The Social Internet of Things (SIoT) enables cross-organisational collaboration for various industrial applications. However, evaluating trust models within such environments remains challenging due to context-dependent dynamics in SIoT environments. Existing evaluation platforms often rely on overly domain-specific or generic datasets, overlooking the inherent uncertainty and dynamicity of real-world SIoT settings. Additionally, there is a lack of practical platforms to assess the feasibility and effectiveness of trust models across diverse scenarios. In this study, we present the Realistic Trust Model Evaluation Platform for the Social Internet of Things (REACT-SIoT) to rigorously assess trust models in SIoT environments, thereby facilitating trustworthy collaboration for sustainable IoT transformations. REACT-SIoT addresses 21 identified requirements essential for simulating a realistic SIoT environment, including categories of heterogeneity, dynamicity, incompleteness, uncertainty, interdependency, and authentic real-world dynamics. We developed a configurable evaluation procedure that mitigates dataset bias and supports the assessment of both existing and newly developed trust models under various scenario-dependent settings. A real-world example demonstrates the platform’s capability to satisfy these requirements effectively. Our analysis reveals that REACT-SIoT meets all defined requirements and outperforms existing evaluation environments based on accuracy, trust convergence, and robustness criteria. The platform has been successfully applied to existing trust models, showcasing its applicability and enabling comparative assessments that were previously constrained by disparate evaluation settings and datasets. In conclusion, REACT-SIoT offers a highly- adaptable evaluation framework that ensures unbiased and comprehensive trust model assessments in SIoT environments. This platform bridges a critical gap in trust evaluation research, enabling the comparison and validation of trust models across diverse, realistic scenarios, thereby supporting the development of more resilient and trustworthy collaborative SIoT systems. • Definition of a realistic Social Internet of Things (SIoT) environment for trust evaluation. • Proposed a trust model evaluation platform that implements a realistic SIoT environment. • Proposed a Canberra Transportation Case Study as a concrete instance to evaluation trust models. • Comprehensive evaluation of trust models in the context of the Canberra Transportation Case Study.

Integrating machine learning (ML) into healthcare has rapidly advanced, necessitating precise and reliable explanatory mechanisms, especially in critical areas such as glaucoma detection and analysis. This systematic review examines how Explainable Artificial Intelligence (XAI) enhances the transparency and comprehensibility of machine learning algorithms for glaucoma detection. By emphasizing XAI, the review aims to demonstrate its critical importance in a field where accuracy and trust are essential. To evaluate the effectiveness of XAI in conjunction with ML, this review meticulously assesses various XAI methodologies for their ability to clarify the intricate workings of ML models. The analysis is grounded in examining well-known medical imaging datasets geared towards glaucoma detection, providing a focused overview of XAI’s role in interpreting complex ML decisions in a healthcare context. Findings from the review indicate that applying XAI techniques has significantly improved clinician trust in ML-driven decisions by making the decision-making processes more transparent and comprehensible. This enhancement in trust is attributed to XAI’s ability to provide deeper insights into the logic and reasoning behind ML algorithms, thereby facilitating a better understanding of their outcomes. Although the application of XAI in glaucoma detection and analysis has shown promising improvements in clinician trust and the transparency of ML models, there remains a critical need for more comprehensive research. Such studies would aim to fully ascertain the long-term impacts of XAI-enhanced ML on healthcare outcomes, particularly in glaucoma analysis, where the stakes for accurate and understandable diagnostic tools are incredibly high.

Agriculture and food production constantly struggle with tracking the growth of crops and controlling weeds. Weeds take away important resources like water, nutrients, and sunlight from crops. This can cause a big decrease in how many crops grow if the weeds are not taken care of properly. Modern agriculture is increasingly using artificial intelligence (AI) based systems to effectively monitor and manage weeds. Mapping weeds with remote sensing or image processing helps effectively measure their impact. Extensive research indicates that machine learning or AI is effective in assessing the impact of weeds and quantifying their presence within crops. However, the internal decision-making processes of some AI approaches are complex, making them difficult to understand even for AI experts. In agriculture, it’s essential that these decision-making approaches are easy to understand for people who are not familiar with AI. In this research, we propose an interpretable method for identifying crops and weeds from images captured by unmanned aerial vehicles (UAVs), or drones. First, we used U-net segmentation on UAV datasets to filter out noise in the images. U-net is effective in extracting detailed local information, like textures, and learning the connections between pixels in an image. The filtered images are then processed by Vision Transformers (ViT), which extract both local and global contextual information about weeds and crops from them. This information aids in measuring the quantity of weeds in the fields. Finaly we apply Explainable AI (XAI) approaches layer-wise relevance propagation (LRP) and pixel density analysis (PDA). These techniques demonstrate the step-by-step decision-making process in measuring the amount of weeds from the images.

Proactive identification and the management of disruption risks play a crucial role in the achievement of a global supply chain’s aims. Given the velocity and volume by which such disruption events occur, it is impractical to expect supply chain managers to determine the occurrence of such events manually. Given the pressures facing global supply chains due to the COVID-19 crisis, it is important for supply chain managers to proactively identify disruption risks to their supply chains and manage them to either achieve the outcomes or develop plans by which resilience against them can be built. In this paper, we demonstrate how the integration of natural language processing and reinforcement learning, which are fundamental artificial intelligence methods, can be used to assist supply chain risk managers in the timely identification of such disruption events. We explain in detail our proposed approach, namely RL-SCRI and show its superiority over the current models in achieving its aim.

