Appl. Syst. Innov., Volume 4, Issue 1 (March 2021) – 23 articles

An enormous amount of clinical free-text information, such as pathology reports, progress reports, clinical notes and discharge summaries have been collected at hospitals and medical care clinics. These data provide an opportunity of developing many useful machine learning applications if the data could be transferred into a learn-able structure with appropriate labels for supervised learning. The annotation of this data has to be performed by qualified clinical experts, hence, limiting the use of this data due to the high cost of annotation. An underutilised technique of machine learning that can label new data called active learning (AL) is a promising candidate to address the high cost of the label the data. AL has been successfully applied to labelling speech recognition and text classification, however, there is a lack of literature investigating its use for clinical purposes. We performed a comparative investigation of various AL techniques using ML and deep learning (DL)-based strategies on three unique biomedical datasets. We investigated random sampling (RS), least confidence (LC), informative diversity and density (IDD), margin and maximum representativeness-diversity (MRD) AL query strategies. Our experiments show that AL has the potential to significantly reducing the cost of manual labelling. Furthermore, pre-labelling performed using AL expediates the labelling process by reducing the time required for labelling. Full article

In this study, the required capabilities and key element technologies of smart underground ammunition storage were analyzed using the Delphi technique. Twenty-four external experts on industry 4.0 smart technology were selected. A total of 18 required capabilities and 32 key element technologies were derived for the construction of smart underground ammunition storage. Smart ammunition storage can be built through the convergence of a range of ICT technologies such as sensors, clouds, big data, precision control, and mobile technologies, along with existing ammunition storages. The combination of these technologies will support human decision making through the use of numerous sensors applied to ammunition storage for collecting data and converting them into big data. In addition, the intelligent information technology introduced in a smart ammunition store will allow soldiers to detect changes in the surrounding environment, which will bring about innovation to an ammunition service. As a result, high-level automation and an intelligent infrastructure can be provided, enabling an improvement in ammunition management capabilities, energy saving, and the establishment of a safe operating environment and a flexible management system. This form of future ammunition storage will be an example solution for major issues in army ammunition services, as well as overcoming challenges such as a reduction in military forces. Full article

Recent studies on chronic obstructive pulmonary disease (COPD) patients in the context of the coronavirus 19 (COVID-19) pandemic have reported two important problems, i.e., high mortality and vulnerability among COPD patients vs. non-COPD patients. The high number of deaths are caused by exacerbations, COVID-19, and other comorbidities. Therefore, the purpose of this article is to reduce the risk factors of COPD in the COVID-19 context. In this article, we propose approaches based on adaptation mechanisms for detecting COVID-19 symptoms, to better provide appropriate care to COPD patients. To achieve this goal, an ontological model called SuspectedCOPDcoviDOlogy has been created, which consists of five ontologies for detecting suspect cases. These ontologies use vital sign parameters, symptom parameters, service management, and alerts. SuspectedCOPDcoviDOlogy enhances the COPDology proposed by a previous research project in the COPD domain. To validate the solution, an experimental study comparing the results of an existing test for the detection of COVID-19 with the results of the proposed detection system is conducted. Finally, with these results, we conclude that a rigorous combination of detection rules based on the vital sign and symptom parameters can greatly improve the dynamic detection rate of COPD patients suspected of having COVID-19, and therefore enable rapid medical assistance. Full article

The quality of execution tracing impacts the time to a great extent to locate errors in software components; moreover, execution tracing is the most suitable tool, in the majority of the cases, for doing postmortem analysis of failures in the field. Nevertheless, software product quality models do not adequately consider execution tracing quality at present neither do they define the quality properties of this important entity in an acceptable manner. Defining these quality properties would be the first step towards creating a quality model for execution tracing. The current research fills this gap by identifying and defining the variables, i.e., the quality properties, on the basis of which the quality of execution tracing can be judged. The present study analyses the experiences of software professionals in focus groups at multinational companies, and also scrutinises the literature to elicit the mentioned quality properties. Moreover, the present study also contributes to knowledge with the combination of methods while computing the saturation point for determining the number of the necessary focus groups. Furthermore, to pay special attention to validity, in addition to the the indicators of qualitative research: credibility, transferability, dependability, and confirmability, the authors also considered content, construct, internal and external validity. Full article

