Enhancing radiographic image interpretation: WARES-PRS model for knee bone tumour detection DOI

Rahamathunnisa Usuff,

Sudhakar Kothandapani,

Rajesh Rangan

и другие.

Network Computation in Neural Systems, Год журнала: 2024, Номер unknown, С. 1 - 31

Опубликована: Июнь 26, 2024

The early diagnosis of tumour is significant in biomedical research field to lower the severity level and restrict process extension from cancer. Moreover, detection sign cancer undertaken with extensive efforts that dedicated disclosure recognition tumours. However, limited data size as well diverse appearance images lowered performance failed detect complex stage tumour. So solve these issues, a Weighted Adaptive Random Ensemble Support Vector-based Partial Reinforcement Search (WARES-PRS) algorithm proposed detected bone lesions accurately also predicted efficiently. Further, performed varied stages diminish presence noise effective classification. validated CNUH dataset enhanced image pre-processing tasks. Despite method uncover mutual relationships between each pixel's local texture overall image's global context. classification efficiency various measures experimental results revealed accuracy for approach by 98.5%. outcomes our study have exhibited substantial contribution assisting physicians knee

Язык: Английский

Enhancing the Zebra Optimization Algorithm with Chaotic Sinusoidal Map for Versatile Optimization DOI Creative Commons
Darpan Anand, Osamah Ibrahim Khalaf,

G. Rajesh Chandra

и другие.

Iraqi Journal for Computer Science and Mathematics, Год журнала: 2024, Номер 5(1)

Опубликована: Янв. 2, 2024

In this study, the Chaotic Sinusoidal Map (CSM)-enhanced Zebra Optimization Algorithm (CZOA)is introduced. CZOA combines CSM's integration strengths with ZOA's optimization skills. ZOA already exhibitsgreat capabilities, but addition of CSM increases its potential even more. This greatlystrengthens exploration and exploitation skills flexibility for various tasks.CZOA outperforms both original contemporary optimisation methods on 23 benchmark functions,including high-dimensional (FD), multimodal (MM), unimodal (UM) challenges. Using chaos toinvestigate regional optimal determine better convergence exploration-exploitation equilibrium are shownby CZOA, which also shows more profitable solution locations. demonstrates resilience versatilitythrough multiple activities, underscoring as an adaptable tool. CZOAbecomes a potent metaheuristic by combining biological inspiration chaotic dynamics to solve difficultoptimisation problems. Inspired natural behaviour zebras, Optimisation (ZOA) is arelatively new technique. It makes use herd mechanism ideas leadership andfollowing, in members population—zebras case—cooperate issues thebest possible ways

Язык: Английский

Процитировано

4
Human vs machine learning in face recognition: a case study from the travel industry DOI Creative Commons
Regina Lionnie,

Vidya Hermanto

SINERGI, Год журнала: 2025, Номер 29(1), С. 229 - 229

Опубликована: Янв. 5, 2025

This research was conducted to help answer whether a machine learning simulation can replace the human ability recognize faces, especially under challenges travel industry requirements. The faces evaluated using series of questions in survey. challenged respondents similar looks, with hair and makeup disguises, only part facial area, dark lighting conditions. At same time, histogram oriented gradient (HoG) combined support vector (SVM) built for simulations. two datasets, i.e., Extended Yale B (EYB) Face dataset challenge conditions Makeup Dataset (EMFD) face disguise. results showed that recognition system yielded accuracy as high 95.4% 70.8% On contrary, 48% accurately recognized lighting. number increased 94-96% when images were adjusted first contrast adjustment method. However, 36-37%

Язык: Английский

Процитировано

0
Deep Dive into Bone Tumor Segmentation and Classification: Methodological Review and Challenges with Deep Learning Approaches DOI Creative Commons

R Singh,

D Vasumathi

ITM Web of Conferences, Год журнала: 2025, Номер 74, С. 01006 - 01006

Опубликована: Янв. 1, 2025

This comprehensive review delves into the advancements made in utilizing Deep Learning (DL) procedures for bone tumor separation and classification. Bone tumors present a complex challenge medical imaging due to their diverse morphological characteristics potential malignant behaviour. Traditional methods analysis often require extensive manual intervention lack efficiency needed clinical applications. learning approaches, with accessibility of large-scale datasets sophisticated computer resources, have emerged as intriguing alternatives solve these constraints. In this connection an attempt is synthesizes recent developments deep architectures, tailored specifically segmentation classification tasks. Additionally, it examines challenges associated data acquisition, preprocessing, annotation, along strategies mitigate them. Furthermore, discusses integration multimodal modalities, improve reliability characterization. The also surveys benchmark dataset sand various commonly employed domain. As result, propose future directions advancing field using methodologies.

Язык: Английский

Процитировано

0
Epilepsy Identification using Hybrid CoPrO-DCNN Classifier DOI Creative Commons

Ganesh Birajadar,

Altaf O. Mulani, Osamah Ibrahim Khalaf

и другие.

