Iterative Improvement Research Articles

Enhancing Performance Metrics: A Google Looker Studio Approach to Key Performance Indicator (KPI) Management System for Homecorp Offshore Drafting Team

The Homecorp Offshore Drafting Key Performance Indicator (KPI) Management System is a comprehensive process that aims to improve the management and monitoring of key performance indicators within the drafting department. This system utilizes Google Looker Studio, which provides a user-friendly real-time data analysis and visualization platform. It enables managers to make well-informed decisions and enhance departmental performance. The process begins with collecting daily task data, logged manually or through automated Google Apps Scripts into a Google Sheets database. This data includes task details such as type, status, and completion time. A KPI-pointing system, developed through focus group discussions, also assigns point values to tasks based on their complexity and time requirements. Integrating Google Looker Studio with Google Sheets allows real-time synchronization and web-based monitoring of key performance indicators (KPIs). The dashboard offers detailed insights such as task counts, average KPIs, and monthly performance graphs, providing a comprehensive performance evaluation. The implementation of this system has been well-received by the team, with survey results indicating improvements in tracking performance metrics, ease of use, and enhanced collaboration. While these outcomes are positive, there is still a recognized need for further refinement, particularly in incorporating qualitative data and improving IT support. The KPI Management System has significantly enhanced performance monitoring and management for the drafting team. To keep the system up-to-date and effective, ongoing feedback and iterative improvements must be maintained. Potential future enhancements could include extending the system's use company-wide to foster a culture of continuous improvement and accountability.

Modified One-Point-and-Area Algorithm for Sub-division of Irregular Parcels

Parcel sub-division is a crucial part of the Land Administration, and its techniques depend on the user requirements and other constraints. Splitting of a parcel based on a given area is one of such constraints whose subdivision has been popularly carried out using the trial-and-error method which is less accurate and time-consuming. For more accurate and direct subdivision, Habib developed algorithms based on popular eight cases. Among them, when the area to be split is known, a point or line is selected as a reference. In case if it has to be a point, then a one-point-and-area method is used for subdivision while a move-line-and-area method is used if line segment is used as reference. It was found that Habib Algorithm worked well for convex shapes, however it could not account for the concavity of irregular-shaped parcels. It was found that the approach for the calculation of the area considered only the cases of convex shapes. Therefore, the researchers observed the issues of clinging and retracting were identified. Thus, this study proposes an effective algorithm for the division of an irregular parcel using an improved version of One-Point-and-Area method used in Habib Algorithm. An additional stage of generating a convex hull was introduced to guide the iteration process, the formula to calculate area was adjusted to compute only the interior area and finally, the determination of the partition polygon was also done through an iterative improvement process rather than the existing one-step process. Experiments showed that the proposed algorithm accurately divided both irregular-shaped parcels and convex parcels. In the case of convex parcels, the result was found to be the same as Habib’s method. Due to the addition of an extra stage of generating a convex hull and extra iterations in the final stage, the proposed algorithm consumed more time. However, it was found negligible in regard to the volume of parcels involved in splitting at a time. Overall, the proposed algorithm accurately solved the issues of clinging and retracting irregular polygons and without changing the results in convex polygons. So, it was concluded to be a suitable replacement of Habib Algorithm, and its implementation will provide more accurate results in parcel sub-division problems.

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification.

Deep learning (DL) models for medical image classification frequently struggle to generalize to data from outside institutions. Additional clinical data are also rarely collected to comprehensively assess and understand model performance amongst subgroups. Following the development of a single-center model to identify the lung sliding artifact on lung ultrasound (LUS), we pursued a validation strategy using external LUS data. As annotated LUS data are relatively scarce-compared to other medical imaging data-we adopted a novel technique to optimize the use of limited external data to improve model generalizability. Externally acquired LUS data from three tertiary care centers, totaling 641 clips from 238 patients, were used to assess the baseline generalizability of our lung sliding model. We then employed our novel Threshold-Aware Accumulative Fine-Tuning (TAAFT) method to fine-tune the baseline model and determine the minimum amount of data required to achieve predefined performance goals. A subgroup analysis was also performed and Grad-CAM++ explanations were examined. The final model was fine-tuned on one-third of the external dataset to achieve 0.917 sensitivity, 0.817 specificity, and 0.920 area under the receiver operator characteristic curve (AUC) on the external validation dataset, exceeding our predefined performance goals. Subgroup analyses identified LUS characteristics that most greatly challenged the model's performance. Grad-CAM++ saliency maps highlighted clinically relevant regions on M-mode images. We report a multicenter study that exploits limited available external data to improve the generalizability and performance of our lung sliding model while identifying poorly performing subgroups to inform future iterative improvements. This approach may contribute to efficiencies for DL researchers working with smaller quantities of external validation data.