Hydrothermal carbonization (HTC) is a promising thermochemical pre-treatment to convert waste biomass into solid biofuels. However, the process yields large amounts of organic process water (PW), which must be properly disposed of or reused. In this study, the PW produced from the hydrothermal carbonization of lemon peel waste (LP) was recycled into HTC process of LP with the aim of maximize energy recovery from the aqueous phase while saving water resources and mitigating the overall environmental impact of the process. The effects of HTC temperature on the properties of solid and liquid products were investigated during PW recirculation. Experiments were carried out at three different operating temperatures (180, 220, 250 °C), fixed residence times of 60 min, and solid to liquid load of 20 wt%, on a dry basis. Hydrochars were characterized in terms of proximate analysis and higher heating values while liquid phases were analyzed in terms of pH and total organic carbon content (TOC). PW recirculation led to a solid mass yield increase and the effect was more pronounced at lower HTC temperature. The increase of solid mass yield, after recirculation steps (maximum increase of about 6% at 180 °C), also led to a significant energy yield enhancement. Results showed that PW recirculation is a viable strategy for a reduction of water consumption and further carbon recovery; moreover preliminary results encourage for an in-depth analysis of the effects of the PW recirculation for different biomasses and at various operating conditions. Full article

Real-world datasets are heavily skewed where some classes are significantly outnumbered by the other classes. In these situations, machine learning algorithms fail to achieve substantial efficacy while predicting these underrepresented instances. To solve this problem, many variations of synthetic minority oversampling methods (SMOTE) have been proposed to balance datasets which deal with continuous features. However, for datasets with both nominal and continuous features, SMOTE-NC is the only SMOTE-based oversampling technique to balance the data. In this paper, we present a novel minority oversampling method, SMOTE-ENC (SMOTE—Encoded Nominal and Continuous), in which nominal features are encoded as numeric values and the difference between two such numeric values reflects the amount of change of association with the minority class. Our experiments show that classification models using the SMOTE-ENC method offer better prediction than models using SMOTE-NC when the dataset has a substantial number of nominal features and also when there is some association between the categorical features and the target class. Additionally, our proposed method addressed one of the major limitations of the SMOTE-NC algorithm. SMOTE-NC can be applied only on mixed datasets that have features consisting of both continuous and nominal features and cannot function if all the features of the dataset are nominal. Our novel method has been generalized to be applied to both mixed datasets and nominal-only datasets. Full article

Efficient Market Hypothesis states that stock prices are a reflection of all the information present in the world and generating excess returns is not possible by merely analysing trade data which is already available to all public. Yet to further the research rejecting this idea, a rigorous literature review was conducted and a set of five technical indicators and 23 fundamental indicators was identified to establish the possibility of generating excess returns on the stock market. Leveraging these data points and various classification machine learning models, trading data of the 505 equities on the US S&P500 over the past 20 years was analysed to develop a classifier effective for our cause. From any given day, we were able to predict the direction of change in price by 1% up to 10 days in the future. The predictions had an overall accuracy of 83.62% with a precision of 85% for buy signals and a recall of 100% for sell signals. Moreover, we grouped equities by their sector and repeated the experiment to see if grouping similar assets together positively effected the results but concluded that it showed no significant improvements in the performance—rejecting the idea of sector-based analysis. Also, using feature ranking we could identify an even smaller set of 6 indicators while maintaining similar accuracies as that from the original 28 features and also uncovered the importance of buy, hold and sell analyst ratings as they came out to be the top contributors in the model. Finally, to evaluate the effectiveness of the classifier in real-life situations, it was backtested on FAANG (Facebook, Amazon, Apple, Netflix & Google) equities using a modest trading strategy where it generated high returns of above 60% over the term of the testing dataset. In conclusion, our proposed methodology with the combination of purposefully picked features shows an improvement over the previous studies, and our model predicts the direction of 1% price changes on the 10th day with high confidence and with enough buffer to even build a robotic trading system. Full article

