Learning Capacity Research Articles

Investigation of the Effect of Virtual Microscopy on Pathology Education in a Medical Faculty

Aim: Virtual microscopy technology has been widely used in histopathological diagnosis and pathology education, replacing the traditional light microscope, which is considered an important visual tool in pathology education. Slides scanned and stored online for use in virtual microscopy were first described in 1985 and have experienced significant developments since 2000. In this study. The aim of this study was to determine how virtual microscopy affected medical school students' pathology education. Methods: The study included the 3rd year students of Izmir Democracy University Faculty of Medicine. The study was conducted prior to the end-of-year pathology practice exam. As a result of the scanning performed by company received support, 102 slides were selected from the training archive and virtualized. Among them, forty slides representing lesions and organs from ten different systems, were chosen. The students were divided into two groups (group 1 and 2.) and the selected slides were used as educational material. Each student was given the opportunity to study both 20 virtual and 20 microscope slides. The students in the first group (G1) examined 20 slides (M1) of the ten systems with the light microscope and the other 20 slides on the virtual microscope (S1). On the other hand, the students in the second group (G2) examined with a light microscope (M2) the slides which shown to the first group in the virtual microscope (V1); and they examined with the virtual microscope (V2) the slides which shown to the first group in the light microscope (M1). This training course was completed in approximately eight hours. For the end-of-year pathology practice exam held the next day, the students were randomly divided into 4 groups and each group was asked questions about 10 slides from 10 different systems. These questions were about the descriptive characteristics of the organs and lesions that are examined. All slides were shown to the examinees one day later. Results: Eighty-nine students in total [n:52 (58.4%) men, n:37 (41.6%) women] took part in the survey. The study found no significant difference in overall exam scores between students using traditional light microscopy and those using virtual microscopy, with average scores being 17.2±7 on a scale of 5 to 40 points. Students who examined slides using light microscopy had an average score of 8.7±4.6, while those who used virtual microscopy had an average score of 8.6±4.1. It was found that the success rates were similar regardless of whether the students used traditional microscopy or virtual reality. Yet when the results were grouped by gender, female students had higher overall (p=0.05) and light microscopy scores (p=0.001). When the groups were investigated separately, the exam scores attained were comparable in terms of from the exam content related to major system disorders did not differ between the groups. based on learning method without any statistical significance between groups. However, while group 1 students who participated in studying with light microscopy training before the exam had higher exam scores in the exam content related to bone and soft tissue pathology compared to group 2 students studying with virtual microscopy (in bone and soft tissue pathology had a mean score of 3±1.5 vs 1.2±1.7) points, virtual learners had a mean score of 1.2±1.7 points, with a statistically significant intergroup difference according to the Mann- Whitney U test (p=0.027). Conclusions: Virtual microscopy is a crucial component of medical students' pathology training in undergraduate medical education in terms of providing opportunities for medical students to see the rare cases and standardization of the training in different institutions. Particularly in undergraduate education, it is crucial for the understanding of rare cases and standardization of the pathology education. But as our study's findings on the pathology of bone and soft tissues showed, conventional light microscopy is still essential for understanding the pathology of some systems. Moreover, one's gender may affect student's capacity for virtual learning. Understanding the distinction between genders in terms of learning capacity may aid in providing students a better education.

Modular Learning Platform Implementation and Cognitive Skills Development of Senior High School Students

The study was conducted in Tacurong National High School Barangay New Isabela, Tacurong City. The study used quantitative research to determine the details needed, using the survey questionnaire. The research design used in this study was descriptive statistics. Slovin’s formula determined the number of samples from the general population. This study utilized the random sampling technique by employing numerous straightforward cluster sampling approaches. On the other hand, the mean, standard deviation, frequency count, percentage distribution, and correlation were used to assess the study’s respondents’ responses. Based on the findings and conclusions of the study, the researchers present the following recommendations; in the level of implementation, the researchers found out that the school’s performance during the implementation of the modular learning platform was high as satisfactory, but it partly reflects the performance of the students. Thus, the curricularists must evaluate the integrated curricula and formulate a more effective aid of teaching using this study as the basis for better integration. The school must further focus on the student’s learning and come up with more effective strategies that will help the students to be more active and productive even with distance learning. Given that the cognitive skills development of the students was low as unsure, the researchers suggest that the Department of Education must focus on learner consultations for modular teaching approach-built confusion in identifying their learning capacities and this may result in low academic performance. Future researchers may further research large-scale and more specific studies aligned with this topic.

Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning

AbstractThe size of sedimentary particles in rivers bears information on the sediment entrainment or deposition mechanisms and the hydraulic conditions controlling them. However, collecting such data from coarse‐grained sediments is work intensive, both in the field and remotely. Therefore, attention has turned to machine learning models to improve the data acquisition. Despite their success, current methods need large quantities of data and yield results limited to a few percentile values of grain size datasets, often additionally affected by a systematic bias. In most cases, the root of these limitations is the challenge of accurately segmenting grains. Here, we present a new approach to improve the segmentation of individual grains based on the capacity of transfer learning in convolutional neural networks. Specifically, we re‐train a state‐of‐the‐art model for cell segmentation in biomedical images to find and segment coarse‐grained particles in images of fluvial sediments. Our results show that the performance in the segmentation tasks can be directly transferred to images of fluvial sediments and that our re‐trained models outperform existing methods. We document that our results are achievable with only 10%–20% of the data needed for training other deep learning models designed to measure the size of fluvial sediments. Moreover, we find that traits in our data control the segmentation performance. This enables data‐driven approaches to create specialist segmentation models. Additionally, comparing our automatically obtained datasets with the results retrieved from image and field‐based surveys confirms that improvements in segmentation are directly leading to more precise and more accurate grain size data even if data collection occurs in images taken at different conditions. Finally, we release a software package, the trained models and our data. The goal is to offer a tool to efficiently segment and measure grains in sediment images in an automated way, which can be adapted to different settings.

Impact of Knowledge Management Strategies on Organizational Ambidexterity Mediated by Organizational Learning Capability

Background: This study intends to investigate the relationship between organizational ambidexterity and knowledge management practices, with a focus on travel and tourism industries specifically. The research is conducted using a descriptive-correlation approach and involves 72 businesses located in Qom, Mashhad, and Tehran. A total of 369 managers and personnel from these organizations participated in the study, providing valuable insights into the dynamics of knowledge management and its impact on organizational learning and ambidexterity within the tourism sector. Methods: In this study, descriptive-correlation research methodology was used. Data were collected through a questionnaire distributed to 369 managers and personnel from 72 tourism organizations. The questionnaire focused on assessing the participants' perspectives on knowledge management strategies, organizational learning capability, and organizational ambidexterity. This quantitative approach allowed for the examination of relationships and mediation effects within the specified variables. Findings: The results of the study show substantial correlation between organizational ambidexterity, learning ability, and knowledge management techniques. It was found to be fascinating that the relationship between organizational ambidexterity and knowledge management strategies in the tourism setting was partially mediated by organizational learning capacity. Conclusion: In conclusion, tourism companies should place a high priority on implementing both explicit and tacit knowledge management strategies in order to attain structural ambidexterity. Effective HRM procedures as well as the advancement of knowledge management and information technology infrastructures must serve as the cornerstones of these strategies. Encouraging learning, unlearning, relearning, experimentation, and knowledge sharing are pivotal for enhancing organizational learning capability and, consequently, achieving organizational ambidexterity. This study underscores the need for a holistic approach that integrates human and technological elements to foster a dynamic and adaptable organizational structure in the tourism sector.

