VORDi*

Cloud computing services mature both economically and technologically and play a more and more extensive role in the domain of software and information systems engineering. SaaS offers advantage for both service providers and consumers. SaaS is faced with the question of appropriate techniques applying at early phase of Requirements engineering of producing system. The paper highlights two traditional methods namely i* and VORD belonging respectively to Goal oriented Requirements Engineering and Viewpoints approaches. The approach proposed try to dealing with the requirements elicitation in the context of Software-as-a-service SaaS. So, the approach benefits from strengths of both VORD and i* models and propose a combination of them in a new approach namely VORDi*.

Effect of Change Agent’s Leadership style on Successful ERP Implementation and Firm Performance Empirical Evidence

The study aims to measure Change Agent’s Leadership style on successful ERP Implementation and Organizational Performance. The data was collected through a self-administered questionnaire from 290 employees working in 14 knowledge-based companies in United Arab Emirates with a response rate of 69.04%. The study uses cross sectional research design with snowball sampling method and data were collected using online survey method. Some of the findings include, all the three leadership styles (transformational, transactional, and laissez-faire) significantly contribute to ERP implementation success and in turn impacts Firm Performance. Transformational leadership style of change agent is found to have highest impact on Firm Performance with ERP implementation acting as a partial mediator. Present study opened the doors by linking leadership style with ERP implementation towards multidimensionality of change agent’s reach not being limited to some aspects. Practitioners can use the insights in understanding the impact of change agent’s deployment in organization.

Implementation of enterprise resource planning (ERP) systems in the gig economy- Revolutionizing the digital transformation

Gig economy has played a significant role in the country's economic development and has led to the growth in the employment of the people worldwide by supplementing the primary income of the people. With the security and autonomy that the gig sector promises, people choose to work as gig workers rather than traditional workers. Almost every company uses an enterprise resource planning system (ERPs) to some extent or the other to improve its performance and competitiveness. This paper devises a conceptual model describing how ERP systems help improve the human resource management of the gig workers, maintain customer relations, and bring digital transformation to its business. The research model would provide an understanding of diagnosing how the ERP system can help improve the conditions of the gig workers and the potential problems faced by them in the areas where the ERP system is not working efficiently. The framework would provide insights in simplifying the implementation of ERP in the gig sector that would be useful in the future.

Service Design as a Catalyst for Patient-Centered eHealth Innovation

Today's healthcare industry is confronted with a myriad of challenges amidst emerging trends and opportunities which trigger a paradigm shift in healthcare design from stand-alone products to holistic services. These three dimensions are critical in assessing and managing healthcare, particularly in underserved settings. This study aims to maximize opportunities presented by both design and information and communication technologies to enhance the implementation of integrated people-centered health services. It is a qualitative study conducted across six government health facilities within Nairobi slums in Kenya as a case study of maternal health information services. Co-design-oriented service design research strategy is employed while a representative sample of (n=47) participants is drawn from different stakeholders in the public health sector. An architectural design framework for cloud-based patient-centered health information service is designed to support maternal care in underserved settings. A prototype service (AfyaTab app) is developed as a proof-of-concept of the proposed design solution.

A Heuristic Approach to Use Behavioral Models to Design for Change

PMD is a method to design for sustainable behavior change within organizations concerning the introduction of innovation. An earlier evaluation of PMD among users and a use case resulted in the need for refinements. In this paper, the authors describe the refined version of PMD and validate this in another case, in which a solution based on the interaction elements resulting from the PMD method was created for a company. Based on data acquired, they designed models of current and requested behavior. They selected the right interaction elements to facilitate the target audience in a change of behavior. After implementing the solution at the pre-fab concrete company, the authors observed a change in behavior among users, growing towards the behavior required to reach the set business objectives. The research allowed for the creation, evaluation, and validation of the PMD method itself in a real-life situation and showed that it is possible, at least in the use case in this research, to design for a required behavior change to increase adoption of innovations in organizations.