Greywater has been identified as a valuable alternative water source over recent years. Few practices (i.e., recycling and reuse) of greywater have attracted global attention in meeting the future water demand. However, essential parameters should be analyzed for reliable reuse and treatment. The present study addresses the possibilities of the alternative source with the treated greywater. Gravity—governed flow methods through a column containing gravel, sand, and activated carbon was applied. The quality of treated greywater from the university campus, which included physical, chemical, and biological parameters, was assessed to check non-potable reuse suitability. The reduction percentage of organics in biological oxygen demand and chemical oxygen demand was 64% and 42%, respectively. Similarly, the reduction percentage was obtained at 74% and 66% for turbidity and electrical conductivity. The removal efficiency was 57%, 77%, 48%, and 44% for total dissolved solids, alkalinity, chlorides, and total hardness. The pH of treated water samples was found in the neutral range suggesting its suitability for reuse. Hence, the proposed greywater treatment method is a cost-effective and straightforward approach to reuse greywater for irrigation, watering the lawns, and car washing. The greywater collected can be disinfected immediately and reused with minimal possibility of regrowth of microorganisms. Full article

Health Information Systems (HIS) are becoming crucial for health providers, not only for keeping Electronic Health Records (EHR) but also because of the features they provide that can be lifesaving, thanks to the advances in Information Technology (IT). These advancements have led to increasing demands for additional features to these systems to improve their intelligence, reliability, and availability. All these features may be provisioned through the use of cloud computing in HIS. This study arrives at three dimensions pertinent to adoption of cloud computing in HIS through extensive interviews with experts, professional expertise and knowledge of one of the authors working in this area, and review of academic and practitioner literature. These dimensions are financial performance and cost; IT operational excellence and DevOps; and security, governance, and compliance. Challenges and drivers in each of these dimensions are detailed and operationalized to arrive at a model for HIS adoption. This proposed model detailed in this study can be employed by executive management of health organizations, especially senior clinical management positions like Chief Technology Officers (CTOs), Chief Information Officers (CIOs), and IT managers to make an informed decision on adoption of cloud computing for HIS. Use of cloud computing to support operational and financial excellence of healthcare organizations has already made some headway in the industry, and its use in HIS would be a natural next step. However, due to the mission′s critical nature and sensitivity of information stored in HIS, the move may need to be evaluated in a holistic fashion that can be aided by the proposed dimensions and the model. The study also identifies some issues and directions for future research for cloud computing adoption in the context of HIS. Full article

This work is devoted to the presentation of a Wireless Sensor System implementation for upper limb rehabilitation to function as a complementary system for a patient’s progress supervision during rehabilitation exercises. A cost effective motion capture sensor node composed by a 9 Degrees-of-Freedom (DoF) Inertial Measurement Unit (IMU) is mounted on the patient’s upper limb segments and sends wirelessly the corresponding measured signals to a base station. The sensor orientation and the upper limb individual segments movement in 3-Dimensional (3D) space are derived by processing the sensors’ raw data. For the latter purpose, a biomechanical model which resembles that of a kinematic model of a robotic arm based on the Denavit-Hartenberg (DH) configuration is used to approximate in real time the upper limb movements. The joint angles of the upper limb model are estimated from the extracted sensor node’s orientation angles. The experimental results of a human performing common rehabilitation exercises using the proposed motion capture sensor node are compared with the ones using an off-the-shelf sensor. This comparison results to very low error rates with the root mean square error (RMSE) being about $0.02$ m. Full article

