Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Journal International of Lingua and Technology World Psychology Journal of Biomedical and Techno Nanomaterials
Smith, James
Unknown Affiliation
Biochemistry, Genetics & Molecular Biology Education Languange, Linguistic, Communication & Media Social Sciences Other

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
ARTIFICIAL INTELLIGENCE IN MEDICINE: A DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK FOR PATHOLOGICAL IMAGE ANALYSIS AND CANCER GRADING Smith, James; Harris, Oliver; Anurogo, Dito
Journal of Biomedical and Techno Nanomaterials Vol. 2 No. 4 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jbtn.v2i4.2480

Abstract

The histopathological analysis of tissue slides is the gold standard for cancer diagnosis and grading. However, this process is labor-intensive, time-consuming, and prone to inter-observer variability, which can affect clinical outcomes. The advent of artificial intelligence (AI), particularly deep learning, presents a transformative opportunity to enhance diagnostic precision and efficiency in pathology. This study aimed to develop, train, and validate a deep learning convolutional neural network (CNN) for the automated analysis of pathological images to accurately classify malignancies and provide reliable cancer grading. A robust CNN model was trained on a comprehensive, curated dataset of thousands of annotated digital histopathology slides from multiple cancer types. The model’s performance was rigorously evaluated against the consensus diagnoses of expert pathologists using key metrics, including accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC-ROC). Our developed CNN model demonstrated exceptional performance, achieving an overall accuracy of 98.7% in distinguishing malignant from benign tissues. For cancer grading, the model yielded a Cohen’s Kappa score of 0.92, indicating almost perfect agreement with expert pathologists. The model also showed high robustness to variations in staining and image acquisition protocols. This research confirms that a deep learning CNN can function as a highly accurate and reliable tool for automated pathological image analysis and cancer grading. Integrating such AI systems into clinical workflows could significantly augment the capabilities of pathologists, leading to improved diagnostic consistency, reduced workload, and ultimately, better patient care.
MOBILE-ASSISTED LANGUAGE LEARNING (MALL) FOR ENGLISH LEARNERS: AN INVESTIGATION OF ITS IMPACT ON VOCABULARY ACQUISITION Shaumiwaty, Shaumiwaty; Smith, James; Taylor, Lucy
Journal International of Lingua and Technology Vol. 5 No. 2 (2026)
Publisher : Sekolah Tinggi Agama Islam Al-Hikmah Pariangan Batusangkar, West Sumatra, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55849/jiltech.v5i2.1215

Abstract

Mobile technologies have become increasingly integrated into educational contexts, offering new opportunities for language learning beyond traditional classroom boundaries. In English language education, vocabulary acquisition remains a fundamental yet persistent challenge, particularly when learning opportunities are limited to formal instructional settings. Mobile-Assisted Language Learning (MALL) has emerged as a promising approach that enables flexible, repeated, and learner-centered vocabulary practice through mobile devices. This study aims to investigate the impact of MALL on vocabulary acquisition among English learners. A quasi-experimental research design was employed, involving an experimental group using mobile-based vocabulary learning applications and a control group receiving conventional vocabulary instruction. Data were collected through standardized pretest and posttest vocabulary assessments and supported by learning activity records. Statistical analyses were conducted to examine differences in vocabulary gains between groups. The results indicate that learners who engaged in MALL achieved significantly higher vocabulary gains than those in the control group. The findings also reveal that consistent engagement with mobile learning activities contributed to more stable and sustained vocabulary development. The study concludes that MALL is an effective instructional approach for enhancing vocabulary acquisition in English language learning contexts. Integrating mobile-assisted vocabulary learning into instructional practices can support improved learning outcomes and provide learners with greater autonomy and access to language input.
DIGITAL TRANSFORMATION AND EMPLOYEE ADAPTABILITY: A STUDY OF PSYCHOLOGICAL FACTORS INFLUENCING WORKPLACE INNOVATION Dodi Setiawan; Smith, James; Davis, Jack
World Psychology Vol. 5 No. 2 (2026)
Publisher : Sekolah Tinggi Agama Islam Al-Hikmah Pariangan Batusangkar, West Sumatra, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55849/wp.v5i2.1245

Abstract

Digital transformation has become a critical factor for organizational success, yet the ability of employees to adapt to technological changes remains a significant challenge. Employee adaptability is influenced by various psychological factors, which have not been sufficiently explored in the context of digital transformation. This study aims to investigate the role of emotional intelligence, cognitive flexibility, self-efficacy, and stress management in shaping employee adaptability during digital transformation processes. A mixed-methods approach was employed, combining quantitative surveys and qualitative interviews with 300 employees and 30 managers from various industries undergoing digital transformation. Descriptive and inferential statistical analysis revealed that emotional intelligence, cognitive flexibility, and self-efficacy significantly correlate with employee adaptability, while stress management showed a weaker relationship. Qualitative interviews supported these findings, highlighting the importance of emotional intelligence in reducing resistance to change and fostering collaboration. The study concludes that organizations should prioritize developing these psychological traits to enhance employee adaptability and improve the success of digital transformation initiatives. The findings contribute to a deeper understanding of the psychological mechanisms involved in employee adaptation, offering practical implications for organizations aiming to optimize workforce performance during technological transitions.
Co-Authors Davis, Jack Dito Anurogo, Dito Dodi Setiawan Harris, Oliver Shaumiwaty, Shaumiwaty Taylor, Lucy