The emergence of artificial intelligence (AI) and its related capabilities has led industries to rethink the existing practices of conventional supply chain management and data analysis. Machine learning (ML), Deep Learning (DL) and their unique ability to predict future data and classify data have led to important research in the supply chain (SC) domain, particularly in identifying and prioritising supply chain risks. This paper proposes several DL methodologies to exploit the benefit of DL, particularly to identify whether any product will be delivered late due to any unforeseen reason in a complex SC system. Four different DL architectures (Simple-LSTM, Deep-LSTM, 1D-CNN, and TCN-1DSPCNN models) are proposed to extract features, while six variant classifiers: Softmax, random trees (RT), random forest (RF), K-nearest neighbor (KNN), artificial neural network (ANN), and support vector machine (SVM), were used to classify delay or non-delay information. By seamlessly capturing intricate temporal dependencies, these DL models enhance accuracy in robustly identifying supply chain late orders. Leveraging their hierarchical feature learning, these proposed DL models excel in recognizing subtle patterns and correlations, making them ideal for classifying late orders within the supply chain. Their parallel processing prowess facilitates real-time decision support, allowing organizations to address potential delays and allocate resources effectively and proactively. Five-fold cross-validation is presented to avoid over-fitting and to prove the efficiency of the proposed DL models. The total accuracies of the six ML classifiers are 74.03, 75.81, 93.35, 87.72, 93.59, and 95.10, respectively, while the maximum accuracies obtained from four proposed DL methodologies obtained an accuracy of 97.6, 98.63, 100, 100% respectively using the SVM classifier for predicting late orders based on five-fold cross-validation.

Abstract Robotic Process Automation (RPA) is an emerging software technology for automating business processes. RPA uses software robots to perform repetitive and error‐prone tasks previously done by human actors quickly and accurately. These robots mimic humans by interacting with existing software applications through user interfaces (UI). The goal of RPA is to relieve employees from repetitive and tedious tasks to increase productivity and to provide better service quality. Yet, despite all the RPA benefits, most organizations fail to adopt RPA. One of the main reasons for the lack of adoption is that organizations are unable to effectively identify the processes that are suitable for RPA. This paper proposes a new method, called Rule‐based robotic process analysis (RRPA), that assists process automation practitioners to classify business processes according to their suitability for RPA. The RRPA method computes a suitability score for RPA using a combination of two RPA goals: (i) the RPA feasibility, which assesses the extent to which the process or the activity lends itself to automation with RPA and (ii) the RPA relevance, which assesses whether the RPA automation is worthwhile. We tested the RRPA method on a set of 13 processes. The results showed that the method is effective at 82.05% and efficient at 76.19%.

Blockchain technology has the potential to be applied widely in supply chain operations. One such area is proactive supply chain risk management (SCRM). In this area, existing researchers have highlighted the fraudulent behaviour of supply chain partners who do not disclose information on the risks that impact their operations. Blockchain can address this problem by encoding each partner’s commitment to SCRM and achieve consensus. However, before this can be achieved, a key challenge to address is the inability of existing consensus mechanisms such as Proof of Work (PoW), Proof of Authority (PoA) and Proof of Stake (PoS) to deal with information that does not have a digital footprint. In this paper, we address this gap by proposing the Proof by Earnestness (PoE) consensus mechanism which accounts for the authenticity, legitimacy and trustworthiness of information that does not have a digital footprint. We also propose the Subjective Information Authenticity Earnestness Framework (SIAEF) as the overarching framework that assists PoE in achieving its aim. We test the applicability of SIAEF and PoE in a real-world blockchain environment by deploying it as a decentralized application (Dapp) and applying it in BscScan Testnet which is an official test blockchain network.

The accuracy and reliability of XAI methods are important to establish their credibility and use in complex decision-making tasks. Existing XAI methods provide little information about the correctness and reliability of their outputs. Furthermore, post-hoc explanation approaches explain the outcomes after producing them, not in a step-by-step glass-box manner to explain how an output is reached. Our proposed approach addresses these drawbacks by designing a Belief-Rule-Based (BRB) framework that interprets in a glass-box manner why a particular decision has been reached. It does that by determining the chance of different output classes occurring for a specific time period by considering the different possible permutations of the inputs along with their influence. This also assists the user to determine if the given input dataset is incomplete, vague, imprecise or inconsistent before trusting the analysis emanating from it. We compare the performance of the proposed BRB approach against the different eXplainable artificial intelligence (XAI) methods, such as SHAP, LIME and LINDA-BN to ensure the users of the trustworthiness of its analysis. This also enables users to determine the extent to which each of the XAI techniques meets the requirements of XAI and the gaps that need to be addressed.

Recommender systems have seen wide adoption in different domains. The motive of such systems has evolved from providing generic recommendations in the past to providing customized and user-focused recommendations. To achieve this aim, the complexity and sophistication of the underlying techniques such systems use have evolved. Current recommender systems use advanced Artificial Intelligence techniques to provide intelligent recommendations and adapt their future workings to the user’s interest and requirements. One such technique currently being used in the literature to achieve this aim is Reinforcement Learning. However, a drawback of this technique is that it is data intensive and needs to be trained on data that represent different scenarios to ensure that the recommended output in a given scenario is accurate. In this article, we present an approach, namely Reinforcement Learning-based News Recommendation System (RL-NRS), to address this drawback in the domain of news recommendation. We explain the different stages of RL-NRS in detail and compare its performance with news articles recommended by Google for a particular search term.

Recommender systems play a vital role in e-commerce by presenting personalized product suggestions, reducing habituation and leading to transactions in an environment with limited human touch. Data used for learning how to select optimal recommendation content, including mouse tracking data, are often imprecise in nature. In this paper, we present a fuzzy approach to model purchase intent based on tracking user interaction with a browser via mouse and keyboard. It appreciates data uncertainty and provides insights into e-commerce customer behavior and the development of shops online. The developed fuzzy rule-based systems had a good accuracy and low interpretability, and results show that to generalize possible purchase intent with fuzzy rules, it is good to begin with looking at such behavioral features as distance of mouse movement, distance of vertical page scrolling, number of mouse clicks and time of user activity on website in relation to page content length. In future work, we intend to look at more features reflecting product parameters and transactions to enhance the modeling results on a larger scale.

Assortment planning is one of the fundamental and complex decisions for online retailers. The complexity of this problem is increasing while considering demand and supply uncertainties in assortment planning (AP). However, this leads to more efficient results in today's uncertain markets. In this paper, the supplier and E-tailer interactions are modeled by the non-cooperative game theory model. As small-scale online retailers opposed to bricks and mortar usually have lower power in front of suppliers, we propose a Stackelberg or leader-follower game model. First, the supplier as a leader announces its decisions regarding selling price to the E-tailer. Consequently, the E-tailer reacts by determining the purchase quantity, selling price to the customers and assortment size. Various scenarios are presented and analyzed to show the effectiveness of the Stackelberg game model in simulating the interactions between small-scale online retailers and a powerful supplier.

