Search

The rapid, increasing adoption of businesses to deliver their services in Software as a Service (SaaS) products in the marketplace presents selection challenges to users. Recently, major cloud service providers such as Amazon Web Services and Microsoft Azure have introduced well-architected frameworks that assess SaaS products in different pillars (also referred to herein as features). Furthermore, customers leave feedback on these features after using SaaS products. However, they do not provide feedback on all the features of a product, which renders the reviews unusable to prospective users needing to assess a product's quality before committing to it. Our study addresses this drawback by imputing or inferring the intensity of the customer's feedback on features that they do not mention in their reviews. Specifically, we propose threshold-based nearest neighbors (T-NN) as an extension of the conventional k-nearest neighbor approach to determine the missing sentiment intensity score of a feature from the values of its other features. We evaluate the proposed approach in two different systems and compare our results with seven other data imputation techniques. The results show that the proposed T-NN approach performs better than the other imputation approaches on the SaaS sentiment dataset. [ABSTRACT FROM AUTHOR]

Blockchain, with its ever-increasing maturity and popularity, is being used in many different applied computing domains. To document the advancements made, researchers have conducted surveys on blockchain from many different viewpoints. However, one perspective which is missing from such surveys is how to assess the authenticity of subjective information and consider this in the processing of blockchain. The goal of this article is to highlight this gap as an open issue. We do this by surveying articles, both from the academic and grey literature and propose a taxonomy to classify the literature as focusing on either the inherent or add-on characteristics of a blockchain. We then focus on those works that aim to build authenticity in the application of blockchains and determine if they address the gap of considering subjective information in their analysis. Based on our findings from the survey, we propose future research directions in this area which are essential to achieve blockchain's envisaged view of it being the single source of truth for all types of information. [ABSTRACT FROM AUTHOR]

Developing an intelligent chatbot has evolved in the last few years to become a trending topic in the area of computer science. However, a chatbot often fails to understand the user's intent, which can lead to the generation of inappropriate responses that cause dialogue breakdown and user dissatisfaction. Detecting the dialogue breakdown is essential to improve the performance of the chatbot and increase user satisfaction. Recent approaches have focused on modeling conversation breakdown using serveral approaches, including supervised and unsupervised approaches. Unsupervised approach relay heavy datasets, which make it challenging to apply it to the breakdown task. Another challenge facing predicting breakdown in conversation is the bias of human annotation for the dataset and the handling process for the breakdown. To tackle this challenge, we have developed a supervised ensemble automated approach that measures Chatbot Quality of Service (CQoS) based on dialogue breakdown. The proposed approach is able to label the datasets based on sentiment considering the context of the conversion to predict the breakdown. In this paper we aim to detect the affect of sentiment change of each speaker in a conversation. Furthermore, we use the supervised ensemble model to measure the CQoS based on breakdown. Then we handle this problem by using a hand-over mechanism that transfers the user to a live agent. Based on this idea, we perform several experiments across several datasets and state-of-the-art models, and we find that using sentiment as a trigger for breakdown outperforms human annotation. Overall, we infer that knowledge acquired from the supervised ensemble model can indeed help to measure CQoS based on detecting the breakdown in conversation. [ABSTRACT FROM AUTHOR]

Evaluating the innovation of a new idea before its implementation is a complicated but important phenomenon as it plays a critical role in the success of a product. The literature widely uses sentiment analysis as a technique for product designers to ascertain users' opinion toward an idea before its implementation. However, that technique focuses only on determining the opinion of users studied. It does not assist designers in providing insights in terms of what needs to be done to propagate the popularity of the idea further to ensure its success. One framework by which this can be done is by considering social network structure and representing users as nodes of that network. In this paper, we investigate how a social network structure can be used to influence a user's opinion among the society. Our proposed framework consists of four main components, namely data collection, sentiment extraction, budget approximation and presentation. After gathering customers' comments in the data collection phase, the opinion of users who have expressed it is analyzed in the sentiment analysis phase. The budget approximation component then determines the cost of spreading positive opinion among the network of users, including those who have not given it. For that, influence maximization is used to compare the cost of convergence of the general opinion of society in the direction of innovation. In presentation component, the comparative information will be used by product designers to assist them in determining the viability of selecting an idea for implementation. The simulation results show that the network structure and the individuals' positions are important factors in the acceptance of an innovation by society. This framework can be used to compare different innovative ideas and provide decision makers in organizations with informative reports as decision support materials. [ABSTRACT FROM AUTHOR]

