RESUMEN
The recent advances in artificial intelligence modern approaches can play vital roles in the Internet of Medical Things (IoMT). Automatic diagnosis is one of the most important topics in the IoMT, including cancer diagnosis. Breast cancer is one of the top causes of death among women. Accurate diagnosis and early detection of breast cancer can improve the survival rate of patients. Deep learning models have demonstrated outstanding potential in accurately detecting and diagnosing breast cancer. This paper proposes a novel technology for breast cancer detection using CrossViT as the deep learning model and an enhanced version of the Growth Optimizer algorithm (MGO) as the feature selection method. CrossVit is a hybrid deep learning model that combines the strengths of both convolutional neural networks (CNNs) and transformers. The MGO is a meta-heuristic algorithm that selects the most relevant features from a large pool of features to enhance the performance of the model. The developed approach was evaluated on three publicly available breast cancer datasets and achieved competitive performance compared to other state-of-the-art methods. The results show that the combination of CrossViT and the MGO can effectively identify the most informative features for breast cancer detection, potentially assisting clinicians in making accurate diagnoses and improving patient outcomes. The MGO algorithm improves accuracy by approximately 1.59% on INbreast, 5.00% on MIAS, and 0.79% on MiniDDSM compared to other methods on each respective dataset. The developed approach can also be utilized to improve the Quality of Service (QoS) in the healthcare system as a deployable IoT-based intelligent solution or a decision-making assistance service, enhancing the efficiency and precision of the diagnosis.
Asunto(s)
Algoritmos , Neoplasias de la Mama , Humanos , Neoplasias de la Mama/diagnóstico , Femenino , Aprendizaje Profundo , Redes Neurales de la Computación , Internet de las CosasRESUMEN
Due to the vast variety of aspects that must be made-many of which are in opposition to one another-choosing a home can be difficult for those without much experience. Individuals need to spend more time making decisions because they are difficult, which results in making poor choices. To overcome residence selection issues, a computational approach is necessary. Unaccustomed people can use decision support systems to help them make decisions of expert quality. The current article explains the empirical procedure in that field in order to construct decision-support system for selecting a residence. The main goal of this study is to build a weighted product mechanism-based decision-support system for residential preference. The said house short-listing estimation is based on several key requirements derived from the interaction between the researchers and experts. The results of the information processing show that the normalized product strategy can rank the available alternatives to help individuals choose the best option. The interval valued fuzzy hypersoft set (IVFHS-set) is a broader variant of the fuzzy soft set that resolves the constraints of the fuzzy soft set from the perspective of the utilization of the multi-argument approximation operator. This operator maps sub-parametric tuples into a power set of universe. It emphasizes the segmentation of every attribute into a disjoint attribute valued set. These characteristics make it a whole new mathematical tool for handling problems involving uncertainties. This makes the decision-making process more effective and efficient. Furthermore, the traditional TOPSIS technique as a multi-criteria decision-making strategy is discussed in a concise manner. A new decision-making strategy, "OOPCS" is constructed with modifications in TOPSIS for fuzzy hypersoft set in interval settings. The proposed strategy is applied to a real-world multi-criteria decision-making scenario for ranking the alternatives to check and demonstrate their efficiency and effectiveness.
RESUMEN
Intrusion detection systems (IDS) play a crucial role in securing networks and identifying malicious activity. This is a critical problem in cyber security. In recent years, metaheuristic optimization algorithms and deep learning techniques have been applied to IDS to improve their accuracy and efficiency. Generally, optimization algorithms can be used to boost the performance of IDS models. Deep learning methods, such as convolutional neural networks, have also been used to improve the ability of IDS to detect and classify intrusions. In this paper, we propose a new IDS model based on the combination of deep learning and optimization methods. First, a feature extraction method based on CNNs is developed. Then, a new feature selection method is used based on a modified version of Growth Optimizer (GO), called MGO. We use the Whale Optimization Algorithm (WOA) to boost the search process of the GO. Extensive evaluation and comparisons have been conducted to assess the quality of the suggested method using public datasets of cloud and Internet of Things (IoT) environments. The applied techniques have shown promising results in identifying previously unknown attacks with high accuracy rates. The MGO performed better than several previous methods in all experimental comparisons.
