei Peng, Zhu-Jun Zheng, Olli Silven, Guoying Zhao
Summary: Inspired by classical neural networks, a novel hybrid quantum-classical neural network with deep residual learning (Res-HQCNN) is proposed in this paper, which shows better performance in learning unknown unitary transformations and handling noisy data through experiments.
Article
Computer Science, Artificial Intelligence
R. I. Minu, Martin Margala, S. Siva Shankar, Prasun Chakrabarti, G. Nagarajan
Summary: Early diagnosis is crucial for cancer patients' survival. Esophageal cancer has a high 5-year survival rate of over 80% but has become more common due to changes in eating habits. Advances in medical screening techniques have improved detection, but accurately identifying the infected area remains a challenge. This research utilizes a hybrid QCNN model to effectively identify infected areas using quantum filters for in-depth feature analysis and early cancer prediction with higher accuracy compared to the classic CNN model.
Article
Computer Science, Information Systems
Tayyaba Shahwar, Junaid Zafar, Ahmad Almogren, Haroon Zafar, Ateeq Ur Rehman, Muhammad Shafiq, Habib Hamam
Summary: In this study, a hybrid classical-quantum machine learning model is proposed for the detection of Alzheimer's disease. By combining classical neural networks and quantum processors, the model achieves optimal preprocessing of complex and high-dimensional data, resulting in high accuracy.
Article
Computer Science, Artificial Intelligence
Ying-Yi Hong, Christian Lian Paulo P. Rioflorido, Weina Zhang
Summary: This work proposes a hybrid deep learning technique that incorporates a quantum-inspired neural network to predict wind speeds 24 h in advance. The proposed method outperforms other methods for 24 h-ahead wind speed forecasting.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Quantum Science & Technology
Maiyuren Srikumar, Charles D. Hill, Lloyd C. L. Hollenberg
Summary: Quantum machine learning is a rapidly growing field at the intersection of classical machine learning and quantum information theory. This work proposes a novel approach that uses a hybrid quantum autoencoder to extract information from quantum states and represent it in a classical space. This approach has potential applications in clustering and semi-supervised classification.
QUANTUM SCIENCE AND TECHNOLOGY
(2022)
Article
Computer Science, Theory & Methods
Fabio Valerio Massoli, Lucia Vadicamo, Giuseppe Amato, Fabrizio Falchi
Summary: In recent years, there have been significant advancements in quantum computing in terms of resources and algorithm development, attracting considerable interest from the scientific community. This article introduces the basic concepts of quantum computations and explains the core functionalities of technologies implementing the Gate Model and Adiabatic Quantum Computing paradigms. Furthermore, it gathers, compares, and analyzes the current state-of-the-art regarding Quantum Perceptrons and Quantum Neural Networks implementations.
ACM COMPUTING SURVEYS
(2023)
Article
Quantum Science & Technology
Fang-Fang Du, Yi-Ming Wu, Gang Fan
Summary: High-efficiency quantum information processing is achieved through logic qubit gates that require the fewest quantum resources and simplest operations. By using a reflection geometry of a single photon interacting with a three-level Λ-type atom-cavity system, the authors propose refined protocols for conducting controlled-not (CNOT), Fredkin, and Toffoli gates on hybrid systems. In these gates, the first control qubit is encoded on a flying photon, while the remaining qubits are encoded on atoms inside the optical cavity. These quantum gates can also be extended to the optimal synthesis of multi-qubit CNOT, Fredkin, and Toffoli gates without auxiliary photons or atoms using O(n) optical elements. Furthermore, the simplest single-qubit operations are applied only to the photon, making these logic gates experimentally feasible with current technology.
ADVANCED QUANTUM TECHNOLOGIES
(2023)
Article
Quantum Science & Technology
Simone Cantori, David Vitali, Sebastiano Pilati
Summary: Predicting the output of quantum circuits is a difficult task in the development of universal quantum computers. Using classical simulations, we trained deep convolutional neural networks (CNNs) to predict output expectation values of random quantum circuits. The CNNs outperform small-scale quantum computers and demonstrate scalability, transfer learning, and noise resilience.
