Minimum Training Research Articles

What Can the Giant Do? Defining the Path to Unsupervised Primary Care Practice by Competence, Not Time.

In this issue of Academic Medicine, Dewan and Norcini examine the significant variability of time-in-training between patient care "giants"-the physicians, nurse practitioners, and physician assistants who practice primary care-and they call for further studies to determine optimal training duration and eventual scope of practice. They ask, what is the minimum education and training required to practice primary care, or "how tall is the shortest giant?" In this Invited Commentary, the authors reframe the question from identifying the minimum length of training required, to identifying desired patient care outcomes. Primary care is not a uniform entity. It ranges from complex elderly chronically ill patients, to twentysomething millennials with acute problems, to pregnant women, to families, and everything in between. The authors argue that training should be fit for purpose and produce high-quality outcomes for patients. Competence should be defined by these outcomes. Drawing parallels with Major League Baseball, the authors note that time to competence development will be variable for different training programs depending on purpose, and also variable for people within those programs, even with shared purpose. While time is a tool for competence attainment, it should not be the metric by which readiness for practice is measured.

A modified neuro-fuzzy classifier and its parallel implementation on modern GPUs for real time intrusion detection

According to the Cisco Visual Networking Index, the annual global network traffic is growing consistently and would reach 3.3 ZB by 2021. The percentage of attack traffic is also increasing with the same rate in network traffic. The rapidly growing unauthorized activities on a network need a time efficient intrusion detection system with the high detection rate of attacks. Here, we propose a modification in the recall phase of a well-known method, enhanced fuzzy min–max neural network (EFMN), with the aim to achieve high detection rate of attacks in the minimum training and recall time. The modified-EFMN is employed for the detection of network attacks and the results are compared with the standard SVM, rule-based, and neuro-fuzzy-based classifiers on the benchmark datasets. We demonstrate that the proposed method provides a time efficient intrusion detection with the competitive detection rate. We also discuss the parallel implementation of the modified-EFMN on the modern Graphics Processing Units (GPUs) to accelerate its performance further for the heavily growing network traffic. The NVIDIA GeForce GTX 750 Ti with 640 cores is used for the implementation.

Can South African biokineticists function as recreational therapists: a review of the minimum training standards relevant to each profession?

ABSTRACTIn South Africa, the profession of Recreational Therapy is recognized by neither the Health Professions Council South Africa (HPCSA) nor the Allied Health Professions Council of South Africa (AHPCSA). However, the South African profession of biokinetics is an accredited HPCSA member, which shares a proximity of Recreational Therapy. The American National Council for Therapeutic Recreation Certification (NCTRC) serves as the gold standard for the prescribed minimum training standards (MTS) of the profession of Recreational Therapy due to the absence of a national South African health statutory affiliation. This commentary reviews the MTS of biokinetics as compared to the NCTRC MTS, so as to ascertain whether biokineticists can function as recreational therapists. A literature search was conducted in Google Scholar, using the key-search terms “recreational therapist biokineticist.” Six hundred and fourteen records were uncovered, which were reduced to nine. The quality of each record was evaluated through the use of the modified Downs and Black Appraisal Scale. The literature analysis suggests that the MTS of the South African Biokinetic curriculum and those of the NCTRC share a number of common prerequisites, but are not wholly in accordance with each other. Biokineticists are therefore inequitable to American NCTRC trained recreational therapists.

Dose-Response Relationship Between Neuromuscular Electrical Stimulation and Muscle Function in People With Rheumatoid Arthritis.

Neuromuscular electrical stimulation (NMES) is a viable intervention for improving impaired muscle function in individuals with rheumatoid arthritis (RA). However, there is limited evidence about the dose-response relationship between NMES and muscle function in these individuals. The objectives of this study were to investigate the dose-response relationship between NMES and muscle function in individuals with RA and to establish the minimal NMES training intensity for promoting improvements. This study was a secondary analysis of data obtained before and after an NMES intervention in a randomized study. The study took place at a research clinic. Only adults diagnosed with RA were included. The intervention consisted of 36 NMES treatment sessions for the quadriceps muscles over 16 weeks. Muscle function was measured before and after the intervention; quadriceps cross-sectional area and muscle quality were assessed using computed tomography, and strength was measured with an isokinetic dynamometer. NMES training intensity was calculated as a percentage by dividing NMES-elicited quadriceps muscle torque by the maximum voluntary isometric contraction. Improvements in muscle function were calculated using paired-sample t tests. The dose-response relationship was determined using curve estimation regression statistics. The minimum NMES training intensity was defined as that sufficient to significantly improve all muscle function measures. Twenty-four people (48 legs) participated (75% women; mean [SD] age = 58 [8] years; mean body mass index=32 [7] kg/m2). Quadriceps cross-sectional area, muscle quality, and strength improved after the intervention. Associations between NMES training intensity and muscle quality (r2=0.20) and strength (r2=0.23) were statistically significant, but that between NMES training intensity and muscle cross-sectional area was not (r2=0.02). The minimum NMES training intensity necessary to improve all measures of muscle function ranged from 11% to 20% of the maximum voluntary isometric contraction. The relatively small sample size was a limitation. The minimum NMES training intensity for significant gains in muscle function was ∼15%. Higher NMES intensities may promote better muscle quality and strength in individuals with RA.