Geographic variation in individual face learning based on plasticity rather than local genetic adaptation in Polistes wasps

Abstract Signals and receiver responses often vary across a species’ geographic range. Effective communication requires a match between signal and receiver response, so there is much interest in the developmental mechanisms that maintain this link. Two potential mechanisms are genetic covariance between signal and receiver response and plasticity where individuals adjust their phenotype based on their partner’s phenotype. Here, we test how plasticity contributes to geographic variation in individual face recognition in Polistes fuscatus wasps. Previous work has shown that P. fuscatus from Michigan, USA (MI) have variable facial patterns used for individual recognition, while P. fuscatus from central Pennsylvania, USA (PA) lack variable facial patterns and are unable to learn individual conspecifics. We experimentally altered rearing environment, so wasps were either reared with their own population or in a common garden with wasps from both populations. Then, we tested the wasps’ capacity to learn and remember individual conspecific faces. Consistent with previous work, MI wasps reared with MI wasps were adept at learning conspecific faces, while PA wasps reared with PA wasps were unable to learn conspecific faces. However, MI and PA wasps reared in a common garden developed similar, intermediate capacity for individual face learning. These results indicate that individual face learning in Polistes wasps is highly plastic and responsive to the social environment. Plasticity in receiver responses may be a common mechanism mediating geographic differences in non-sexual signaling systems and may play a role in maintaining links between signals and receiver responses in geographically variable communication systems.

Supplemental Material for Reward Learning Capacity in a Community Sample of Individuals Who Use Cannabis

Supplemental Material for Reward Learning Capacity in a Community Sample of Individuals Who Use Cannabis

Quantifying organisational resilience: an integrated resource efficiency view

ABSTRACT Organisations are increasingly exposed to risks from globally disruptive events, triggering interest and new research into organisational resilience. Several levers to increase resilience are defined in the literature but organisations still find it challenging to prepare for the next disruption. This study contributes to the resilience literature by drawing on the integrated resource efficiency view (IREV) framework to measure four levers of organisational resilience and derive an organisational resilience index (ORI). Levers include resiliency management, business continuity and organisational learning capacity, which are related to the levels of preparedness of the organisation for potential disruptions, and operational flexibility, which relates to how quickly it can reconfigure resources in changing situations. Results show that a composite index encompassing the four levers is strongly associated with increased organisational resilience. The ORI provides leaders and decision makers with an approach to assess resilience at the level of the whole organisation and with sample groups, such as business type or geographical location, enabling structured multi-level comparisons and analysis. Furthermore the ORI helps managers target attention and resources to improve preparedness and take action to mitigate constraints on operational flexibility.

Inductive detection of influence operations via graph learning

Influence operations are large-scale efforts to manipulate public opinion. The rapid detection and disruption of these operations is critical for healthy public discourse. Emergent AI technologies may enable novel operations that evade detection and influence public discourse on social media with greater scale, reach, and specificity. New methods of detection with inductive learning capacity will be needed to identify novel operations before they indelibly alter public opinion and events. To this end, we develop an inductive learning framework that: (1) determines content- and graph-based indicators that are not specific to any operation; (2) uses graph learning to encode abstract signatures of coordinated manipulation; and (3) evaluates generalization capacity by training and testing models across operations originating from Russia, China, and Iran. We find that this framework enables strong cross-operation generalization while also revealing salient indicators-illustrating a generic approach which directly complements transductive methodologies, thereby enhancing detection coverage.

Exploring the dependence of gas cooling and heating functions on the incident radiation field with machine learning

ABSTRACT Gas cooling and heating functions play a crucial role in galaxy formation. But, it is computationally expensive to exactly compute these functions in the presence of an incident radiation field. These computations can be greatly sped up by using interpolation tables of pre-computed values, at the expense of making significant and sometimes even unjustified approximations. Here, we explore the capacity of machine learning to approximate cooling and heating functions with a generalized radiation field. Specifically, we use the machine learning algorithm XGBoost to predict cooling and heating functions calculated with the photoionization code cloudy at fixed metallicity, using different combinations of photoionization rates as features. We perform a constrained quadratic fit in metallicity to enable a fair comparison with traditional interpolation methods at arbitrary metallicity. We consider the relative importance of various photoionization rates through both a principal component analysis (PCA) and calculation of SHapley Additive exPlanation (shap) values for our XGBoost models. We use feature importance information to select different subsets of rates to use in model training. Our XGBoost models outperform a traditional interpolation approach at each fixed metallicity, regardless of feature selection. At arbitrary metallicity, we are able to reduce the frequency of the largest cooling and heating function errors compared to an interpolation table. We find that the primary bottleneck to increasing accuracy lies in accurately capturing the metallicity dependence. This study demonstrates the potential of machine learning methods such as XGBoost to capture the non-linear behaviour of cooling and heating functions.