QUANTUM SCIENCE AND TECHNOLOGY
(2023)
Article
Quantum Science & Technology
Niyazi Furkan Bar, Hasan Yetis, Mehmet Karakose
Summary: Nowadays, machine learning techniques are widely applied to various fields, and the idea of using quantum computing to solve problems is gaining popularity. Researchers are experimenting with quantum circuits in machine learning methods to overcome the limitations of qubits. In this study, a variational quantum circuit (VQC) using amplitude encoding is proposed and applied to a navigation problem, showing promising performance.
QUANTUM INFORMATION PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Surin Gweon, Sanghoon Kang, Kwantae Kim, Hoi-Jun Yoo
Summary: With the widespread adoption of deep neural networks in various applications, the use of DNNs on tiny platforms such as IoT devices is becoming more common. However, traditional digital implementations of multiply-and-accumulate (MAC) acceleration face limitations due to energy and form factor constraints. This article proposes the FlashMAC architecture, inspired by flash ADC, which supports multibit multiplication and achieves low latency accumulation with low power consumption. By integrating time- and frequency-domain computing methods, it achieves high energy efficiency and supports complex DNN models requiring higher precision.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2022)
Article
Physics, Multidisciplinary
Jihye Kim, Byungdu Oh, Yonuk Chong, Euyheon Hwang, Daniel K. Park
Summary: In this work, a deep learning-based protocol is presented for reducing readout errors on quantum hardware. By training a neural network to correct non-linear noise, the limitations of existing linear inversion methods are overcome.
NEW JOURNAL OF PHYSICS
(2022)
Article
Physics, Multidisciplinary
Maida Wang, Anqi Huang, Yong Liu, Xuming Yi, Junjie Wu, Siqi Wang
Summary: Machine learning has achieved remarkable success in various applications, particularly in deep anomaly detection research. The interaction between ML and quantum computing has led to a promising field called quantum machine learning. This paper focuses on addressing the problem of image anomaly detection using a novel quantum machine learning solution.
Article
Physics, Multidisciplinary
Junhua Liu, Kwan Hui Lim, Kristin L. Wood, Wei Huang, Chu Guo, He-Liang Huang
Summary: The study introduces a hybrid quantum-classical convolutional neural network that can efficiently perform feature mapping on noisy intermediate-scale quantum computers, proposes a framework for automatic computation of loss function gradients, and demonstrates the architecture's potential in surpassing classical CNN in learning accuracy for classification tasks.
SCIENCE CHINA-PHYSICS MECHANICS & ASTRONOMY
(2021)
Article
Computer Science, Hardware & Architecture
Nurzhan Zhuldassov, Rassul Bairamkulov, Eby G. Friedman
Summary: Heterogeneous computing utilizes various technologies within a system and the different components are placed in separate temperature zones. Selecting an appropriate operating temperature is crucial for power dissipation, cooling power, system performance, and ambient temperature. This article proposes a framework for thermal optimization in heterogeneous computing systems, considering the effects of temperature on delay and power consumption, as well as thermal interactions between components. A practical case study is conducted to determine the target temperature for each component in a quantum computing system, aiming to minimize total power under performance constraints.
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
(2023)
Article
Energy & Fuels
Su Fong Chien, Heng Siong Lim, Michail Alexandros Kourtis, Qiang Ni, Alessio Zappone, Charilaos C. Zarakovitis
Summary: The paper explores the development of a quantum neural network algorithm to address the energy efficiency problem in wireless communications, showing that the algorithm is trainable and exhibits slightly faster convergence speed than traditional artificial neural network algorithms.
Article
Engineering, Chemical
Rachel S. Bang, Michael Bergman, Tianyu Li, Fiona Mukherjee, Abdulelah S. Alshehri, Nicholas L. Abbott, Nathan C. Crook, Orlin D. Velev, Carol K. Hall, Fengqi You
Summary: This article proposes an integrated chemical engineering approach to improve our understanding of microplastics (MPs). Through artificial intelligence, theoretical methods, and experimental techniques, existing data can be integrated into models of MPs, unknown features of MPs can be investigated, and future research areas can be identified.
