Computer Supported Research Articles

New possibilities of artificial intelligence in medicine: a narrative review

The purpose of the narrative review is to provide a descriptive analysis of the emerging capabilities of artificial intelligence (AI) to improve the diagnosis, prevention and treatment of various diseases. The article discusses which modern AI tools can be used in clinical practice, healthcare organization and medical education. The paper considers various aspects of medical AI systems, which are mainly computer support systems for medical decision-making in the process of clinical work. Much attention is paid to the possibilities of generative AI in medicine. Potential applications of AI in clinical practice have been investigated, highlighting promising prospects for both practitioners and their patients. The limitations associated with the use of AI in various fields of medicine are described, and possible ways of solving them are suggested. The problems of information security and ethical constraints associated with the introduction of AI are outlined. The broad integration of AI into public health will enhance clinical and management decision support, speed up disease diagnosis, and improve the overall quality and accessibility of healthcare services.

Using digital technologies for correction in the health condition process for IT specialists

Computers have swiftly integrated into people's daily lives, and their utilization continues to surge. The role of an IT support specialist encompasses expertise in network analysis, system administration, information security and assurance, IT audits, database administration, and web administration. The overarching objective is to cultivate a professionally adept and competitive specialist, whose attributes are shaped not only by professional aptitude but also by their personal lifestyle. Pursuing a career in IT necessitates adherence to several criteria, including possessing relevant education, intellectual acumen, teamwork capabilities, self-educational proficiency, a commitment to skill enhancement, and the ability to work autonomously. It is evident that the significance of this industry is growing each year. It is crucial to highlight that, without the implementation of occupational health and safety regulations, there is a substantial risk of a considerable decline in health protection, potentially leading to irreversible impacts on the overall functioning of the body. Adopting a healthy lif estyle involves establishing a self-designed system that safeguards an individual from risks encountered in an active life. To address this, we have developed a sequence of exercises aimed at providing psychological and physical relief for IT workers. The objective is to safeguard the health of employees in this category, incorporating exercises such as tapping biologically active zones, "Crane wings," and "Snake rings." The experimentally verified complex of measures designed for mental and physical relief for IT workers has demonstrated its effectiveness. Additionally, the execution of the exercise routine results in the alignment of morning and evening indicators, indicating an overall improvement in well-being and stable psycho-emotional state. The acquired results highlight a considerable decrease in fatigue indicators and the normalization of mood after completing the exercise routine.

Free for All

Periodic website redesign projects have become essential -- though often complex and costly -- measures that libraries take to ensure users’ ease of access to resources. Though administrators often enlist university web designers or even outside contractors to undertake these projects, librarians themselves can and should be at the center of any library website redesign. This is easier for libraries with employees who have considerable web development-related skills, but it is also within reach for libraries with smaller staff and limited web development skills. Indeed, free UX testing applications, basic office software, and open source or freely available CMSes such as Drupal make library website redesign projects both feasible and affordable. Generating buy-in and recruiting content editors to help build the new site are two vital measures for a successful redesign, as well as ongoing, post-launch maintenance. During our library website redesign, we leveraged both the communication of UX testing results and periodic peer training activities to create support, invite feedback or input, and recruit partners for content creation on the new site. As our site launched, we sustained the momentum of our peers’ involvement with the site by providing training materials, tech support, and targeted documentation. By combining freely available, user-friendly applications with a strategic, inclusive implementation process, even libraries with limited resources can successfully complete significant website redesign projects.

Abstract 7193: ABCB1-mediated chemotherapeutic drug resistance is reversed by a potent p53-MDM2 inhibitor NVP-HDM201

Abstract The failure of chemotherapy in cancer persists as a result of overexpression of various ATP-binding cassette (ABC) transporters. ABCB1 is one such transporter that actively pumps out chemotherapeutic drugs and it is one of the reasons for multidrug resistance (MDR). In the last few years, activation of p53 has been targeted as a therapeutic strategy in the treatment of cancers. Siremadlin (NVP-HDM201) is a potent and selective inhibitor of p53-MDM2 interaction. The objective of this study was to explore the ability of HDM201 to reverse tumor MDR attributable to overexpression of ABC transporters. According to our findings, HDM201 significantly increased the sensitivity of ABCB1-overexpressing cells to ABCB1 substrates, such as colchicine and doxorubicin. We found that HDM201 reverses ABCB1-mediated MDR by interacting with ABCB1 and blocking its function without affecting the expression and cellular localization of ABCB1. Moreover, HDM201 promoted the accumulation of paclitaxel in cell lines that overexpress ABCB1. At both high and low doses, HDM201 increased the ATPase activity of ABCB1. The computational support for the cross-reactivity of this p53 inhibitor with human ABCB1 comes from docking simulation results that align with the binding conformation of HDM201 within the vast cavity of the transmembrane region of ABCB1. In conclusion, by blocking the transport function of ABCB1, HDM201 can reverse ABCB1-mediated MDR in vitro. Citation Format: Harsh Patel, Chaoyun Cai, Zhuoxun Wu, Qiuxu Teng, Hanli Li, Zhe-Sheng Chen. ABCB1-mediated chemotherapeutic drug resistance is reversed by a potent p53-MDM2 inhibitor NVP-HDM201 [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7193.