RESUMEN
Feature selection techniques are considered one of the most important preprocessing steps, which has the most significant influence on the performance of data analysis and decision making. These FS techniques aim to achieve several objectives (such as reducing classification error and minimizing the number of features) at the same time to increase the classification rate. FS based on Metaheuristic (MH) is considered one of the most promising techniques to improve the classification process. This paper presents a modified method of the Slime mould algorithm depending on the Marine Predators Algorithm (MPA) operators as a local search strategy, which leads to increasing the convergence rate of the developed method, named SMAMPA and avoiding the attraction to local optima. The efficiency of SMAMPA is evaluated using twenty datasets and compared its results with the state-of-the-art FS methods. In addition, the applicability of SMAMPA to work with real-world problems is evaluated by using it as a quantitative structure-activity relationship (QSAR) model. The obtained results show the high ability of the developed SMAMPA method to reduce the dimension of the tested datasets by increasing the prediction rate. In addition, it provides results better than other FS techniques in terms of performance metrics.
RESUMEN
A sustainable environment by decreasing fossil fuel utilization and anthropogenic greenhouse gases is a globally main goal due to climate change and serious air pollution. Carbon dioxide (CO2) is a heat-trapping (greenhouse) that is released into the earth's atmosphere from natural processes, such as volcanic respiration and eruptions, as well as human activities, such as burning fossil fuels and deforestation. Due to this fact, underground carbon storage (UCS) is a promising technology to cut carbon emissions. However, there are some barriers to prevent UCS from applying globally. One of them is evaluating the feasibility of storage projects. Thus, the prediction accuracy of CO2 storage efficiencies may promote the attention of the community for UCS. In this study, we utilize the recent advances of swarm intelligence to develop a hybrid algorithm called AOSMA, employed to train the long short-term memory (LSTM). The developed swarm intelligence method (AOSMA) is an enhanced Aquila optimizer (AO) using the search mechanism of the slime mould algorithm (SMA). It is used to boost the prediction capability of the LSTM by optimizing its parameters. We considered two CO2 trapping indices, called residual trapping index (RTI) and solubility trapping index (STI). The evaluation experiments have shown that the AOSMA achieved significant results compared to the original AO and SMA and several swarm intelligence and optimization algorithms. The developed smart tools could use as a game changer to provide fast and accurate storage efficiency for projects that have similar parameters falling within the range of the database.
Asunto(s)
Contaminación del Aire , Agua Subterránea , Humanos , Dióxido de Carbono/análisis , Memoria a Corto Plazo , Contaminación del Aire/prevención & control , Combustibles FósilesRESUMEN
Recently, the unmanned aerial vehicles (UAV) under the umbrella of the Internet of Things (IoT) in smart cities and emerging communities have become the focus of the academic and industrial science community. On this basis, UAVs have been used in many military and commercial systems as emergency transport and air support during natural disasters and epidemics. In such previous scenarios, boosting wireless signals in remote or isolated areas would need a mobile signal booster placed on UAVs, and, at the same time, the data would be secured by a secure decentralized database. This paper contributes to investigating the possibility of using a wireless repeater placed on a UAV as a mobile booster for weak wireless signals in isolated or rural areas in emergency situations and that the transmitted information is protected from external interference and manipulation. The working mechanism is as follows: one of the UAVs detect a human presence in a predetermined area with the thermal camera and then directs the UAVs to the location to enhance the weak signal and protect the transmitted data. The methodology of localization and clusterization of the UAVs is represented by a swarm intelligence localization (SIL) optimization algorithm. At the same time, the information sent by UAV is protected by blockchain technology as a decentralization database. According to realistic studies and analyses of UAVs localization and clusterization, the proposed idea can improve the amplitude of the wireless signals in far regions. In comparison, this database technique is difficult to attack. The research ultimately supports emergency transport networks, blockchain, and IoT services.
RESUMEN
The forecasting and prediction of crude oil are necessary in enabling governments to compile their economic plans. Artificial neural networks (ANN) have been widely used in different forecasting and prediction applications, including in the oil industry. The dendritic neural regression (DNR) model is an ANNs that has showed promising performance in time-series prediction. The DNR has the capability to deal with the nonlinear characteristics of historical data for time-series forecasting applications. However, it faces certain limitations in training and configuring its parameters. To this end, we utilized the power of metaheuristic optimization algorithms to boost the training process and optimize its parameters. A comprehensive evaluation is presented in this study with six MH optimization algorithms used for this purpose: whale optimization algorithm (WOA), particle swarm optimization algorithm (PSO), genetic algorithm (GA), sine-cosine algorithm (SCA), differential evolution (DE), and harmony search algorithm (HS). We used oil-production datasets for historical records of crude oil production from seven real-world oilfields (from Tahe oilfields, in China), provided by a local partner. Extensive evaluation experiments were carried out using several performance measures to study the validity of the DNR with MH optimization methods in time-series applications. The findings of this study have confirmed the applicability of MH with DNR. The applications of MH methods improved the performance of the original DNR. We also concluded that the PSO and WOA achieved the best performance compared with other methods.