The constant increase in the growth of the cloud market creates new challenges for cloud service providers. One such challenge is the need to avoid possible service level agreement (SLA) violations and their consequences through good SLA management. Researchers have proposed various frameworks and have made significant advances in managing SLAs from the perspective of both cloud users and providers. However, none of these approaches guides the service provider on the necessary steps to take for SLA violation abatement; that is, the prediction of possible SLA violations, the process to follow when the system identifies the threat of SLA violation, and the recommended action to take to avoid SLA violation. In this paper, we approach this process of SLA violation detection and abatement from a risk management perspective. We propose a Risk Management-based Framework for SLA violation abatement (RMF-SLA) following the formation of an SLA which comprises SLA monitoring, violation prediction and decision recommendation. Through experiments, we validate and demonstrate the suitability of the proposed framework for assisting cloud providers to minimize possible service violations and penalties.

Summary Business service advertisements are today published online to convey essential information about services to customers. However, current Web search engines are unable to search and combine online service advertisements. Semantic service annotation is important for its ability to enable machines to understand the meaning of services and support in effective service retrieval and service composition. Existing research in the area of semantic service annotation has focused on the annotation of Web services in a semi‐automated approach. It cannot be applied to business service information as it is not in the form of Web Services Description Language but in free text format. Moreover, semi‐automated approaches are inappropriate for annotating a large amount of online service information which changes dynamically and they are therefore not suitable for the timely dissemination of service information to customers. To solve these issues, we propose SERNOTATE, which is an automated approach for business service description annotation for efficient service retrieval and composition. We propose new semantic‐based linking approaches, namely, Extended Case‐based Reasoning, vector‐based, and classification‐based, that automatically annotate business services to relevant service concepts. Each approach assists in the single‐label and multi‐label annotation of service terms to concept terms to provide a better representation of services. The experimental results test and validate the applicability of the proposed approaches to the automatic annotation of business service descriptions to service concepts on a real‐world dataset.

intelligent, complex, reliable, and optimized cloud computing systems with Internet of Things (IoT) technologies among researchers, developers, and industrial experts.

We propose an interactive decision-making framework to assist a Customer Service Representative (CSR) in the efficient and effective recognition of customer records in a database with many ambiguous entries. Our proposed framework consists of three integrated modules. The first module focuses on the detection and resolution of duplicate records to improve effectiveness and efficiency in customer recognition. The second module determines the level of ambiguity in recognizing an individual customer when there are multiple records with the same name. The third module recommends the series of feature-related questions that the CSR should ask the customer to enable rapid recognition, based on that level of ambiguity. In the first module, the F-Swoosh approach for duplicate detection is used, and in the second module a dynamic programming-based technique is used to determine the level of ambiguity within the customer database for a given name. In the third module, Levenshtein edit distance is used for feature selection in combination with weights based on the Inverse Document Frequency (IDF) of terms. The algorithm that requires the minimum number of questions to be put to the customer to achieve recognition is the algorithm that is chosen. We evaluate the proposed framework on a synthetic dataset and demonstrate how it assists the CSR to rapidly recognize the correct customer.

There is increasing interest in sharing the experience of products and services on the web platform, and social media has opened a way for product and service providers to understand their consumers needs and expectations. This paper explores reviews by cloud consumers that reflect consumers experiences with cloud services. The reviews of around 6,000 cloud service users were analysed using sentiment analysis to identify the attitude of each review, and to determine whether the opinion expressed was positive, negative, or neutral. The analysis used two data mining tools, KNIME and RapidMiner, and the results were compared. We developed four prediction models in this study to predict the sentiment of users reviews. The proposed model is based on four supervised machine learning algorithms: K-Nearest Neighbour (k-NN), Nave Bayes, Random Tree, and Random Forest. The results show that the Random Forest predictions achieve 97.06% accuracy, which makes this model a better prediction model than the other three.

Health, Safety, Environment and Ergonomie (HSEE) are important factors in any organization. An organization always have to assess its compliance in these factors to the required benchmarks and take proactive actions to improve them if required. In this paper, we propose a Fuzzy Cognitive Map-Bayesian network (BN) model in order to assist organizations in doing this process. Fuzzy Cognitive Map (FCM) method is used for constructing graphical model of BN to ascertain the relationships between the inputs and the impact which they will have on the quantified HSEE. Noisy-OR method and EM are used to ascertain the conditional probability between the inputs and quantifying the HSEE value. Using this, we find out the most influential input factor on HSEE quantification which can then be managed for improving an organization's compliance to HSEE. Leveraging the power of Bayesian network in modeling HSEE and augmenting it with FCM is the main contribution of this research work which opens this line of research.

Effective business planning requires seamless access and intelligent analysis of information in its totality to allow the business planner to gain enhanced critical business insights for decision support. Current business planning tools provide insights from structured business data (i.e. sales forecasts, customers and products data, inventory details) only and fail to take into account unstructured complementary information residing in contracts, reports, user's comments, emails etc. In this article, a planning support system is designed and developed that empower business planners to develop and revise business plans utilizing both structured data and unstructured information conjointly. This planning system activity model comprises of two steps. Firstly, a business planner develops a candidate plan using planning template. Secondly, the candidate plan is put forward to collaborating partners for its revision interleaving deliberation. Planning interleaving deliberation activity in the proposed framework enables collaborating planners to challenge both a decision and the thinking that underpins the decision in the candidate plan. The planning system is modeled using situation calculus and is validated through a prototype development.

Cloud-of-things service providers use various descriptions languages to describe Quality of Service (QoS) attributes. However, existing modelling approaches provide support for modelling static QoS attributes only and lack features to model and reason with dynamic QoS attributes such as response time and availability. This paper presents an event-based approach for monitoring dynamic QoS values and their compliance by modelling the behavior of QoS attributes using an Event Calculus (EC) based framework. The logic based reasoning is then performed to proactively identify the possible QoS violations in future.