Transferability and the effect of colour calibration during multi-image classification of Arctic vegetation change

Mapping changes in vegetation cover is essential for understanding the consequences of climate change on Arctic ecosystems. Classification of ultra-high spatial-resolution (UHR, < 1 cm) imagery can provide estimates of vegetation cover across space and time. The challenge of this approach is to assure comparability of classification across many images taken at different illumination conditions and locations. With warming, vegetation at higher elevation is expected to resemble current vegetation at lower elevation. To investigate the value of classification of UHR imagery for monitoring vegetation change, we collected visible and near-infrared images from 108 plots with hand-held cameras along an altitudinal gradient in Greenland and examined the classification accuracy of shrub cover on independent images (i.e. classification transferability). We implemented several models to examine if colour calibration improves transferability based on an in-image calibration target. The classifier was trained on different number of images to find the minimum training subset size. With a training set of ~ 20% of the images the overall accuracy levelled off at about 81% and 68% on the non-calibrated training and validation images, respectively. Colour calibration improved the accuracy on training images (1–4%) while it only improved the classifier transferability significantly for training sets < 20%. Linear calibration only based on the target’s grey series improved transferability most. Reasonable transferability of Arctic shrub cover classification can be obtained based only on spectral data and about 20% of all images. This is promising for vegetation monitoring through multi-image classification of UHR imagery acquired with hand-held cameras or Unmanned Aerial Systems.

An Ecological Niche Model to Predict Range Expansion of the Eastern Gray Squirrel in California

The eastern gray squirrel, Sciurus carolinensis (EGS) has been introduced to California and has expanded its geographic range since initial introductions. In this study we projected the potential future geographic range of the EGS in California using Maxent to create an ecological niche model. Location data were obtained over the time period of 2004–2015 from museum specimens, wildlife rehabilitation centers, the California Department of Public Health, the California Roadkill Observation System, and non-iNaturalist citizen science observations. Research grade data from iNaturalist was obtained over the time period of 2004–2018. Range and habitat suitability maps were developed by mapping in ArcGIS. Three threshold selection methods were used to create different estimates of the potential future range of the EGS in California. The first method used the 10th percentile logistic threshold, the second used the minimum training presence logistic threshold, and the third used Jenks Natural Breaks. We propose that Jenks Natural Breaks has distinct advantages over the other two methods for estimating the potential future range of the introduced EGS in California, because it provides information on the habitat suitability ranking throughout California, whereas the other methods only provide a binary suitable/unsuitable map.

Low-Overhead Hierarchically-Sparse Channel Estimation for Multiuser Wideband Massive MIMO

Numerical evidence suggests that compressive sensing (CS) approaches for wideband massive MIMO channel estimation can achieve very good performance with limited training overhead by exploiting the sparsity of the physical channel. However, analytical characterization of the (minimum) training overhead requirements is still an open issue. By observing that the wideband massive MIMO channel can be represented by a vector that is not simply sparse but has well defined structural properties, referred to as hierarchical sparsity, we propose low complexity channel estimators for the uplink multiuser scenario that take this property into account. By employing the framework of the hierarchical restricted isometry property, rigorous performance guarantees for these algorithms are provided suggesting concrete design goals for the user pilot sequences. For a specific design, we analytically characterize the scaling of the required pilot overhead with increasing number of antennas and bandwidth, revealing that, as long as the number of antennas is sufficiently large, it is independent of the per user channel sparsity level as well as the number of active users. These analytical insights are verified by simulations demonstrating also the superiority of the proposed algorithm over conventional CS algorithms that ignore the hierarchical sparsity property.

