A Novel partial sequence technique based Chaotic biogeography optimization for PAPR reduction in generalized frequency division multiplexing waveform

Xue, Xingsi; Palanisamy, SatheeshKumar; A, Manikandan; Selvaraj, DhanaSekaran; Khalaf, Osamah Ibrahim; Abdulsahib, Ghaida Muttashar

doi:10.1016/j.heliyon.2023.e19451

Cited by 16 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent work by Bonawitz et al 8 proposes that machine learning on multipartite distributed data sets maintains data privacy. Li et al 9 establish a novel framework for FL to make it more resistant to hostile assaults. Abdul Rahman et al 10 offer a thorough analysis of FL, including its uses, difficulties, and privacy-preserving methods.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Federated learning with hybrid differential privacy for secure and reliable cross‐IoT platform knowledge sharing

Ibrahim Khalaf,

S.R,

Algburi

et al. 2024

Security and Privacy

Self Cite

View full text Add to dashboard Cite

The federated learning has gained prominent attention as a collaborative machine learning method, allowing multiple users to jointly train a shared model without directly exchanging raw data. This research addresses the fundamental challenge of balancing data privacy and utility in distributed learning by introducing an innovative hybrid methodology fusing differential privacy with federated learning (HDP‐FL). Through meticulous experimentation on EMNIST and CIFAR‐10 data sets, this hybrid approach yields substantial advancements, showcasing a noteworthy 4.22% and up to 9.39% enhancement in model accuracy for EMNIST and CIFAR‐10, respectively, compared to conventional federated learning methods. Our adjustments to parameters highlighted how noise impacts privacy, showcasing the effectiveness of our hybrid DP approach in striking a balance between privacy and accuracy. Assessments across diverse FL techniques and client counts emphasized this trade‐off, particularly in non‐IID data settings, where our hybrid method effectively countered accuracy declines. Comparative analyses against standard machine learning and state‐of‐the‐art FL approaches consistently showcased the superiority of our proposed model, achieving impressive accuracies of 96.29% for EMNIST and 82.88% for CIFAR‐10. These insights offer a strategic approach to securely collaborate and share knowledge among IoT devices without compromising data privacy, ensuring efficient and reliable learning mechanisms across decentralized networks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Let p a be the participants count and H be the degrees of data heterogeneity. The overall privacy budget ε is then distributed according to the degree of heterogeneity α ( h, p a ) to the level h, p a : of each participant is provided in equation (9).…”

Section: Dynamic Allocationmentioning

confidence: 99%

Federated learning with hybrid differential privacy for secure and reliable cross‐IoT platform knowledge sharing

Ibrahim Khalaf,

S.R,

Algburi

et al. 2024

Security and Privacy

Self Cite

View full text Add to dashboard Cite

show abstract

“…An increase in delta/theta ratio indicates heightened slow-wave activity relative to theta activity, which is often associated with abnormal brain states such as [115] epileptic seizures. A decrease in alpha/delta ratio suggests reduced alpha activity relative to slow-wave delta activity, [116] which may be indicative of abnormal cortical functioning observed in epilepsy. An increase in theta/delta variance suggests [117] greater variability in the balance between theta and delta activity, which could reflect dynamic changes in brain states associated with epileptic activity.…”

Section: Ratio Indicesmentioning

confidence: 99%

Epilepsy Identification using Hybrid CoPrO-DCNN Classifier

Basawaraj Birajadar,

Osman Mulani,

Ibrahim Khalaf

et al. 2024

IJCDS

View full text Add to dashboard Cite

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

show abstract

“…Vandana et al [15] puts forth an optimized Graph Cut-based clustering architecture for determining the malignancy degree in hematoxylin and eosin (H&E) stained HIs. This technique performs repeated Graph Cut methodology (GCM) for excerpting front objects out of biopsy images.…”

Section: Survey Upon Deep Nn For Fementioning

confidence: 99%

Optimized Swarm Enabled Deep Learning Technique for Bone Tumor Detection using Histopathological Image

Anand,

Khalaf,

Hajjej

et al. 2023

Sinergi

View full text Add to dashboard Cite

Cancer subjugates a community that lacks proper care. It remains apparent that research studies enhance novel benchmarks in developing a computer-assisted tool for prognosis in radiology yet an indication of illness detection should be recognized by the pathologist. In bone cancer (BC), Identification of malignancy out of the BC’s histopathological image (HI) remains difficult because of the intricate structure of the bone tissue (BTe) specimen. This study proffers a new approach to diagnosing BC by feature extraction alongside classification employing deep learning frameworks. In this, the input is processed and segmented by Tsallis Entropy for noise elimination, image rescaling, and smoothening. The features are excerpted employing Efficient Net-based Convolutional Neural Network (CNN) Feature Extraction. ROI extraction will be employed to enhance the precise detection of atypical portions surrounding the affected area. Next, for classifying the accurate spotting and for grading the BTe as typical and a typical employing augmented XGBoost alongside Whale optimization (WOA). HIs gathering out of prevailing scales patients is acquired alongside texture characteristics of such images remaining employed for training and testing the Neural Network (NN). These classification outcomes exhibit that NN possesses a hit ratio of 99.48 percent while this occurs in BT classification.

show abstract

A Novel partial sequence technique based Chaotic biogeography optimization for PAPR reduction in generalized frequency division multiplexing waveform

Cited by 16 publications

References 38 publications

Federated learning with hybrid differential privacy for secure and reliable cross‐IoT platform knowledge sharing

Federated learning with hybrid differential privacy for secure and reliable cross‐IoT platform knowledge sharing

Epilepsy Identification using Hybrid CoPrO-DCNN Classifier

Optimized Swarm Enabled Deep Learning Technique for Bone Tumor Detection using Histopathological Image

Contact Info

Product

Resources

About