The big data research topic has grown rapidly for the past decade due to the advent of the "data deluge". Recent advancements in the literature leverage human computing power known as crowdsourcing to manage and harness big data for various applications. However, human involvement in the completion of crowdsourcing tasks is an error-prone process that affects the overall performance of the crowd. Thus, controlling the quality of workers is an essential step for crowdsourcing systems, which due to unavailability of ground-truth data for any task at hand becomes increasingly challenging. To propose a solution to this problem, in this study, we propose OSQC (Online Statistical Quality Control Framework) for managing the performance of workers in crowdsourcing. OSQC ascertains the worker's performance by using a statistical model and then leverages the traditional statistical control techniques to decide whether to retain a worker for crowdsourcing or to evict him. We evaluate our proposed framework on a real dataset and demonstrate how OSQC assists crowdsourcing to maintain its accuracy.

With the rapid growth of cloud services, there has been a significant increase in the number of online consumer reviews and opinions on these services on different social media platforms. These reviews are a source of valuable information in regard to cloud market position and cloud consumer satisfaction. This study explores cloud consumers' reviews that reflect the user's experience with Software as a Service (SaaS) applications. The reviews were collected from different web portals, and around 4000 online reviews were analysed using sentiment analysis to identify the polarity of each review, that is, whether the sentiment being expressed is positive, negative, or neutral. Also, this research develops a model for predicting the sentiment of Software as a Service consumers' reviews using a supervised learning machine called a support vector machine (SVM). The sentiment results show that 62% of the reviews are positive which indicates that consumers are most likely satisfied with SaaS services. The results show that the prediction accuracy of the SVM-based Binary Occurrence approach (3-fold crossvalidation testing) is 92.30%, indicating it performs better in determining sentiment compared with other approaches (Term Occurrences, TFIDF). This work also provides valuable insight into online SaaS reviews and offers the research community the first SaaS polarity dataset.

A cloud business environment comprises service providers and service consumers. Services are supplied through a Service Level Agreement (SLA) which defines all deliverables, commitments, obligations, QoS, violation penalties etc. that help a service provider and a service consumer to execute their business transactions. The primary aim of a service provider is to fulfill its commitment to a consumer by forming a viable SLA that wisely assigns the appropriate amount of resources to a requesting consumer. In this paper, we propose a viable SLA model that helps a service provider form a viable agreement with a consumer, based on its previous resource usage profile. The model uses a Fuzzy Inference System and takes the reliability and the contract duration of a consumer as input to calculate the suitability of this consumer, which is also used as input along with the risk propensity of a service provider to determine the amount of resources to offer to a consumer. We evaluate our approach and find that by using an optimized viable SLA model, providers are able to allocate an appropriate amount of resources to avoid an SLA violation.

There has been a dramatic increase in the sharing of opinions and information across different web platforms and social media, especially online product reviews. Cloud web portals, such as getApp.com, were designed to amalgamate cloud service information and to also examine how consumers evaluate their experience of using cloud computing products. The current literature shows the growing importance of online users' reviews, hence this study focuses on investigating consumers' feedback on Software-as-a- Service (SaaS) products by developing models to predict reviewers' attitudes. The goal of this paper is to develop prediction models to predict the sentiment of SaaS consumers' reviews (positive or negative). This research proposes five models that are based on five algorithms, the Support Vector Machine algorithm, Naive Bayes algorithm, Naive Bayes (Kernel) algorithm, k-nearest neighbors algorithm, and the decision tree algorithm to predict the attitude of SaaS reviews. The prediction accuracy of the space vector algorithm (5-fold cross-validation) is 92.37% which suggests that this algorithm is able to better determine the sentiment of online reviews compared with the other models. The results of this study provide valuable insight into online SaaS reviews and will assist in the design of SaaS review websites.

Service level agreement (SLA) is an essential agreement formed between a consumer and a provider in business activities. The SLA defines the business terms, objectives, obligations and commitment of both parties to a business activity, and in cloud computing it also defines a consumer's request for both fixed and variable resources, due to the elastic and dynamic nature of the cloud-computing environment. Providers need to thoroughly analyze such variability when forming SLAs to ensure they commit to the agreements with consumers and at the same time make the best use of available resources and obtain maximum returns. They can achieve this by entering into viable SLAs with consumers. A consumer's profile becomes a key element in determining the consumer's reliability, as a consumer who has previous service violation history is more likely to violate future service agreements; hence, a provider can avoid forming SLAs with such consumers. In this paper, we propose a novel optimal SLA formation architecture from the provider's perspective, enabling the provider to consider a consumer's reliability in committing to the SLA. We classify existing consumers into three categories based on their reliability or trustworthiness value and use that knowledge to ascertain whether to accept a consumer request for resource allocation, and then to determine the extent of the allocation. Our proposed architecture helps the service provider to monitor the behavior of service consumers in the post-interaction time phase and to use that information to form viable SLAs in the pre-interaction time phase to minimize service violations and penalties.

Software as a Service is the most adopted cloud service (46%) compared with Infrastructure as a Service (IaaS) (35%) and Platform as a Service (PaaS) (34%) [1]. Currently, the capability of discovering a SaaS of interest online across multiple cloud providers and reviews websites is a significant challenge, especially when using general search mechanisms (Google and Yahoo!) and search tools provided by existing reviews and directories. Discovering a SaaS is time-consuming, requiring consumers to browse several websites to select the appropriate service. This paper addresses the issues related to the efficient discovery of SaaS across review websites by developing the SaaS Nutch Hadoop-based Crawler Engine - SaaS Nhbased Crawler. The crawler is capable of crawling cloud reviews to find SaaSs of interest and enable the establishment of a central repository that could be used to discover SaaSs much more efficiently. The results show that the SaaS Nhbased crawler can effectively crawl review websites and provide a list of the latest SaaS being offered.

Due to the rapid increase in the use of social networking websites and applications, the need to stream video over wireless networks has increased. There are a number of considerations when transmitting streaming video between the nodes connected through wireless networks, such as throughput, the size of the multimedia file, response time, delay, scalability and loss of data. The scalability of ad-hoc networks needs to be analyzed by considering various aspects, such as self-organization, security, routing flexibility, availability of bandwidth, data distribution, Quality of Service, throughput, response time and efficiency. In this paper, we discuss the existing approaches to multimedia routing and transmission over wireless ad-hoc networks by considering scalability. The study draws several conclusions and makes recommendations for future directions.