Impact of Teacher Professional Development on Student Learning at Secondary Level

Abstract: In this paper we discuss about a study on impact of teacher professional development on student learning at secondary level. In a world where teachers are required to become ‘high-level knowledge workers’, the emergence of the school as learning organization is vital. In this context, the aim of this systematic review was to explore what comprises effective professional development for educators: i.e. what forms of teacher professional development definitively lead to positive outcomes for students? The NEP-2020 provides for a comprehensive, sustainable and reformative roadmap for a paradigm shift in the entire education system in the country, and is culturally grounded, is geared toward quality transformation, and is internationally competitive. Teacher professional development involves a continuous process of reflection, learning and further a teacher’s knowledge and skills, leading to enhanced teaching practices that positively impact on student’s learning. A teacher training programme provides teachers with skills and current pedagogy practices to help them connect with, manage, and educate their students in a way that ensures all students are learning and benefiting. A teacher professional development provides teachers with technical help to educate them and further train them in specialized areas. It also provides them with an in-depth understanding of how teacher training affects student learning. When executed properly and with the appropriate material, teacher development programmes have the potential to develop teachers to the point where they can favorably affect students not just academically but also socially. Education is the cornerstone of societal development, and at the heart of education is the teacher-student dynamic. The role of teachers extends far beyond imparting knowledge; they shape young minds, inspire curiosity, and foster a love for learning. Teachers are an important element of the education system and play an important role in the effective development and implementation of educational policies. Teacher training is not a one-time event; it is an ongoing process that encourages continuous professional development. Educators who engage in regular training sessions stay abreast of the latest educational research, methodologies, and best practices. This commitment to lifelong learning ensures that teachers remain effective and adaptable throughout their careers, positively impacting student outcomes. Teachers may have a significant influence on students and push them to stay on track during their formative years. Students who see their teachers as role models achieve extraordinary results.

Rapid pyrolysis mechanism and product distribution of coal model compounds containing typical C–O bonds

The structure and reactivity of coal is the core problem of coal chemistry, and solving it at the molecular level has been an international unsolved problem. The chemical similarity-based coal chemistry group elevates the study from the macroscopic to the molecular level. However, the previous free radical mechanism lacks experimental confirmation and theoretical computational support. Here, the pyrolysis products of model compounds are first utilized to predict pyrolysis. The hydrogen-donating solvent is then used as a radical trap to confirm the reaction. Subsequently, density functional theory calculations are utilized to aid in the validation. Finally, family components are utilized to demonstrate the universality of the free radical mechanism of coal pyrolysis. This work combines radical trapping with quantum chemical calculations to analyze the radical reaction mechanism of coal pyrolysis in depth at the molecular level. This will provide a theoretical basis for coal pyrolysis and clean and efficient utilization.

Conclusion: what should be the role of tourism education social structures to create and support collaborative learning environments and the tourism sector?

PurposeThis theme issue sought to find answers to the question: What should be the role of tourism education social structures to create and support collaborative learning environments and the tourism sector?Design/methodology/approachA thematic analysis of the articles in this collection draws together the key outcomes related to the strategic question, with particular reference to the contribution to knowledge, important to generate ideas and conceptual researches that will support institutions teaching tourism and hospitality. Archive research results and recommendations to encourage the collaboration of different stakeholders involved in sustainable tourism development. Most importantly to raise awareness of the question of what educators are doing in tourism education for social, organizational structures in learning environments and the actual tourism sector.FindingsTwo key players, the educator and sector has been challenged to consider their roles in education as well as depicting the role of social and organizational structures that support the students, institutions and the tourism sector. The main findings have proven the important role education plays for a truly sustainable tourism model, suggesting that it is not possible to create awareness of the sustainable development goals without incorporating them in the tourism education system with the support of information computer technology.Originality/valueThis paper reflects on the strategic question discussed in this theme issue, and it contains valid reviews, research studies by practitioners who are experienced in the field of tourism education with an opportunity to research, reflect and develop new possibilities in learning, mitigate negative points and increase positive tourism education roles for sustainable tourism development, in the destination and industry.