Stock price prediction can be made more efficient by considering the price fluctuations and understanding people’s sentiments. A limited number of models understand financial jargon or have labelled datasets concerning stock price change. To overcome this challenge, we introduced FinALBERT, an ALBERT based model trained to handle financial domain text classification tasks by labelling Stocktwits text data based on stock price change. We collected Stocktwits data for over ten years for 25 different companies, including the major five FAANG (Facebook, Amazon, Apple, Netflix, Google). These datasets were labelled with three labelling techniques based on stock price changes. Our proposed model FinALBERT is fine-tuned with these labels to achieve optimal results. We experimented with the labelled dataset by training it on traditional machine learning, BERT, and FinBERT models, which helped us understand how these labels behaved with different model architectures. Our labelling method’s competitive advantage is that it can help analyse the historical data effectively, and the mathematical function can be easily customised to predict stock movement. Full article

This paper explicitly clarifies an employee’s goal to voluntarily stay in his/her current employment. A large volume of research has concentrated on corporate environments on the causes of workforce turnover. Nevertheless, little was done to investigate workers’ desire to remain, which was the essential parameter in determining their stay in the construction sector. Therefore, this research was undertaken to explore the relationship between job embeddedness (off-the-job and on-the-job and the intent of staying in Malaysian construction companies with the mediating impact of continuance commitment. For the analysis, a simple random under probability sampling technique was used. Of the overall 280 samples surveyed, 243 responded and used it in the report, 86.8% of the response rate. A structural equation modeling approach was used to analyze the direct and indirect relationships as drawn by the hypotheses. This research showed that the component of the off-the-job, on-the-job embeddedness and intention to stay were substantially linked. At the same time, continuance commitment plays a full mediation between the convergence of off-the-job, on-the-job and the intention to stay. These findings suggest that construction companies in Malaysia need to consider organizational and community embeddedness relationships along with continuance commitment in the invention of programs designated to influence workers’ intention to stay on their current jobs. Full article

Currently, the deficiencies of the 5G mobile system as an enabler of Internet of Everything (IoE) applications are stimulating global research activities to focus on the sixth generation (6G) wireless system. The potential of IoE is enormous and growing exponentially. With the dawn of the fifth industrial revolution, IoE is transposing into industrial Internet of Everything (IIoE) projects which are complex and are eventuating to become a prominent technology for all industries offering new opportunities. This study embodies a synthesis of 6G, IoT, IoE, IIoE exhaustive literature review advancing knowledge to facilitate theory development. For the first time, a novel theoretical framework for the 6G-enabled IIoE (henceforth referred to as 6GIIoE) system was developed. Judiciously, sequential methodology is best suited for this emerging discipline research to create significant new knowledge in the literature contributing eternal insights to expound valuable contexts to ruminate significant findings. The theoretical framework developed recognizes 6GIIoE priority areas, challenges, and applications bestowing a guide for 6G-enabled IIoE initiatives divulging opportunities for future research activities. Full article

Due to the necessity of developing renewable energy sources, the anaerobic digestion for producing biomethane has developed significantly in the last years, since it allows to both reduce disposal treatment and produce green energy. In this field, fruit and vegetable wastes have been recently put forward, since they could represent a suitable resource for producing biomethane as a new frontier within the context of a circular economy. This study aims at filling the gap in the knowledge of the production, quantities and biogas potential production of these residues. On this basis, a GIS-based model was developed and applied to the Sicily region by investigating the specific regulatory framework as well as by analysing descriptive statistics. The results of the GIS analyses enabled the localisation of the highest productive territorial areas and highlighted where fruit and vegetable wastes are abundantly located. In this regard, about 7 million Nm³ of biogas could be produced by reusing only the fruit and vegetable residues coming from the three most representative Sicilian wholesale markets among those considered. Finally, the regulatory framework is of crucial importance in inhibiting or supporting the use of the selected biomass in a specific sector, with regard to the case study considered. Full article