Does early nutrition predict cognitive skills during later childhood? Evidence from two developing countries

The existing evidence linking early undernutrition to educational outcomes in developing countries is largely focused on assessing its impacts on grade attainment and achievement test scores, with limited evidence on the foundational cognitive skills required to perform well at school. We use unique data collected in Ethiopia and Peru as part of the Young Lives Study to investigate the relationship between early undernutrition and four foundational cognitive skills measured later in childhood, the first two of which measure executive functioning: working memory, inhibitory control, long-term memory, and implicit learning. We exploit the rich longitudinal data available to control for potential confounders at the household and individual level and for time-invariant community characteristics. We also take advantage of the availability of data for paired-siblings to obtain household fixed-effects estimates. In the latter specification, we find robust evidence that stunting at ∼age 5 is negatively related with executive functions measured years later, predicting reductions in working memory and inhibitory control by 12.6 % and 5.8 % of a standard deviation. Although the main cohort of Young Lives was around 12 years old when executive functions were measured, complementary results and analysis of the data available for the younger siblings suggest that the impact of stunting on executive functions—specifically, on working memory—starts at an earlier age. Our results shed light on the mechanisms that explain the relationship between early nutrition and school achievement tests suggesting that good nutrition is an important determinant of children’s learning capacities.

STUDENTS' MOTIVATION TO LEARN DURING THE PANDEMIC IN THE LEARNING PROCESS FROM HOME

This study examines students' learning motivation during the pandemic in the learning process from home. In the learning process, motivation is needed. Motivation can arise from intrinsic (within the individual) or extrinsic (outside the individual). These two factors are very important and continuous in increasing student motivation. During the COVID-19 pandemic, the learning process is carried out from home, so learning motivation can be influenced by several factors. From the research results obtained, there are many factors that do not support the student learning process during the pandemic. These factors, among others; technological skills, internet network connections, learning media used, student capacity for online learning, and so on. Thus, it can be neglected that student motivation during the pandemic in the learning process from home has decreased.

Research on improved YOLOx weed detection based on lightweight attention module

Accurate weed detection is essential for precise weed control in farmland, and machine vision serves as an effective method for identifying and targeting these unwanted plants. An advanced YOLOx weed detection model, incorporating a deep network connection lightweight attention mechanism, has been proposed to effectively identify distinct types of weeds in maize seedling fields. The lightweight attention module is connected to the deep network of YOLOx-Darknet, which weakens the channel noise effect of residual computation and thus makes the detection model more efficient. A deconvolution layer has been introduced in the residual module to improve the small size feature extraction capability. The Generalized Intersection over Union (GIoU) has replaced the Intersection over Union (IoU) to minimize the positional discrepancy between the predicted frame and the actual frame, thereby enhancing the learning capacity of the detection model. Compared with the original algorithm, the improved one achieved an average detection accuracy of 94.86% in the performance evaluation, 0.07% better in the F1 value, and 1.16% better in the AP value. The weeding robot with an improved YOLOx algorithm had 92.45% detection rate of maize seedlings and 88.94% detection rate of weed recognition at 0.2 m s−1. The results of this study can provide technical references for real-time weed detection and robotic precision weeding.