Automated all-functionals infrared and Raman spectra

AbstractInfrared and Raman spectroscopies are ubiquitous techniques employed in many experimental laboratories, thanks to their fast and non-destructive nature able to capture materials’ features as spectroscopic fingerprints. Nevertheless, these measurements frequently need theoretical and computational support in order to unambiguously decipher and assign complex spectra. Linear-response theory provides an effective way to obtain the higher-order derivatives needed, but its applicability to modern exchange-correlation functionals and pseudopotential formalism remains limited. Here, we devise an automated, open-source, user-friendly approach based on density-functional theory and the electric-enthalpy functional to allow seamless calculation from first principles of infrared absorption and reflectivity, together with zone-center phonons, static dielectric tensor, and Raman spectra. By employing a finite-displacement and finite-field approach, we allow for the use of any functional, as well as an efficient treatment of large low-symmetry structures. Additionally, we propose a simple scheme for efficiently sampling the Brillouin zone at different electric fields. To demonstrate the capabilities of the present approach, we study ferroelectric LiNbO3 crystal as a paradigmatic example, and predict infrared and Raman spectra using various (semi)local, Hubbard corrected, and hybrid functionals. Our results also show how PBE0 and extended Hubbard functionals (PBEsol+U+V) yield for this case the best match in term of peak positions and intensities, respectively.

Cybersecurity and critical care staff: A mixed methods study

IntroductionCyberattacks on healthcare organisations are becoming increasingly common and represent a growing threat to patient safety. The majority of breaches in cybersecurity have been attributed to human error. Intensive care departments are particularly vulnerable to cyberattacks. The aim of this study was to investigate cybersecurity awareness, knowledge and behaviours among critical care staff. MethodsThis was a multi-site cross-sectional survey study administered to critical care staff. Cybersecurity awareness was evaluated using the validated HAIS-Q instrument. Knowledge and behaviours were evaluated by direct questioning and scenario-based multiple-choice questions. Free text options were also offered to respondents. Thematic analysis was performed on free text sections. ResultsMedian scores of 12–15 in each of the HAIS-Q focus areas were achieved, indicating high levels of cybersecurity awareness among critical care staff. However, self-reported confidence in cybersecurity practices, especially identifying signs of cybersecurity breaches and reporting cybersecurity incidents, were relatively low. Participants responses to the scenarios demonstrated a lack of knowledge and awareness of some of the mechanisms of cyberattacks. Barriers to safe cybersecurity practices among staff that emerged from the qualitative analysis included: a lack of training and education; heavy workloads and staff fatigue; perceived lack of IT support and poor IT infrastructure. ConclusionCritical care staff appear to have a high-level cybersecurity awareness. However, in practice safe cybersecurity practices are not always followed. ICU departments and hospitals must invest in the human aspect of cybersecurity to strength their cyber-defences and to protect patients.

Trajectory-Aware Offloading Decision in UAV-Aided Edge Computing: A Comprehensive Survey.

Recently, the integration of unmanned aerial vehicles (UAVs) with edge computing has emerged as a promising paradigm for providing computational support for Internet of Things (IoT) applications in remote, disaster-stricken, and maritime areas. In UAV-aided edge computing, the offloading decision plays a central role in optimizing the overall system performance. However, the trajectory directly affects the offloading decision. In general, IoT devices use ground offload computation-intensive tasks on UAV-aided edge servers. The UAVs plan their trajectories based on the task generation rate. Therefore, researchers are attempting to optimize the offloading decision along with the trajectory, and numerous studies are ongoing to determine the impact of the trajectory on offloading decisions. In this survey, we review existing trajectory-aware offloading decision techniques by focusing on design concepts, operational features, and outstanding characteristics. Moreover, they are compared in terms of design principles and operational characteristics. Open issues and research challenges are discussed, along with future directions.

Machine Learning-Based Prediction of Glioma IDH Gene Mutation Status Using Physio-Metabolic MRI of Oxygen Metabolism and Neovascularization (A Bicenter Study).