Global Health Initiatives: International Physician-to-Physician Consultation Programs

PurposeThe goal of this article is to provide technical and operational blueprints for two successful global telehealth programs. MethodsThe authors designed a physician-to-physician consultation program to provide subspecialty expertise to physicians in war-torn Ukraine. Leveraging secure web applications, telehealth platforms, and image-sharing platforms, the authors repeatedly iterated upon infrastructure and workflows, which in turn facilitated the development of a parallel international program for US Department of State (DOS) employees and families. The authors provide descriptive statistics and metrics of both programs’ successes and failures and detail iterative improvements with workflow visuals. To measure the added value of subspecialty imaging consultation, two radiologists performed a retrospective comparative review of the DOS program imaging reports, comparing the initial report to the consult report in consensus, measuring diagnostic report agreement, and rating the clinical impact of identified discrepancies on a three-point scale (mild, moderate, or major). Bivariate analyses using χ2 tests were conducted to assess associations between diagnostic discrepancies and patient or imaging factors. P values <.05 were considered to indicate statistical significance. ResultsThe Ukraine program (May 2022 to August 2023) provided 114 patient consultations with 77 subspecialty radiology consults, >50 WhatsApp chats, and >1,000 messages exchanged, with a 92% overall consult request response rate. The DOS program (November 2022 to July 2023) provided 275 consultations with 70 subspecialty radiology consults and a 36% to 38% rate of alternative diagnoses, with 20% rated as incurring moderate or major clinical impact. Bivariate analyses demonstrated no significant patient or imaging association with diagnostic disagreements (P > .05 for all). ConclusionsGlobal telehealth infrastructure and multiple applications and platforms can be optimized in a workflow to provide efficient, high-level clinical and imaging consultation services across the globe.

Design and Development of Self Balancing Two Wheeler

The Self-balancing robots represent a fascinating intersection of technology and practical application. This project aims to design and develop a self-balancing two- wheeler robot capable of maintaining stability and balance autonomously. Drawing inspiration from principles observed in human balance and locomotion, the robot employs a combination of sensors, actuators, and control algorithms to achieve its objective. The project begins with an in-depth literature survey, exploring existing research and methodologies in the field of self-balancing robotics. Leveraging insights from key publications, the project outlines fundamental principles, sensor fusion techniques, advanced control methodologies, and challenges inherent in self-balancing robot design. Key components including an Arduino Uno board, accelerometers, gyroscopes, DC motors, batteries, and optional reaction wheels are carefully selected and integrated into the robot's hardware architecture. A systematic approach to hardware selection, assembly, sensor integration, microcontroller programming, and motor control ensures a coherent and functional design. Throughout the development process, emphasis is placed on rigorous testing, calibration, and iterative improvement. The robot is subjected to various environmental conditions and scenarios to validate its stability and performance. Calibration procedures refine sensor accuracy and control algorithms, enhancing the robot's ability to maintain balance under dynamic conditions. The project culminates in the creation of a comprehensive documentation package, detailing schematics, code explanations, assembly instructions, and testing methodologies. Additionally, a presentation showcases the robot's functionality, design rationale, and potential applications. By meticulously following the outlined steps and leveraging insights from existing research, this project aims to contribute to the advancement of self-balancing robotics and serve as a foundation for future exploration and innovation in this exciting field