Breathe out the Secret of the Lung: Video Classification of Exhaled Flows from Normal and Asthmatic Lung Models Using CNN-Long Short-Term Memory Networks

In this study, we present a novel approach to differentiate normal and diseased lungs based on exhaled flows from 3D-printed lung models simulating normal and asthmatic conditions. By leveraging the sequential learning capacity of the Long Short-Term Memory (LSTM) network and the automatic feature extraction of convolutional neural networks (CNN), we evaluated the feasibility of the automatic detection and staging of asthmatic airway constrictions. Two asthmatic lung models (D1, D2) with increasing levels of severity were generated by decreasing the bronchiolar calibers in the right upper lobe of a normal lung (D0). Expiratory flows were recorded in the mid-sagittal plane using a high-speed camera at 1500 fps. In addition to the baseline flow rate (20 L/min) with which the networks were trained and verified, two additional flow rates (15 L/min and 10 L/min) were considered to evaluate the network’s robustness to flow deviations. Distinct flow patterns and vortex dynamics were observed among the three disease states (D0, D1, D2) and across the three flow rates. The AlexNet-LSTM network proved to be robust, maintaining perfect performance in the three-class classification when the flow deviated from the recommendation by 25%, and still performed reasonably (72.8% accuracy) despite a 50% flow deviation. The GoogleNet-LSTM network also showed satisfactory performance (91.5% accuracy) at a 25% flow deviation but exhibited low performance (57.7% accuracy) when the deviation was 50%. Considering the sequential learning effects in this classification task, video classifications only slightly outperformed those using still images (i.e., 3–6%). The occlusion sensitivity analyses showed distinct heat maps specific to the disease state.

The interlink between chrono-nutrition and stunting: current insights and future perspectives.

Stunting is the one factor that is responsible for the irretrievable damage to children's mental and physical health. Stunting imitates chronic undernutrition throughout the most extreme critical stages of growth and development of a child in their early life, and due to that stunted child does not completely develop and are too short for their age. Stunting is mainly linked with brain underdevelopment, along with lifelong damaging consequences, comprising weakened mental and learning capacity, deprived performance in school during childhood, and enhanced risks of nutrition linked to chronic long-lasting ailments, such as diabetes, hypertension, diabesity, and obesity in the future. In this review, the authors mainly summarize the latest studies related to chronic nutrition and how it is related to stunting. Optimal nutrition, particularly during pregnancy and the first 24 months of a child's life, is crucial in preventing stunting. Circadian rhythms play a significant role in maternal and fetal health, affecting outcomes such as premature birth and stunting. Maintaining a balanced diet, avoiding late-night carbohydrate-heavy meals during pregnancy, and promoting breastfeeding align with the body's biological clock, which can benefit newborns in various ways. Providing dedicated spaces for breastfeeding in public places is important to support infant health.

THE HOUSEHOLD AS A LEARNING ORGANIZATION

Economic research shows that a complex entity such as a household, may be sometimes reduced to individual transactional decisions. The same is true in this paper, since the learning capacity of a household is understood as the sum of the capacities of household members. It turns out that household members function just like members of an organization (employees of a company/organisation). The question arises: what characteristics of households and their members (taking into account the functions they perform) are conducive to the household learning process and the development of household ability to use the potential of their members to perform in the market better than others, i.e. to respond more effectively to the turbulences occurring in the market. The hypotheses proposed in the study are related to the authors’ belief that: firstly, households can be treated as organizations; secondly, households have the ability to learn; thirdly, households can use their learning ability in order to adapt to changes occurring in the turbulent external environment. The objective was to: determine the characteristics of households which, when an interdisciplinary approach is applied, can be treated as organizations; define the features, which enable households to learn; define the requirements that have to be met to enable the households to apply their acquired knowledge and experience to make decisions leading to the planned changes in their behaviour;verify empirically the key determinants of the household learning process.The range of problems addressed by the paper belongs to the field of interdisciplinary studies dedicated to changes in households’ market behaviour resulting from the pressures exerted by the turbulent environment. The paper employed methods of critical literature analysis regarding the following: organization and management, operations in the market, as well as the system and benchmarking analyses. Additionally, the authors applied a questionnaire survey to provide data for the statistical analysis of co-dependencies of qualitative characteristics.