In the recent past, semantic technologies have played an significant role in service retrieval and service querying. Annotating services semantically enables machines to understand the purpose of services and can further assist in intelligent and precise service retrieval, selection and composition. A key issue in semantically annotating services is the manual nature of service annotation. Manual service annotation requires a large amount of time and updating happens infrequently, hence annotations may get out-of-date due to service description changes. Although some researchers have studied semantic service annotation, they have only focused on web services not business service information. Moreover, their approaches are semi-automated, and still require service providers to select appropriate service annotations. In this paper, we propose a completely automated semantic annotation approach for e-services. The aim of this paper is to semantically annotate a service to relevant service concepts in domain-specific ontologies. Services and service concepts are represented by an extended VSM model, based on fuzzy rules. Then, we link a service to a concept, based on the similarity value of the representing vectors. We found during the experimentation process that the performances of the proposed approach and the VSM-based approach were quite similar and, as a result, developed a system to retrieve services that are annotated to relevant concepts. Experiments using a high service retrieval threshold demonstrated a retrieval approach based on extended VSM annotation performed much better than an approach based on VSM annotation.

A Service Level Agreement (SLA) is a contract between a service provider and a consumer which specifies in detail the level of service expected from the service provider, obligations, commitment and objectives. In the cloud computing environment, both the cloud provider and the cloud consumer want to know of a likely service violation before the actual violation occurs and to adjust the scaling of the cloud resources appropriately. A consumer's previous resource usage profile is a key element in determining the possibility of service violation in the cloud computing environment, which has not been an area of research focus so far. In this paper, we analyze and compare QoS prediction by considering the consumer's previous resource usage profile in various conditions. From comparative analysis, we observe that by combining a consumer's previous resource usage profile history along with the previous resource usage profile history of its nearest neighbors, we obtain an optimal result.

Cloud computing is a very attractive option for service users and service providers for their businesses because of the benefits it provides. A major concern among service users regarding cloud adoption, however, is the unpredictability of performance in relation to the services provided. Even though guarantees in the form of service-level agreements are provided to users by service providers, real-time service-level degradability remains a critical concern; hence, there is a need for an approach that assists users to manage a service before it fails. The approaches proposed in the literature assess and evaluate the performance of the cloud infrastructure of providers, but this does not guarantee that a given service instance will meet the desired quality level because there may be factors other than the provider's infrastructure that will affect the level of quality of the service instance. In this paper, we present an approach that measures the quality of a service instance in real time and provides important analysis for service users as to whether they will achieve their desired objectives. This analysis also constitutes an important input for service users in the assessment and management of a service to avoid the failure to achieve objectives.

Argumentation is the practice of systematic conscious reasoning involving the construction and evaluation of arguments to justify or support a particular conclusion. This article discusses, compares, contrasts and categorizes existing argumentation-based frameworks and applications as either philosophical or logic-based, and provides critical analysis that emphasizes the structure of arguments and the interactions between them. This review compares and contrasts the frameworks and applications of argumentation-based approaches on Web 2.0 and the Semantic Web, and subsequently highlights the importance and challenges of attaining monological argumentation on the Semantic Web.

Summary The demand of software as a service (SaaS)‐based services delivering computing resources as on‐demand software is on the rise in the IT industry. However, one of the drawbacks of the existing SaaS services is that they offer limited or no personalization of the services provided according to the users profile. Personalization as mentioned in the literature has been a key driver in the adoption and usage of various applications and in providing better service experience to the users. However, overwhelming majority of such personalized services rely extensively on the server side, without embracing fast‐developing client‐side technologies. In SaaS‐based cloud services, utilizing this technology is necessary considering their limited processing specifications. Approaches have been proposed in the literature that focus on cloud‐based personalization using client‐side technologies but none of them actually address all the different components that are required for a scalable and holistic personalization framework for SaaS‐based cloud services. In this paper, we address this drawback by proposing a user‐focussed personalization framework. Our proposed framework takes advantage of powerful client side browsers to reduce server overheads, ameliorate performance, establish high intelligence and enrich data processing. To validate and demonstrate the applicability of our framework, we build a prototype model and compare its performance against existing approaches using different metrics. Copyright © 2014 John Wiley & Sons, Ltd.

Summary Recent growth and advancements in the Semantic Web have shifted the research focus from being knowledge‐centered to data‐centered. This has led to the increased use of ontologies to structurally represent the data, thereby generating huge amounts of RDF data, which we term Big RDF Data. Nevertheless, the literature lacks the tools to analyze Big RDF Data and make sense of it. Access to such tools would enable pragmatic inputs and insights for users in respect of such tasks as the usage and adoption of Ontologies, their uptake by different users in the community, and the identification of prevalent patterns. This analysis, which we term Ontology Usage, is important from the viewpoint of users who need informed inputs in the various stages of the ontology engineering lifecycle, such as ontology evolution, ontology population, and ontology deployment. In this paper, we propose the Ontology USage Analysis F̌ramework (OUSAF), which performs analysis of Ontology Usage on Big RDF Data and synthesizes the usage knowledge acquired. OUSAF provides a methodological approach to performing the various phases such as identifying, analyzing, representing, and utilizing the Ontology usage results from Big RDF Data. We describe in detail each of those phases and the metrics required to perform the analysis of each phase. The utilization of the OUSAF results obtained by users such as data publishers and ontology developers is demonstrated by a dataset collected in the e‐business domain. Copyright © 2014 John Wiley & Sons, Ltd.

Trust modeling of both the interacting parties in a virtual world, is a critical element of business intelligence. A key aspect in trust modeling is to be able to accurately predict the future trust value of an interacting party. In this paper, we propose an intelligent method for predicting the future trust value of a trusted entity. We propose the use of Z-number to represent both the trust value and its corresponding reliability. Subsequently, we apply Artificial Neural Network (ANN) to predict future trust values. We generate a large number of synthetic time series, with a view to model real-world trust values of trusted entity. We validate the working of our methodology using the generated time series.

