Computer-based Tools Research Articles

Optimization of temperature, humidity and airflow in African Indigenous Vegetable (AIV) greenhouse

This research presents a novel approach for effectively optimizing growth rate and yield in a greenhouse. With the market demanding higher-quality standards, greenhouse cultivation is becoming increasingly sophisticated and competitive. However, the implementation of protected cultivation systems is expensive. Therefore, it is crucial for African Indigenous Vegetable (AIV) greenhouses to be optimized under stringent production conditions to remain competitive. Currently, greenhouse management decisions are categorized into various levels, ranging from real-time control to environmental optimization and seasonal market planning. The primary objective of our research is to optimize greenhouse conditions, specifically temperature, humidity, and airflow, at the Agro Industrial Park (AIP). To accomplish this, Design-Expert software, which is a computer-based tool equipped with contemporary statistical models and tools, was employed to accurately estimate the required ranges of microclimate parameters that should be maintained to achieve optimal growth rate and yield. By utilizing this approach, this study aimed to provide valuable insights and recommendations for enhancing greenhouse productivity. Ultimately, this study contributes to the development and advancement of AIV greenhouses by offering practical solutions to optimize microclimate conditions, resulting in improved growth and increased yield.

An Active Learning Computer-Based Teaching Tool for Enhancing Students’ Learning and Visualization Skills in Electromagnetics

An Active Learning Computer-Based Teaching Tool for Enhancing Students’ Learning and Visualization Skills in Electromagnetics

A deep transfer learning approach for identification of diabetic retinopathy using data augmentation

In ophthalmology, deep learning acts as a computer-based tool with numerous potential capabilities and efficacy. Throughout the world, diabetic retinopathy (DR) is considered as a principal cause of disease however loss of sight cannot be seen in adults aged 20-74 years. The primary objective for early detection of DR is screening on a regular basis at separate intervals which should have a time difference of every ten to twenty months for the patients with no or mild case of DR. Regular screening plays a major role to prevent vision loss, the expected cases increase from 415 million in 2015 to 642 million in 2040 means is a challenging task of ophthalmologists to do screening and follow-up representations. In this research, a transfer learning model was proposed with data augmentation techniques and gaussian-blur, circle-crop pre-processing techniques combination to identify every stage of DR using Resnet 50 with top layers. Models are prepared with Kaggle Asia Pacific Tele-Ophthalmology Society blindness dataset on a top line graphical processing data. The result depicts- the comparison of classification metrics using synthetic and non-synthetic images and achieve accuracy of 91% using the synthetic data and 86% accuracy without using synthetic data.

Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models.

Recently, many diseases have negatively impacted people's lifestyles. Among these, knee osteoarthritis (OA) has been regarded as the primary cause of activity restriction and impairment, particularly in older people. Therefore, quick, accurate, and low-cost computer-based tools for the early prediction of knee OA patients are urgently needed. In this paper, as part of addressing this issue, we developed a new method to efficiently diagnose and classify knee osteoarthritis severity based on the X-ray images to classify knee OA in (i.e., binary and multiclass) in order to study the impact of different class-based, which has not yet been addressed in previous studies. This will provide physicians with a variety of deployment options in the future. Our proposed models are basically divided into two frameworks based on applying pre-trained convolutional neural networks (CNN) for feature extraction as well as fine-tuning the pre-trained CNN using the transfer learning (TL) method. In addition, a traditional machine learning (ML) classifier is used to exploit the enriched feature space to achieve better knee OA classification performance. In the first one, we developed five classes-based models using a proposed pre-trained CNN for feature extraction, principal component analysis (PCA) for dimensionality reduction, and support vector machine (SVM) for classification. While in the second framework, a few changes were made to the steps in the first framework, the concept of TL was used to fine-tune the proposed pre-trained CNN from the first framework to fit the two classes, three classes, and four classes-based models. The proposed models are evaluated on X-ray data, and their performance is compared with the existing state-of-the-art models. It is observed through conducted experimental analysis to demonstrate the efficacy of the proposed approach in improving the classification accuracy in both multiclass and binary class-based in the OA case study. Nonetheless, the empirical results revealed that the fewer multiclass labels used, the better performance achieved, with the binary class labels outperforming all, which reached a 90.8% accuracy rate. Furthermore, the proposed models demonstrated their contribution to early classification in the first stage of the disease to help reduce its progression and improve people's quality of life.

