Kenneth Ang

It is a crucial need for a clustering technique to produce high-quality clusters from biomedical and gene expression datasets without requiring any user inputs. Therefore, in this paper we present a clustering technique called KUVClust that produces high-quality clusters when applied on biomedical and gene expression datasets without requiring any user inputs. The KUVClust algorithm uses three concepts namely multivariate kernel density estimation, unique closest neighborhood set and vein-based clustering. Although these concepts are known in the literature, KUVClust combines the concepts in a novel manner to achieve high-quality clustering results. The performance of KUVClust is compared with established clustering techniques on real-world biomedical and gene expression datasets. The comparisons were evaluated in terms of three criteria (purity, entropy, and sum of squared error (SSE)). Experimental results demonstrated the superiority of the proposed technique over the existing techniques for clustering both the low dimensional biomedical and high dimensional gene expressions datasets used in the experiments.

As more and more applications are deployed using the Internet of Things (IoT) technologies, the fragmentation of general purpose IoT technologies to target particular sectors with different requirements is becoming necessary. In this paper, we summarize the latest developments of applicationspecific IoTs (ASIoTs) (a term to conceptualize the development of IoTs targeted toward specific domains, communications mediums, and industry sectors) in eight representative studies (Internet of Battlefield Things (IoBT), Internet of Medical Things (IoMT), Internet of Animal Things (IoAT), Internet of Waste Things (IoWT), Internet of Underwater Things (IoUWT), Internet of Underground Things (IoUGT), Internet of Nano Things (IoNT), and Internet of Mobile Things (IoMobT) such as the Internet of Vehicles). The paper gives contributions to ASIoTs from three perspectives: First, we offer a basic classification taxonomy for ASIoTs and discuss various representative studies and applications which can be found in the literature; Second, we discuss a use case for a biometrics-based ASIoT (termed IoBioT) for illustration and experiments of face-based biometric recognition on IoBioT are also performed; and Third, we give discussions and future directions for ASIoTs. An objective of this paper is to spur researchers and facilitate the development of ASIoTs for the different user-defined domains, communication mediums, and technology constrained platforms.

Due to human influence and its negative impacts on the world's environment, the world is changing into a cleaner and more sustainable energy system. In both private and public buildings, there is a desire to reduce electricity usage, automate appliances, and optimize the electricity usage of a building. This paper presents the design and implementation of a secured smart home switching system based on wireless communications and self-energy harvesting. The proposed secured smart home switching system integrates access control of the building's electricity, energy harvesting, and storage for the active electronic components and circuitries, and wireless communication for smart switches and sockets. The paper gives two contributions to the design of smart home systems: 1) A practical design and implementation of security (access control system) for a building's power supply which adds a locking feature such that only authorized personnel are capable of altering the power state of the smart sockets and switches in a building, and; 2) A model of energy harvesting and storage system for the active electronic components of the circuitries and wireless communication for smart switches and sockets. The access control involves four stages (a control unit, a comparator unit, a memory unit, and the switching unit). The access control system provides means of access control by having a security keypad that switches ON or OFF the building's electricity, provided the user knows the security pin code (8 coded pins). The proposed system also harvests and stores energy for all the active electronic devices using a photovoltaic system with ultracapacitor energy buffer. The designed secured smart home utilized smart power and switches, and message queuing telemetry transport for ease of controlling energy usage. The experimental results obtained from extensive testing of the prototype shows an improvement in security and energy management in a building.

The exponential growth of multimodal content in today's competitive business environment leads to a huge volume of unstructured data. Unstructured big data has no particular format or structure and can be in any form, such as text, audio, images, and video. In this paper, we address the challenges of emotion and sentiment modeling due to unstructured big data with different modalities. We first include an up-to-date review on emotion and sentiment modeling including the state-of-the-art techniques.We then propose a new architecture of multimodal emotion and sentiment modeling for big data. The proposed architecture consists of five essential modules: data collection module, multimodal data aggregation module, multimodal data feature extraction module, fusion and decision module, and application module. Novel feature extraction techniques called the divide-and-conquer principal component analysis (Div-ConPCA) and the divide-andconquer linear discriminant analysis (Div-ConLDA) are proposed for the multimodal data feature extraction module in the architecture. The experiments on a multicore machine architecture are performed to validate the performance of the proposed techniques.