The mutational status of the isocitrate dehydrogenase (IDH) gene plays a key role in the treatment of glioma patients because it is known to affect energy metabolism pathways relevant to glioma. Physio-metabolic magnetic resonance imaging (MRI) enables the non-invasive analysis of oxygen metabolism and tissue hypoxia as well as associated neovascularization and microvascular architecture. However, evaluating such complex neuroimaging data requires computational support. Traditional machine learning algorithms and simple deep learning models were trained with radiomic features from clinical MRI (cMRI) or physio-metabolic MRI data. A total of 215 patients (first center: 166 participants + 16 participants for independent internal testing of the algorithms versus second site: 33 participants for independent external testing) were enrolled using two different physio-metabolic MRI protocols. The algorithms trained with physio-metabolic data demonstrated the best classification performance in independent internal testing: precision, 91.7%; accuracy, 87.5%; area under the receiver operating curve (AUROC), 0.979. In external testing, traditional machine learning models trained with cMRI data exhibited the best IDH classification results: precision, 84.9%; accuracy, 81.8%; and AUROC, 0.879. The poor performance for the physio-metabolic MRI approach appears to be explainable by site-dependent differences in data acquisition methodologies. The physio-metabolic MRI approach potentially supports reliable classification of IDH gene status in the presurgical stage of glioma patients. However, non-standardized protocols limit the level of evidence and underlie the need for a reproducible framework of data acquisition techniques.

The Effect of Role Stress on Burnout in IT Support

The widespread digitalization in society has resulted in technological advances in various fields growing rapidly so the number of workers in the field of Information and Communication Technology is increasing. However, it cannot be denied that the burden and demands of work in the IT field are very heavy and might cause burnout. The research aims to find out whether there is an influence of the multidimensional construct of role stress on burnout in IT Support workers. This research uses a quantitative correlational approach using simple linear regression analysis and multiple linear regression. 140 IT support workers aged 21 – 35 years who had experience in the IT field for at least 1 year participated in this study. The result of this study revealed that there is a positive and significant influence on the role of stress on burnout. The role ambiguity and role overflow dimensions have a positive effect on burnout, but the role conflict dimension does not affect burnout.

Influence of Implementing an Opioid Stewardship Team in the Primary Care Setting.

Background: The Updated 2022 Centers for Disease Control (CDC) Clinical Practice Guideline for Prescribing Opioids for Pain highlights the importance of shared decision making and provider-patient relationships. Interprofessional teams may be helpful in supporting providers and patients. A large, multi-site primary care department created an interprofessional primary care opioid stewardship team to target high-risk opioid prescribing and improve practice alignment with CDC recommendations through dashboard reporting and education. Objective: The primary objective was to assess reduction in morphine milligram equivalents (MME) from baseline to 6 months in patients on opioid doses ≥90 MME daily. The secondary objective assessed change in number of naloxone prescriptions from baseline to 6 months after education. Methods: The study was conducted across 30 primary care sites of one health system within Michigan from 2021 to 2022. The opioid stewardship team included 2 physicians, 3 pharmacists, a project operations manager, and IT support. Interventions included creation of a dashboard, provider education, dissemination of policy, and chart audits. Using the electronic health record (EHR) dashboard, patients on chronic opioid doses ≥90 MME daily or missing an active naloxone prescription were identified. Primary care providers (PCP) were provided with an individual list of patients for whom to consider intervention. Support was provided for prescribers, but the team did not interact with patients directly. Results: Baseline analysis identified 290 patients on doses ≥ 90 MME daily. There was reduction in median daily MME from baseline to 6 months in the overall study population (140 [105 240] vs 120 [90 240], P < .001). At 6 months 181 (62.4%) of patients had been given a prescription for naloxone versus 108 (37.2%) who had one at baseline, P < .001. Conclusion: The initiatives implemented by the opioid stewardship team resulted in statistically significant reductions in MME and an increase in naloxone prescribing from baseline to 6 months post-education.

Computational modeling and analysis of a fluid test rig

Nanofluids, which are suspensions of metallic or ceramic nanoparticle fillers in a variety of liquids, are a new category of heat-transfer fluids. Owing to the changes in thermal conductivity caused by nanofillers, they have thermal properties that are superior to those of conventional fluids; this leads to a more efficient heat transfer, making them attractive for various industrial applications. Using numerical models to support in situ experiments is necessary to analyze nanofluids’ thermal properties and flow; creating a test ring has been suggested to describe the characteristics and behavior of fluids under controlled conditions. Modeling and computational analysis support such advances, which are essential for understanding and optimizing phenomena occurring during experimental tests; the modeling and computational analysis of a test rig designed to characterize a diphenyl oxide/biphenyl blend base fluid are presented in this research work. The test rig design included an integrated stainless-steel piping system with a flow-controlled pump and heat exchanger; the computational model considers the conjugate effects of fluid dynamics to facilitate the construction of test rigs.

