Privacy boundary determination of smart meter data using an artificial intelligence adversary

Air quality index forecast in Beijing based on CNN-LSTM multi-model

Considerable attention has recently been focused on classification and regression-based convolutional neural network (CNN) and long short-term memory (LSTM) due to their excellent performance in capturing complex spatial and temporal information characteristics for structural damage identification. However, few studies have considered structural damage identification as a classification and regression problem. In addition, bridges in practical engineering are vulnerable to various environmental and vehicle loading conditions. Hence, this study proposed a new two-stage CNN–LSTM configuration for bridge damage identification using vibration data considering the influence of temperatures. First, a classification-based CNN–LSTM is designed to perform multiclass damage detection tasks, and then a regression-based CNN–LSTM is developed for damage localization and severity prediction tasks. The performance of the proposed damage identification method was evaluated through a simulation dataset of a concrete highway bridge model and a field experiment dataset of Z24-bridge (Switzerland). In addition, a set of statistical evaluation metrics such as sparse categorical cross-entropy loss, accuracy, confusion matrix, mean squared loss, mean absolute error, mean absolute percentage error, and coefficient of determination were used to compare the damage identification performance of the proposed CNN–LSTM configuration with a regular CNN model and conventional machine learning (ML) algorithms. Prediction results indicate that the proposed CNN–LSTM model outperforms the regular CNN model and conventional ML algorithms for bridge damage identification.

Advanced smart meters generate meter readings in a time unit less than a second. Fine-grained meter readings enable various smart grid applications, such as load monitoring, automatic billing, and power generation planning. However, those meter readings threaten individuals' privacy by revealing details of one's daily activities. The time granularity of smart meters is often much finer than the one a smart grid application demands. Thus, the storage and access control mechanisms of meter readings are critical to balancing privacy requirements and application functionalities. Previous studies address the issue by considering a locally trusted storage device and using cryptographic primitives. We consider a storage outsourcing scenario, where the external storage environment is semi-trusted. We construct a privacy preserving metering system by using a trusted platform module in a smart meter and pseudorandom number generators inside the module. Our system guarantees the secure storage of meter readings and supports multiple time granularities. In our system, a user grants a service provider an access right over meter readings at a time granularity S. The granted service provider is only allowed to get the power consumption at a time unit of the granted time granularity. Our system provides a simple yet very practical solution to the privacy preserving smart metering system. Moreover, we provide a privacy model to capture the privacy requirement and show that our system is privacy preserving against honest-but-curious service providers.

Online leakage current classification using convolutional neural network long short-term memory for high voltage insulators on web-based service

The prevalence of extreme weather events gives rise to a significant degree of prediction bias in the forecasting of photovoltaic (PV) power. In order to enhance the precision of forecasting outcomes, this study examines the interrelationships between China’s 24 conventional solar terms and extreme meteorological events. Additionally, it proposes a methodology for estimating the short-term generation of PV power based on the division of solar term time series. Firstly, given that the meteorological data from the same festival is more representative of the climate state at the current prediction moment, the sample data are grouped according to the 24 festival time nodes. Secondly, a convolutional neural network–long short-term memory (CNN-LSTM) PV power prediction model based on an Attention mechanism is proposed. This model extracts temporal change information from nonlinear sample data through LSTM, and a CNN link is added at the front end of LSTM to address the issue of LSTM being unable to obtain the spatial linkage of multiple features. Additionally, an Attention mechanism is incorporated at the back end of the CNN to obtain the feature information of crucial time steps, further reducing the multi-step prediction error. Concurrently, a PV power error prediction model is constructed to rectify the outcomes of the aforementioned prediction model. The examination of the measured data from PV power stations and the comparison and analysis with other prediction models demonstrate that the model presented in this paper can effectively enhance the accuracy of PV power predictions.

In this study, a multi-channel Electroencephalogram (EEG) mental fatigue detection algorithm is proposed based on the Convolutional Neural Network- Long Short-Term Memory (CNN-LSTM) network. The CNN-LSTM deep network model is used to distinguish three different mental fatigue states: awake, mild fatigue and severe fatigue. The model is validated on a self-collected dataset collected by the 2-BACK experimental paradigm. The data set contains fatigue data for a total of 10 healthy adults without adverse habits. The average recognition accuracy of the model is 97.12%. The model yields a sensitivity of 97.80% and a specificity of 99.28%. Results show that our proposed CNN-LSTM model can distinguish the three different mental fatigue states effectively.