Development of a Computer-Based Tool for Supporting Impact Assessments of EDU4D Projects

Impact assessments are crucial for measuring the effectiveness of developmental projects. However, hurdles such as the complexity, limited applicability, and lack of empirical evidence of impact assessments are hinderances to use impact assessments more widely. Computer-based tools could help ease these problems as they can help the implementation process and foster usage. However, currently there are no computer-based tools available to support ICT for development (ICT4D) impact assessments in the educational domain. For this research, a computer-based tool was developed to support impact assessments of ICT4D projects in education (EDU4D). A literature study was performed and interviews with field experts were conducted to decide upon the requirements. Subsequently, a computer-based tool was developed that aims to guide the user to accurately perform a situational impact assessment method for EDU4D (SIAM-Ed) and to work in low resource environments. Finally, a small pilot study was conducted that showed positive results on the effectiveness of the tool.

Detection of COVID-19: A Smartphone-Based Machine-Learning-Assisted ECL Immunoassay Approach with the Ability of RT-PCR CT Value Prediction.

The unstoppable spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has severely threatened public health over the past 2 years. The current ubiquitously accepted method for its diagnosis provides sensitive detection of the virus; however, it is relatively time-consuming and costly, not to mention the need for highly skilled personnel. There is a clear need to develop novel computer-based diagnostic tools to provide rapid, cost-efficient, and time-saving detection in places where massive traditional testing is not practical. Here, we develop an electrochemiluminescence (ECL)-based detection system whose results are quantified as reverse transcriptase polymerase chain reaction (RT-PCR) cyclic threshold (CT) values. A concentration-dependent signal is generated upon the introduction of the virus to the electrode and is recorded with a smartphone camera. The ECL images are used to train machine learning algorithms, and a model using artificial neural networks (ANNs) for 45 samples was developed. The model demonstrated more than 90% accuracy in the diagnosis of 50 unknown real samples, detecting up to a CT value of 32 and a limit of detection (LOD) of 10-12 g mL-1 in the testing of artificial samples.

Individualized Patient Care Through Model-Informed Precision Dosing: Reflections on Training Future Practitioners.

Prior to his passing, Dr. Roger Jelliffe, expressed the need for educating future physicians and clinical pharmacists on the availability of computer-based tools to support dose optimization in patients in stable or unstable physiological states. His perspectives were to be captured in a commentary for the AAPS J with a focus on incorporating population pharmacokinetic (PK)/pharmacodynamic (PD) models that are designed to hit the therapeutic target with maximal precision. Unfortunately, knowing that he would be unable to complete this project, Dr. Jelliffe requested that a manuscript conveying his concerns be completed upon his passing. With this in mind, this final installment of the AAPS J theme issue titled "Alternative Perspectives for Evaluating Drug Exposure Characteristics in a Population - Avoiding Analysis Pitfalls and Pigeonholes" is an effort to honor Dr. Jelliffe's request, conveying his concerns and the need to incorporate modeling and simulation into the training of physicians and clinical pharmacists. Accordingly, Dr. Jelliffe's perspectives have been integrated with those of the other three co-authors on the following topics: the clinical utility of population PK models; the role of multiple model (MM) dosage regimens to identify an optimal dose for an individual; tools for determining dosing regimens in renal dialysis patients (or undergoing other therapies that modulate renal clearance); methods to analyze and track drug PK in acutely ill patients presenting with high inter-occasion variability; implementation of a 2-cycle approach to minimize the duration between blood samples taken to estimate the changing PK in an acutely ill patient and for the generation of therapeutic decisions in advance for each dosing cycle based on an analysis of the previous cycle; and the importance of expressing therapeutic drug monitoring results as 1/variance rather than as the coefficient of variation. Examples showcase why, irrespective of the overall approach, the combination of therapeutic drug monitoring and computer-informed precision dosing is indispensable for maximizing the likelihood of achieving the target drug concentrations in the individual patient.

