Mohd Azraai Mohd Razman – författare

This book presents essentially a collection of proceedings that deliberate on the key challenges and recent trends on robotics, automation and data analytics which are the pillars of Industry 4.0. Solutions that are employed in the multitude spectra of innovative robotics & automation and data analytics are discussed. The readers are expected to gain an insightful view on the current trends, issues, mitigating factors as well as solutions from the book. This book consists of selected papers presented at the 2nd International Conference on Innovative Technology, Engineering and Sciences 2020 (iCITES) hosted virtually by Universiti Malaysia Pahang on 22nd December 2020. iCITES is a biennial conference, aimed at building a platform that allows relevant stakeholders to share and discuss their latest researches, ideas and survey reports from theoretical to a practical standpoint especially in the Innovative Robotics & Automation and Data Analytics tracks which was published in this book.

This book highlights the fundamental association between aquaculture and engineering in classifying fish hunger behaviour by means of machine learning techniques. Understanding the underlying factors that affect fish growth is essential, since they have implications for higher productivity in fish farms. Computer vision and machine learning techniques make it possible to quantify the subjective perception of hunger behaviour and so allow food to be provided as necessary. The book analyses the conceptual framework of motion tracking, feeding schedule and prediction classifiers in order to classify the hunger state, and proposes a system comprising an automated feeder system, image-processing module, as well as machine learning classifiers. Furthermore, the system substitutes conventional, complex modelling techniques with a robust, artificial intelligence approach. The findings presented are of interest to researchers, fish farmers, and aquaculture technologist wanting to gain insights into the productivity of fish and fish behaviour.

This book explores the application of data mining and machine learning techniques in studying the activity pattern, decision-making skills, misconducts, and actions resulting in the intervention of VAR in European soccer leagues referees. The game of soccer at the elite level is characterised by intense competitions, a high level of intensity, technical, and tactical skills coupled with a long duration of play. Referees are required to officiate the game and deliver correct and indisputable decisions throughout the duration of play. The increase in the spatial and temporal task demands of the game necessitates that the referees must respond and cope with the physiological and psychological loads inherent in the game. The referees are also required to deliver an accurate decision and uphold the rules and regulations of the game during a match. These demands and attributes make the work of referees highly complex. The increasing pace and complexity of the game resulted in the introduction of the Video Assistant Referee (VAR) to assist and improve the decision-making of on-field referees. Despite the integration of VAR into the current refereeing system, the performances of the referees are yet to be error-free. Machine learning coupled with data mining techniques has shown to be vital in providing insights from a large dataset which could be used to draw important inferences that can aid decision-making for diagnostics purposes and overall performance improvement.

Cancer is the leading cause of mortality in most, if not all, countries around the globe. It is worth noting that the World Health Organisation (WHO) in 2019 estimated that cancer is the primary or secondary leading cause of death in 112 of 183 countries for individuals less than 70 years old, which is alarming. In addition, cancer affects socioeconomic development as well. The diagnostics of cancer are often carried out by medical experts through medical imaging; nevertheless, it is not without misdiagnosis owing to a myriad of reasons. With the advancement of technology and computing power, the use of state-of-the-art computational methods for the accurate diagnosis of cancer is no longer far-fetched. In this brief, the diagnosis of  four types of common cancers, i.e., breast, lung, oral and skin, are evaluated with different state-of-the-art feature-based transfer learning models. It is expected that the findings in this book are insightful to various stakeholders in the diagnosis of cancer.