Article
Engineering, Chemical
Apoorv Lal, Fengqi You
Summary: This article presents a systematic framework for the sustainable design of hydrogen production systems that integrate different pathways and infrastructure. A life cycle optimization model is developed to find the optimal design of steam methane reforming-based hydrogen production systems, considering various process options and operating conditions.
Article
Engineering, Environmental
Fengqi You, Xiang Zhao
Summary: Plastic pollution caused by material losses and their subsequent chemical emissions is widespread in the natural environment and can worsen over time. Analyzing the environmental consequences of plastic losses throughout its life cycle, this study investigates the cascaded processing of plastic waste compared to other waste end-of-life management pathways. Plastic losses can lead to the formation of volatile organic chemicals and have significant global warming, ecotoxicity, and air pollution effects, which can increase by at least 189% in the long run. Cascaded plastic waste processing utilizing upcycling technologies can effectively reduce environmental losses and outperform landfills and incineration in terms of ozone formation and air pollution reduction, while also saving fossil fuels.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Fiona Mukherjee, Anye Shi, Xin Wang, Fengqi You, Nicholas L. Abbott
Summary: This study explores the formation of distinct 2D patterns of microplastics (MPs) at the aqueous interfaces of liquid crystal (LC) films, aiming to develop surface-sensitive methods for identifying MPs. Polyethylene (PE) and polystyrene (PS) microparticles exhibit different aggregation patterns, with anionic surfactant amplifying the differences in aggregation patterns. Statistical analysis using deep learning image recognition models accurately classifies the assembly patterns, with dense, multibranched assemblies identified as unique features of PE. The study predicts LC-mediated interactions and concludes that rough surfaces of PE microparticles weaken LC elastic interactions and enhance capillary forces. Overall, LC interfaces show potential for rapid identification of colloidal MPs based on their surface properties.
Article
Multidisciplinary Sciences
Haoyue Liang, Fengqi You
Summary: Reshoring silicon photovoltaic manufacturing back to the U.S. has multiple benefits including improving domestic competitiveness, advancing decarbonization goals, and mitigating climate change. A study projects that if c-Si PV panel manufacturing is fully brought back by 2035, greenhouse gas emissions and energy consumption would be significantly lower compared to relying on global imports in 2020. Achieving the reshored manufacturing target by 2050 would further reduce climate change and energy impacts.
NATURE COMMUNICATIONS
(2023)
Article
Energy & Fuels
Ning Zhao, Haoran Zhang, Xiaohu Yang, Jinyue Yan, Fengqi You
Summary: The decarbonization of energy systems is crucial for mitigating climate change, as the energy sector is the main contributor to global greenhouse gas emissions. Renewable transition planning and sustainable systems operations are two major challenges in energy systems decarbonization. Incorporating emerging information and communication technologies, such as artificial intelligence, quantum computing, blockchain, next-generation communication technologies, and the metaverse, can facilitate the design and operations of future smart energy systems with high penetrations of renewable energy and decentralized structures. This comprehensive review explores the applicability of these technologies in renewable transition and smart energy systems and discusses relevant research directions and industrial use cases.
ADVANCES IN APPLIED ENERGY
(2023)
Article
Energy & Fuels
Guoqing Hu, Fengqi You
Summary: This paper proposes a data-driven robust MPC framework for a multi-zone building considering thermal comfort and uncertain weather forecast errors. The framework improves energy efficiency and meets thermal constraints. A state-space model and machine learning approaches are used to handle the building's temperature and humidity. The proposed framework achieves significant energy savings and better thermal control compared to conventional methods.