RESUMEN
In this paper, we study the applications of metaheuristics (MH) optimization algorithms in human activity recognition (HAR) and fall detection based on sensor data. It is known that MH algorithms have been utilized in complex engineering and optimization problems, including feature selection (FS). Thus, in this regard, this paper used nine MH algorithms as FS methods to boost the classification accuracy of the HAR and fall detection applications. The applied MH were the Aquila optimizer (AO), arithmetic optimization algorithm (AOA), marine predators algorithm (MPA), artificial bee colony (ABC) algorithm, genetic algorithm (GA), slime mold algorithm (SMA), grey wolf optimizer (GWO), whale optimization algorithm (WOA), and particle swarm optimization algorithm (PSO). First, we applied efficient prepossessing and segmentation methods to reveal the motion patterns and reduce the time complexities. Second, we developed a light feature extraction technique using advanced deep learning approaches. The developed model was ResRNN and was composed of several building blocks from deep learning networks including convolution neural networks (CNN), residual networks, and bidirectional recurrent neural networks (BiRNN). Third, we applied the mentioned MH algorithms to select the optimal features and boost classification accuracy. Finally, the support vector machine and random forest classifiers were employed to classify each activity in the case of multi-classification and to detect fall and non-fall actions in the case of binary classification. We used seven different and complex datasets for the multi-classification case: the PAMMP2, Sis-Fall, UniMiB SHAR, OPPORTUNITY, WISDM, UCI-HAR, and KU-HAR datasets. In addition, we used the Sis-Fall dataset for the binary classification (fall detection). We compared the results of the nine MH optimization methods using different performance indicators. We concluded that MH optimization algorithms had promising performance in HAR and fall detection applications.
Asunto(s)
Accidentes por Caídas , Dispositivos Electrónicos Vestibles , Humanos , Redes Neurales de la Computación , Algoritmos , Actividades HumanasRESUMEN
Effective prioritization plays critical roles in precision medicine. Healthcare decisions are complex, involving trade-offs among numerous frequently contradictory priorities. Considering the numerous difficulties associated with COVID-19, approaches that could triage COVID-19 patients may help in prioritizing treatment and provide precise medicine for those who are at risk of serious disease. Prioritizing a patient with COVID-19 depends on a variety of examination criteria, but due to the large number of these biomarkers, it may be hard for medical practitioners and emergency systems to decide which cases should be given priority for treatment. The aim of this paper is to propose a Multidimensional Examination Framework (MEF) for the prioritization of COVID-19 severe patients on the basis of combined multi-criteria decision-making (MCDM) methods. In contrast to the existing literature, the MEF has not considered only a single dimension of the examination factors; instead, the proposed framework included different multidimensional examination criteria such as demographic, laboratory findings, vital signs, symptoms, and chronic conditions. A real dataset that consists of data from 78 patients with different examination criteria was used as a base in the construction of Multidimensional Evaluation Matrix (MEM). The proposed framework employs the CRITIC (CRiteria Importance Through Intercriteria Correlation) method to identify objective weights and importance for multidimensional examination criteria. Furthermore, the VIKOR (VIekriterijumsko KOmpromisno Rangiranje) method is utilized to prioritize COVID-19 severe patients. The results based on the CRITIC method showed that the most important examination criterion for prioritization is COVID-19 patients with heart disease, followed by cough and nasal congestion symptoms. Moreover, the VIKOR method showed that Patients 8, 3, 9, 59, and 1 are the most urgent cases that required the highest priority among the other 78 patients. Finally, the proposed framework can be used by medical organizations to prioritize the most critical COVID-19 patient that has multidimensional examination criteria and to promptly give appropriate care for more precise medicine.
