Lance Chun Che Fung

—Question answering over knowledge graphs (KGQA) seeks to automatically answer natural language questions by retrieving triples within the knowledge graph (KG). In the context of multi-hop KGQA, reasoning across multiple edges of the KG becomes crucial for obtaining answers. Existing methods align with either the path-searching-based mainstream, emphasizing structural KG analysis, or the subgraph-based mainstream, focusing on semantic KG embeddings. Both streams have two primary challenges: (1) KG incompleteness, where path searching or subgraph construction faces limitations in the absence of links between entities; (2) candidate answer selection, wherein most approaches employ pre-defined searching sizes or heuristics. Many recent studies incorporate Graph Convolutional Network (GCN) to encode KGs, yet they overlook the potential over-smoothing issue inherent in GCNs. The over-smoothing problem arises from the tendency of closely connected nodes to exhibit similar embeddings within the deep convolutional architecture of GCNs. To address these challenges, this paper proposes a two-stage framework named ComPath, leveraging insights from both mainstreams. ComPath utilizes GCN to tackle KG incompleteness and introduces a path analyser to mitigate the over-smoothing issue associated with GCN. Candidate answers are selected using semantic similarity. The ablation studies and comparative experiments on the three KGQA benchmark datasets shown that the proposed ComPath performed better than the other KGQAs.

Drug repurposing is a technique for probing new usages of existing medicines, but its traditional methods, such as computational approaches, can be time-consuming and laborious. Recently, knowledge graphs (KGs) have emerged as a powerful approach for graph-based representation in drug repurposing, encoding entities and relations to predict new connections and facilitate drug discovery. As COVID-19 has become a major public health concern, it is critical to establish an appropriate COVID-19 KG for drug repurposing to combat the spread of the virus. However, most publicly available COVID-19 KGs lack support for multi-relations and comprehensive entity types. Moreover, none of them originates from COVID-19-related drugs, making it challenging to identify effective treatments. To tackle these issues, we developed Drug-CoV, a drug-origin and multi-relational COVID-19 KG. We evaluated the quality of Drug-CoV by performing link prediction and comparing the results to another publicly available COVID-19 KG. Our results showed that Drug-CoV outperformed the comparing KG in predicting new links between entities. Overall, Drug-CoV represents a valuable resource for COVID-19 drug repurposing efforts and demonstrates the potential of KGs for facilitating drug discovery.

The present study evaluates the potential use of graphene oxide (GO) and reduced graphene oxide (RGO) additives to improve the photothermal response and evaporation rates of basin water used in solar thermal stills. The prepared GO-based and RGO-based test solutions were dilute, well dispersed, and stable. Improvements in photothermal response and evaporation rates were found to be significant. The best-performing fluid was the 30% RGO stock solution-based water solution, which achieved a temperature enhancement of 5.2% and a significant evaporation rate improvement of 30.5% compared to pure water samples. Importantly, the evaporation rates achieved were at relatively lower solution temperatures that were typically between 39 and 41 °C, thus highlighting the advantage of adding either GO or RGO to basin water to improve evaporation rates for solar thermal stills operating at lower temperatures. All GO- and RGO-based solutions displayed excellent dispersion stability over the investigated temperature range.

The applications related to ultra-low power wearables like internet of things, robotics, intrusion detection, and image security have become a major computing paradigm and the latest disruptive technology after artificial intelligence. Ability of ultra-low power wearables to connect with other systems and applications from low to high level has prompted unprecedented array of applications in all fields of human activity from science, engineering, health, leisure and everyday life, etc. The technological growth in ultra-low power wearables is going hand-by-hand with enormous research efforts by an ever increasing community in a fascinating multidisciplinary field.

The motivation of this special issue is to offer an essential guide to the readers on the applications: internet of things security, wireless sensor network, image processing, intrusion detection, antenna, optimization, and cryptography. The accepted manuscripts are used as a reference text for graduate and undergraduate studies. Hence, the manuscripts are written in plain and easy to follow language and explain every main concept the first time it appears, helping readers with no prior background in the field. It is a “must-read” guide to the subject matter.

This special issue intends to provide a platform for researchers to share innovative work in many applications like internet of things security, wireless sensor network, image processing, intrusion detection, antenna, optimization, and cryptography. After a double-blinded peer-review procedure, 14 papers have been accepted and included in this special issue, which contains different methods to solve different kinds of complex problems.

Representation learning of knowledge graphs aims to embed entities and relations into low-dimensional vectors. Most existing works only consider the direct relations or paths between an entity pair. It is considered that such approaches disconnect the semantic connection of multi-relations between an entity pair, and we propose a convolutional and multi-relational representation learning model, ConvMR. The proposed ConvMR model addresses the multi-relation issue in two aspects: (1) Encoding the multi-relations between an entity pair into a unified vector that maintains the semantic connection. (2) Since not all relations are necessary while joining multi-relations, we propose an attention-based relation encoder to automatically assign weights to different relations based on semantic hierarchy. Experimental results on two popular datasets, FB15k-237 and WN18RR, achieved consistent improvements on the mean rank. We also found that ConvMR is efficient to deal with less frequent entities.