In this paper, an enhanced quantum-based neural network learning algorithm (EQNN-S) which constructs a neural network architecture using the quantum computing concept is proposed for signature verification. The quantum computing concept is used to decide the connection weights and threshold of neurons. A boundary threshold parameter is introduced to optimally determine the neuron threshold. This parameter uses min, max function to decide threshold, which assists efficient learning. A manually prepared signature dataset is used to test the performance of the proposed algorithm. To uniquely identify the signature, several novel features are selected such as the number of loops present in the signature, the boundary calculation, the number of vertical and horizontal dense patches, and the angle measurement. A total of 45 features are extracted from each signature. The performance of the proposed algorithm is evaluated by rigorous training and testing with these signatures using partitions of 60–40 and 70–30%, and a tenfold cross-validation. To compare the results derived from the proposed quantum neural network, the same dataset is tested on support vector machine, multilayer perceptron, back propagation neural network, and Naive Bayes. The performance of the proposed algorithm is found better when compared with the above methods, and the results verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The growth and adoption of the Internet of Things (IoT) is increasing day by day. The large number of IoT devices increases the risk of security threats such as (but not limited to) viruses or cyber-attacks. One possible approach to achieve IoT security is to enable a trustworthy IoT environment in IoT wherein the interactions are based on the trust value of the communicating nodes. Trust management and trust assessment has been extensively studied in distributed networks in general and the IoT in particular, but there are still outstanding pressing issues such as bad-mouthing of trust values which prevent them from being used in practical IoT applications. Furthermore, there is no research in ensuring that the developed IoT trust solutions are scalable across billions of IoT nodes. To address the above-mentioned issues, we propose a methodology for scalable trust management solution in the IoT. The methodology addresses practical and pressing issues related to IoT trust management such as trust-based IoT clustering, intelligent methods for countering bad-mouthing attacks on trust systems, issues of memory-efficient trust computation and trust-based migration of IoT nodes from one cluster to another. Experimental results demonstrate the effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

Health, safety, environment and ergonomics (HSEE) are important factors for any organization. In fact, organizations always have to assess their 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 undertaking this process. The fuzzy cognitive map (FCM) method is used for constructing graphical models of BN to ascertain the relationships between the inputs and the impact which they will have on the quantified HSEE. Using the notion of Fuzzy logic assists us to work with humans and their linguistic inputs in the process of experts’ opinion solicitation. The noisy-OR method and the EM are used to ascertain the conditional probability between the inputs and quantifying the HSEE value. Using this, we find out that the most influential input factor on HSEE quantification which can then be managed for improving an organization’s compliance to HSEE. Finding the same influential input factor in both BN models which are based on the noisy-OR method and EM demonstrate how FCM is useful in constructing a reliable BN model. Leveraging the power of Bayesian network in modelling HSEE and augmenting it with FCM is the main contribution of this research work which opens the new line of research in the area of HSE management. [ABSTRACT FROM AUTHOR]

Although we are living in the era of big data, in many real-world applications, being able to access the right set and quantity of data is still a challenging task. One solution to address this drawback is to transform the existing information and knowledge from its tacit form back to data which can be used to simulate and regenerate the required knowledge in different scenarios for further analysis in explicit form. In this paper, we present our developed fuzzy inference-based learning system to achieve this objective. Our proposed framework is based on both conventional fuzzy-based modelling and the adaptive network-based fuzzy inference system (ANFIS) that first transforms the existing tacit information and knowledge into a fuzzy form which is then fed into ANFIS to develop a trained model that regenerates them for analysis purposes. We validate our proposed model and demonstrate its accuracy to estimate the fuel efficiency of heavy duty trucks using real-world data. [ABSTRACT FROM AUTHOR]

This paper presents an integrated algorithm based on fuzzy simulation, fuzzy linear programming (FLP), and fuzzy data envelopment analysis (FDEA) to cope with a special case of workshop facility layout design problem with ambiguous environmental and health indicators. First a software package is used for generating feasible layout alternatives and then quantitative performance indicators are calculated. Weights are estimated by LP for pairwise comparisons (by linguistic terms) in evaluating certain qualitative performance indicators. Fuzzy simulation is then employed for modeling different layout alternatives with uncertain parameters. Next, the impacts of environment and health indicators are retrieved from a standard questionnaire. Finally, FDEA is used for ranking the alternatives and consequently finding the optimal layout design alternatives. A possibilistic programming approach is used to modify the fuzzy DEA model to an equivalent crisp one. Moreover, fuzzy principal component analysis method is used to validate the results of FDEA model at various α-cut levels by Spearman correlation experiment. This is the first study that presents an integrated algorithm for optimization of facility layout with environmental and health indicators. [ABSTRACT FROM AUTHOR]