RESUMEN
Nowadays, the emerging information technologies in smart handheld devices are motivating the research community to make use of embedded sensors in such devices for healthcare purposes. In particular, inertial measurement sensors such as accelerometers and gyroscopes embedded in smartphones and smartwatches can provide sensory data fusion for human activities and gestures. Thus, the concepts of the Internet of Healthcare Things (IoHT) paradigm can be applied to handle such sensory data and maximize the benefits of collecting and analyzing them. The application areas contain but are not restricted to the rehabilitation of elderly people, fall detection, smoking control, sportive exercises, and monitoring of daily life activities. In this work, a public dataset collected using two smartphones (in pocket and wrist positions) is considered for IoHT applications. Three-dimensional inertia signals of thirteen timestamped human activities such as Walking, Walking Upstairs, Walking Downstairs, Writing, Smoking, and others are registered. Here, an efficient human activity recognition (HAR) model is presented based on efficient handcrafted features and Random Forest as a classifier. Simulation results ensure the superiority of the applied model over others introduced in the literature for the same dataset. Moreover, different approaches to evaluating such models are considered, as well as implementation issues. The accuracy of the current model reaches 98.7% on average. The current model performance is also verified using the WISDM v1 dataset.
RESUMEN
The development of smart network infrastructure of the Internet of Things (IoT) faces the immense threat of sophisticated Distributed Denial-of-Services (DDoS) security attacks. The existing network security solutions of enterprise networks are significantly expensive and unscalable for IoT. The integration of recently developed Software Defined Networking (SDN) reduces a significant amount of computational overhead for IoT network devices and enables additional security measurements. At the prelude stage of SDN-enabled IoT network infrastructure, the sampling based security approach currently results in low accuracy and low DDoS attack detection. In this paper, we propose an Adaptive Machine Learning based SDN-enabled Distributed Denial-of-Services attacks Detection and Mitigation (AMLSDM) framework. The proposed AMLSDM framework develops an SDN-enabled security mechanism for IoT devices with the support of an adaptive machine learning classification model to achieve the successful detection and mitigation of DDoS attacks. The proposed framework utilizes machine learning algorithms in an adaptive multilayered feed-forwarding scheme to successfully detect the DDoS attacks by examining the static features of the inspected network traffic. In the proposed adaptive multilayered feed-forwarding framework, the first layer utilizes Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), k-Nearest Neighbor (kNN), and Logistic Regression (LR) classifiers to build a model for detecting DDoS attacks from the training and testing environment-specific datasets. The output of the first layer passes to an Ensemble Voting (EV) algorithm, which accumulates the performance of the first layer classifiers. In the third layer, the adaptive frameworks measures the real-time live network traffic to detect the DDoS attacks in the network traffic. The proposed framework utilizes a remote SDN controller to mitigate the detected DDoS attacks over Open Flow (OF) switches and reconfigures the network resources for legitimate network hosts. The experimental results show the better performance of the proposed framework as compared to existing state-of-the art solutions in terms of higher accuracy of DDoS detection and low false alarm rate.
RESUMEN
Oil production forecasting is an important task to manage petroleum reservoirs operations. In this study, a developed time series forecasting model is proposed for oil production using a new improved version of the adaptive neuro-fuzzy inference system (ANFIS). This model is improved by using an optimization algorithm, the slime mould algorithm (SMA). The SMA is a new algorithm that is applied for solving different optimization tasks. However, its search mechanism suffers from some limitations, for example, trapping at local optima. Thus, we modify the SMA using an intelligence search technique called opposition-based learning (OLB). The developed model, ANFIS-SMAOLB, is evaluated with different real-world oil production data collected from two oilfields in two different countries, Masila oilfield (Yemen) and Tahe oilfield (China). Furthermore, the evaluation of this model is considered with extensive comparisons to several methods, using several evaluation measures. The outcomes assessed the high ability of the developed ANFIS-SMAOLB as an efficient time series forecasting model that showed significant performance.
RESUMEN
This study proposes a novel framework to improve intrusion detection system (IDS) performance based on the data collected from the Internet of things (IoT) environments. The developed framework relies on deep learning and metaheuristic (MH) optimization algorithms to perform feature extraction and selection. A simple yet effective convolutional neural network (CNN) is implemented as the core feature extractor of the framework to learn better and more relevant representations of the input data in a lower-dimensional space. A new feature selection mechanism is proposed based on a recently developed MH method, called Reptile Search Algorithm (RSA), which is inspired by the hunting behaviors of the crocodiles. The RSA boosts the IDS system performance by selecting only the most important features (an optimal subset of features) from the extracted features using the CNN model. Several datasets, including KDDCup-99, NSL-KDD, CICIDS-2017, and BoT-IoT, were used to assess the IDS system performance. The proposed framework achieved competitive performance in classification metrics compared to other well-known optimization methods applied for feature selection problems.
