Search

Internet of Things (IoT) devices are increasingly popular due to their wide array of application domains. In IoT networks, sensor nodes are often connected in the form of a mesh topology and deployed in large numbers. Managing these resource-constrained small devices is complex and can lead to high system costs. A number of standardized protocols have been developed to handle the operation of these devices. For example, in the network layer, these small devices cannot run traditional routing mechanisms that require large computing powers and overheads. Instead, routing protocols specifically designed for IoT devices, such as the routing protocol for low-power and lossy networks, provide a more suitable and simple routing mechanism. However, they incur high overheads as the network expands. Meanwhile, reinforcement learning (RL) has proven to be one of the most effective solutions for decision making. RL holds significant potential for its application in IoT device's communication-related decision making, with the goal of improving performance. In this paper, we explore RL's potential in IoT devices and discuss a theoretical framework in the context of network layers to stimulate further research. The open issues and challenges are analyzed and discussed in the context of RL and IoT networks for further study. [ABSTRACT FROM AUTHOR]

An accurate fuel consumption prediction model is the basis for ship navigation status analysis, energy conservation, and emission reduction. In this study, we develop a black-box model based on machine learning and a white-box model based on mathematical methods to predict ship fuel consumption rates. We also apply the Kwon formula as a data preprocessing cleaning method for the black-box model that can eliminate the data generated during the acceleration and deceleration process. The ship model test data and the regression methods are employed to evaluate the accuracy of the models. Furthermore, we use the predicted correlation between fuel consumption rates and speed under simulated conditions for model performance validation. We also discuss applying the data-cleaning method in the preprocessing of the black-box model. The results demonstrate that this method is feasible and can support the performance of the fuel consumption model in a broad and dense distribution of noise data in data collected from real ships. We improved the error to 4% of the white-box model and the R 2 to 0.9977 and 0.9922 of the XGBoost and RF models, respectively. After applying the Kwon cleaning method, the value of R 2 also can reach 0.9954, which can provide decision support for the operation of shipping companies. [ABSTRACT FROM AUTHOR]

Modern systems produce and handle a large volume of sensitive enterprise data. Therefore, security vulnerabilities in the software systems must be identified and resolved early to prevent security breaches and failures. Predicting security vulnerabilities is an alternative to identifying them as developers write code. In this study, we studied the ability of several machine learning algorithms to predict security vulnerabilities. We created two datasets containing security vulnerability information from two open-source systems: (1) Apache Tomcat (versions 4.x and five 2.5.x minor versions). We also computed source code metrics for these versions of both systems. We examined four classifiers, including Naive Bayes, Decision Tree, XGBoost Classifier, and Logistic Regression, to show their ability to predict security vulnerabilities. Moreover, an ensemble learner was introduced using a stacking classifier to see whether the prediction performance could be improved. We performed cross-version and cross-project predictions to assess the effectiveness of the best-performing model. Our results showed that the XGBoost classifier performed best compared to other learners, i.e., with an average accuracy of 97% in both datasets. The stacking classifier performed with an average accuracy of 92% in Struts and 71% in Tomcat. Our best-performing model—XGBoost—could predict with an average accuracy of 87% in Tomcat and 99% in Struts in a cross-version setup. [ABSTRACT FROM AUTHOR]

Most of the utility meters in Sweden are now integrated with Internet of Things (IoT) technology. This modern approach significantly enhances our understanding of energy consumption patterns and empowers consumers with detailed insights into their power usage. Additionally, it provides energy companies and grid owners with critical data to facilitate future energy production planning. However, having data at our disposal is only half the battle won. The method employed to forecast energy consumption is equally important due to the complex interplay between long-term trends, seasonal fluctuations, and other unpredictable factors. To optimally utilize this data, we analyzed several robust time-series forecasting models: Random Forest, XGBoost, SARIMAX, FB Prophet, and a Convolutional Neural Network (CNN). Each of these models was chosen for its unique strengths in capturing long-term trends and short-term variations, making them appropriate candidates for predicting power consumption. We showcase the models' performance on the energy consumption data from commercial property owners in 2021 and evaluate their performance based on key performance metrics such as mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), Relative Root Mean Square Error (RRMSE), Coefficient of determination (R 2), and Standard Deviation (SD). Our results demonstrate that while FB Prophet, with its ability to effectively factor in external parameters such as price and temperature, fared well in predicting aggregated consumption, it was effectively outperformed by the CNN classifier. The CNN model demonstrated exceptional prediction capabilities and flexibility in adding additional features to the model. For example, the CNN model with the highest accuracy showed the lowest MSE compared to Random Forest, XGBoost, SARIMAX, and FB Prophet with reductions of 75.70%, 69.48%, 49.45%, and 30.62%, respectively. Additionally, the CNN model showed superior R 2 values, indicating a better fit to the data. Specifically, the R 2 value for the CNN model was 0.93% on the training set and 0.60% on the testing set, outperforming the other models in terms of explained variance. We also utilized AutoML to analyze a 4-year dataset (2021–2023) to showcase the generalizability of the models. Using AutoML, the R 2 value increased from 47% to 83% with an expanded dataset, indicating that other models will also achieve better results. From a qualitative perspective, contrary to the prevailing notion that deep learning models demand substantial resources, our experience revealed that training a CNN model did not pose significantly greater challenges than traditional models. This reinforces the untapped potential of deep learning in time-series forecasting, highlighting that complex problems like electricity consumption forecasts may benefit from advanced solutions like CNN. • Integrated power data with hourly temp, pricing, and building features for analysis. • Visualized trends to improve power forecasting, focusing on commercial buildings. • Used AutoML for feature analysis, correlation matrix, and model generalizability. • Compared RF, XGBoost, SARIMAX, FB Prophet, and CNN models for daily power forecasts. [ABSTRACT FROM AUTHOR]