ADVANCES IN APPLIED ENERGY
(2023)
Article
Energy & Fuels
Tianqi Xiao, Fengqi You
Summary: This article proposes a novel physically consistent deep learning (PCDL) approach for building thermal modeling and assesses its potential for optimizing building energy efficiency and indoor thermal comfort through model predictive control (MPC). The PCDL model considers physical relationships between system inputs and outputs and is applied to predict the indoor thermal climate. The proposed approach demonstrates better performance in reducing energy consumption and improving thermal comfort compared to other controllers.
Article
Energy & Fuels
Jiahan Xie, Akshay Ajagekar, Fengqi You
Summary: Integrating renewable energy resources and deploying energy management devices provide opportunities for autonomous energy management in grid-responsive buildings. Demand response can enhance flexibility and efficiency while reducing costs. This study proposes a novel multi-agent deep reinforcement learning (MADRL) approach for real-time coordinated demand response in buildings. The approach demonstrates the ability to minimize electricity costs and shape loads without knowledge of building energy systems, and also achieves a significant reduction in net load demand compared to standard reinforcement learning approaches.
Article
Green & Sustainable Science & Technology
Shoudong Zhu, Nathan Preuss, Fengqi You
Summary: With the rapid increase in untreated wet waste due to global population growth, urbanization, and improved living standards, waste management and environmental concerns have become critical challenges. This study introduces a novel framework that combines advanced machine learning techniques and dual-objective optimization to compare the solid products of hydrothermal carbonization (HTC) and pyrolysis, focusing on their carbon stability and energy investment return. The results demonstrate the potential of tailoring char production for high energy efficiency and stable carbon sequestration, contributing to achieving Sustainable Development Goals 7 and 15.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Green & Sustainable Science & Technology
Peng Jiang, Lei Zhang, Siming You, Yee Van Fan, Raymond R. Tan, Jirf Jaromfr Klemes, Fengqi You
Summary: Rapid population growth and urbanization have led to increased waste generation and posed a major challenge for waste management worldwide. Blockchain technology, with its features of information security and meeting the data needs of waste management, has attracted attention in the field. However, further research and exploration are needed as this emerging technology has not been widely accepted.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Green & Sustainable Science & Technology
Apoorv Lal, Thomas Renaldy, Larissa Breuning, Thomas Hamacher, Fengqi You
Summary: Research shows that battery electric light commercial vehicles (LCVs) are cost-competitive and can reduce greenhouse gas emissions by 15%-48% over the vehicle's lifetime. Additionally, if the hydrogen used in a fuel cell LCV is produced via water electrolysis powered by low-carbon electricity, a Mid-FC LCV has lower environmental impacts than an FC LCV. These findings provide critical insights for fleet operators in balancing cost-effectiveness and environmental sustainability in LCV selection.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Multidisciplinary Sciences
Yanqiu Tao, Longqi Yang, Sonia Jaffe, Fereshteh Amini, Peter Bergen, Brent Hecht, Fengqi You
Summary: The growth of remote and hybrid work due to COVID-19 has significant environmental implications. A study in the United States found that switching from onsite to remote work can reduce up to 58% of work's carbon footprint, with negligible impacts from information and communication technology usage, but important impacts from office energy use and noncommute travel. The study suggests that achieving the environmental benefits of remote work requires proper lifestyle setup.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2023)
Article
Chemistry, Multidisciplinary
Xueyu Tian, Bart Roose, Samuel D. Stranks, Fengqi You
Summary: Propose periodic module recycling as a strategy to address resource scarcity and stability requirements, accelerating the commercialization of halide perovskite tandem PV. Experimental results show that indium tin oxide-coated substrates can be reused without significant performance loss. Recycling reduces greenhouse gas emissions and improves energy return on investment, providing new strategies for sustainable PV technologies.
ENERGY & ENVIRONMENTAL SCIENCE
(2023)
Article
Chemistry, Multidisciplinary
Ning Zhao, Fengqi You
Summary: The rapid expansion of the metaverse industry has potential climate impacts that are not yet fully understood. However, our prospective analyses show that the adoption of metaverse technologies can reduce global surface temperature and greenhouse gas emissions. By examining various applications in working, traveling, education, non-fungible tokens, and gaming, we find that metaverse growth accelerates decarbonization efforts and improves air quality.