An evaluation of the efficacy of a supplemental computer-based tutorial to enhance the informed consent process for cataract surgery: an exploratory randomized clinical study

BackgroundTo assess whether informing patients with a computer-based tutorial in addition to standard informed consent influences the patient’s attitude towards surgery and increases patient’s knowledge.MethodsIn this prospective, exploratory, randomized clinical study, patients scheduled for their first eye cataract surgery were randomly allocated to two groups, receiving standard face-to-face informed consent (control group) or additionally using an interactive computer-based tool (CatInfo) containing an audiovisual presentation about cataract and its treatment (study group). Cataract-related knowledge and decisional confidence (decisional conflict scale (DCS)) were assessed as well as one-month postoperatively decisional regret (decision regret scale (DRS)) and willingness to exchange face-to-face discussion time for the use of such a tool.ResultsThe study comprised 134 patients, 64 patients in the study group and 70 in the control group. Patients in the study group answered more questions correctly, 16.3 ± 2.0 (median 16.5, 11.0–19.0) versus 15.5 ± 1.9 (median 16.0, 8.0–19.0; p = 0.01). Patients showed a high decisional confidence with a study group mean DCS score of 92.4 ± 9.8 (median 96.9, 65.6–100) and control group score of 91.6 ± 10.9 (median 95.3, 43.3–100; p = 0.52). Mean DRS score in the study group was 2.5 ± 8.0 (median 0, 0–40) and 4.3 ± 12.5 (median 0, 0–75) in the control group (p = 0.14). Of study group patients 23 (67.6%) were willing to trade time, on average 158 ± 180 s (median 120 s, 45–900). Satisfaction with the tool was high with a mean of 9.1 ± 1.3 out of 10 (median 9.7, 5.0–10).ConclusionsCataract-related knowledge was generally good, with slightly higher scores in the study group. In both groups, decisional confidence was high and regret after surgery was low. A tendency towards slightly higher decisional confidence and lower regret was found in the study group, although these differences were not statistically significant. Additional use of an interactive computer-based tool may prove useful in the informed consent process in a high-volume cataract outpatient setting.Trial registrationClinicalTrials.gov, NCT04975126. Retrospectively registered – July 23, 2021.

Challenges and Opportunities for Increasing Adoption of Hypofractionated Radiotherapy in Low- and Middle-Income Countries

Purpose/Objective(s)In the advent of the COVID-19 pandemic, professional societies including the American Society for Radiation Oncology and the National Comprehensive Cancer Network recommended increased adoption of evidence-based hypofractionated radiotherapy (HFRT), with benefits including significantly reducing the number of clinical visits for each patient to minimize potential exposure to infection, and reducing treatment costs and stress on limited workforce, particularly beneficial in Low-and-Middle-Income Countries (LMICs). Despite these benefits, HFRT adoption remains low, especially in LMICs. The purpose of this study is to investigate the challenges and opportunities for increased adoption of evidence-based HFRT in LMICs.Materials/MethodsAn IRB-approved survey was implemented in 18 sample radiotherapy centers in African LMIC to assess the challenges and utilization of HFRT. The experiences of three cancer centers were documented as part of an ongoing multi-center HFRT clinical trial designed to compare results with those reported for clinical trials involving North American and European Populations. Based on the findings assessed, challenges from the survey, and recorded experiences from the three centers, an online education and training program was developed in collaboration with the Global Health Catalyst, Radiation Knowledge and computer-based training tools for treatment planning, contouring, and online learning, with remote support provided by members from the international councils of ASTRO and AAPM.ResultsOnly 8 of 18 surveyed clinics reported adopting HFRT as a common practice. Analysis of survey data demonstrated a significant need for training on contouring for radiation oncologists, and treatment planning and quality assurance. An education and training program was developed for implementation in the LMICs via a collaborative education model involving ASTRO and AAPM members who are faculty in USA institutions in collaboration with LMIC radiation oncology professionals.ConclusionThe findings demonstrate a need for additional investment in infrastructure and training, as well as better ongoing education of oncology leaders on the benefits of increased adoption of evidence-based HFRT. The project also highlights opportunities and approaches for leveraging information and communication technology for collaborative high-impact global radiation oncology education, with the participation of members across both LMIC and USA institutions and professional societies. The HFRT training program provides a template for continuous education and training to increase the adoption of evidence-based approaches to HFRT that can significantly increase improved access to radiotherapy and reduce disparities in advancing globally the practice of radiation oncology. The impact of such a program and approach will be presented and discussed.