Unified Framework for Faster Clustering via Joint Schatten p-Norm Factorization With Optimal Mean.

To enhance the effectiveness and efficiency of subspace clustering in visual tasks, this work introduces a novel approach that automatically eliminates the optimal mean, which is embedded in the subspace clustering framework of low-rank representation (LRR) methods, along with the computationally factored formulation of Schatten p -norm. By addressing the issues related to meaningful computations involved in some LRR methods and overcoming biased estimation of the low-rank solver, we propose faster nonconvex subspace clustering methods through joint Schatten p -norm factorization with optimal mean (JS p NFOM), forming a unified framework for enhancing performance while reducing time consumption. The proposed approach employs tractable and scalable factor techniques, which effectively address the disadvantages of higher computational complexity, particularly when dealing with large-scale coefficient matrices. The resulting nonconvex minimization problems are reformulated and further iteratively optimized by multivariate weighting algorithms, eliminating the need for singular value decomposition (SVD) computations in the developed iteration procedures. Moreover, each subproblem can be guaranteed to obtain the closed-form solver, respectively. The theoretical analyses of convergence properties and computational complexity further support the applicability of the proposed methods in real-world scenarios. Finally, comprehensive experimental results demonstrate the effectiveness and efficiency of the proposed nonconvex clustering approaches compared to existing state-of-the-art methods on several publicly available databases. The demonstrated improvements highlight the practical significance of our work in subspace clustering tasks for visual data analysis. The source code for the proposed algorithms is publicly accessible at https://github.com/ZhangHengMin/TRANSUFFC.

Determinants of Implementing an Information and Communication Technology Tool for Social Interaction Among Older People: Qualitative Content Analysis of Social Services Personnel Perspectives.

Older people are particularly vulnerable to social isolation and loneliness, which can lead to ill-health, both mentally and physically. Information and communication technology (ICT) can supplement health and social care and improve health among the vulnerable, older adult population. When ICT is used specifically for communication with others, it is associated with reduced loneliness in older populations. Research is sparse on how the implementation of ICT, used specifically for communication among older people in social services, can be performed. It is recommended to consider the determinants of implementation, that is, barriers to and facilitators of implementation. Determinants related to older people using ICT tools are reported in several studies. To the best of our knowledge, studies investigating the determinants related to the social services perspective are lacking. This study aims to explore the determinants of implementing the Fik@ room, a new, co-designed, and research-based ICT tool for social interaction among older people, from a social services personnel perspective. This study used an exploratory, qualitative design. An ICT tool called the Fik@ room was tested in an intervention study conducted in 2021 in 2 medium-sized municipalities in Sweden. Informants in this study were municipal social services personnel with experience of implementing this specific ICT tool in social services. We conducted a participatory workshop consisting of 2 parts, with 9 informants divided into 2 groups. We analyzed the data using qualitative content analysis with an inductive approach. The results included 7 categories of determinants for implementing the ICT tool. Being able to introduce the ICT tool in an appropriate manner concerns the personnel's options for introducing and supporting the ICT tool, including their competencies in using digital equipment. Organizational structure concerns a structure for communication within the organization. Leadership concerns engagement and enthusiasm as driving forces for implementation. The digital maturity of the social services personnel concerns the personnel's skills and attitudes toward using digital equipment. Resources concern time and money. IT support concerns accessibility, and legal liability concerns possibilities to fulfill legal responsibilities. The results show that implementation involves an entire organization at varying degrees. Regardless of how much each level within the organization comes into direct contact with the ICT tool, all levels need to be involved to create the necessary conditions for successful implementation. The prerequisites for the implementation of an ICT tool will probably change depending on the digital maturity of future generations. As this study only included 9 informants, the results should be handled with care. The study was performed during the COVID-19 pandemic, which has probably affected the results.

