ZLZhu Licai

Zhu Licai

*This is an algorithmically generated author record based on publicly available information.

Zhu Licai has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An Artificial Intelligence-Enhanced Framework for Day-Ahead Market Bidding of Wind and Photovoltaic Systems With Demand Response in Virtual Power Plants Using Deep Long Short-Term Memory Forecasting

    by Yaser A. Nanehkaran, Tolga Pusatli, Amir Niromandfam, Behrouz Niroomandfam, Shixi Tang, Licai Zhu

    With growing concerns about the environment and the rising risks and costs associated with fossil fuels, today’s power systems are rapidly transitioning toward renewable energy sources. While subsidies and incentives often drove early adoption, renewable energy producers now face the challenge of competing in open electricity markets while ensuring profitability. This paper presents an AI-enhanced bidding strategy for a virtual power plant (VPP) that integrates wind and solar generation with demand response (DR) capabilities. At the core of the proposed hybrid approach is a Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and Long Short-Term Memory (LSTM) neural network that forecasts wind power output, PV generation, market prices, and demand profiles for the day-ahead horizon. These forecasts feed into a multi-objective optimization framework that strategically allocates DR resources and determines optimal market bids. Technically, this framework enhances grid reliability by minimizing Expected Energy Not Supplied (EENS), reducing active power losses, and lowering outage-related consumer costs. Commercially, the strategy enhances profitability by anticipating market conditions and minimizing imbalance settlement costs through optimal DR deployment. The method is validated on the IEEE 24-bus test system, demonstrating strong performance in both market outcomes and system reliability.


  • Open Access

    Azarshahr travertine compression strength prediction based on point-load index (Is) data using multilayer perceptron

    by Yimin Mao, Zhu Licai, Li Feng, Yaser A. Nanehkaran, Maosheng Zhang

    Azarshahr County in the northwest of Iran is predominantly covered by Azarshahr travertine, a prevailing sedimentary rock. This geological composition has led to extensive open-pit mining activities, particularly in the western and southwestern parts of the county. The rock's drillability and resistance to excavation play a pivotal role in determining its overall durability and hardness, crucial factors that influence the mining process. These attributes are intimately tied to the compressive strength of the rock. Accurate assessment of rock strength is vital for devising reliable excavation methodologies at mining sites. However, conventional approaches for analyzing rock strength have limitations that undermine the precision of strength estimations. In response, this study endeavors to leverage artificial intelligence techniques, specifically the Multilayer Perceptron (MLP), to enhance the prediction of travertine's compressive strength. To formulate a robust model, a comprehensive database containing data from 150 point-load index (Is) tests on Azarshahr travertine was compiled. This dataset serves as the foundation for the development of the MLP-based predictive model, which proves instrumental in projecting rock compressive strength. The model's accuracy and efficacy were rigorously assessed using the Receiver Operating Characteristic (ROC) curve, employing both training and testing datasets. The modeling outcomes reveal impressive results. The estimated R-squared coefficient attained an impressive value of 0.975 for axial strength and 0.975 for diametral strength. The overall accuracy, as indicated by the Area Under the Curve (AUC) metric, stands at an impressive 0.968. These exceptional performance metrics underscore the efficacy of the MLP model in accurately predicting compressive strength based on the point-load index of samples. The implications of this study are substantial. The predictive model, empowered by the MLP approach, has profound implications for excavation planning and drillability assessment within the studied region's travertine deposits. By facilitating accurate forecasts of rock strength, this model equips mining endeavors with valuable insights for effective planning and execution.


  • Open Access

    Diagnosis of Chronic Diseases Based on Patients’ Health Records in IoT Healthcare Using the Recommender System

    by Y. A. Nanehkaran, Zhu Licai, Junde Chen, Qiu Zhongpan, Yuan Xiaofeng, Yahya Dorostkar Navaei, Sajad Einy

    Due to the growth of IoT applications, especially health care, the information of patients’ health records using data collection from IoT‐connected devices has been considered. Biological data of patients in the health record helps to monitor the patient’s status and identify various diseases. Chronic diseases are a type of silent disease that, if not diagnosed in time, can cause irreparable damage to patients. The use of patients’ medical record data for early diagnosis of chronic diseases has recently attracted the attention of many researchers. On the other hand, the application of machine learning methods in the form of recommender systems has taken an important step in improving medical services and health care. In this paper, a medical recommender system was presented to identify and treat chronic diseases using an IoT device. In the present method, the electronic patient health record dataset that is loaded in the PhysioNet data repository has been used. In the present dataset, patients’ health records have been recorded according to the identified diseases and the physician’s diagnosis. In the proposed method, the K‐nearest neighbor classification method is used to identify the type of disease, and the collaborative filtering method is used to find the appropriate treatment for patients. The results of the implementation of the proposed method show that this approach, based on the use of symptom similarity among patients, has good accuracy in diagnosing and predicting chronic diseases and has provided higher results than previous methods.


  • Open Access

    Anomaly Detection in Heart Disease Using a Density‐Based Unsupervised Approach

    by Y. A. Nanehkaran, Zhu Licai, Junde Chen, Ahmed A. M. Jamel, Zhao Shengnan, Yahya Dorostkar Navaei, Mohsen Abdollahzadeh Aghbolagh

    Cardiovascular disease is one of the most common diseases in the modern world, which, if diagnosed early, can greatly reduce the damage to the patient. Diagnosis of heart disease requires great care, and in some cases, the process can be disrupted by human error. Machine learning methods, especially data mining, have gained international acceptance in almost all aspects of life, especially the prediction of heart disease. On the other hand, datasets related to heart patients have many biological features that most of these features do not have a direct impact on diagnosis. By removing redundant features from the dataset, in addition to reducing computational complexity, the accuracy of heart patients’ predictions can also be increased. This paper presents a density‐based unsupervised approach to the diagnosis of abnormalities in heart patients. In this method, the basic features in the dataset are first selected based on the filter‐based feature selection approach. Then, the DBSCAN clustering method with adaptive parameters has used to increase the clustering accuracy of healthy instances and to determine abnormal instances as cardiac patients. Partition clustering methods suffer from the selection of the number of clusters and the initial central points and are very sensitive to noise. The DBSCAN method solves these problems by creating density‐based clusters, but the selection of the neighborhood radius threshold and the number of connected points in the neighborhood remains unresolved. In the proposed method, these two parameters are selected adaptively to achieve the highest accuracy for the diagnosis and prediction of heart patients. The results of the experiments show that the accuracy of the proposed method for predicting heart patients is approximately 95%, which has improved in comparison with previous methods.


  • Open Access

    TagCare: Using RFIDs to Monitor the Status of the Elderly Living Alone

    by Licai Zhu, Ruchuan Wang, Zhongqin Wang, Hao Yang

    Falling is one of the major health threats to the independent living of elders, and falling has received much attention in academia and industry over the past two decades. Previous fall detection methods either require specialized hardware or invade people's daily lives. These limitations make it difficult to widely deploy fall detection systems in houses. On the other hand, a long static case is also one of the health threats to the elderly; these cases indicate that something is abnormal. In this paper, we present the design and implementation of a motion detection system based on passive radio frequency identification tags. The key finding is that static, regular action, and sudden falls make an impact on the RSS and Doppler frequency values differently. Such features help us to detect the status of the elderly. A wavelet transform is used to pre-process the signal data, and a support vector machine is adopted to improve the accuracy of the fall detection. We implemented a prototype monitoring system called TagCare and conducted extensive experiments to demonstrate the accuracy and efficiency of TagCare in movement detection and fall behavior identification for the elderly.