Assessing the impact of COVID-19 measures on COPD management and patients: a simulation-based decision support tool for COPD services in the UK

ObjectivesTo develop a computer-based decision support tool (DST) for key decision makers to safely explore the impact on chronic obstructive pulmonary disease (COPD) care of service changes driven by restrictions...

PERSONAL THOUGHTS ON AUTOMATION, PROGRAMMING CULTURE, AND MODELBASED SOFTWARE ENGINEERING

When compared to more conventional development techniques, model-based software engineering (MBSE), a methodology for developing software, is characterized in part by much higher levels of automation. Many important components of development involve the use of computer-based tools, such as authoring support (many MBSE languages are primarily visual), automatic or semi-automatic verification, the automated conversion of requirements into corresponding programmers, and many more. There is little question that automation, when correctly designed and achieved, may significantly boost the productivity of software developers and improve the quality of their programme, given the historical examples, such as the advent of compilation technology. Therefore, it becomes sense to predict that MBSE will swiftly overtake other software development methods, much to how computer-aided design methods for hardware were quickly adopted. However, this hasn't happened. This is an opinion piece that draws from the author's extensive knowledge of MBSE and its use in business. In it, we look at the factors that led to this paradoxical situation.

Geospatial tools offer fresh perspective on patient care.

By combining geographic information system (GIS) technology with data from electronic health records, health registries, and other sources, clinicians can have a powerful tool to improve patient care, says geospatial pharmacy specialist Jing Wu. Wu is a former account executive at Esri in Arlington, VA, where she helped healthcare organizations incorporate GIS technology into their platforms. She said that by viewing patients through a GIS lens, pharmacists and other clinicians are better able “to think about our patients within the context of their lives [and] create more targeted interventions.” “I think that’s going to be the standard of practice,” Wu added. The Centers for Disease Control and Prevention (CDC) describes GIS as computer-based tools for storing, visualizing, analyzing, and interpreting geographic data. The many things GIS data can map include disease cases, hospitals, clinic types and sites, roads, public transit routes, waterways, and land boundaries. CDC uses GIS data for research on population health, toxicology, chronic disease prevention, disease surveillance, and other health issues.

A Novel Computer-Based Assessment Tool for Evaluating Early Literacy Skills in Italian Preschoolers

ABSTRACT The present contribution aims at presenting an assessment tool (i.e., the TALK-assessment) built to evaluate the language development and school readiness of Italian preschoolers before they enter primary school, and its predictive validity for the children’s reading and writing skills at the end of the first year of primary school. The early literacy competences of 98 preschoolers were assessed and the statistical proprieties (item difficulty level and Discrimination Index, and the factorial structure using Confirmatory Factor Analysis) of each subtest of the assessment were presented (Study 1). Results showed that the subtests of the tool have good psychometric properties, with the only exception of the morpho-syntactic comprehension task, and are adequate for use with preschoolers in the school context. Study 2 investigated the early literacy skills of a group of 62 preschoolers and their reading and writing abilities at the end of primary school 1st grade. The scores obtained in the phonological awareness task of the final version of the assessment in preschool significantly predicted children’s reading scores 12 months later, at primary school. The scores obtained in the lexical comprehension and morpho-syntactic production (i.e., sentence repetition) tasks of the final version of the assessment in preschool significantly predicted children’s writing scores 12 months later, at primary school. The assessment has specific characteristics that make it a valuable candidate for adoption in educational settings, both to identify fragile areas in time to modify the children’s developmental paths to literacy and to prevent future language and literacy difficulties at primary school.