Multiclass Classification Using Random Forest Classifier

A multiclass classification using Random Forest Classifier is proposed in this paper. The Random forest classifier is commonly used for solving the multiclass classification tasks in machine learning. The Random forest classifier predicts a valid classification results with minimum training time when compared to other classifier algorithms. For pattern classification tasks on an image dataset are performed in order to evaluate the performance of the proposed classifier. First, we consider some sample datasets of flower species and birds. Second, we train the object class models by using datasets to develop the random forest classifier for image classification. Third, we test the object class models and find the accuracy .In this we use Haralick,Hu moments to extract global features to quantify an image. In the experiments we test our method using FLOWERS-17,CUB_200_2011 dataset and compare the results with other methods like logistic regression, k-nearest neighbour, support vector machine.

CAN A WEARABLE NEUROMUSCUAR DEVICE REPLACE NEUROMUSCULAR TRAINING PROGRAMS?

Background: Scientific studies have shown female soccer athletes to be 3 times more likely to injure their anterior cruciate ligament (ACL) than their male counterparts and the majority of these injuries are from a non-contact mechanism. The biomechanical factors of this phenomenon have been extensively studied in a laboratory-based setting, but there has been little progress in reducing the incidence of ACL injury in young female athletes. It is plausible, therefore, to suggest that the biomechanical improvements noted in a laboratory-based setting do not directly translate to a field-based setting. Preventive neuromuscular training programs are typically field-based and have been shown to be an effective intervention for reducing ACL injury risk by improving dynamic, frontal-plane knee stability. However, these programs are time consuming and prone to compliance and implementation issues. For these reasons, researchers have attempted to identify the minimum viable training program or wearable device that can be studied in the field using video cameras to determine their influence on movement-related risk factors for ACL injury. Purpose: The aim of this study was to evaluate the effectiveness of a wearable neuromuscular device (WND) with or without the addition of a field-based, preventive neuromuscular training program on jump-landing risk assessment in young female soccer athletes. Methods: Thirty-nine female soccer players (161.0 +/- 6.6 cm; 49.4 kg +/- 5.9; 13.3 +/- 0.5 y) from two different teams in a local soccer club volunteered to participate in this study. Team 1 (n = 25) performed a 6-week, field-based NMT program while wearing a WND. The NMT was instructed by a trained exercise specialist. The NMT program was divided into three, two-week blocks of progressively increasing levels of exercise complexity and intensity focused on improving the strength and activation behavior of the trunk, hip and thigh muscles. Field-based movement testing was performed in the first week before training began (pre-test) and in the seventh week upon completion of the NMT program (post-test). During testing video cameras recorded a jump-landing task in the frontal and sagittal planes. The Landing Error Scoring System (LESS) and a novel version of the LESS (LESS-RMC) was used to asses movement quality related to ACL injury risk. Team 2 (n=14) wore the WND for an equal amount of athletic exposures over 7 weeks but did not perform the NMT program. Four different raters were recruited to visually score all jump landing trials using the two different rating protocols during the pre-test and post-test. For each visual assessment (LESS &amp; LESS-RMC) a repeated measures ANOVA was conducted to explore within group (test) and between group (team) differences. Results: Repeated measure ANOVA results for the LESS score scale indicated a significant within factor difference in pretest and post test scores F(7.398, 27.533) = 8.598, P &lt; 0.05. Pretest scores for team 1 (6.18 +/- 1.68) and team 2 (6.95 +/- 0.94) both saw a significant reduction in ACL risk scores to 5.44 +/- 1.70 and 6.31 +/- 1.75, respectively. ANOVA results for the LESS-RMC scale also indicated a significant within factor difference in pretest and posttests F(6.756, 35.624) = 6.069, p &lt; 0.05. Pretest scores for Team 1 (6.02 +/- 1.99) and Team 2 (6.49 +/- 1.33) both saw a significant reduction in ACL risk scores to 5.10 +/- 1.77 and 6.09 +/- 1.50, respectively. ANOVA results revealed no significant differences between team scores for the LESS (F(0.031,27.533) = 0.036, p &gt; 0.05) or LESS-RMC (F(1.053,35.624) = .946, p &gt; 0.05) scales. Conclusion: The results reveal that the NMT program utilized in this study had no statistically significant additive effect on the visual risk assessment scores for Team 1 compared to Team 2, who had no NMT intervention and only wore the WND. Collectively, these results suggest that simply wearing a WND during 6 weeks of practice may be a less evasive and cheaper alternative to a NMT program.