International Journal of Computing and Digital Systems, Год журнала: 2024, Номер 15(1), С. 783 - 796

Опубликована: Май 8, 2024

The Electroencephalogram (EEG) stands as a burgeoning frontier in the study of neuronal activity, offering rich tapestry information crucial for identifying abnormalities and addressing cognitive disorders irregularities.This paper delves into examination EEG from subjects exhibiting abnormalities, contrasting them with those normal subjects.Various topographical features such Mean, Entropy, Wavelet bands are meticulously evaluated compared.Inspired by adaptive hunting strategies observed coyotes, this introduces novel hybrid computational model that integrates deep learning architectures, aiming to amplify diagnostic accuracy.The methodology hinges upon development unique algorithm inspired intricate behaviors seamlessly fused potent data-driven capabilities neural networks.This is applied scrutinize data detection brain disorders, capitalizing on both biologically-inspired data-centric strengths learning.The results obtained innovative approach highly promising.The proposed scheme exhibits remarkable accuracy, achieving an impressive rate 98.65 per training (True Positive -TP) 98.82 utilizing k-fold validation.These preliminary findings underscore potential efficacy accurately discerning signals.However, it essential acknowledge these represent initial success form just fragment extensive evaluation process.This marks significant stride towards leveraging interdisciplinary insights, blending principles ethology advanced techniques tackle complex neurological challenges.By harnessing sophisticated nature alongside cutting-edge technological advancements, research endeavors carve path more nuanced precise tools understanding disorders.Further exploration refinement hold promise revolutionizing landscape neurodiagnostics, hope effective interventions treatments realm health.

Язык: Английский

Процитировано

1
A superior secure key spawn using boosted uniqueness encryption for cloud computing in advanced extensive mobile network DOI Creative Commons

G. Rajesh Chandra,

K. Jagan Mohan,

Osamah Ibrahim Khalaf

и другие.

SINERGI, Год журнала: 2024, Номер 28(2), С. 405 - 405

Опубликована: Май 6, 2024

The cloud computing sector, including mobile networks has increased in the present time. Because of advanced features and security related information cloud. So many methods are available for handling these problems. Cloud security, large number existing provide security. Among that, so widespread techniques cast-off to protected data based on Individuality encryption. This method specialty is allowing only authorized end users access legal avoid smalevolent attack. -based encryption follows up four stages like Name, Key generation, decryption. generation most important generating secure key. It provides unbreakable non-derivable keys strong paper a novel approach providing called identity-based uses segment bitidentity thread demandto evade seepage user’s identity, if any attacker decodes key also. Statistical reports show that proposed algorithm takes less time process decryption compared other traditional approaches. One more feature our skinning uniqueness by using parametric curve fitting. contains polynomial interpolation function.

Язык: Английский

Процитировано

1
Early detection of diabetes potential using cataract image processing approach DOI Creative Commons
Moh. Khairudin,

Rendy Mahaputra,

Wiharto Wiharto

и другие.

SINERGI, Год журнала: 2023, Номер 28(1), С. 55 - 55

Опубликована: Дек. 15, 2023

Diabetes is a disease characterized by high level of sugar in the blood. The occurs because disruption metabolic system when insulin not produced effectively and functions properly. High blood levels, for an extended period time, can harm few organ systems, including heart kidneys. Moreover, it may cause blindness or death if carefully monitored. Because diabetes symptoms are rarely seen, one factors that self-awareness. Thus, with Artificial Intelligence, this problem be solved. intelligence studies how machines function like humans. This study implemented Convolutional Neural Network algorithm (1) input layer, (2) feature learning (3) classification (4) output layer as architecture AI. accuracy developed AI model was measured from its precision, recall, f1-score. results show obtained 90% f1-score real-world cases found two hospitals located Solo Yogyakarta, Indonesia. According to tests, 9 out 10 patients were correctly predicted having risk based on their eye images.

Язык: Английский

Процитировано

2
Enhancing radiographic image interpretation: WARES-PRS model for knee bone tumour detection DOI

Rahamathunnisa Usuff,

Sudhakar Kothandapani,

Rajesh Rangan

и другие.

Network Computation in Neural Systems, Год журнала: 2024, Номер unknown, С. 1 - 31

Опубликована: Июнь 26, 2024

The early diagnosis of tumour is significant in biomedical research field to lower the severity level and restrict process extension from cancer. Moreover, detection sign cancer undertaken with extensive efforts that dedicated disclosure recognition tumours. However, limited data size as well diverse appearance images lowered performance failed detect complex stage tumour. So solve these issues, a Weighted Adaptive Random Ensemble Support Vector-based Partial Reinforcement Search (WARES-PRS) algorithm proposed detected bone lesions accurately also predicted efficiently. Further, performed varied stages diminish presence noise effective classification. validated CNUH dataset enhanced image pre-processing tasks. Despite method uncover mutual relationships between each pixel's local texture overall image's global context. classification efficiency various measures experimental results revealed accuracy for approach by 98.5%. outcomes our study have exhibited substantial contribution assisting physicians knee

Язык: Английский

Процитировано

0