In today's digital world, information can very easily be accessed and digitally processed anywhere. Devices which are capable of processing digital data range from desktop computers to laptops, mobile phones, tablets, and personal digital assistants. For effective communication, text on a Web site should catch a reader's attention and should be easy to both read and understand. Different constraints are associated with on-screen text readability and legibility, such as font size, color, and style, as well as foreground and background color contrast, line spacing, text congestion, vocabulary and grammar, but text recognition and comprehension are two of the major problems. In this study, we address the issue of how to enhance text readability for non-native English speakers who have a basic understanding of English language and speak local languages which are not formally taught in academia. We select a use case in Pakistan, a country in which English and Urdu are the official languages, and a number of local languages are spoken in different parts of the country. Due to the wide variety of local languages, no Web site can support the many local language scripts or alphabets and display them on digital devices. When users with only a basic knowledge of English-particularly low-literate users from a local language background-try to read an English text, it is highly challenging for them to understand the meaning of words. In this study, we propose a plain language scheme in which a text is converted into a roman text. A roman text is formed by using the English alphabet and combining letters in such a way that when it is read, it sounds like a local language. To evaluate the applicability of our approach, we conducted a survey of users from different educational backgrounds, using a text written in English, local and plain language from users who speak particular local language. For each survey, we took three to four paragraphs in English on general interest topics and translated it into local language and plain language. To measure the acceptability of each approach, we used five usability engineering attributes as a benchmark-efficiency, effectiveness, learnability, memorability, and satisfaction. From the results of the analysis, we observe that our proposed plain language scheme is more efficient, effective, learnable and memorable, and achieves a higher satisfaction level for low-literate users than two other languages. [ABSTRACT FROM AUTHOR]

Cloud computing is a new computing paradigm in which virtualized hardware and software resources are provided to the users over the Internet as services with pay-as-you-go like pricing mechanisms. This enables the cloud users to fulfil their IT requirements by using virtualized computing resources, located at a cloud service provider, as cloud services over the Internet instead of establishing an in-house computing infrastructure of their own. This is beneficial for the users as they only have to pay for the resources which they are actually using rather than paying for the entire cost of hardware and software, as is the case in other computing paradigms. However, to ensure that users' achieve their required outcomes, monitoring and managing the QoS of the cloud service they are receiving is a very important aspect. This is different from monitoring and managing the QoS of the cloud service at the platform side which is done by service providers. In this paper, we propose and demonstrate the working of an approach that enables users to forecast and appropriately manage the cloud service based on the QoS they are receiving at their end. [ABSTRACT FROM AUTHOR]

The growing number of cloud services has made service selection a challenging decision-making problem by offering 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 fulfills the user's requirements. In this paper, we present a cloud service selection methodology that utilizes quality of service history of cloud services over different time periods and performs parallel 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 rank of all the available options for cloud service selection. This methodology assists the cloud service user to select the best possible available service according to the requirements. The multi-criteria decision making processes used for each time period are independent of the other time periods and are executed in parallel. [ABSTRACT FROM AUTHOR]

In this study, an analysis was conducted for the relationships between the main components of customer relationship management (CRM) and customer complaints in the domain of logistics and transport. Today, complaints and the handling of complaints play a pivotal role in customer relationships. Moreover, companies are reluctant to admit that they have difficulties with customers' complaints, but as yet there appears to be no complete solution to this issue. To remedy this situation, customer complaints must be comprehensively collected and analysed. Issues must be classified, and timely solutions must be developed. In this paper, a conceptual framework is proposed including mathematical models, hypothesised relationships, perceived value and interactivity between customer, business and the system, as well as customer satisfaction analytics. The framework will address the relationship between customer satisfaction issues, loyalty and customer acquisition and estimate customer satisfaction and loyalty. For the purpose of analysis, this study uses both qualitative and quantitative approaches. For data collection, a survey questionnaire was distributed to 60 Fremantle Port logistics and transport customers. For the quantitative approach, linear and nonlinear modelling is adopted. Using the model, we are able to address the shortcomings of CRM technology, and tackle the issues of loyalty improvement and customer acquisition. Finally, based on nonlinear modelling and using a fuzzy inference system, namely the Takagi-Sugeno-type approach, we defined fuzzy rules, by means of which we ascertain the relationship between customer satisfaction and the main relevant variables. [ABSTRACT FROM AUTHOR]

In cloud computing, service providers offer cost-effective and on-demand IT services to service users on the basis of Service Level Agreements (SLAs). However the effective management of SLAs in cloud computing is essential for the service users to ensure that they achieve the desired outcomes from the formed service. In this paper, we introduce a SLA management framework that will enable service users to select the best available service provider on the basis of its reputation and then monitor the run time performance of the service provider to determine whether or not it will fulfill its promise defined in the SLA. Such analysis will assist the service user to make an informed decision about the continuation of service with the service provider. [ABSTRACT FROM AUTHOR]

This special issue is devoted to recent research findings in the field of Cyber Physical Systems. The special issue follows 'The IEEE 26th International Conference on Advanced Information Networking and Applications (AINA-2012)', held at the Fukuoka Institute of Technology, Fukuoka, Japan, March 26-29, 2012. [ABSTRACT FROM AUTHOR]