Levels of training in critical care echocardiography in adults. Recommendations from the College of Intensive Care Medicine Ultrasound Special Interest Group.

Critical care echocardiography (CCE) is commonly performed in many intensive care units across Australia and New Zealand (ANZ). The scope of practice ranges from Basic CCE through to Advanced CCE and includes the use of transthoracic echocardiography and transoesophageal echocardiography. Many training and qualification pathways exist with no standardisation of education goals. This document defines different levels of CCE expertise and recommends minimum training standards for each level of adult CCE in ANZ. Guidelines committee of College of Intensive Care Medicine's Ultrasound Special Interest Group held multiple face to face meetings, organised teleconferences, conducted a survey of the Fellows of the college and reviewed the international CCE training pathways prior to writing these guidelines.

Self-reported health problems, health care seeking behaviour and cost coping mechanism of older people: Implication for primary health care delivery in rural Bangladesh.

Background:Optimum utilization of primary health care system by older people is a challenge for every low and middle income country. Little is known about self reported health problems, health care seeking behaviour and cost coping mechanism of older people in developing countries.Objectives:This study aimed to measure self-reported health problems, health care seeking behaviour and expenditure coping mechanism of older people, and to describe its implication for primary health care delivery in rural Bangladesh.Methodology:It was a cross sectional study. In total, 362 older people were enrolled who sought health care preceding the last month of the interview. Descriptive and bivariate data analysis along with proportion test (z test) was carried out.Results:The most frequent self-reported health problems were fever (43.8%) followed by physical pain (15.2%). More than half of the respondents (57.5%) had a second health problem. Only one third (33.8%) visited qualified health providers having minimum western health or medical training from government approved authority. More than half (54%) of the older people spent for health care out of pocket from their own. Only 2% older people sold their assets or took loans to meet their health care. 36% older people thought that they could afford to pay for health care in future.Conclusions:The findings of this study will help in developing primary health care policy for older people in rural Bangladesh and similar settings in South Asia.

МОДЕРНІЗАЦІЯ ЗАГАЛЬНОЇ СЕРЕДНЬОЇ ТА ПРОФЕСІЙНОЇ ОСВІТИ В УКРАЇНІ: ЦИВІЛІЗАЦІЙНИЙ І НАЦІОНАЛЬНИЙ КОНТЕКСТ

У статті зазначено, що проблему аксіологічних імперативів державної освітньої політики у зв’язку з її комплексністю й системним характером розглядають представники різних галузей наукового знання – футурологи, філософи, педагоги, соціологи, економісти – у цивілізаційному та національному вимірах. Виявлено, що на етапі становлення демократично-споживчого суспільства (який сьогодні переживає наша країна) його аксіологічними орієнтирами є ринкові цінності – прибуток і попит платоспроможних споживачів. У цих умовах освіта розглядається як звичайний ринковий товар і через свою неприбутковість посідає в ієрархії суспільних цінностей досить низький щабель. При цьому відповідно до попиту держави як суспільного споживача заклади загальної середньої освіти обмежуються мінімальною академічною підготовкою учнів, основну увагу приділяючи їх соціалізації та професіоналізації. Визначено, що ринкова вимога мінімізації витрат на освіту негативно вплинула на її якість. Тож у другій половині ХХ ст. широка громадськість дізналася про феномен, з яким вже були обізнані спеціалісти, а саме, функціональну неграмотність населення високорозвинених країн. Охарактеризовано відбірково-поточну освітню модель, яку деякі західні вчені розглядають як інструмент не тільки професійної, а й соціальної селекції молоді. За цією моделлю, що ґрунтується на генетичній парадигмі здібностей, працювала в ХХ ст. значна кількість закладів загальної середньої освіти у високорозвинених країнах. У статті актуалізовано значущість врахування цивілізаційних тенденцій розвитку освіти для модернізації освіти України, до яких належить осучаснення освітньої галузі на засадах STEM-освіти, що передбачає її фундаменталізацію, формування в учнів і студентів узагальнювальних наскрізних знань природничо-математичного спрямування та інформаційно-цифрової компетентності, а також спроможності здійснювати наукові дослідження та розв’язувати інженерні завдання.