Philosophy of Al-Farabi In Developing A Digital Music Notation Training Model for High School Art and Culture Teachers Based on CSCL

This article explores the philosophical aspects of Al-Farabi in the development of a music art training model, aimed at assisting high school Art and Culture teachers in understanding and teaching digital music notation. Al-Farabi, a great philosopher from the Classical Islamic period, offers valuable insights into education and learning, which are applicable in the context of music art teaching. The article elucidates how Al-Farabi's views, particularly on ethics, morality, and happiness, can be integrated into a training model based on Computer Support Collaborative Learning (CSCL) to enrich the art teachers' learning experience. Furthermore, it provides an overview of how digital music notation can be implemented in high school cultural arts education and why this approach is relevant in the rapidly evolving context of music education. This article is expected to serve as a guide for developing a holistic and philosophical training model in music art education, focusing on understanding digital music notation and applying Al-Farabi's philosophical principles in the learning process. Additionally, this research highlights the importance of integrating technology in art education, demonstrating how digital approaches can broaden the horizons of music art learning. Moreover, the article seeks to prove how teaching methods inspired by Al-Farabi's thoughts can enhance students' creativity and conceptual understanding in music art.

Effectiveness of IT-supported patient recruitment: study protocol for an interrupted time series study at ten German university hospitals

BackgroundAs part of the German Medical Informatics Initiative, the MIRACUM project establishes data integration centers across ten German university hospitals. The embedded MIRACUM Use Case “Alerting in Care - IT Support for Patient Recruitment”, aims to support the recruitment into clinical trials by automatically querying the repositories for patients satisfying eligibility criteria and presenting them as screening candidates. The objective of this study is to investigate whether the developed recruitment tool has a positive effect on study recruitment within a multi-center environment by increasing the number of participants. Its secondary objective is the measurement of organizational burden and user satisfaction of the provided IT solution.MethodsThe study uses an Interrupted Time Series Design with a duration of 15 months. All trials start in the control phase of randomized length with regular recruitment and change to the intervention phase with additional IT support. The intervention consists of the application of a recruitment-support system which uses patient data collected in general care for screening according to specific criteria. The inclusion and exclusion criteria of all selected trials are translated into a machine-readable format using the OHDSI ATLAS tool. All patient data from the data integration centers is regularly checked against these criteria. The primary outcome is the number of participants recruited per trial and week standardized by the targeted number of participants per week and the expected recruitment duration of the specific trial. Secondary outcomes are usability, usefulness, and efficacy of the recruitment support. Sample size calculation based on simple parallel group assumption can demonstrate an effect size of d=0.57 on a significance level of 5% and a power of 80% with a total number of 100 trials (10 per site). Data describing the included trials and the recruitment process is collected at each site. The primary analysis will be conducted using linear mixed models with the actual recruitment number per week and trial standardized by the expected recruitment number per week and trial as the dependent variable.DiscussionThe application of an IT-supported recruitment solution developed in the MIRACUM consortium leads to an increased number of recruited participants in studies at German university hospitals. It supports employees engaged in the recruitment of trial participants and is easy to integrate in their daily work.

Calanthe yingjiangensis (Epidendroideae; Orchidaceae), a new species from China: evidence from morphological and molecular data

A new species of Orchidaceae, Calanthe yingjiangensis, is described from Yingjiang (Yunnan, China) based on morphology and molecular phylogenetics. This new species is like C. puberula, but it differs from the latter in its midlob of lip with an elliptic yellow spot near the base of the column and four purple veins, triangular lateral lip lobs that is much smaller than middle lobe and twisted lateral sepals. Molecular phylogenetic analyses based on three plastid DNA makers (rbcL, matK and trnL-trnF) and nuclear ribosomal ITS support C. yingjiangensis as sister to C. puberula in Calanthe section Vernae.

A Lung Cancer Detection with Pre-Trained CNN Models

Lung cancer is a common cancer in Malaysia, affecting the majority of male citizens. The early detection of lung cancer will decrease its death rate. The only way to detect lung cancer is with a CT scan, and it also requires the doctor to check the scan to confirm the disease. In another way, the computer's support for the detection and diagnosis tool will assist doctors in determining lung cancer more accurately and efficiently. There are three main objectives for this research work. The first target is to study state-of-the-art research work to detect and recognize lung cancer from CT scan images. Then, the article will aim to adopt pre-trained convolutional neural network models in lung cancer detection. It also evaluates the performance of convolutional models on lung cancer imagery data. Then, the pre-trained models with a few added layers and modifications to parameters such as epochs, batch size, optimizer, etc. to conduct model training in this article. After that, Python Pylidc is used in image pre-processing to filter the dataset. Overall, pre-trained models such as ResNet-50, VGG-16, Xception, and MobileNet achieve above-state-of-the-art performance in classifying lung cancer from CT scan images in the range of 78% to 86% accuracy. The best detection accuracy result is the pre-trained VGG-16 model with the addition of some fully connected layers, 16 batch sizes, and the Adam optimizer, which achieved 86.71%.