ENERGY & ENVIRONMENTAL SCIENCE
(2023)
Article
Energy & Fuels
Shitong Fang, Houfan Du, Tao Yan, Keyu Chen, Zhiyuan Li, Xiaoqing Ma, Zhihui Lai, Shengxi Zhou
Summary: This paper proposes a new type of nonlinear VIV energy harvester (ANVEH) that compensates for the decrease in peak energy output at low wind speeds by introducing an auxiliary structure. Theoretical and experimental results show that ANVEH performs better than traditional nonlinear VIV energy harvesters under various system parameter variations.
Article
Energy & Fuels
Wei Jiang, Shuo Zhang, Teng Wang, Yufei Zhang, Aimin Sha, Jingjing Xiao, Dongdong Yuan
Summary: A standardized method was developed to evaluate the availability of solar energy resources in road areas, which combined the Analytic Hierarchy Process (AHP) and the Geographic Information System (GIS). By analyzing critical factors and using a multi-indicator evaluation method, the method accurately evaluated the utilization of solar energy resources and guided the optimal location selection for road photovoltaic (PV) projects. The results provided guidance for the application of road PV projects and site selection for route corridors worldwide, promoting the integration of transportation and energy.
Article
Energy & Fuels
Chang Liu, Jacob A. Wrubel, Elliot Padgett, Guido Bender
Summary: The study investigates the effects of coating defects on the performance of the anode porous transport layer (PTL) in water electrolyzers. The results show that an increasing fraction of uncoated regions on the PTL leads to decreased cell performance, with continuous uncoated regions having a more severe impact compared to multiple thin uncoated strips.
Article
Energy & Fuels
Marcos Tostado-Veliz, Xiaolong Jin, Rohit Bhakar, Francisco Jurado
Summary: In this paper, a coordinated charging price mechanism for clusters of parking lots is proposed. The research shows that enabling vehicle-to-grid characteristics can bring significant economic benefits for users and the cluster coordinator, and vehicle-to-grid impacts noticeably on the risk-averse character of the uncertainty-aware strategies. The developed pricing mechanism can reduce the cost for users, avoiding to directly translate the energy cost to charging points.
Article
Energy & Fuels
Duan Kang
Summary: Building an energy superpower is a key strategy for China and a long-term goal for other countries. This study proposes an evaluation system and index for measuring energy superpower, and finds that China has significantly improved its ranking over the past 21 years, surpassing other countries.
Article
Energy & Fuels
Fucheng Deng, Yifei Wang, Xiaosen Li, Gang Li, Yi Wang, Bin Huang
Summary: This study investigated the synergistic blockage mechanism of sand and hydrate in gravel filling layer and the evolution of permeability in the layer. Experimental models and modified permeability models were established to analyze the effects of sand particles and hydrate formation on permeability. The study provided valuable insights for the safe and efficient exploitation of hydrate reservoirs.
Article
Energy & Fuels
Hao Wang, Xiwen Chen, Natan Vital, Edward Duffy, Abolfazl Razi
Summary: This study proposes a HVAC energy optimization model based on deep reinforcement learning algorithm. It achieves 37% energy savings and ensures thermal comfort for open office buildings. The model has a low complexity, uses a few controllable factors, and has a short training time with good generalizability.
Article
Energy & Fuels
Moyue Cong, Yongzhuo Gao, Weidong Wang, Long He, Xiwang Mao, Yi Long, Wei Dong
Summary: This study introduces a multi-strategy ultra-wideband energy harvesting device that achieves high power output without the need for external power input. By utilizing asymmetry, stagger array, magnetic coupling, and nonlinearity strategies, the device maintains a stable output voltage and high power density output at non-resonant frequencies. Temperature and humidity monitoring are performed using Bluetooth sensors to adaptively assess the device.