Adaptive Neuro-Fuzzy Inference System Based Orientation Control of an Intra-operative Ultrasound Robot

Trans-esophageal echocardiography (TEE) is a miniatured intra-operative ultrasound system, widely used in routine diagnosis and interventional procedure monitoring, to assess cardiac structures and functions. As a way to assist the operation of TEE remotely, we have developed an add-on robotic system to actuate a commercial TEE probe. For the proposed robot, understanding the inverse kinematics (IK) which relates the probe pose to the joint parameters is the fundamental step towards automatic control of the system. Rather than using conventional numerical-based techniques which may have problems with speed, convergence, and stability when applying to the TEE robot, this paper explores a soft computing approach by constructing an Adaptive Neuro-Fuzzy Inference System (ANFIS) to learn from training data generated by the forward kinematics (FK) and then computing the inverse kinematics in order to control the orientation of the TEE probe. With 1900 training data over 40 epochs, the minimum training error for each joint parameter was found to be less than 0.1 degree. Validation using a separate data set has indicated that the maximum error was less than 0.3 degree for each joint parameter. It is therefore concluded that the ANFIS-based approach is an effective way, with acceptable accuracy, to compute the inverse kinematics of the TEE robot.

Cardiology Training in Brazil and Developed Countries: Some Ideas for Improvement.

Huge variations exist in cardiology training programs across the world. In developing (middle-income) countries, such as Brazil, to find the right balance between training improvements and social and economic conditions of the country may be a difficult task. Adding more training years or different mandatory rotations, for instance, may be costly and not have an immediate direct impact on enhancing patient care or public health. In this text, we compare the Brazilian cardiology training system with other proposals implemented in developed countries from North America and Europe, aiming to point out issues worth of future discussion. Factors such as training rotations and competencies, and program duration and distribution across the countries are presented. The number of first year cardiology trainees per inhabitants is similar between Brazil and the United States (0.24 medical residents/100,000 inhabitants in Brazil and 0.26 medical residents/100,000 inhabitants in the USA). These numbers should be analyzed considering the inequality in training program distribution across Brazil, since most centers are located in the Southeast and South regions. Having more residency programs in distant areas could improve cardiovascular care in these areas. Duration of cardiology Residency Training is shorter in Brazil (two years) in comparison with developed countries (> 3 years). Brazilian residency programs give less emphasis to scientific research and diagnostic methods. Unifying minimum training requirements across the globe would facilitate the development of international learning opportunities and even professional exchange around the world.

Bioclimatic and environmental suitability models for capercaillie (Tetrao urogallus) conservation: Identification of optimal and marginal areas in Rodopi Mountain-Range National Park (Northern Greece)

Capercaillie is a species of particular conservation importance for Europe due to the observed population decline in various parts of its distribution. In the current study, the environmental and habitat requirements of the species are investigated at the southernmost range of its European distribution (Rodopi Mountain-Range National Park, northern Greece) using a set of 95 observations of species presence and a maximum-entropy (MaxEnt) modeling approach. A bioclimatic dataset derived from the Bioclim open source database and a set of environmental variables, mainly forest land-cover types and topographical variables, were employed to explain the current distribution of the species and to delineate potentially suitable areas for its distribution. The best scale per environmental variable was chosen among three different spatial scales (10 ha, 100 ha and 500 ha), in order to build a multiscale environmental model. According to our results, the species demonstrated a very narrow niche which is determined primarily by bioclimatic factors while a number of habitat requirements within a strict bioclimatic zone where also identified. It requires wet areas with mean summer temperature not exceeding 10 °C, which are only found at the higher altitudes of the National Park. Α strong tendency was also found for capercaillies to inhabit forest stands of norway spruce (Picea abies) with a minimum cover of 10% at an intermediate scale of 100 ha, followed at a larger scale i.e. 500 ha by pure beech (Fagus spp.) forests or mixed with pines (Pinus spp.), where optimum tree density ranges from 50% to 80%. Bioclimatic and environmental presence-prediction maps were reclassified in four suitability classes (unsuitable, marginal, sub-optimal, optimal), based on three Maxent thresholds (Minimum Training Presence, Fixed Cumulative Value 5 and Value 10). Monitoring the marginal climatic zone for the species and ensuring suitable habitats within it is the key for the species conservation in its southernmost part of its distribution.