Practical Multi-Mesh Registration for Few-View Poly-Chromatic X-Ray Inspection

Accurate 3D mesh registration is essential in many industrial applications of X-ray imaging, as it allows quality assessment and inspection of manufactured objects. Conventional methods rely mainly on time-consuming and expensive X-ray computed tomography (X-CT) or ancillary camera systems. Instead, we propose a novel approach for efficient 3D multi-mesh registration in few-view industrial X-ray imaging scenarios. Our approach harnesses the capabilities of CAD-ASTRA, an X-ray mesh projector, compatible with the ASTRA toolbox and popular GPU libraries such as CuPy and PyTorch, for the simulation of X-ray projec tions from a known object surface mesh. As a differentiable program, CAD-ASTRA allows iterative improvement of the objects’ position in space by back-propagation of a differentiable measure of the projection error. The potential of this approach is demonstrated through tests on simultaneous multiple object registration in a poly-chromatic imaging, even in cases where the spectral characteristics of the imaging system are unknown. Results from a diverse set of real experiments highlight the efficacy of mesh registration, achieving successful registrations even when only two projections at a 10∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\circ $$\\end{document} angle relative to the scanning system center are available. The mesh projector facilitates resource-efficient registration in industrial applications with few viewpoints, thereby reducing the demand for resources and eliminating the need for X-CT reconstruction.

Impact of Implementing Serious Illness Conversations Across a Comprehensive Cancer Center Using an Interdisciplinary Approach.

Gaps in communication of end-of-life care preferences increase risk of patient harm. Adoption of oncology practice guidelines advocating serious illness communication for patients with advanced cancer is limited. (1) Increase Serious Illness Conversation (SIC) use across oncology teams via an interdisciplinary quality improvement (QI) approach and (2) assess patient reported shared decision making (SDM) experiences with clinicians engaged in SIC implementation. QI methodology was applied to spread the implementation of SIC across 4 oncology teams. CollaboRATE scores were used to evaluate patient reported outcomes of SDM for patients with advanced cancer. The SIC QI initiative was a component of the Promise Partnership Learning Health System (PPLHS) piloted in the Dartmouth Cancer Center, Lebanon, NH, USA. (1) The percentage of eligible patients with documented SIC and (2) a comparison of a patient reported measure of SDM (CollaboRATE) among SIC eligible patients in encounters with providers who took part in the implementation versus those who did not. Oncology teams screened a total of 538 patients, identified 278 eligible patients, and completed 144 SIC conversations. The teams improved the proportion of documented SIC among eligible patients from near 0% to a collective frequency of 52%. For clinicians' top-box CollaboRATE scores, a chi-squared test demonstrated a statistically significant association between providers implementing SIC into practice and patient reported shared decision making (.16, p = .031). This approach allows for tailoring of iterative improvement cycles to mitigate barriers and improve the practice of SIC among oncology teams.

Beyond conventional teaching towards networked learning

With Generative Artificial Intelligence (GenAI) adoption growing, education has seen the emergence of innovative technologies like chatbots. However, little research has examined the impacts of GenAI integration in specialized higher education contexts. This study explored graduate students’ experiences using a GenAI chatbot, PEARL, within a graduate-level teacher education course focused on teaching students how to collaboratively conduct program evaluations using practice cases. Four students participated in our study and shared perceptions of interviewing personas with PEARL when evaluating the practice cases. Thematic analysis identified advantages like enhanced efficiency and accessibility, plus limitations regarding authenticity of artificial interactions. Findings emphasized the continued importance of human guidance and peer learning to enrich GenAI-enabled education aligning with principles of networked learning. Students highlighted the need for ethical considerations despite interacting with artificial entities, underscoring nuanced understanding. The significance of collaborative analysis and ongoing iterative improvements also emerged as themes integral to meaningful learning. Although GenAI presents transformational potential in instructional designs, findings support the use of blended approaches that strategically integrate its advantages with human activity and collaborative inquiry. The study makes contributions by elucidating domain-specific nuances of integrating GenAI into teaching in higher education. Practical implications encourage scaffolding GenAI curricula to promote authenticity and collaborative knowledge construction. Further research could examine variations across disciplines, technologies, and demographics. Overall, as GenAI shapes academia’s evolution, reflective pedagogical examination will be key to evidence-guided integration. This exploratory study presents a preliminary yet important step, unveiling opportunities for networked learning and complexities of GenAI adoption in teaching program evaluation skills in education contexts.