Robust and Refined Salient Object Detection Based on Diffusion Model

Salient object detection (SOD) networks are vulnerable to adversarial attacks. As adversarial training is computationally expensive for SOD, existing defense methods instead adopt a noise-against-noise strategy that disrupts adversarial perturbation and restores the image either in input or feature space. However, their limited learning capacity and the need for network modifications limit their applicability. In recent years, the popular diffusion model coincides with the existing defense idea and exhibits excellent purification performance, but there still remains an accuracy gap between the saliency results generated from the purified images and the benign images. In this paper, we propose a Robust and Refined (RoRe) SOD defense framework based on the diffusion model to simultaneously achieve adversarial robustness as well as improved accuracy for benign and purified images. Our proposed RoRe defense consists of three modules: purification, adversarial detection, and refinement. The purification module leverages the powerful generation capability of the diffusion model to purify perturbed input images to achieve robustness. The adversarial detection module utilizes the guidance classifier in the diffusion model for multi-step voting classification. By combining this classifier with a similarity condition, precise adversarial detection can be achieved, providing the possibility of regaining the original accuracy for benign images. The refinement module uses a simple and effective UNet to enhance the accuracy of purified images. The experiments demonstrate that RoRe achieves superior robustness over state-of-the-art methods while maintaining high accuracy for benign images. Moreover, RoRe shows good results against backward pass differentiable approximation (BPDA) attacks.

COVID-19 infection analysis framework using novel boosted CNNs and radiological images

COVID-19, a novel pathogen that emerged in late 2019, has the potential to cause pneumonia with unique variants upon infection. Hence, the development of efficient diagnostic systems is crucial in accurately identifying infected patients and effectively mitigating the spread of the disease. However, the system poses several challenges because of the limited availability of labeled data, distortion, and complexity in image representation, as well as variations in contrast and texture. Therefore, a novel two-phase analysis framework has been developed to scrutinize the subtle irregularities associated with COVID-19 contamination. A new Convolutional Neural Network-based STM-BRNet is developed, which integrates the Split-Transform-Merge (STM) block and Feature map enrichment (FME) techniques in the first phase. The STM block captures boundary and regional-specific features essential for detecting COVID-19 infectious CT slices. Additionally, by incorporating the FME and Transfer Learning (TL) concept into the STM blocks, multiple enhanced channels are generated to effectively capture minute variations in illumination and texture specific to COVID-19-infected images. Additionally, residual multipath learning is used to improve the learning capacity of STM-BRNet and progressively increase the feature representation by boosting at a high level through TL. In the second phase of the analysis, the COVID-19 CT scans are processed using the newly developed SA-CB-BRSeg segmentation CNN to accurately delineate infection in the images. The SA-CB-BRSeg method utilizes a unique approach that combines smooth and heterogeneous processes in both the encoder and decoder. These operations are structured to effectively capture COVID-19 patterns, including region-homogenous, texture variation, and border. By incorporating these techniques, the SA-CB-BRSeg method demonstrates its ability to accurately analyze and segment COVID-19 related data. Furthermore, the SA-CB-BRSeg model incorporates the novel concept of CB in the decoder, where additional channels are combined using TL to enhance the learning of low contrast regions. The developed STM-BRNet and SA-CB-BRSeg models achieve impressive results, with an accuracy of 98.01%, recall of 98.12%, F-score of 98.11%, Dice Similarity of 96.396%, and IOU of 98.85%. The proposed framework will alleviate the workload and enhance the radiologist's decision-making capacity in identifying the infected region of COVID-19 and evaluating the severity stages of the disease.