Issues on Quality Research to Publish

Aims: To sensitize authors and new researchers to produce a quality research manuscript.&#x0D; Methods: Review of experiences and challenges faced by scientifi c journal editors and new authors; and scientifi c writing guidelines and workshops.&#x0D; Results: Impatient submission of manuscript with inadequate understanding of authors’ guidelines. Strength of own research and scope of journal not matching; lack of minimum training on writing and submission; journal publication from professional organizations not in primary priority list because of its voluntary nature of work.&#x0D; Conclusions: Publishing depends on professional commitment, academic interest and need, personal career and institutional interest, and availability of specifi c biomedical publishers.&#x0D; Keywords: authors’ guideline, biomedical journal, publication

Educação Infantil no Município de Teresina: perfil formativo dos docentes

Este artigo apresenta um estudo sobre o perfil da formação inicial do professor de Educação Infantil do Município de Teresina, considerando a exigência da LDB nº 9.394/96 que trata da formação mínima exigida para atuar nessa etapa de Educação Básica. O estudo compreendeu o universo de 2.342 docentes que atuavam na rede municipal e privada desse município. Trata-se de uma pesquisa de abordagem quantitativa, tendo como fonte os Microdados do Censo Escolar da Educação Básica do ano de 2017, disponibilizados no portal INEP. A extração desses Microdados e a posterior análise estatística foram realizadas com o auxílio do SPSS. A pesquisa revelou que, apesar dos avanços, o perfil de formação dos professores é diversificado. No entanto, considerando o percentual de docentes que já possuíam e estavam cursando licenciatura em Pedagogia, pode-se projetar uma melhoria desse perfil formativo a curto ou médio prazo.

Competence in thoracic ultrasound.

Ultrasound examination is traditionally considered a safe and repeatable exam, but its use is highly operator-dependent. Because of this, lack of sufficient operator skills could lead to diagnostic errors and damage to patient safety related to unnecessary tests or interventional procedures. The indications for lung ultrasound include: diagnosis, quantification, and follow-up of different conditions for which acute respiratory failure or chest pain are the main clinical presentation. Clinicians should have theoretical and practical knowledge on: physics and technology of ultrasound, indications and methodology of ultrasound examination, normal thoracic anatomy identification by echography, and detection of signs of pleuro-pulmonary pathology. Consequently, according to international recommendations, core basic skills and minimum training recommendations for the practice of medical ultrasound and image acquisition are needed to ensure competence of clinicians using ultrasound.

European postgraduate curriculum in geriatric medicine developed using an international modified Delphi technique.

Backgroundthe European Union of Medical Specialists (UEMS-GMS) recommendations for training in Geriatric Medicine were published in 1993. The practice of Geriatric Medicine has developed considerably since then and it has therefore become necessary to update these recommendations.Methodsunder the auspices of the UEMS-GMS, the European Geriatric Medicine Society (EuGMS) and the European Academy of Medicine of Ageing (EAMA), a group of experts, representing all member states of the respective bodies developed a new framework for education and training of specialists in Geriatric Medicine using a modified Delphi technique. Thirty-two expert panel members from 30 different countries participated in the process comprising three Delphi rounds for consensus. The process was led by five facilitators.Resultsthe final recommendations include four different domains: ‘General Considerations’ on the structure and aim of the syllabus as well as quality indicators for training (6 sub-items), ‘Knowledge in patient care’ (36 sub-items), ‘Additional Skills and Attitude required for a Geriatrician’ (9 sub-items) and a domain on ‘Assessment of postgraduate education: which items are important for the transnational comparison process’ (1 item).Conclusionthe current publication describes the development of the new recommendations endorsed by UEMS-GMS, EuGMS and EAMA as minimum training requirements to become a geriatrician at specialist level in EU member states.

Cross-Trained Worker Assignment Problem in Cellular Manufacturing System Using Swarm Intelligence Metaheuristics

Cross-trained worker assignment has become increasingly important for manufacturing efficiency and flexibility in cellular manufacturing system because of the recent increase in labor cost. Researchers mainly focused on assigning skilled workers to tasks for favorable capacity or cost. However, few of them have recognized the need for skill level enhancement through cross-training to avoid excessive training, especially for workload balance across multiple cells. This study presents a new mathematical programming model aimed at minimum training and maximum workload balance with economical labor utilization, to address the worker assignment problem with a cross-training plan spanning multiple cells. The model considers the trade-off between training expenditure and workload balance to achieve a more flexible solution based on decision-maker’s preference. Considering the computational complexity of the problem, the classical swarm intelligence optimizers, i.e., particle swarm optimization (PSO) and artificial bee colony (ABC), are implemented to search the problem landscape. To improve the optimization performance, a superior tracking ABC with an augmented information sharing strategy is designed to address the problem. Ten benchmark problems are employed for numerical experiments. The results indicate the efficiency and effectiveness of the proposed models as well as the developed algorithms.