Pre-feasibility methodology to compare productive uses of energy supplied by stand-alone solar photovoltaic systems: A Tanzanian case study

This paper provides a standardised methodology to assess the suitability of using stand-alone solar photovoltaic (PV) systems for different productive uses of energy (PUE) at a country-wide level. The focus has been on the country of Tanzania, but the methodology is suitable for any location. This analysis has reviewed fourteen different PUE categories, with several sub-categories. The PUE were assessed for a wide range of factors, including cost of the system, potential income from the PUE, and potential market size. This report also highlights the PUE load profiles and energy requirements for comparison.Assessing a potential productive use is a complex process with multiple stakeholders and decision factors. The analysis here is not meant as a definitive answer, but to highlight the technical characteristics and economics of the potential productive uses for comparison. This methodology is a first pass method to assess the suitability of stand-alone PV systems for PUE applications at a country-wide level. For more detailed analysis of the PUE potential, the enabling environment, socio-cultural context and supporting services must be investigated in much greater detail. The quantitative methodology given here used computer-based simulation tools, including data processing (Excel & Python), geographical information systems (QGIS) and power system simulation (HOMER Pro). Input data from multiple sources, including in-country fieldwork, was used. This analysis has highlighted PUE with smaller energy requirements but low sensitivity to equipment or service cost to be the most suitable for more detailed analysis.Applying this methodology to Tanzania has shown stand-alone solar PV systems for barbershops, tailors, mobile carpenters, drip-feed irrigation systems and fishing lights as the lowest risk PUE for implementation.

Extending the lighting design objectives procedure for holistic lighting solutions

The author has previously proposed a novel spreadsheet-based lighting design objectives procedure (LiDOs) that enables practitioners to reconcile interacting LiDOs relating to the spatial distribution of illumination within a space, and this procedure has been successfully adopted by several lighting design practices. This paper proposes that the procedure is developed into an extended computer-based lighting design tool (LiDOs2) that includes LiDOs relating to spectral and temporal illumination distributions, as well as spatial distribution. This would enable regulators to specify limiting values for basic indoor lighting objectives such as perceived adequacy of illumination while at the same time guiding practitioners to incorporate LiDOs that address characteristics of lighting chosen to suit specific applications. The LiDOs2 procedure would be capable of generating holistic lighting performance specifications that would enable practitioners to conduct informed searches for light sources and luminaires, and to determine layouts and control circuits with confidence that the specified combination of LiDOs would be achieved.

Existing tools enabling the implementation of EN 16883:2017 Standard to integrate conservation-compatible retrofit solutions in historic buildings

• Review of computer-based decisional tools for conservation-compatible energy retrofit. • Collaborative information-search methodology. • Three levels of action (single building component, whole building, district level). • Analysis of tools’ structure, aim, limitations and link to EN16883 procedure. • Overview of potential future developments of the tools to enable the use of EN16883. The heterogeneity of historic buildings and environmental conditions, as well as the variety of possible technical solutions, introduce great challenges to the decision-making process for the definition and implementation of energy retrofit projects. The variety of stakeholders involved in the process, each bringing specific skills and goals, further add to this complexity. How can the decision be finalised when multiple and often conflicting objectives and different stakeholders are involved? In this context, the European Standard EN 16883:2017 provides guidelines to improve the energy performance of historic buildings while respecting their heritage significance. It presents a normative working procedure to select conservation-compatible retrofit solutions, which is based on a step-by-step investigation, analysis and documentation of the building. However, the recommendations provided in the Standard remain at a general level and it is the task for the stakeholders to tailor the intervention to the specific case. This paper investigates how the implementation of the EN 16883:2017 can be enabled by adopting a selection of existing computer-based tools to support the identification, assessment, and selection of retrofit solutions in historic buildings. To this end, a number of tools were analysed, highlighting their advantages, input data, outcomes and main limitations, in relation to their possible use in support of the implementation of the Standard procedure (or steps of it).

Automated Detection of Myocardial Infarction and Heart Conduction Disorders Based on Feature Selection and a Deep Learning Model.

