The proliferation of the internet of things (IoT) technology has led to numerous challenges in various life domains, such as healthcare, smart systems, and mission-critical applications. The most critical issue is the security of IoT nodes, networks, and infrastructures. IoT uses the routing protocol for low-power and lossy networks (RPL) for data communication among the devices. RPL comprises a lightweight core and thus does not support high computation and resource-consuming methods for security implementation. Therefore, both IoT and RPL are vulnerable to security attacks, which are broadly categorized into RPL-specific and sensor-network-inherited attacks. Among the most concerning protocol-specific attacks are rank attacks and wormhole attacks in sensor-network-inherited attack types. They target the RPL resources and components including control messages, repair mechanisms, routing topologies, and sensor network resources by consuming. This leads to the collapse of IoT infrastructure. In this paper, a lightweight multiclass classification-based RPL-specific and sensor-network-inherited attack detection model called MC-MLGBM is proposed. A novel dataset was generated through the construction of various network models to address the unavailability of the required dataset, optimal feature selection to improve model performance, and a light gradient boosting machine-based algorithm optimized for a multiclass classification-based attack detection. The results of extensive experiments are demonstrated through several metrics including confusion matrix, accuracy, precision, and recall. For further performance evaluation and to remove any bias, the multiclass-specific metrics were also used to evaluate the model, including cross-entropy, Cohn’s kappa, and Matthews correlation coefficient, and then compared with benchmark research.

In this research, we address the problem of accurately predicting lane-change maneuvers on highways. Lane-change maneuvers are a critical aspect of highway safety and traffic flow, and the accurate prediction of these maneuvers can have significant implications for both. However, current methods for lane-change prediction are limited in their ability to handle naturalistic driving scenarios and often require large amounts of labeled data. Our proposed model uses a bidirectional long short-term memory (BiLSTM) network to analyze naturalistic vehicle trajectories recorded from multiple sensors on German highways. To handle the temporal aspect of vehicle behavior, we utilized a sliding window approach, considering both the preceding and following vehicles’ trajectories. To tackle class imbalances in the data, we introduced rolling mean computed weights. Our extensive feature engineering process resulted in a comprehensive feature set to train the model. The proposed model fills the gap in the state-of-the-art lane change prediction methods and can be applied in advanced driver assistance systems (ADAS) and autonomous driving systems. Our results show that the BiLSTM-based approach with the sliding window technique effectively predicts lane changes with 86% test accuracy and a test loss of 0.325 by considering the context of the input data in both the past and future. The F1 score of 0.52, precision of 0.41, recall of 0.75, accuracy of 0.86, and AUC of 0.81 also demonstrate the model’s high ability to distinguish between the two target classes. Furthermore, the model achieved an accuracy of 83.65% with a loss value of 0.3306 on the other half of the data samples, and the validation accuracy was observed to improve over these epochs, reaching the highest validation accuracy of 92.53%. The F1 score of 0.51, precision of 0.36, recall of 0.89, accuracy of 0.82, and AUC of 0.85 on this data sample also demonstrate the model’s strong ability to identify both positive and negative classes. Overall, our proposed approach outperforms existing methods and can significantly contribute to improving highway safety and traffic flow.

For networks with limited resources, such as IoT-enabled smart homes, smart industrial equipment, and urban infrastructures, the Routing Protocol for Low-power and Lossy Networks (RPL) was developed. Additionally, a number of optimizations have been suggested for its application in other contexts, such as smart hospitals, etc. Although these networks offer efficient routing, the lack of active security features in RPL makes them vulnerable to attacks. The types of attacks include protocol-specific ones and those inherited by wireless sensor networks. They have been addressed by a number of different proposals, many of which have achieved substantial prominence. However, concurrent handling of both types of attacks is not considered while developing a machine-learning-based attack detection model. Therefore, the ProSenAD model is proposed for addressing the identified gap. Multiclass classification has been used to optimize the light gradient boosting machine model for the detection of protocol-specific rank attacks and sensor network-inherited wormhole attacks. The proposed model is evaluated in two different scenarios considering the number of attacks and the benchmarks for comparison in each scenario. The evaluation results demonstrate that the proposed model outperforms with respect to the metrics including accuracy, precision, recall, Cohen’s Kappa, cross entropy, and the Matthews correlation coefficient.

The automation of medical report generation has been an area of interest for researchers over the years, with significant advancements in computational techniques and natural language processing. Traditionally, the focus has remained on rule-based or template-driven approaches to streamline the documentation process. However, recent breakthroughs in generative AI models have substantially enhanced the capabilities of automated medical report generation. Hence, the field has gained significant attention in recent years due to its potential to support healthcare professionals and improve diagnostic workflows. One key challenge in these models is the reliance on pre-trained, general-purpose tokenizers, which often fail to capture the domain-specific vocabulary essential for accurate medical reporting. When using a general tokenizer, the generated reports may lack coherence, relevance, or even correct medical terminology, leading to poor quality outputs. This problem is particularly acute in specialized fields like ECG, where precise terminology is critical. To address this gap, we train a Byte Pair Encoding (BPE) tokenizer to incorporate ECG-specific vocabulary, resulting in improved coherence and relevance in text generation. The custom tokenizer was integrated into a GPT-2 model for image-to-text generation tasks, where ECG reports were generated from ECG waveforms. Our experiments show that using the custom tokenizer leads to a 85% improvement in coherence and a 45% increase in relevance of generated reports compared to a general-purpose tokenizer.

Twitter has become a unique platform for social interaction from people all around the world, leading to an extensive amount of knowledge that can be used for various reasons. People share and spread their own ideologies and point of views on unique topics leading to the production of a lot of content. Sentiment analysis is of extreme importance to various businesses as it can directly impact their important decisions. Several challenges related to the research subject of sentiment analysis includes issues such as imbalanced dataset, lexical uniqueness, and processing time complexity. Most machine learning models are sequential: they need a considerable amount of time to complete execution. Therefore, we propose a model sentiment analysis specifically designed for imbalanced datasets that can reduce the time complexity of the task by using various text sequenced preprocessing techniques combined with random majority under-sampling. Our proposed model provides competitive results to other models while simultaneously reducing the time complexity for sentiment analysis. The results obtained after the experimentation corroborate that our model provides great results producing the accuracy of 86.5% and F1 score of 0.874 through XGB.

The internet of things (IoT) is becoming more significant in everyday life as a mechanism for making major decisions in different fields as smart devices and data in real time are connected and updated. IoT is being used in a variety of ways to provide digital services to the public. Online payment, property purchase, and sailing are just a few examples. On the other hand, users' complaints about the safety and privacy of their personal information are growing. The internet of things (IoT) is becoming more popular and significantly enhances e-government. This chapter primarily focuses on how potential users can obtain information to use the internet of things and its related services within the e-government sectors. There are several technological, administrative, and political challenges to IoT adoption problems in e-government and legal problems that must be solved to develop effective and required applications. It's crucial to explore these problems and potential solutions. Request access from your librarian to read this chapter's full text.