In today's highly dynamic economy and society, the performance evaluation of Decision Making Units (DMUs) is of high importance. This study presents an efficient model for analyzing the outputs of performance measurement methodologies by means of trust, which provides explicit qualitative scales instead of representing pure numerical data. The efficiency rate of the current, previous and coming years, as well as the average efficiency and standard deviation, are the five inputs for this model. These efficiency rates are calculated using Data Envelopment Analysis (DEA). The approach uses time series forecasting to predict the future efficiency rate. Furthermore, the implemented Auto Regressive (AR) model includes an Auto Correlation Function (ACF) for input selection. The model utilizes T-norms and S-norms as the final modeling tools. To illustrate the applicability of the proposed model, we apply it to a data set of DMUs. Ultimately, modified trust values for these DMUs are determined using the proposed approach.

With the advent of Cloud computing and subsequent big data, online decision makers usually find it difficult to make informed decisions because of the great amount of irrelevant, uncertain, or inaccurate information. In this paper, we explore the application of multicriteria decision-making (MCDM) techniques in the area of Cloud computing and big data, to find an efficient way of dealing with criteria relations and fuzzy knowledge based on a great deal of information. We propose a MCDM framework, which combines the ISM-based and ANP-based techniques, to model the interactive relations between evaluation criteria, and to handle data uncertainties. We present an application of Cloud service selection to prove the efficiency of the proposed framework, in which a user-oriented sigmoid utility function is designed to evaluate the performance of each criterion.

QoS-based service rating has made positive contributions to the area of service selection. Especially for Cloud service users, the right decision when choosing suitable Cloud services can help them improve user satisfaction and trading revenues. This work aims to address the issue of uncertainty in service requests, service descriptions, user and expert preferences, as well as evaluation criteria in a MCDM-based service selection procedure. A hybrid fuzzy framework for Cloud service selection is proposed, addressing the challenge using three approaches: a fuzzy-ontology-based approach for function matching and service filtering, a fuzzy AHP technique for informed criterion weighting, and, a fuzzy TOPSIS approach for service ranking.

SUMMARY In the recent past, there has been an exponential growth in Resource Description Framework data on the web known as web of data. The emergence of the web of data is transforming the existing web from a document‐sharing medium to a decentralized knowledge platform for publishing and sharing information between humans and computers. To enable common understanding between different users, domain ontologies are being developed and deployed to annotate information on the web. This semantically annotated information is then accessed by machines to extract and aggregate information, on the basis of the underlying ontologies used. To effectively and efficiently access data on the web, insight into the usage of ontology is pivotal, because this assists users in experiencing the benefits offered by the Semantic Web. However, such an approach has not been proposed in the literature. In this paper, we present a pragmatic approach to the analysis of domain ontology usage on the web. We propose metrics to measure the use of domain ontology constructs on the web from different aspects. To comprehensively understand the usage patterns of conceptual knowledge, instance data, and ontology co‐usability, we considered GoodRelations ontology as the domain ontology and built a dataset by collecting structured data from 211 web‐based data sources that have published information using the domain ontology. The dataset is analyzed by using the proposed metrics and observations along with their usability and applicability to the different users of the Semantic Web. Copyright © 2013 John Wiley & Sons, Ltd.

Smart grids have created an emerging entity of “prosumer” in the energy value network who not only consumes energy but also generates and shares the green energy with the utility grid. Hence, effective management of prosumers has become pivotal to ensure a long-term, sustainable energy-sharing process. Recently, the concept of a Prosumer Community Group (PCG) has emerged as one of the most promising and effective ways to manage prosumers. However, developing sustainable PCGs is challenging. One of the key challenges in this regard is to assess the contribution made by individual prosumers of a PCG, and find a subset of the most influential prosumers whose behavior would facilitate the long-term sustainability of the PCG. In this paper, we have focused on this challenge and proposed an innovative methodology to assess and rank the prosumers, in order to build an influential membership base. We have assessed the long-term and short-term energy behaviors of prosumers based on multiple evaluation criteria and accordingly decided the ranks of the prosumers, whereby the higher ranked prosumers are deemed to be more influential in enhancing the long-term sustenance of the PCG. Furthermore, we have presented simulation results to verify our proposed methodology. The current literature on smart-grid research field has no work investigating this challenge, making our contribution novel.

The growing number of cloud services have made service selection a challenging decision-making problem by providing wide ranging choices for cloud service consumers. This necessitates the use of formal decision making methodologies to assist a decision maker in selecting the service that best fulfils the user's requirements. In this paper, we present a cloud service selection methodology that utilizes QoS history over different time periods, performs Multi-Criteria Decision Analysis to rank all cloud services in each time period in accordance with user preferences before aggregating the results to determine the overall service rank of all the available services for cloud service selection.

A decade-long conscious effort by the Semantic Web community has resulted in the formation of a decentralized knowledge platform which enables data interoperability at a syntactic and semantic level. For information interoperability, at a syntactic level, RDF provides the standard format for publishing data and RDFS gives structure to the information. For semantic-level interoperability, ontologies are used which allow information dissemination and assimilation among diverse applications and systems; where information is equally accessible and useful to humans and machines. The success of the linked open data project, recognition of explicit semantics (annotated through web ontologies) by search engines and the realized potential advantages of semantic data for publishers have resulted in tremendous growth in the use of web ontologies on the web. In order to promote the adoption of ontologies (to new users), reusability of adopted ontologies, effective and efficient utilization on ontological knowledge and evolving the ontological model, erudite insight on the usage of ontologies is imperative. While ontology evaluation attempts to evaluate a developed ontology to assess its fitness and quality, it does not provide any insight into how ontologies are being used and what is the state of prevalent knowledge patterns. Realizing the importance of measuring and analysing ontology usage to advance the adoption, reusability and exploitation of ontologies, we present a semantic framework for measuring and analysing ontology usage on the Web on empirical grounding. Our methodological approach is discussed to highlight the detail and role of each step. A framework is presented along with the set of metrics developed to measure ontology usage from different aspects such as ontology richness, usage and incentives to provide a holistic view on the state of ontology usage. The framework is then evaluated using an important use-case scenario to identify the prevalent knowledge patterns in order to rank the terminological knowledge for annotating the information.