Iterative improvement in tacholess speed estimation using instantaneous error estimation for machine condition monitoring in variable speed

Knowing the instantaneous angular speed (IAS) is crucial for monitoring the condition of variable speed rotating machinery. Thanks to advantages such as cost-saving, simplicity, and reduced installation difficulties, tacholess speed estimation (TSE) methods, based on the vibration signal itself, have attracted increasing attention in recent years. The major problem limiting the use of TSE methods in industry is that the accuracy of the IAS estimates is usually unknown. A less accurate IAS estimate implies errors in the extracted phase-time map. When this map is used for order tracking, it leads to a smeared order spectrum, thereby affecting subsequent vibration analysis. However, how the smearing of the order spectrum, introduced by phase modulation from the IAS error, can be used to further improve the accuracy of the estimated IAS has not been fully studied. This study first investigates the influence of the IAS error on the order tracked signal. It is realized that the instantaneous error of an estimated IAS can be estimated from the order tracked vibration signal. The estimated IAS can therefore be calibrated iteratively using the estimated instantaneous error in the IAS. The proposed method for iteratively improving accuracy of the estimated IAS based on the estimated instantaneous IAS error is validated using industrial data from wind turbines. While the method does add significant computational complexity, little additional human input is required beyond that of established methods. The results show the effectiveness of the method in producing IAS estimates that are several times more accurate than those given by existing methods.

Development of a protocol for using geo-trackers to identify zoonotic enteric pathogen transmission pathways in a pilot study in Kenya

Abstract Humans and animals can be exposed to fecally-transmitted pathogens in both private and public domain environments. Animals may also acquire pathogen infections from these two environments and transmit them to humans through different pathways. Evidence on how often and where interactions occur between the two environments could improve the effectiveness of public health programs for preventing zoonotic disease transmission and response to disease outbreaks. This study aimed to develop a protocol for using geo-trackers to measure the spatial-temporal movement and interaction between animals and children in households and public areas in low- and middle-income categories of urban neighbourhoods in Kenya. It also aimed to identify opportunities and challenges for the scale-up of these methods’ for surveillance of other zoonotic diseases of public health significance. One commercial geo-tracker device with the best technological performance and usability that met pre-defined criteria for the study context was identified. Community engagement meetings were then conducted to gather input on a proposed study protocol. Afterwards, infants and animals were geo-tracked in 10 households in urban informal settlements of Kibera and Jericho, Nairobi over two consecutive weeks with iterative improvements to protocols. The effectiveness of the geo-tracking exercise was evaluated through in-depth interviews with Community Health Volunteers (CHVs) and infant caregivers. Animal and infant behaviour and battery reliability of the geo-trackers were also monitored; and observed opportunities and challenges in implementing the protocol during the exercise were documented. Community members were receptive and accepted the use of geo-trackers on animals and children. In pilot testing, there was no change of behaviour from 10 infants tracked. Discomfort was observed for up to 30 min after the placement for some of the seven animals tracked, but the animals quickly adjusted. The battery for all geo-tracker devices lasted for the 24-h geo-tracking period. Some caregivers and CHVs were concerned whether the geo-trackers could record personal information. It was shown that geo-tracker devices can be successfully deployed to study animal-child interactions and movement in different categories of urban neighbourhoods. Recommendations have been made on the lessons learnt from the study to help scientists who would use geo-trackers for future community-based human and animal research. One Health impact statement Assessing human and animal risks of acquiring enteric infections from environmental contamination, or contributing to pathogen contamination of the environment requires understanding spatial-temporal patterns of human and animal movement between private households and the community. Movement of domestic animals is relevant for understanding household-community spatial patterns of pathogen transmission because animal ownership and contact with humans is common, and free-roaming animals carrying enteric pathogens can spread diverse faecal pathogens between environments. The community-based participatory research approach of this study evaluated implementation feasibility from the lens of technical usability and reliability of geo-tracking devices, as well as social acceptability and ethics related to using such devices for the community-based study of human and animal subjects in urban settings. Evidence and recommendations from this study will be useful to anyone interested in understanding human-animal-environment interactions and their contributions to infectious disease transmission.