Asunto(s)
Aprendizaje Profundo , Internet de las Cosas , Animales , Reptiles , Algoritmos , Redes Neurales de la ComputaciónRESUMEN
With the widespread use of intelligent information systems, a massive amount of data with lots of irrelevant, noisy, and redundant features are collected; moreover, many features should be handled. Therefore, introducing an efficient feature selection (FS) approach becomes a challenging aim. In the recent decade, various artificial methods and swarm models inspired by biological and social systems have been proposed to solve different problems, including FS. Thus, in this paper, an innovative approach is proposed based on a hybrid integration between two intelligent algorithms, Electric fish optimization (EFO) and the arithmetic optimization algorithm (AOA), to boost the exploration stage of EFO to process the high dimensional FS problems with a remarkable convergence speed. The proposed EFOAOA is examined with eighteen datasets for different real-life applications. The EFOAOA results are compared with a set of recent state-of-the-art optimizers using a set of statistical metrics and the Friedman test. The comparisons show the positive impact of integrating the AOA operator in the EFO, as the proposed EFOAOA can identify the most important features with high accuracy and efficiency. Compared to the other FS methods whereas, it got the lowest features number and the highest accuracy in 50% and 67% of the datasets, respectively.
RESUMEN
Human activity recognition (HAR) plays a vital role in different real-world applications such as in tracking elderly activities for elderly care services, in assisted living environments, smart home interactions, healthcare monitoring applications, electronic games, and various human-computer interaction (HCI) applications, and is an essential part of the Internet of Healthcare Things (IoHT) services. However, the high dimensionality of the collected data from these applications has the largest influence on the quality of the HAR model. Therefore, in this paper, we propose an efficient HAR system using a lightweight feature selection (FS) method to enhance the HAR classification process. The developed FS method, called GBOGWO, aims to improve the performance of the Gradient-based optimizer (GBO) algorithm by using the operators of the grey wolf optimizer (GWO). First, GBOGWO is used to select the appropriate features; then, the support vector machine (SVM) is used to classify the activities. To assess the performance of GBOGWO, extensive experiments using well-known UCI-HAR and WISDM datasets were conducted. Overall outcomes show that GBOGWO improved the classification accuracy with an average accuracy of 98%.
RESUMEN
Classification of COVID-19 X-ray images to determine the patient's health condition is a critical issue these days since X-ray images provide more information about the patient's lung status. To determine the COVID-19 case from other normal and abnormal cases, this work proposes an alternative method that extracted the informative features from X-ray images, leveraging on a new feature selection method to determine the relevant features. As such, an enhanced cuckoo search optimization algorithm (CS) is proposed using fractional-order calculus (FO) and four different heavy-tailed distributions in place of the Lévy flight to strengthen the algorithm performance during dealing with COVID-19 multi-class classification optimization task. The classification process includes three classes, called normal patients, COVID-19 infected patients, and pneumonia patients. The distributions used are Mittag-Leffler distribution, Cauchy distribution, Pareto distribution, and Weibull distribution. The proposed FO-CS variants have been validated with eighteen UCI data-sets as the first series of experiments. For the second series of experiments, two data-sets for COVID-19 X-ray images are considered. The proposed approach results have been compared with well-regarded optimization algorithms. The outcomes assess the superiority of the proposed approach for providing accurate results for UCI and COVID-19 data-sets with remarkable improvements in the convergence curves, especially with applying Weibull distribution instead of Lévy flight.
RESUMEN
Developing cyber security is very necessary and has attracted considerable attention from academy and industry organizations worldwide. It is also very necessary to provide sustainable computing for the the Internet of Things (IoT). Machine learning techniques play a vital role in the cybersecurity of the IoT for intrusion detection and malicious identification. Thus, in this study, we develop new feature extraction and selection methods and for the IDS system using the advantages of the swarm intelligence (SI) algorithms. We design a feature extraction mechanism depending on the conventional neural networks (CNN). After that, we present an alternative feature selection (FS) approach using the recently developed SI algorithm, Aquila optimizer (AQU). Moreover, to assess the quality of the developed IDS approach, four well-known public datasets, CIC2017, NSL-KDD, BoT-IoT, and KDD99, were used. We also considered extensive comparisons to other optimization methods to verify the competitive performance of the developed method. The results show the high performance of the developed approach using different evaluation indicators.