Predictions of stock and foreign exchange (Forex) have always been a hot and profitable area of study. Deep learning applications have been proven to yield better accuracy and return in the field of financial prediction and forecasting. In this survey, we selected papers from the Digital Bibliography & Library Project (DBLP) database for comparison and analysis. We classified papers according to different deep learning methods, which included Convolutional neural network (CNN); Long Short-Term Memory (LSTM); Deep neural network (DNN); Recurrent Neural Network (RNN); Reinforcement Learning; and other deep learning methods such as Hybrid Attention Networks (HAN), self-paced learning mechanism (NLP), and Wavenet. Furthermore, this paper reviews the dataset, variable, model, and results of each article. The survey used presents the results through the most used performance metrics: Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Square Error (MSE), accuracy, Sharpe ratio, and return rate. We identified that recent models combining LSTM with other methods, for example, DNN, are widely researched. Reinforcement learning and other deep learning methods yielded great returns and performances. We conclude that, in recent years, the trend of using deep-learning-based methods for financial modeling is rising exponentially. Full article

In spite of the increasing understanding of the importance of social support attached to health and medical services in suburban areas, a support model needs to be established that can benefit those areas with different living patterns. To that end, this research employs both quantitative and qualitative analyses to investigate the medication, social support, and care forms and sources in the suburban hills of an area in a central Taiwan village. Different types of data sources were collected during the analysis phase to develop a support model. A new model integrated with the boundaries between the demander and the provider was developed. An experimental mobile app was also developed, and this app was based on the concept of this new support model. It is hoped that the medicine service, care support, and key information on society health activities could be provided by means of using the easiest and simplest GUI through which the local healthcare economic system could be further established. Full article

When the world was engulfed by a COVID-19 pandemic crisis, various activities could not be carried out normally. Activities may continue from home during a crisis by the use of a smartphone through the internet, because almost all people have their own smartphone, without requiring additional purchase of hardware. For formal learning, people can take the opportunity to use social media platforms to undertake conversations easily by using smart phones, even tablets. Teenagers or adults who are still studying in higher education institutions can undertake continuous learning for their work assignments. For example, they can use these tools to communicate through social media such as the WhatsApp, Telegram, Zoom, Microsoft Team, and Edmodo apps to connect with friends and lecturers. This research reveals trends of digital social media security and usability in the time of the COVID-19 pandemic situation, such as working from home, establishing a start-up, improving business processes and conducting online business within the digital ecosystem. The result is interesting and there are many uses of social media which have been addressed in this study during the COVID-19 pandemic for business purposes. The various social media platforms have different features that are available for use by subscribers, and also make it easier for people to do business. This is mainly due to the fact that they open up the global market and also make it cheaper to advertise. The government as well as the private sector has been in the forefront when it comes to the use of social media. Maintaining a good online presence is one of the key aspects that determine the success of start-up companies. This is due to the fact that most customers usually rely on the customer reviews in determining the ability of a company to meet the needs of clients. The main reason why most companies set up a customer relations department that is mandated with the responsibility of responding to customer feedback on various online platforms. On the other hand, the increased use of social media has brought new challenges when it comes to the security of information. Users must, therefore, secure their servers and technology from external and internal threats. One of the strategies used is the use of passwords to log into a portal where each person authorized to access the portal is provided with a password that is unique and known only by the user. The study has covered all these areas in detail including the use of database management systems in an organization or individual. Full article

In a multiple parallel-connected inverters system, limiting the circulating current phenomenon is mandatory since it may influence efficiency and reliability. In this paper, a new control method aimed at this purpose and conceived to be implemented on a Field Programmable Gate Array (FPGA) device is presented. Each of the inverters, connected in parallel, is conceived to be equipped with an FPGA that controls the Pulse-Width Modulation (PWM) waveform without intercommunication with the others. The hardware implemented is the same for every inverter; therefore, the addition of a new module does not require redesign, enhancing system modularity. The system has been simulated in a Simulink environment. To study its behavior and to improve the control method, simulations with two parallel-connected inverters have been firstly conducted, then additional simulations have been performed with increasing complexity to demonstrate the quality of the algorithm. The results prove the ability of the method proposed to limit the circulating currents to negligible values. Full article