An electrocardiogram (ECG) is an essential piece of medical equipment that helps diagnose various heart-related conditions in patients. An automated diagnostic tool is required to detect significant episodes in long-term ECG records. It is a very challenging task for cardiologists to analyze long-term ECG records in a short time. Therefore, a computer-based diagnosis tool is required to identify crucial episodes. Myocardial infarction (MI) and conduction disorders (CDs), sometimes known as heart blocks, are medical diseases that occur when a coronary artery becomes fully or suddenly stopped or when blood flow in these arteries slows dramatically. As a result, several researchers have utilized deep learning methods for MI and CD detection. However, there are one or more of the following challenges when using deep learning algorithms: (i) struggles with real-life data, (ii) the time after the training phase also requires high processing power, (iii) they are very computationally expensive, requiring large amounts of memory and computational resources, and it is not easy to transfer them to other problems, (iv) they are hard to describe and are not completely understood (black box), and (v) most of the literature is based on the MIT-BIH or PTB databases, which do not cover most of the crucial arrhythmias. This paper proposes a new deep learning approach based on machine learning for detecting MI and CDs using large PTB-XL ECG data. First, all challenging issues of these heart signals have been considered, as the signal data are from different datasets and the data are filtered. After that, the MI and CD signals are fed to the deep learning model to extract the deep features. In addition, a new custom activation function is proposed, which has fast convergence to the regular activation functions. Later, these features are fed to an external classifier, such as a support vector machine (SVM), for detection. The efficiency of the proposed method is demonstrated by the experimental findings, which show that it improves satisfactorily with an overall accuracy of 99.20% when using a CNN for extracting the features with an SVM classifier.

The effect of virtual laboratory simulations on medical laboratory techniques students’ knowledge and vocational laboratory education

Abstract Objectives Virtual laboratory simulations (VLSs) are computer-based tools that offer unlimited application options in scientific, medical, and engineering fields. The aim of this study was to evaluate whether VLSs are efficient learning tools and how these simulations can be integrated into laboratory practice in medical laboratory education. Methods In this pre-test/post-test control group study, 32 volunteers were randomly assigned to either experimental or control groups. The experimental group performed laboratory simulations based on biochemistry and microbiology and then completed a self-report survey to evaluate their satisfaction and beliefs about simulations. Results In the experimental group, post-test scores of each simulation were significantly elevated compared to pre-test scores; however, pre- and post-test scores of control group were statistically the same. The experimental group agreed that these simulations should be applied before theoretical lectures and laboratory practices. They also highlighted that translating from English to their native language creates difficulties in applying and understanding the simulation. Conclusions We emphasized that VLSs are excellent learning tools that increase not only the knowledge but also the self-motivation and focus of the students. Based on feedbacks, native language options are necessary to enable the students to achieve equality of opportunity in education.

Online Assessment and Game-Based Development of Inductive Reasoning.

The aims of the study were (1) to develop a domain-general computer-based assessment tool for inductive reasoning and to empirically test the theoretical models of Klauer and Christou and Papageorgiou; and (2) to develop an online game to foster inductive reasoning through mathematical content and to investigate its effectiveness. The sample was drawn from fifth-grade students for the assessment (N = 267) along with the intervention study (N = 122). The online figurative test consisted of 54 items: nine items were developed for each of the six inductive reasoning processes. The digital game-based training program included 120 learning tasks embedded in mathematical content with differential feedback and instructional support. The test had good psychometric properties regarding reliabilities, means, and standard deviations. Confirmatory factor analyses revealed that the six processes of inductive reasoning and the three latent factors of Similarity, Dissimilarity, and Integration could be empirically confirmed. The training program was effective in general (corrected effect size = .38); however, the process of cross-classification was not developed significantly. Findings could contribute to a more detailed understanding of the structure and the modifiability of inductive reasoning processes and could reveal further insights into the nature of fluid intelligence.

Effects of collaboration on students’ learning using Intelligent Tutoring System

Computer-based learning tools called Intelligent Tutoring Systems (ITS) assist students to become better learners by simulating human tutors using Artificial Intelligence (AI) approaches. Students can interact using collaborative ITSs from various locations to study, discuss, and articulate concepts relevant to a certain problem. This paper presents a collaborative ITS to teach UML that is built to enable students to effectively communicate and share each other's mistakes. The ITS is capable of detecting and identifying student errors and offers students suggestions during the problem-solving stage, giving them guidance on how to proceed. The ITS also determines a student's current level of thinking and intellect in order to assign them activities that need more attention. The evaluations conducted for this study revealed that the experimental group had considerably more learning gains (81% scores on the posttest) than the control group, where students only showed a very low significant change in their learning with posttest scores of 46%