This paper proposes the prediction model of wind speed and direction using convolutional neural network - long short-term memory (CNN-LSTM). The proposed prediction model combines CNN, LSTM, and fully connected neural networks (FCNN) which are useful for getting high prediction accuracy of wind speed and direction for wind power. Performances of the prediction models are evaluated by using root mean square error (RMSE) between actual measurement data and predicted data. To verify the effectiveness of the proposed prediction model in comparison with that using FCNN, CNN, or LSTM model. The usefulness of the proposed prediction model is evaluated from the improvement of prediction accuracy for each season. The proposed prediction model using CNN-LSTM can improve 27.95 - 42.16% for wind speed and 28.71 - 35.15% for wind direction depending on the season in comparison with using the FCNN that is a higher accuracy than CNN and LSTM models, and also it indicates the strongest prediction model.

In recent years, domain generation algorithms (DGAs) are the foundational mechanisms for many malware families. Mainly, due to the fact that DGA can generate immense number of pseudo random domain names to associate to a command and control (C2) infrastructures. This paper focuses on to detect and classify the pseudo random domain names without relying on the feature engineering or any other linguistic, contextual or semantics and statistical information by adopting deep learning approaches. A deep learning approach is a complex model of traditional machine learning mechanism that has received renewed interest by solving the long-standing tasks in artificial intelligence (AI) related to the field of natural language processing, image recognition, speech processing and many others. They have immense capability to extract optimal feature representations by taking input as in the form of raw input texts. To leverage this and to transfer the performance enhancement in aforementioned areas towards characterize, detect and classify the DGA generated domain names to a specific malware family, this paper adopts deep learning mechanisms with a known one million benign domain names from Alexa, OpenDNS and a corpus of malicious domain names generated from 17 DGA malware families in real time for training in character and bigram level and a trained model has been evaluated on the OSNIT data set in real-time. Specifically, to understand the effectiveness of various deep learning mechanisms, we used recurrent neural network (RNN), identity-recurrent neural network (I-RNN), long short-term memory (LSTM), convolution neural network (CNN), and convolutional neural network-long short-term memory (CNN-LSTM) architectures. Additionally, to find out an optimal architecture, experiments are done with various configurations of network parameters and network structures. All experiments run up to 1000 epochs with a learning rate set in the range [0.01-0.5]. Overall, deep learning approaches, particularly family of recurrent neural network and a hybrid network (where the first layer is CNN and a subsequent layer is LSTM) have showed significant performance with a highest detection rate 0.9945 and 0.9879 respectively. The main reason is deep learning approaches have inherent mechanisms to capture hierarchical feature extraction and long range-dependencies in sequence inputs.

COVID-19 pandemic has indeed plunged the global community especially African countries into an alarming difficult situationculminating into a great deal amounts of catastrophes such as economic recession, political instability and loss of jobs. Thepandemic spreads exponentially and causes loss of lives. Following the outbreak of the omicron new variant of concern,forecasting and identification of the COVID-19 infection cases is very vital for government at various levels. Hence, havingknowledge of the spread at a particular point in time, swift actions can be taken by government at various levels with a view toaccordingly formulate new policies and modalities towards minimizing the trajectory of the consequences of COVID-19 pandemicto both public health and economic sectors. Here, a potent combination of Convolutional Neural Network (CNN) learning algorithm along with Long Short Term Memory(LSTM) learning algorithm has been proposed in this work in order to produce a hybrid of a deep learning algorithm ConvolutionalNeural Network - Long Short Term Memory (CNN-LSTM) for forecasting COVID-19 infection cases particularly in Nigeria, SouthAfrica and Botswana. Forecasting models for COVID-19 infection cases in Nigeria, South Africa and Botswana, were developedfor 10 days using deep learning-based approaches namely CNN, LSTM and CNN-LSTM deep learning algorithm respectively. The models were evaluated on the basis of four standard performance evaluation metrics which include accuracy, MSE, MAEand RMSE respectively. However, the CNN-LSTM deep learning-based forecasting model achieved the best accuracy of98.30%, 97.60%, and 97.74% for Nigeria, South Africa and Botswana respectively; and in the same manner, achieved lesserMSE, MAE and RMSE values compared to models developed with CNN and LSTM respectively. Taken together, the CNN-LSTM deep learning-based forecasting model for COVID-19 infection cases in Nigeria, South Africaand Botswana dramatically surpasses the two other DL based forecasting models (CNN and LSTM) for COVID-19 infectioncases in Nigeria, South Africa and Botswana in terms of not only the best accuracy of with 98.30%, 97.60%, and 97.74% but alsoin terms of lesser MSE, MAE and RMSE.