Enhancing cubic polynomial solutions: A comprehensive analysis and iterative refinement strategy in response to the versatility of cubic equations of state

The study presents a comprehensive evaluation of ten distinct methods for solving cubic equations, encompassing both analytical, numerical, and linear algebra-based approaches. Among these, an analytical technique involving the transformation of cubic equations into Chebyshev polynomials emerged as the most efficient. To mitigate issues arising from numerical round-off errors, the study proposes an iterative refinement strategy. Furthermore, the research introduces a novel criterion grounded in Vieta's formulas to identify and isolate areas where round-off errors may occur. This criterion aids in the application of the proposed iterative refinement technique. The novel solution method, which involves the conversion of cubic equations into Chebyshev polynomials and subsequent error-checking and iterative refinement, exhibits significant advantages. Firstly, it proves efficient, reducing computational time by 15–20 % in comparison to the well-established Cardano analytical method. It also demonstrates robustness in effortlessly identifying regions of potential error and offers a method for iterative improvement when needed. Additionally, its reliability is underscored by its independence from the specific cubic equation of state under consideration, making it well-suited for the intensive solution of a wide range of cubic equations.

Plan-do-study-act (PDSA) interventions to improve real-world endoscopy unit productivity.

Background and study aims The Plan-Do-Study Act (PDSA) ramp is a framework that uses initial small changes to build consensus and momentum for subsequent, iterative process improvement. Our aim was to study its impact on endoscopy unit efficiency and throughput. Methods Following a granular time-and-motion analysis to evaluate baseline performance (phase 1) we instituted successive interventions and measured their impact on core efficiency metrics including procedure volume and turnover time (phases 2-3). Results We identified that inefficiency in turnover of anesthesia-supported endoscopy was the most crucial issue. Implementation of a pre-procedure anesthesia visit in phase 2 reduced turnover time by 15.5 minutes (95% confidence interval 3.9-27.1 minutes). Subsequent changes (phase 3) including front-loaded procedure scheduling and parallel in-room preparation resulted in an 18% increase in procedure volume. Conclusions The PDSA ramp model is an effective means of assessing operational processes, developing novel interventions, and building consensus to improve the real-world productivity in a resource-conscious manner.

Construction Path of Rural Study Base Based on Service Design Concept

The establishment of rural study bases offers a promising opportunity to improve educational opportunities and community development in remote areas. This research investigates the development path of rural study bases using service design concepts that emphasize user-centric methods, stakeholder interaction, and iterative improvement procedures. Understanding rural communities' particular needs and goals allows remote study bases to plan and implement meaningful and impactful educational programs and services. Rural study bases strive to build favourable learning settings that encourage active engagement and cooperation by combining physical infrastructure development, digital resource integration, and community outreach efforts. This paper, using examples from diverse industries and situations, discusses essential issues and best practices for efficiently adopting service design principles in the establishment of rural study bases. Finally, rural studies based on service design concepts show promise for improving socioeconomic outcomes and empowering rural people through education. As an outcome, it provides high user satisfaction (94%), effective community outreach, excellent digital resource integration, enhanced academic performance, and strong stakeholder engagement

Culture change and lessons learned from ten years in the VA centers of excellence in primary care education

BackgroundTeam-based care is critical to achieving health care value while maximizing patient outcomes. Few descriptions exist of graduate-level team training interventions and practice models. Experience from the multisite, decade-long Veterans Affairs (VA) Centers of Excellence in Primary Care Education provides lessons for developing internal medicine training experiences in interprofessional clinical learning environments.MethodsA review of multisite demonstration project transforming traditional silo-model training to interprofessional team-based primary care. Using iterative quality improvement approaches, sites evaluated curricula with learner, faculty and staff feedback. Learner- and patient-level outcomes and organizational culture change were examined using mixed methods, within and across sites. Participants included more than 1600 internal medicine, nurse practitioner, nursing, pharmacy, psychology, social work and physical therapy trainees. This took place in seven academic university-affiliated VA primary care clinics with patient centered medical home designResultsEach site developed innovative design and curricula using common competencies of shared decision making, sustained relationships, performance improvement and interprofessional collaboration. Educational strategies included integrated didactics, workplace collaboration and reflection. Sites shared implementation best practices and outcomes. Cross-site evaluations of the impacts of these educational strategies indicated improvements in trainee clinical knowledge, team-based approaches to care and interest in primary care careers. Improved patient outcomes were seen in the quality of chronic disease management, reduction in polypharmacy, and reduced emergency department and hospitalizations. Evaluations of the culture of training environments demonstrated incorporation and persistence of interprofessional learning and collaboration.ConclusionsAligning education and practice goals with cross-site collaboration created a robust interprofessional learning environment. Improved trainee/staff satisfaction and better patient care metrics supports use of this model to transform ambulatory care training.Trial registrationThis evaluation was categorized as an operation improvement activity by the Office of Academic Affairs based on Veterans Health Administration Handbook 1058.05, in which information generated is used for business operations and quality improvement (Title 38 Code of Federal Regulations Part 16 (38 CFR 16.102(l)). The overall project was subject to administrative oversight rather Human Subjects Institutional Review Board, as such informed consent was waived as part of the project implementation and evaluation.