The modern approach to realization of large, expensive projects with long payback periods in various sectors of infrastructure often involves combining the financial resources of public authorities and the private sector through a public–private partnership (PPP) mechanism. The PPP mechanism has a high potential for attracting investments and facilitating other conditions necessary for the project. At the same time, the project participants need a third-party coordination platform that is objective and able to organize their dialog on equal terms. The authors of this article, for these purposes, consider the capabilities of digital platforms (DP). Digital platforms are able to unite many project participants in a single information field and provide them with the necessary services. Given the potential multitude of participants in such a system, there arises the question of meeting their basic needs to create mutually beneficial conditions during the implementation of projects. Thus, there is a need for flexible DPs. Flexibility can be achieved by using systems engineering (SE) approaches during the design of the DP. The practice of interaction with stakeholders in the framework of systems engineering allows the determination of the basic needs and areas of activity of the participants. The results of this practice will form the basis for the functional and physical design of the future DPs. Full article

With the rapid industrialization and technological advancements, innovative engineering technologies which are cost effective, faster and easier to implement are essential. One such area of concern is the rising number of accidents happening due to gas leaks at coal mines, chemical industries, home appliances etc. In this paper we propose a novel approach to detect and identify the gaseous emissions using the multimodal AI fusion techniques. Most of the gases and their fumes are colorless, odorless, and tasteless, thereby challenging our normal human senses. Sensing based on a single sensor may not be accurate, and sensor fusion is essential for robust and reliable detection in several real-world applications. We manually collected 6400 gas samples (1600 samples per class for four classes) using two specific sensors: the 7-semiconductor gas sensors array, and a thermal camera. The early fusion method of multimodal AI, is applied The network architecture consists of a feature extraction module for individual modality, which is then fused using a merged layer followed by a dense layer, which provides a single output for identifying the gas. We obtained the testing accuracy of 96% (for fused model) as opposed to individual model accuracies of 82% (based on Gas Sensor data using LSTM) and 93% (based on thermal images data using CNN model). Results demonstrate that the fusion of multiple sensors and modalities outperforms the outcome of a single sensor. Full article

In the context of the COVID-19 pandemic, the use of forecasting techniques can play an advisory role in policymakers’ early implementation of non-pharmaceutical interventions (NPIs) in order to reduce SARS-CoV-2 transmission. In this article, we present a simple approach to even day and 14 day forecasts of the number of COVID-19 cases. The 14 day forecast can be taken as a proxy nowcast of infections that occur on the calculation day in question, if we assume the hypothesis that about two weeks elapse from the day a person is infected until the health authorities register it as a confirmed case. Our approach relies on polynomial regression between the dependent variable y (cumulative number of cases) and the independent variable x (time) and is modeled as a third-degree polynomial in x. The analogy between the pandemic spread and the kinematics of linear motion with variable acceleration is useful in assessing the rate and acceleration of spread. Our frame is applied to official data of the cumulative number of cases in Spain from 15 June until 17 October 2020. The epidemic curve of the cumulative number of cases adequately fits the cubic function for periods of up to two months with coefficients of determination R-squared greater than 0.97. The results obtained when testing the algorithm developed with the pandemic figures in Spain lead to short-term forecasts with relative errors of less than ±1.1% in the seven day predictions and less than ±4.0% in the 14 day predictions. Full article

The increasing micronutrient deficiency within the nutritional habits of the world’s population and the growing need for healthy foods have given rise to the development of biofortified crops. In a context where the consumer’s attention is focused on a healthy lifestyle and respect for the environment, the cultivation of potatoes enriched with selenium offers an undisputed advantage in the pursuit of this twofold objective. The crop has been analyzed through the life-cycle assessment (LCA) methodology in order to highlight the environmental burden generated by selenium (Se) potato cultivation and to compare it with potato in conventional regime. The LCA highlights how the biofortified product is more sustainable than the conventional one, and this not only provides a benefit for the consumer, but also designates a new time for farmers who have the opportunity to implement more environmentally friendly practices. Full article