Article
Energy & Fuels
Tianshu Dong, Xiudong Duan, Yuanyuan Huang, Danji Huang, Yingdong Luo, Ziyu Liu, Xiaomeng Ai, Jiakun Fang, Chaolong Song
Summary: Electrochemical water splitting is crucial for hydrogen production, and improving the hydrogen separation rate from the electrode is essential for enhancing water electrolyzer performance. However, issues such as air bubble adhesion to the electrode plate hinder the process. Therefore, a methodology to investigate the two-phase flow within the electrolyzer is in high demand. This study proposes using a microfluidic system as a simulator for the electrolyzer and optimizing the two-phase flow by manipulating the micro-structure of the flow.
Article
Energy & Fuels
Shuo Han, Yifan Yuan, Mengjiao He, Ziwen Zhao, Beibei Xu, Diyi Chen, Jakub Jurasz
Summary: Giving full play to the flexibility of hydropower and integrating more variable renewable energy is of great significance for accelerating the transformation of China's power energy system. This study proposes a novel day-ahead scheduling model that considers the flexibility limited by irregular vibration zones (VZs) and the probability of flexibility shortage in a hydropower-variable renewable energy hybrid generation system. The model is applied to a real hydropower station and effectively improves the flexibility supply capacity of hydropower, especially during heavy load demand in flood season.
Article
Energy & Fuels
Zhen Wang, Kangqi Fan, Shizhong Zhao, Shuxin Wu, Xuan Zhang, Kangjia Zhai, Zhiqi Li, Hua He
Summary: This study developed a high-performance rotary energy harvester (AI-REH) inspired by archery, which efficiently accumulates and releases ultralow-frequency vibration energy. By utilizing a magnetic coupling strategy and an accumulator spring, the AI-REH achieves significantly accelerated rotor speeds and enhanced electric outputs.
Article
Energy & Fuels
Yi Yang, Qianyi Xing, Kang Wang, Caihong Li, Jianzhou Wang, Xiaojia Huang
Summary: In this study, a novel hybrid Quantile Regression (QR) model is proposed for Probabilistic Load Forecasting (PLF). The model integrates causal dilated convolution, residual connection, and Bidirectional Long Short-Term Memory (BiLSTM) for multi-scale feature extraction. In addition, a Combined Probabilistic Load Forecasting System (CPLFS) is proposed to overcome the inherent flaws of relying on a single model. Simulation results show that the hybrid QR outperforms traditional models and CPLFS exceeds the best benchmarks in terms of prediction accuracy and stability.
Article
Energy & Fuels
Wen-Jiang Zou, Young-Bae Kim, Seunghun Jung
Summary: This paper proposes a dynamic prediction model for capacity fade in vanadium redox flow batteries (VRFBs). The model accurately predicts changes in electrolyte volume and capacity fade, enhancing the competitiveness of VRFBs in energy storage applications.
Article
Energy & Fuels
Yuechao Ma, Shengtie Wang, Guangchen Liu, Guizhen Tian, Jianwei Zhang, Ruiming Liu
Summary: This paper focuses on the balance of state of charge (SOC) among multiple battery energy storage units (MBESUs) and bus voltage balance in an islanded bipolar DC microgrid. A SOC automatic balancing strategy is proposed considering the energy flow relationship and utilizing the adaptive virtual resistance algorithm. The simulation results demonstrate the effectiveness of the proposed strategy in achieving SOC balancing and decreasing bus voltage unbalance.
Article
Energy & Fuels
Raad Z. Homod, Basil Sh. Munahi, Hayder Ibrahim Mohammed, Musatafa Abbas Abbood Albadr, Aissa Abderrahmane, Jasim M. Mahdi, Mohamed Bechir Ben Hamida, Bilal Naji Alhasnawi, A. S. Albahri, Hussein Togun, Umar F. Alqsair, Zaher Mundher Yaseen
Summary: In this study, the control problem of the multiple-boiler system (MBS) is formulated as a dynamic Markov decision process and a deep clustering reinforcement learning approach is applied to obtain the optimal control policy. The proposed strategy, based on bang-bang action, shows superior response and achieves more than 32% energy saving compared to conventional fixed parameter controllers under dynamic indoor/outdoor actual conditions.