This paper presents deep learning models—specifically, Long Short-Term Memory (LSTM) networks and hybrid Convolutional Neural Network–LSTM (CNN-LSTM) with a Copula-Based Random Forest (CBRF) model to estimate Heterogeneous Treatment Effects (HTEs) in survival analysis. The proposed method is designed to capture non-linear relationships and temporal dependencies in clinical and genomic data, with a particular focus on exploring how treatment effects vary by race as a moderating factor. Using breast cancer data from the TCGA-BRCA dataset, which includes both clinical variables and gene expression profiles, we filter the data to focus on two racial groups: Black or African American and White. Dimensionality reduction is performed using Principal Component Analysis (PCA). We compare the CNN-LSTM, LSTM, and CBRF models under three weighting strategies—no weights, Horvitz–Thompson (HT) weights, and Inverse Probability of Treatment Weighting (IPTW)—for predicting treatment effects. Model performance is evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Concordance statistic (C-statistic), Average Treatment Effect (ATE), and Conditional Average Treatment Effect (CATE) by race. The CNN-LSTM model consistently outperforms the others, achieving the lowest prediction errors and highest discrimination, particularly under IPTW. Among the weighting strategies, IPTW yields the most substantial improvements in model performance and bias reduction. Importantly, race-specific treatment effects exhibit notable variation: CNN-LSTM estimates a slightly higher CATE for Black individuals under IPTW. Overall, CNN-LSTM with IPTW is recommended for robust and equitable causal inference, especially in racially stratified settings.

Heterogeneous data have become a key issue restricting the monitoring accuracy of volcanic ash cloud and rapid application of remote sensing. In view of the characteristics of classification and heterogeneous data in volcanic ash cloud monitoring, a monitoring method of volcanic ash cloud using feature fusion, convolutional neural networks (CNN) and long short-term memory (LSTM) (FF–CNN–LSTM) is presented in this paper. In this method, firstly, the target features in image are identified by CNN and the time sequence information in text is extracted by LSTM. Secondly, the mapping relationship between text information and image features is learned by fusing image target and text high-level features, and then the identification and diffusion of volcanic ash cloud from heterogeneous data containing only image and text were performed. Finally, the presented FF–CNN–LSTM method is tested by the simulation experiment and the true heterogeneous data of Enta volcanic ash cloud case. The experimental results show that compared with the single CNN, LSTM and the simple combination between CNN and LSTM (CNN–LSTM), the presented FF–CNN–LSTM method in this paper can be fitted with less training steps and has high accuracy and low loss rate; the obtained distribution of volcanic ash cloud is clear and intuitive and has the characteristics with fewer model parameters, simple calculation and high accuracy. It also shows the feasibility and effectiveness of the presented method in volcanic ash cloud monitoring to some extent. The results reveal that the presented method can potentially contribute the monitoring of volcanic ash cloud and disaster prevention and mitigation.

A common endocrine condition, thyroid dysfunction can lead to major side effects like obesity, infertility, cardiovascular disease, and cognitive decline if left untreated. Traditional diagnostic methods use biochemical assays, which are time-consuming, expensive, and invasive despite their accuracy. This paper suggests a completely automated, non-invasive screening framework that uses human voice acoustics as a thyroid dysfunction biomarker in order to overcome these difficulties. Subjects with both normal and abnormal thyroid conditions had their voice recordings taken, and they were pre-processed using spectral analysis, noise reduction, framing, and the feature extraction of Mel-Frequency Cepstral Coefficients (MFCCs). In order to capture both long-term temporal dependencies and local spectral structures in the vocal signal, a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model was created. While LSTM layers modeled temporal variations associated with vocal fold vibrations influenced by thyroid abnormalities, CNN layers extracted hierarchical representations from spectral features. Experiments showed that the CNN-LSTM architecture outperformed conventional classifiers like Support Vector Machines (SVM), Random Forests (RF), and K-Nearest Neighbors (KNN) by achieving an overall classification accuracy of over 98%. The results show how voice can be a trustworthy, non-invasive biomarker and how deep learning models can be used to create thyroid dysfunction diagnostic tools that are affordable, scalable, and easy for patients to use.