Architecture-level energy model for high-capacity STT-MRAM memory

ABSTRACT Nowadays, STT-MRAM has emerged as one of the leading contenders for next-generation memory technologies. However, STT-MRAM still exhibits high energy consumption due to its peripheral circuits, including the read/write and the sample amplifier (SA) circuits. Therefore, it is crucial to accurately evaluate the energy consumption of memory architectures during the early stages of the design process. Traditionally, energy evaluation can be conducted using the NVSim platform. However, the peripheral read/write circuitry of STT-MRAM undergoes iterative improvements, which cannot be promptly incorporated into NVSim. To addreGss this limitation and to enable comprehensive energy consumption evaluations spanning from device-level to architecture-level for STT-MRAM, an architecture-level energy consumption model is proposed in this paper. The model offers high accuracy and flexibility for the STT-MRAM memory array structure, abstracting the influences of read/write circuits for power evaluations. Comparative analysis is performed between the proposed model and the traditional approaches. When estimating a memory array with 128 × 64, the deviation using the proposed model is less than 2%, showing improved accuracy compared to that with analytical formulas. Notably, the proposed model offers up to 97% time savings in the whole circuit simulation, thus enhancing efficiency in the design and evaluation process.

Assessing ChatGPT 4.0’s test performance and clinical diagnostic accuracy on USMLE STEP 2 CK and clinical case reports

While there is data assessing the test performance of artificial intelligence (AI) chatbots, including the Generative Pre-trained Transformer 4.0 (GPT 4) chatbot (ChatGPT 4.0), there is scarce data on its diagnostic accuracy of clinical cases. We assessed the large language model (LLM), ChatGPT 4.0, on its ability to answer questions from the United States Medical Licensing Exam (USMLE) Step 2, as well as its ability to generate a differential diagnosis based on corresponding clinical vignettes from published case reports. A total of 109 Step 2 Clinical Knowledge (CK) practice questions were inputted into both ChatGPT 3.5 and ChatGPT 4.0, asking ChatGPT to pick the correct answer. Compared to its previous version, ChatGPT 3.5, we found improved accuracy of ChatGPT 4.0 when answering these questions, from 47.7 to 87.2% (p = 0.035) respectively. Utilizing the topics tested on Step 2 CK questions, we additionally found 63 corresponding published case report vignettes and asked ChatGPT 4.0 to come up with its top three differential diagnosis. ChatGPT 4.0 accurately created a shortlist of differential diagnoses in 74.6% of the 63 case reports (74.6%). We analyzed ChatGPT 4.0’s confidence in its diagnosis by asking it to rank its top three differentials from most to least likely. Out of the 47 correct diagnoses, 33 were the first (70.2%) on the differential diagnosis list, 11 were second (23.4%), and three were third (6.4%). Our study shows the continued iterative improvement in ChatGPT’s ability to answer standardized USMLE questions accurately and provides insights into ChatGPT’s clinical diagnostic accuracy.

