ABSTRACT
There is no doubt that the involvement of the Internet of Things (IoT) in our daily lives has changed the way we live and interact as a global community, as IoT enables intercommunication of digital objects around us, creating a pervasive environment. As of now, this IoT is found in almost every domain that is vital for human survival, such as agriculture, medical care, transportation, the military, and so on. Day by day, various IoT solutions are introduced to the market by manufacturers towards making our life easier and more comfortable. On the other hand, even though IoT now holds a key place in our lives, the IoT ecosystem has various limitations in efficiency, scalability, and adaptability. As such, biomimicry, which involves imitating the systems found in nature within human-made systems, appeared to be a potential remedy to overcome such challenges pertaining to IoT, which can also be referred to as bio-inspired IoT. In the simplest terms, bio-inspired IoT combines nature-inspired principles and IoT to create more efficient and adaptive IoT solutions, that can overcome most of the inherent challenges pertaining to traditional IoT. It is based on the idea that nature has already solved many challenging problems and that, by studying and mimicking biological systems, we might develop better IoT systems. As of now, this concept of bio-inspired IoT is applied to various fields such as medical care, transportation, cyber-security, agriculture, and so on. However, it is noted that only a few studies have been carried out on this new concept, explaining how these bio-inspired concepts are integrated with IoT. Thus, to fill in the gap, in this study, we provide a brief review of bio-inspired IoT, highlighting how it came into play, its ecosystem, its latest status, benefits, challenges, and future directions.
ABSTRACT
Throughout the course of human history, owing to innovations that shape the future of mankind, many technologies have been innovated and used towards making people's lives easier. Such technologies have made us who we are today and are involved with every domain that is vital for human survival such as agriculture, healthcare, and transportation. The Internet of Things (IoT) is one such technology that revolutionizes almost every aspect of our lives, found early in the 21st century with the advancement of Internet and Information Communication (ICT) Technologies. As of now, the IoT is served in almost every domain, as we mentioned above, allowing the connectivity of digital objects around us to the Internet, thus allowing the remote monitoring, control, and execution of actions based on underlying conditions, making such objects smarter. Over time, the IoT has progressively evolved and paved the way towards the Internet of Nano-Things (IoNT) which is the use of nano-size miniature IoT devices. The IoNT is a relatively new technology that has lately begun to establish a name for itself, and many are not aware of it, even in academia or research. The use of the IoT always comes at a cost, owing to the connectivity to the Internet and the inherently vulnerable nature of IoT, wherein it paves the way for hackers to compromise security and privacy. This is also applicable to the IoNT, which is the advanced and miniature version of IoT, and brings disastrous consequences if such security and privacy violations were to occur as no one can notice such issues pertaining to the IoNT, due to their miniaturized nature and novelty in the field. The lack of research in the IoNT domain has motivated us to synthesize this research, highlighting architectural elements in the IoNT ecosystem and security and privacy challenges pertaining to the IoNT. In this regard, in the study, we provide a comprehensive overview of the IoNT ecosystem and security and privacy pertaining to the IoNT as a reference to future research.
Subject(s)
Internet of Things , Privacy , Humans , Ecosystem , Computer Security , Delivery of Health Care , InternetABSTRACT
Specialized data preparation techniques, ranging from data cleaning, outlier detection, missing value imputation, feature selection (FS), amongst others, are procedures required to get the most out of data and, consequently, get the optimal performance of predictive models for classification tasks. FS is a vital and indispensable technique that enables the model to perform faster, eliminate noisy data, remove redundancy, reduce overfitting, improve precision and increase generalization on testing data. While conventional FS techniques have been leveraged for classification tasks in the past few decades, they fail to optimally reduce the high dimensionality of the feature space of texts, thus breeding inefficient predictive models. Emerging technologies such as the metaheuristics and hyper-heuristics optimization methods provide a new paradigm for FS due to their efficiency in improving the accuracy of classification, computational demands, storage, as well as functioning seamlessly in solving complex optimization problems with less time. However, little details are known on best practices for case-to-case usage of emerging FS methods. The literature continues to be engulfed with clear and unclear findings in leveraging effective methods, which, if not performed accurately, alters precision, real-world-use feasibility, and the predictive model's overall performance. This paper reviews the present state of FS with respect to metaheuristics and hyper-heuristic methods. Through a systematic literature review of over 200 articles, we set out the most recent findings and trends to enlighten analysts, practitioners and researchers in the field of data analytics seeking clarity in understanding and implementing effective FS optimization methods for improved text classification tasks.