Gated Convolution and Stacked Self-Attention Encoder–Decoder-Based Model for Offline Handwritten Ethiopic Text Recognition

Offline handwritten text recognition (HTR) is a long-standing research project for a wide range of applications, including assisting visually impaired users, humans and robot interactions, and the automatic entry of business documents. However, due to variations in writing styles, visual similarities between different characters, overlap between characters, and source document noise, designing an accurate and flexible HTR system is challenging. The problem becomes serious when the algorithm has a low learning capacity and when the text used is complex and has a lot of characters in the writing system, such as Ethiopic script. In this paper, we propose a new model that recognizes offline handwritten Ethiopic text using a gated convolution and stacked self-attention encoder–decoder network. The proposed model has a feature extraction layer, an encoder layer, and a decoder layer. The feature extraction layer extracts high-dimensional invariant feature maps from the input handwritten image. Using the extracted feature maps, the encoder and decoder layers transcribe the corresponding text. For the training and testing of the proposed model, we prepare an offline handwritten Ethiopic text-line dataset (HETD) with 2800 samples and a handwritten Ethiopic word dataset (HEWD) with 10,540 samples obtained from 250 volunteers. The experiment results of the proposed model on HETD show a 9.17 and 13.11 Character Error Rate (CER) and Word Error Rate (WER), respectively. However, the model on HEWD shows an 8.22 and 9.17 CER and WER, respectively. These results and the prepared datasets will be used as a baseline for future research.

Deep learning enhances acute lymphoblastic leukemia diagnosis and classification using bone marrow images.

Acute lymphoblastic leukemia (ALL) poses a significant health challenge, particularly in pediatric cases, requiring precise and rapid diagnostic approaches. This comprehensive review explores the transformative capacity of deep learning (DL) in enhancing ALL diagnosis and classification, focusing on bone marrow image analysis. Examining ten studies conducted between 2013 and 2023 across various countries, including India, China, KSA, and Mexico, the synthesis underscores the adaptability and proficiency of DL methodologies in detecting leukemia. Innovative DL models, notably Convolutional Neural Networks (CNNs) with Cat-Boosting, XG-Boosting, and Transfer Learning techniques, demonstrate notable approaches. Some models achieve outstanding accuracy, with one CNN reaching 100% in cancer cell classification. The incorporation of novel algorithms like Cat-Swarm Optimization and specialized CNN architectures contributes to superior classification accuracy. Performance metrics highlight these achievements, with models consistently outperforming traditional diagnostic methods. For instance, a CNN with Cat-Boosting attains 100% accuracy, while others hover around 99%, showcasing DL models' robustness in ALL diagnosis. Despite acknowledged challenges, such as the need for larger and more diverse datasets, these findings underscore DL's transformative potential in reshaping leukemia diagnostics. The high numerical accuracies accentuate a promising trajectory toward more efficient and accurate ALL diagnosis in clinical settings, prompting ongoing research to address challenges and refine DL models for optimal clinical integration.

Why cognitive absorption is not enough: The role of knowledge absorption capacity and technological opportunity for individual learning

The purpose of this paper is to address the basic question why does high absorptive training programmes are not always beneficial for individual level learning? Thus, we seek to understand when and how cognitive absorption is beneficial for individual learning. The proposed model was tested using data obtained in a field study (N = 371) and in an experiment (N = 119). For field study, data was obtained at two points in time from three data sources (co-workers, subordinates, supervisors) working at a private commercial bank operating in Pakistan. For laboratory experiment, data was collected from the business students of a private sector university in Pakistan. The obtained data for both studies were analysed for random coefficient models with Mplus. Based on the motivation-ability-opportunity theory of behaviour, we proposed a model. It was found that cognitive absorption and highest individual learning was contingent upon the individual level knowledge absorption capacity. It was further found that training programmes with high cognitive absorption are likely to produce high levels of individual learning when the participants also have both high level of knowledge absorption capacity and technological opportunity. With this research, we inform practitioners that in these learner-focused trainings, personal characteristics of the participants and technology play vital role in determining effectiveness for high level of individual learning. The research findings will help practitioners understand what they need to add in training programmes for high level individual learning experience. Doing so will bring best value in form of higher learning to the cost of trainings.