The increasing popularity of the cloud computing paradigm and the emerging concept of federated cloud computing have motivated research efforts towards intelligent cloud service selection aimed at developing techniques for enabling the cloud users to gain maximum benefit from cloud computing by selecting services which provide optimal performance at lowest possible cost. Given the intricate and heterogeneous nature of current clouds, the cloud service selection process is, in effect, a multi criteria optimization or decision-making problem. The possible criteria for this process are related to both functional and nonfunctional attributes of cloud services. In this context, the two major issues are: (1) choice of a criteria-set and (2) mechanisms for the assessment of cloud services against each criterion for thorough continuous cloud service monitoring. In this paper, we focus on the issue of cloud service monitoring wherein the existing monitoring and assessment mechanisms are entirely dependent on various benchmark tests which, however, are unable to accurately determine or reliably predict the performance of actual cloud applications under a real workload. We discuss the recent research aimed at achieving this objective and propose a novel user-feedback-based approach which can monitor cloud performance more reliably and accurately as compared with the existing mechanisms.

What makes some students failed to perform well in their study is lack of talent and interest to the chosen of field of study. For example in Indonesia, there are around 2, 785 senior high school students failed in the National Examination in 2010 because most of them choose unappropriate field of study which is not related to interest and talent. It is important to assist students to choose a potential area of study commensurate with their talents and interests and which covers all possible fields of study. To achieve that aim, standard to represents knowledge as a set of concepts is needed. This paper proposes an ontological framework to assist students to recognize the prospective fields of study related to their talent and interest. The framework is including two ontologies with different perspectives which will be linked using matching engine to get the possible field of study. Then, selection engine is to be used to get the final result of the appropriate field of study for student. This framework can be applied in educational field to improve student's capacity and to help them in maintain their future life.

Smart Grid (SG) achieves bidirectional energy and information flow between the energy user and the utility grid, allowing energy users not only to consume energy, but also to generate the energy and share the excess energy with the utility grid or with other energy consumers. This type of energy user is called the “prosumer”. In current society, a massive number of energy-users have transformed into prosumers due to many reasons such as the strong society attitude with respect to alleviation of negative climate impacts, desires to decrease electricity costs, and various government regulations, including generous feed-in tariff schemes. This leads much attention within the research community on investigating the aspects of prosumers connected to SG. However most researchers find it challenges to find a large dataset of prosumers for performing the experiments. This leads the necessity of identifying the generic prosumers' realistic energy behaviors, and accordingly generates a synthetic dataset. In this research paper, we present prosumers' realistic energy behavior profiles during summer and winter periods in Australia and present its application in generating a synthetic dataset. The new researchers can use the identified energy profiles as a benchmark to generate a synthetic dataset for their experiments.

Cyber-Physical Systems (CPS) provides a smart infrastructure connecting abstract computational artifacts with the physical world. This paper presents some challenges for developing distributed real-time Cyber-Physical Systems. The focus is on one particular challenge, namely event modelling in distributed real-time CPS. A Web-of-Things based CPS framework for event handling and processing is proposed. To illustrate the application of the proposed framework, a case study for achieving demand response in a smart home is provided.

Due to the rapid growth of wireless applications, Cognitive Radio (CR) has been considered as a technology to solve spectrum source deficiency by improving effective utilization of limited radio spectrum resources for future wireless communications and mobile computing. However, the unique characteristics of CRNs make security a greater challenge. Moreover, due to the dynamic characteristics of CRNs, a member of CRNs, may join or leave the network at any time. The issue of supporting secure communication in CRNs therefore becomes more serious than for conventional wireless networks. Public key encryption and signature techniques have been adopted here to ensure the security of message transmission in CRNs. This work proposes a digital signature-based trust-oriented scheme to ensure communication by identifying efficient trustworthy users in CRNs. The security analysis is analyzed to guarantee that the proposed approach achieves security proof.

Cloud computing is a new paradigm for service-based computing and is gaining popularity. An efficient way for the assurances of the expected service levels in cloud computing is to establish a tailor-made Service Level Agreement (SLA) and to ensure the commitment of SLAs by service providers. In this paper, we conduct a survey of the state of the art in cloud SLA assurance from two aspects -- pre- and post-interaction phases, based on which research gaps in existing approaches are identified. New research requirements for SLA assurance are then presented.

In recent years, there has been a tremendous growth in Semantic Web data on the Web being annotated using Web ontologies. The use of Web ontologies by different data publishers is transforming the Web into a decentralized knowledge platform. To capitalize on structured and semantically rich data, we need to understand how these ontologies are being used. In this paper, to analyse the usage of ontologies by data publishers, we model ontology usage as an Ontology Usage Network. The Ontology Usage Network, which is a bipartite affiliation network, is used to study statistical and structural properties such as degree distribution, centrality measures and identification of cohesive subgroups. Finally, we present the analysis results and their interpretation.

Recently, there has been much research focus on trust and reputation modelling as one of the key strategies for the formation of successful business intelligence strategies, particularly for service in mobile applications. One of the key trust modelling activities is trust prediction. During this process, the accuracy and reliability of the predicted trust values play an important role in the making of informed business decisions. Key factors to be considered at this stage are the variability and the high levels of distortion in the input series that have to be captured when predicting the trust values at a point in time in the future. In this paper, we propose a Multi-layer Feed Forward Artificial Neural Network to predict the future trust values of entities (services, agents, products etc.) for a future point in time based on data series input. We use four different non-uniform’ data input series and measure the accuracy of the predicted values under different experimental scenarios for benchmarking and comparison with existing approaches. Results indicate that the model is reliable in predicting trust values even in scenarios where there are only limited data available on training the neural network and a high level of distortion is present in the input series.