Collaborative-based personalization has been one of the most successful techniques used in building personalization for recommender systems and facet selection. The technique predicts users’ interests based on the preferences of similar people or items. The prediction is usually made on one single group of users or items/facets. However, multiple facet selection creates a different challenge where the prediction needs to be based on the similarity among different groups of users and facets. In conventional collaborative approach, user–facet representation is created from the concatenation of user preferences on each facet. This creates a spared representation which affects the accuracy of the personalized model. It is essential to develop a more suitable representation that effectively represents the collaborative preferences given across multiple facets and a predictive model to estimate the possible preferences across those groups. Multiple facets appear to be correlated to each other and this can be useful for associating the existing preferences. None of the previous works has addressed the issue due to the association of facet relationships. Hence, this paper aims to examine the effectiveness of a new approach that utilizes multiple-facet relationships to associate the collaborative interests across different facets. This study proposes a new collaborative-based personalization model for multiple facet selection, called Relation-aware Collaborative Autoencoder (RCAE) Model. A new embedding methodology was introduced for incorporating multiple facet relationships into user–facet interaction. Evaluations based on four real-world datasets demonstrated that the proposed model utilizing facet relationships has achieved significant improvement over the conventional collaborative approach.

Two types of highly stable 0.1% graphene oxide-based aqueous nanofluids were synthesised and investigated. The first nanofluid (GO) was prepared under the influence of ultrasonic irradiation without surfactant. The second nanofluid was treated with tetra ethyl ammonium hydroxide to reduce the graphene oxide to form reduced graphene oxide (RGO) during ultrasonic irradiation. The GO and RGO powders were characterised by various techniques such as field emission scanning electron microscopy, transmission electron microscopy, X-ray diffraction and Raman. Also UV–visible absorption spectroscopy was carried out and band gap energies were determined. Optical band gap energies for indirect transitions ranged from 3.4 to 4.4 eV and for direct transitions they ranged between 2.2 and 3.7 eV. Thermal conductivity measurements of the GO-based aqueous nanofluid revealed an enhancement of 9.5% at 40 °C compared to pure water, while the RGO-based aqueous nanofluid at 40 °C had a value 9.23% lower than pure water. Furthermore, the photothermal response of the RGO-based aqueous nanofluid had a temperature increase of 13.5 °C, (enhancement of 60.2%) compared to pure water, the GO-based aqueous nanofluid only displayed a temperature rise of 10.9 °C, (enhancement of 46.6%) after 20 min exposure to a solar irradiance of 1000 W m−2. Both nanofluid types displayed good long-term stability, with the GO-based aqueous nanofluid having a zeta potential of 30.3 mV and the RGO-based aqueous nanofluid having a value of 47.6 mV after 6 months. The good dispersion stability and photothermal performance makes both nanofluid types very promising working fluids for low-temperature direct absorption solar collectors.

Question Answering (QA) systems over Knowledge Graphs (KGs) (KGQA) automatically answer natural language questions using triples contained in a KG. The key idea is to represent questions and entities of a KG as low-dimensional embeddings. Previous KGQAs have attempted to represent entities using Knowledge Graph Embedding (KGE) and Deep Learning (DL) methods. However, KGEs are too shallow to capture the expressive features and DL methods process each triple independently. Recently, Graph Convolutional Network (GCN) has shown to be excellent in providing entity embeddings. However, using GCNs to KGQAs is inefficient because GCNs treat all relations equally when aggregating neighbourhoods. Also, a problem could occur when using previous KGQAs: in most cases, questions often have an uncertain number of answers. To address the above issues, we propose a graph summarization technique using Recurrent Convolutional Neural Network (RCNN) and GCN. The combination of GCN and RCNN ensures that the embeddings are propagated together with the relations relevant to the question, and thus better answers. The proposed graph summarization technique can be used to tackle the issue that KGQAs cannot answer questions with an uncertain number of answers. In this paper, we demonstrated the proposed technique on the most common type of questions, which is single-relation questions. Experiments have demonstrated that the proposed graph summarization technique using RCNN and GCN can provide better results when compared to the GCN. The proposed graph summarization technique significantly improves the recall of actual answers when the questions have an uncertain number of answers.

The present study investigated the improvement in photothermal response and temperature enhancement of a commercially available organic thermal oil when small quantities of graphene oxide (0.1 to 0.3% w/v) were added. Characterisation studies revealed the ultrasonic processing procedure did not change the chemical composition of the organic oil, which was found to be thermally stable up to 175 °C before complete decomposition at 315 °C. When the GO-based fluids were exposed to a solar irradiance of 985 Wm-2, the temperature enhancements achieved over the exposure period of 20 minutes typically ranged from 42.4 to 43.2%. The temperature enhancements achieved indicate the GO-based fluids have the potential to be used in direct-absorption solar collectors for improved performance.