Smart grid enables two-way communications between smart meters and operation centers to collect real-time power consumption of customers to improve flexibility, reliability, and efficiency of the power system. It brings serious privacy issues to customers, since the meter readings possibly expose customers' activities in the house. Data encryption can protect the readings, but lengthens the data size. Secure data aggregation improves communication efficiency and preserves customers' privacy, while fails to support dynamic billing, or offer integrity protection against public collectors, which may be hacked in reality. In this paper, we define a new security model to formalize the misbehavior of collectors, in which the misbehaving collectors may launch pollution attacks to corrupt power consumption data. Under this model, we propose a novel privacy-preserving smart metering scheme to prevent pollution attacks for the balance of security and efficiency in smart grid. It achieves end-to-end security, data aggregation, and integrity protection against the misbehaving collectors, which act as local gateways to collect and aggregate usage data and forward to operation centers. As a result, the misbehaving collectors cannot access or corrupt power usage data of customers. In addition, we design a dynamic billing mechanism based on individual power consumption maintained on collectors with the verification of customers. Our analysis shows that the proposed scheme achieves secure smart metering and verifiable dynamic billing against misbehaving collectors with low computational and communication overhead.

Mildew infestation is a significant cause of loss during grain storage. The growth and metabolism of mildew leads to changes in gas composition and temperature within granaries. Recent advances in sensor technology and machine learning enable the prediction of grain mildew during storage. Current research primarily focuses on predicting mildew occurrence or grading using simple machine learning methods, without in-depth exploration of the time series characteristics of mildew process data. A monitoring device was designed and developed to capture high-quality microenvironment parameters and image data during a simulated mildew process experiment. Using the “Yongyou 15” rice varieties from Zhejiang Province, five simulation experiments were conducted under varying temperature and humidity conditions between January and May 2023. Mildew grades were defined through manual analysis to construct a multimodal dataset for the rice mildew process. This study proposes a combined model (CNN–LSTM–A) that integrates convolutional neural networks (CNN), long short-term memory (LSTM) networks, and attention mechanisms to predict the mildew grade of stored rice. The proposed model was compared with LSTM, CNN–LSTM, and LSTM–Attention models. The results indicate that the proposed model outperforms the others, achieving a prediction accuracy of 98%. The model demonstrates superior accuracy and more stable performance. The generalization performance of the prediction model was evaluated using four experimental datasets with varying storage temperature and humidity conditions. The results show that the model achieves optimal prediction stability when the training set contains similar storage temperatures, with prediction accuracy exceeding 99.8%. This indicates that the model can effectively predict the mildew grades in rice under varying environmental conditions, demonstrating significant potential for grain mildew prediction and early warning systems.

In the era of social commerce, recommendation systems must transcend traditional paradigms by incorporating multimodal data to personalize content more effectively. This study proposes a sentiment-guided, multimodal recommendation framework that integrates text and image-based features to enhance product recommendation strategies, particularly in influencer marketing and fashion retail. The proposed architecture utilizes Gated Recurrent Units (GRUs) for analyzing user-generated textual comments to capture emotional tone and sentiment directionality. Concurrently, a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) pipeline processes product images, extracting semantic features and generating descriptive captions that encapsulate visual attributes such as color, category, and brand. By fusing textual sentiment with visual embeddings, the system produces contextually relevant and emotionally resonant recommendations. The GRU-based sentiment classifier achieves a classification accuracy of 89%, while the CNN-LSTM image captioning module attains a BLEU-1 score of 0.68 and 85% accuracy in visual attribute prediction. The real-time filtering mechanism dynamically modulates content delivery based on sentiment polarity—suppressing recommendations during negative user sentiment to reduce cognitive load and enhance user trust. Designed with scalability in mind, the system supports real-time interaction through streaming APIs and can be deployed on cloud platforms or edge devices. It enables automated visual tagging, reduces manual annotation overhead, and improves content discovery by aligning recommendations with both emotional and aesthetic user preferences. This architecture thus transforms passive browsing into an adaptive, emotionally intelligent interaction—offering a significant leap forward in personalized marketing and user engagement in visually rich environments.