Machine learning can be used to automate a wide range of tasks. Smart buildings, which use the Internet of Things (IoT) to connect building operations, enable activities, such as monitoring temperature, safety, and maintenance, for easier controlling via mobile devices and computers. Smart buildings are becoming core aspects in larger system integrations as the IoT is becoming increasingly widespread. The IoT plays an important role in smart buildings and provides facilities that improve human security by using effective technology-based life-saving strategies. This review highlights the role of IoT devices in smart buildings. The IoT devices platform and its components are highlighted in this review. Furthermore, this review provides security challenges regarding IoT and smart buildings. The main factors pertaining to smart buildings are described and the different methods of machine learning in combination with IoT technologies are also described to improve the effectiveness of smart buildings to make them energy efficient.

Feature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce the number of these features and maximise the classifier accuracy. This paper proposes a Dynamic Butterfly Optimization Algorithm (DBOA) as an improved variant to Butterfly Optimization Algorithm (BOA) for feature selection problems. BOA represents one of the most recently proposed optimization algorithms. BOA has demonstrated its ability to solve different types of problems with competitive results compared to other optimization algorithms. However, the original BOA algorithm has problems when optimising high-dimensional problems. Such issues include stagnation into local optima and lacking solutions diversity during the optimization process. To alleviate these weaknesses of the original BOA, two significant improvements are introduced in the original BOA: the development of a Local Search Algorithm Based on Mutation (LSAM) operator to avoid local optima problem and the use of LSAM to improve BOA solutions diversity. To demonstrate the efficiency and superiority of the proposed DBOA algorithm, 20 benchmark datasets from the UCI repository are employed. The classification accuracy, the fitness values, the number of selected features, the statistical results, and convergence curves are reported for DBOA and its competing algorithms. These results demonstrate that DBOA significantly outperforms the comparative algorithms on the majority of the used performance metrics.

The recent two decades have witnessed tremendous growth in Internet of things (IoT) applications. There are more than 50 billion devices connected globally. IoT applications’ connectivity with the Internet persistently victimized them with a divergent range of traditional threats, including viruses, worms, malware, spyware, Trojans, malicious code injections, and backdoor attacks. Traditional threats provide essential services such as authentication, authorization, and accountability. Authentication and authorization are the process of verifying that a subject is bound to an object. Traditional authentication and authorization mechanisms use three different factors to identity a subject to verify if the subject has the right capability to access the object. Further, it is defined that a computer virus is a type of malware. Malware includes computer viruses, worms, Trojan horses, spyware, and ransomware. There is a high probability that IoT systems can get infected with a more sophisticated form of malware and high-frequency electromagnetic waves. Purpose oriented with distinct nature IoT devices is developed to work in a constrained environment. So there is a dire need to address these security issues because relying on existing traditional techniques is not good. Manufacturers and researchers must think about resolving these security and privacy issues. Most importantly, this study identifies the knowledge and research gap in this area. The primary objective of this systematic literature review is to discuss the divergent types of threats that target IoT systems. Most importantly, the goal is to understand the mode of action of these threats and develop the recovery mechanism to cover the damage. In this study, more than 170 research articles are systematically studied to understand security and privacy issues. Further, security threats and attacks are categorized on a single platform and provide an analysis to explain how and to what extent they damage the targeted IoT systems. This review paper encapsulates IoT security threats and categorizes and analyses them by implementing a comparative study. Moreover, the research work concludes to expand advanced technologies, e.g., blockchain, machine learning, and artificial intelligence, to guarantee security, privacy, and IoT systems.

Topic Modeling in Sentiment Analysis: A Systematic Review

Aspect extraction or opinion target extraction is the key task of sentiment analysis, which aims to identify targets of people’s sentiments. This is the most important task of aspect-based sentiment analysis as without the aspects, there is no much use of extracted opinions. Recent approaches have shown the significance of dependency-based rules for the given task. These rules are heavily dependent on the dependency parser and generated with the help of grammatical rules. In this article, we are proposing to learn from user’s behaviour to identify the relation among aspects and opinions. The use of sequential patterns has been proposed for the extraction of aspects. The key purpose of this research is to study the impact of sequential pattern mining in the phase of aspect extraction. Our experimental results show that the approach proposed in our work produced better results as compared with the state-of-the-art approaches.