An Incremental Model Projection Applied to Streamline Software Architecture Assessment and Monitoring

Managing software architecture represents a big challenge throughout the development lifecycle. The complexity of the involved structural elements and the relations among them make the specified models look oversized and fuzzy, which makes the architecture incomprehensible, hard to maintain, and difficult to assess its quality. This paper's goal is to propose a powerful methodology for simplifying and reducing models' complexity to increase understandability, smoothing maintenance, and facilitating architecture monitoring and assessment. For this purpose, the authors rely heavily on two major concepts, multi-view modeling, and incremental model projection. The multi-viewing requires that all models must have two main views to describe the architecture and the mapping to its relevant quality attributes. The incremental projection is a methodology used to specialize and minimize models progressively to make them simpler and clearer. The results show that projecting models incrementally can reduce and narrow them significantly.

Aligning Information Technology and Supply Chain

Information technology (IT) has a critical importance. Information technology governance (ITG) is the system that allows enterprises to master the complexity of IT in order to maximize its use and to foster the competitive advantage. Control objectives for information and related technology (COBIT) is a well-known IT governance (ITG) framework that groups IT best practices. There is little research about the correlation between COBIT and domain specific frameworks, like supply chain operation reference (SCOR) for supply chain (SC). The paper proposes an approach to map SCOR's components to COBIT with ArchiMate, which is a standard language to model enterprise architecture (EA). The mapping can simplify, by visualization, the complexity of both frameworks. It can also provide a view on possible overlaps and synergies between SCOR and COBIT. Two detailed illustrations are presented. The evaluation is done according the Bunge-Wand-Weber method. An example of the utility of the mapping is done for a real case scenario.

Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves

Agriculture contributes majorly to all nations' economies, but crop diseases are now becoming a very big issue that has to be resolving immediately. Because of this, crop/plant disease detection becomes a very significant area to work. However, a huge number of studies have been done for automatic disease detection using machine learning, but less work has been done using deep learning with efficient results. The research article presents a convolution neural network for plant disease detection by using open access ‘PlantVillage' dataset for three versions that are colored, grayscale, and segmented images. The dataset consists of 54,305 images and is being used to train a model that will be able to detect disease present in edible plants. The proposed neural network achieved the testing accuracy of 99.27%, 98.04%, and 99.14% for colored, grayscale, and segmented images, respectively. The work also presents better precision and recall rates on colored image datasets.

A Hybrid Approach for Feature Selection Based on Genetic Algorithm and Recursive Feature Elimination

Machine learning has become an integral part of our life in today's world. Machine learning when applied to real-world applications suffers from the problem of high dimensional data. Data can have unnecessary and redundant features. These unnecessary features affect the performance of classification systems used in prediction. Selection of important features is the first step in developing any decision support system. In this paper, the authors have proposed a hybrid feature selection method GARFE by integrating GA (genetic algorithm) and RFE (recursive feature elimination) algorithms. Efficiency of proposed method is analyzed using support vector machine classifier on the scale of accuracy, sensitivity, specificity, precision, F-measure, and execution time parameters. Proposed GARFE method is also compared to eight other feature selection methods. Results demonstrate that the proposed GARFE method has increased the performance of classification systems by removing irrelevant and redundant features.

Software-Based Testing Kit Using Machine Learning for Diagnosis and Predictive Analytics of COVID-19 Patients

Nowadays, the global community is being affected with COVID-19 disease and integrated infections, which are becoming a menace to the whole world. Research is going on to find out the solution, and still, no particular vaccination or solution has been achieved. This research work is focusing on the analytics of dataset extracted, which has assorted attributes, and these attributes are processed in the machine learning algorithm so that the prime factor can be recognized. In this research manuscript, the usage of COVID-19 dataset is done and trained using supervised learning approach of artificial neural network (ANN) on Levenberg-Marquardt (LM) algorithm so that the predictions of the test patients can be done on the key attributes of age, gender, location, and related parameters. The selection of LM-based implementation with ANN is done as it is the faster approach compared to other functions in neural networks.