In a recent decade many universities responded to challenges of the internet penetration into the society and economics by simply adding computerized facilities to their existing curriculum services as their e-learning strategy [3] so that the traditional teaching and learning model could be preserved. This e-learning strategy deployment is now being challenged by the emergence of Social Networking System/Site (SNS). In order to evaluate how SNS would have affected current Higher Education System (HES), one needs to look into the inner working of value exchange within a broader societal community to extract relational interactions among its participating components (entities), and substantiate what had been challenged internally of a community to prepare for the external intrusion of SNS in a foreseeable future. In this paper, a triple-entity learning community framework is proposed with its Core Value that glues the participating entities together (Figure 5). Prior to this framework, graduate's employability issues as part of the Core Value are brought to the surface to help educators revise their existing e-learning strategies, so that curriculum content providing educational resources to its clients will be serviced in a more timely and responsive manner.

This paper presents a proposal for the development of an ontology evolution strategy which refines ontological relations in scientific ontologies. In addition to experts' consensus, it is desirable to define ontological relations between any two concepts in a scientific ontology based on scientific evidence. To address this issue, we can relate ontological relations to different research results obtained from various studies. To implement this solution, our envisaged evidence/discovery-based methodology integrates a higher-level ontology (systematic review ontology) into a systematic review agent which employs a Fuzzy Inference System in order to automatically modify ontological relations of a domain ontology based on the evidence received from information resources. The evidence/discovery-based methodology will further use the domain ontology to discover novel connections between distinct literatures, thereby, enrich its conceptualization.

The Digital Business Ecosystem (DBE) is the result of the co-evolution of the Business Ecosystem and the Digital Ecosystem. There are numerous approaches and enabling technologies which are used in modeling open business marketplaces and, due to the similarities between the Digital Business environments, they can also help to enable the Digital Business Ecosystem but with some limitations. The complete lifecycle of the DBE can be decomposed into the following phases: formation, evolution and dissipation. In this work, our main focus is on the importance of negotiation in the DBE formation phase and especially on the structure of Contract Net Protocol. We will present an extension to the primitive Contract Net Protocol and name it Contract Net with Quality Protocol (CNQP or Q-Contract Net) to facilitate the negotiation process by adding the quality evaluation steps during the negotiation phase of the DBE formation.

Risk assessment in business interactions is carried out to determine beforehand the occurrence of undesirable events and their associated consequences. In the literature, approaches have been proposed by which an interaction initiating agent can ascertain the occurrence of undesirable event/s and determine their consequences in an interaction. But those approaches just consider those events that are related to the performance of the other agent, with whom the interaction initiating agent is forming an interaction. It is possible that there may also be such events that are not dependent on the other agent's performance, but will directly or indirectly have an impact on the successful completion of the business interaction. In this paper, we will highlight the importance of considering such event/s during the process of risk assessment, and propose a methodology by which the interaction initiating agent can determine and quantify their effect on the successful completion of its business interaction.

In a business interaction, transactional risk highlights the uncertainty associated in not achieving the desired outcomes. The assessment of transactional risk gives the interacting user the different levels of failure in achieving its desired outcomes and the consequences that it can experience. In a business interaction, the consequences that can be experienced pertain to the financial resources invested to achieve the desired outcomes. The level of financial loss that could be experienced plays a very important role in the interacting userpsilas decision to form a business interaction. The level of financial loss is dependent on the different types of uncertain events associated with the business interaction. In this paper, we will propose a methodology by which the interacting user in an e-business interaction can capture the different types of uncertainties and ascertain the financial risk that could be experienced from it.

To ascertain the possible level of risk in a digital business ecosystem interaction, the initiating agent has to determine beforehand the probability of failure, the possible consequences of failure, and the loss of investment probability to its resources while interacting with the other agent. Out of these three constituents, the initiating agent can determine beforehand the probability of failure in interacting with an agent either by considering its past interaction history with it or by soliciting recommendations from other agents. In both cases, it is imperative for the agent who is either considering its past interaction history, or who is communicating a recommendation about the other agent, to know the accurate level of failure in interacting with the other agent. To achieve this, in this paper we propose a methodology by which the initiating agent of the interaction ascertains the level of failure in the interaction, after interacting with an agent.

In this paper we present an overview of the definitions of the terms of trust and reputation from the literature. Trust and reputation have been defined in different ways by the various researchers. As a result of these various definitions of trust and reputation there is a lot of confusion regarding what these terms actually mean. Additionally in the literature there is no work towards collecting all the definitions of trust and reputation. In this paper we discuss and present an overview of the terms of trust and reputation from the literature.

Due to technological advancement of the Internet, conducting e-commerce transactions have become a part of our daily lives. In a financial interaction to be carried over the digital business ecosystem domain, it is rational for an agent instigating the interaction to analyse beforehand the possible risk in interacting with any other agent. Doing so would give the instigating agent an idea of direction in which its interaction might head and also help it to make an informed decision of its future course of action with that particular agent. For risk analysis, the instigating agent has to determine beforehand the probability of failure and the possible consequences of failure in interacting with an agent. In this paper, we propose such a methodology by which the instigating agent quantifies the probability of failure beforehand in interacting with an agent according to the demand of its future interaction with it.

The trusting peer in order to determine the likelihood of the loss in its resources might analyze the Risk before engaging in an interaction with any trusted peer. This likelihood of the loss in the resources is termed as Risk in the interaction. Risk analysis is important in e-commerce transactions because of the vast literature that argues that the decision to buy is based on the Risk-adjusted cost-benefit analysis. If the trusting peer can determine the future Riskiness value or reputation of a trusted peer for the time period of its interaction, before engaging in an activity with it, then it can ease its decision making process of whether to interact with the trusted peer or not. In this paper we present such a novel method which predicts the dynamic nature of Risk and determines the future Riskiness value of the trusted peer, before the interaction starts, thus helping the trusting peer considerably in making its decision. © 2006 IEEE.

As there is a lack of central management in an e-commerce interaction carried out based on peer-to-peer architecture, it is obvious for the trusting peer to analyze the risk beforehand that could be involved in dealing with a trusted peer in these types of interactions. Another characteristic of peer-to-peer architecture interactions is that the trusting peer might have to choose a peer to interact with, from a set of possible trusted peers. It can ease its decision making process of choosing a peer to interact with by analyzing the risk that could be involved in dealing with each of the possible trusted peers. In this paper we highlight and propose a solution to this problem by which the trusting peer can decide with which peer to interact with after analyzing the risk that could be associated in dealing with each of them