Asunto(s)
Aprendizaje Profundo , Águilas , Internet de las Cosas , Animales , Seguridad Computacional , Redes Neurales de la ComputaciónRESUMEN
In this study, we propose an improved version of the adaptive neuro-fuzzy inference system (ANFIS) for forecasting the air quality index in Wuhan City, China. We propose a hybrid optimization method to improve ANFIS performance, called PSOSMA, using a new modified meta-heuristics (MH) algorithm, Slime mould algorithm (SMA), which is improved by using the particle swarm optimizer (PSO). The proposed PSOSMA-ANFIS has been trained with air quality index time series data of three years and has been applied to forecast the fine particulate matter (PM2.5), sulfur dioxide (SO2), carbon dioxide (CO2), and nitrogen dioxide (NO2) for one year. We also compared the proposed PSOSMA to other MH algorithms used to train ANFIS. We found that the modified ANFIS using PSOSMA achieved better performance than compared algorithms. Moreover, we analyzed the impacts of the lockdown of Wuhan City on the concentrations of PM2.5, NO2, CO2, and SO2. We compared the correspondence period with previous years, and we concluded that there are significant decreases in the concentrations of PM2.5, CO2, SO2, and NO2.
Asunto(s)
Contaminación del Aire , COVID-19 , Contaminación del Aire/análisis , China , Ciudades , Control de Enfermedades Transmisibles , Humanos , Material Particulado/análisis , SARS-CoV-2RESUMEN
COVID-19 is a new member of the Coronaviridae family that has serious effects on respiratory, gastrointestinal, and neurological systems. COVID-19 spreads quickly worldwide and affects more than 41.5 million persons (till 23 October 2020). It has a high hazard to the safety and health of people all over the world. COVID-19 has been declared as a global pandemic by the World Health Organization (WHO). Therefore, strict special policies and plans should be made to face this pandemic. Forecasting COVID-19 cases in hotspot regions is a critical issue, as it helps the policymakers to develop their future plans. In this paper, we propose a new short term forecasting model using an enhanced version of the adaptive neuro-fuzzy inference system (ANFIS). An improved marine predators algorithm (MPA), called chaotic MPA (CMPA), is applied to enhance the ANFIS and to avoid its shortcomings. More so, we compared the proposed CMPA with three artificial intelligence-based models include the original ANFIS, and two modified versions of ANFIS model using both of the original marine predators algorithm (MPA) and particle swarm optimization (PSO). The forecasting accuracy of the models was compared using different statistical assessment criteria. CMPA significantly outperformed all other investigated models.
RESUMEN
Over the past few decades, air pollution has caused serious damage to public health. Therefore, making accurate predictions of PM2.5 is a crucial task. Due to the transportation of air pollutants among areas, the PM2.5 concentration is strongly spatiotemporal correlated. However, the distribution of air pollution monitoring sites is not even making the spatiotemporal correlation between the central site and surrounding sites vary with different density of sites, and this was neglected by previous methods. To this end, this study proposes a weighted long short-term memory neural network extended model (WLSTME), which addressed the issue that how to consider the effect of the density of sites and wind conditions on the spatiotemporal correlation of air pollution concentration. First, a number of nearest surrounding sites were chosen as the neighbor sites to the central site, and their distance, as well as their air pollution concentration and wind condition, were input to multilayer perception (MLP) to generate weighted historical PM2.5 time series data. Second, historical PM2.5 concentration of the central site and weighted PM2.5 series data of neighbor sites were input into a long short-term memory (LSTM) to address spatiotemporal dependency simultaneously and extract spatiotemporal features. Finally, another MLP was utilized to integrate spatiotemporal features extracted above with the meteorological data of the central site to generate the forecasts future PM2.5 concentration of the central site. Daily PM2.5 concentration and meteorological data on Beijing-Tianjin-Hebei from 2015 to 2017 were collected to train models and to evaluate its performance. Experimental results with three existing methods showed that the proposed WLSTME model has the lowest RMSE (40.67) and MAE (26.10) and the highest p (0.59). Further experiments showed that in all seasons and regions, WLSTME performed the best. This finding confirms that WLSTME can significantly improve PM2.5 prediction accuracy.