Improving emergency evacuation capacity for subway stations based on agent-based modelling

Purpose Modern subway transportation systems need to satisfy increasing safety demands to rapidly evacuate passengers under hazardous emergency circumstances, such as fires, accidents or terrorist attacks, to reduce passenger injuries or life losses. The emergency evacuation capacity (EEC) of a subway station needs to be revised timely, in case passenger demand increases or the evacuation route changes in the future. However, traditional ways of estimating EEC, e.g. fire drills are time- and resource-consuming and are difficult to revise from time to time. The purpose of this study is to establish an intuitive modelling approach to increase the EEC of subway stations in a stepwised manner. Design/methodology/approach This study develops an approach to combine agent-based evacuation modelling and building information modelling (BIM) technology to estimate the total evacuation time of a subway station. Findings Evacuation time can be saved (33% in the studied case) from iterative improvements including stopping escalators running against the evacuation flow and modifying the geometry around escalator exits. Such iterative improvements rely on integrating agent-based modelling and BIM. Originality/value The agent-based model can provide a more realistic simulation of intelligent individual movements under emergency circumstances and provides precise feedback on locations of evacuation bottlenecks. This study also examined the effectiveness of two rounds of stepwise improvements in terms of operation or design to increase the EEC of the station.

Structural Survey of Antigen Recognition by Synthetic Human Antibodies.

Synthetic antibody libraries have been used extensively to isolate and optimize antibodies. To generate these libraries, the immunological diversity and the antibody framework(s) that supports it outside of the binding regions are carefully designed/chosen to ensure favorable functional and biophysical properties. In particular, minimalist, single-framework synthetic libraries pioneered by our group have yielded a vast trove of antibodies to a broad array of antigens. Here, we review their systematic and iterative development to provide insights into the design principles that make them a powerful tool for drug discovery. In addition, the ongoing accumulation of crystal structures of antigen-binding fragment (Fab)-antigen complexes generated with synthetic antibodies enables a deepening understanding of the structural determinants of antigen recognition and usage of immunoglobulin sequence diversity, which can assist in developing new strategies for antibody and library optimization. Toward this, we also survey here the structural landscape of a comprehensive and unbiased set of 50 distinct complexes derived from these libraries and compare it to a similar set of natural antibodies with the goal of better understanding how each achieves molecular recognition and whether opportunities exist for iterative improvement of synthetic libraries. From this survey, we conclude that despite the minimalist strategies used for design of these synthetic antibody libraries, the overall structural interaction landscapes are highly similar to natural repertoires. We also found, however, some key differences that can help guide the iterative design of new synthetic libraries via the introduction of positionally tailored diversity.

Weight Optimization for missing data prediction of Landslide Susceptibility Mapping in Remote sensing Analysis

To keep track of changes to the Earth's surface, extensive time series of data from remote sensing using image processing is required. This research is motivated by the effectiveness of computational modelling techniques; however, the problem of missing data is multifaceted. When data at numerous a-periodic timestamps are absent during multi-temporal analysis, the issue becomes increasingly problematic. To make remote sensing time series analysis easier, weight optimised machine learning is used in this study to rebuild lost data. Keeping the causality restriction in mind, this method makes use of data from previous and subsequent timestamps. The architecture is based on an ensemble of numerous forecasting modules, built on the observed data in the time-series order. Dummy data is used to connect the forecasting modules, which were previously linked by the earlier half of the sequence. After that, iterative improvements are made to the dummy data to make it better fit the next segment of the sequence. On the basis of Landsat-7 TM-5 satellite imagery, the work has been proven to be accurate in forecasting missing images in normalised difference vegetation index time series. In a performance evaluation, the proposed forecasting model was shown to be effective.

SmartFarm: A Machine Learning-Based Analytical System for Soil Classification and Crop Recommendation in Precision Agriculture

Abstract: SmartFarm is an innovative machine learning-driven analytical system designed to revolutionize precision agriculture through accurate soil classification and tailored crop recommendations. The project focuses on collecting comprehensive soil and historical crop data, employing rigorous preprocessing techniques, and implementing knowledge-based classification and non-parametric classifiers such as decision trees and neural networks. The system integrates these models, ensuring a cohesive approach to support seamless decision-making for farmers. With a user-friendly interface, SmartFarm enables farmers to input soil data and receive personalized crop recommendations. The project's scalability, adaptability, and commitment to iterative improvement through user feedback make it a promising solution for enhancing agricultural productivity and sustainability. The outcomes contribute to the evolving landscape of precision agriculture, emphasizing the power of machine learning in informed decision support systems. The outcomes underscore the potential of machine learning in fostering informed decision-making and sustainable farming in the evolving landscape of precision agriculture