With the rapid growth of wireless communication, the deployment of cyber-physical system (CPS) is increasing day by day. As a cyber physical system involves a tight coupling between the physical and computational components, it is critical to ensure that the system, apart from being secure, is available for both the cyber and physical processes. Traditional methods have generally been employed to defend an infrastructure system against physical threats. However, this does not guarantee that the availability of the system will always be high. In this paper, we propose a multi-cyber (computational unit) framework to improve the availability of CPS based on Markov model. We evaluate the effectiveness of our proposed framework in terms of availability, downtime, downtime cost and reliability of the CPS framework. [ABSTRACT FROM AUTHOR]

The availability of integrated, high quality information is a pre-requisite for a decision support system (DSS) to aid in the decision-making process. The introduction of semantic web ensures the seamless integration of information derived from diverse sources and transforms the DSS to an adoptable and flexible Semantic Web-DSS (Web-DSS). However, due to the monotonic nature of the layered development of semantic web, it lacks the capability to represent, reason and integrate incomplete and conflicting information. This, in turn, renders an enterprise incapable of knowledge integration; that is, integration of information about a subject that could potentially be incomplete, inconsistent and distributed among different Web-DSS within or across enterprises. In this article, we address the issues of incomplete and inconsistent semantic information and knowledge integration by using argumentation and argumentation schemes. We discuss the Argumentation-enabled Information Integration Web-DSS (Web@IDSS) along with its syntax and semantics for semantic information integration, and devise a methodology for sharing the results of Web@IDSS in Argument Interchange Format (AIF) format. We also discuss Argumentation-enabled Knowledge Integration Web-DSS (Web@KIDSS) for semantic knowledge integration. We provide formal syntax and semantics for the Web@KIDSS, propose a conceptual framework, and describe it in detail. We present the algorithms for knowledge integration and the prototype application for validation of results. [ABSTRACT FROM AUTHOR]

Personalized recommendation has become a pivotal aspect of online marketing and e-commerce as a means of overcoming the information overload problem. There are several recommendation techniques but collaborative recommendation is the most effective and widely used technique. It relies on either item-based or user-based nearest neighborhood algorithms which utilize some kind of similarity measure to assess the similarity between different users or items for generating the recommendations. In this paper, we present a new similarity measure which is based on rating frequency and compare its performance with the current most commonly used similarity measures. The applicability and use of this similarity measure from the perspective of multimedia content recommendation is presented and discussed. [ABSTRACT FROM AUTHOR]

In Demand-driven Production with Just-in-Time inputs, there are several sources of uncertainty which impact on the manufacturer's ability to meet the required customer's demand within the given time frame. This can result in a loss of revenue and customers, which will have undesirable impacts on the financial aspects and on the viability of the manufacturer. Hence, a key concern for manufacturers in just-in-time production is to determine whether they can meet a specific level of demand within a given time frame, to meet the customers' orders and also to achieve the required revenue target for that period of time. In this paper, we propose a methodology by which a manufacturer can ascertain the probability of not meeting the required demand within a given period by considering the uncertainties in the availability of production units and raw materials, and the loss of financial revenue that it would experience as a result. [ABSTRACT FROM AUTHOR]

Credit scoring computation essentially involves taking into account various financial factors and the previous behavior of the credit requesting person. There is a strong degree of correlation between the compliance level and the credit score of a given entity. The concept of trust has been widely used and applied in the existing literature to determine the compliance level of an entity. However it has not been studied in the context of credit scoring literature. In order to address this shortcoming, in this paper we propose a six-step bio-inspired methodology for trust-based credit lending decisions by credit institutions. The proposed methodology makes use of an artificial neural network-based model to classify the (potential) customers into various categories. To show the applicability and superiority of the proposed algorithm, it is applied to a credit-card dataset obtained from the UCI repository. Due to the varying spectrum of trust levels, we are able to solve the problem of binary credit lending decisions. A trust-based credit scoring approach allows the financial institutions to grant credit-based on the level of trust in potential customers. [ABSTRACT FROM AUTHOR]

The modelling and management of trust between interacting parties are crucial parts of the overall business intelligence strategy for any organization. Predicting trust values is a key element of modelling and managing trust. It is of critical importance when the interaction is to be conducted at a future point in time. In the existing body of work, there are a few approaches for predicting trust. However, none of these approaches proposes a framework or methodology by which the predicted trust value can be considered in light of its accuracy or confidence level. This is a key element in order to ensure optimized trust prediction. In this paper, we propose a methodology to address this critical issue. The methodology comprises a suite of metrics-maturity, distance and density (MD) which are capable of capturing various aspects of the confidence level in the predicted trust value. The proposed methodology is exemplified with the help of case studies. [ABSTRACT FROM AUTHOR]