Face Recognition using Raspberry Pi

Boxey, Aasawari; Jadhav, Anushri; Gade, Pradnya; Ghanti, Priyanka; Mulani, Dr.A.O.

doi:10.55529/jipirs.24.15.23

Cited by 8 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the feature extraction, the RE-LIEEF [46], [47] filters the removed features by rating them and sorting them according to the weights calculated. The features chosen are passed to the DCNN classifier, which incorporates a hybrid CoPrO-based algorithm [48], [49] for classifier tuning. The developed research highlights worth of the hybrid CoPrO-based algorithm for fine-tuning the inner model structure like bias and weight of DCNN classifier.…”

Section: Methodsmentioning

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

Section: Methodsmentioning

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

show abstract

“…The nuchal translucency zone was segmented using mean shift interpretation and canny edge detection, and even the precise width was calculated utilizing Blob analytics. Sciortino et al [10] propose a technique for conducting accurate investigations utilizing mid-sagittal sections centered on wavelet analysis and neural network classifiers to uncover relevant features for identifying mid-sagittal planes. Thomas et al [11] propose Image Segmentation strategies such as Area Growing, Chan-vase, and Level Set that are analyzed and evaluated to correctly identify the NT area with ultrasonography imaging.…”

Section: Journal Of Applied Pharmaceutical Research (Joapr)| January ...mentioning

confidence: 99%

Clinical investigations to calculate nuchal translucency using F-LNET

Chaudhari,

Oza

2024

JAPR

View full text Add to dashboard Cite

Background: According to ongoing research, assessing nuchal translucency (NT) in ultrasound pictures can help to identify fetal development that deviates from the norm. The chance of chromosomal abnormalities in a newborn is predicted by the nuchal translucency (NT) width in ultrasound sonography pictures performed on the child between 11 and 14 weeks of gestation. Method: Deeply learned convolutional networks have recently significantly improved NT region detection performance. This paper discusses a novel approach to learning a cutting-edge NT Region identification algorithm. To address the difficulty of improving the accuracy of NT recognition in various lighting and posture conditions, a Framework Learning Network (F-LNET) is employed. Discussion: The limitations of the current NT estimating technique include findings that are unpredictable and intra-personal, inter-personal, and inter-variation restrictions. On the other hand, existing solutions have a high processing overhead and are, hence, unsuitable for rapid NT limiting and localization, which is critical for reliable recognition. However, current methods could be better for quick NT limiting and localization, which is essential for trustworthy identification schemes because of their significant processing overhead. The suggested automated clinical finding approach, which computes the error between human and automated measurements, is very beneficial to both doctors and society at large. Conclusion: The suggested way reduces the error to 0.42, whereas the error of other methods ranges from 0.8 to 1.1.

show abstract

Utilizing Information and Communication Technology in Scalable Management Strategies for Teacher Development

Rukajat,

Gusniar,

Abas

et al. 2023

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

INTRODUCTION: Teachers are human resources who play an important and strategic role in the success of learning so they must fulfill adequate competencies. Teachers with low competence will not be able to produce students who excel both academically and non-academically. Efforts to improve teacher competency include education and training. OBJECTIVE: This research aims to see how information and communication technology is used in developing teachers' pedagogical and professional competencies. METHODS: This research was carried out using a descriptive qualitative approach. The data used in this research was obtained from various relevant sources. RESULTS: The results of this research found that increasing teacher pedagogical and professional competence through the integration of Information and Communication Technology (ICT) and scalable management strategies opens up new perspectives on the importance of investing in the development of teaching staff. CONCLUSION: The alignment of modern pedagogical approaches with the use of technology and efficient management strategies allows teachers to develop as more effective and competitive educators. Increasing pedagogical competence allows educators to create more dynamic and relevant learning environments for students. By incorporating innovative teaching methods, such as the use of digital tools and resources, teachers can adapt learning to students' diverse learning styles.

show abstract

Face Recognition using Raspberry Pi

Cited by 8 publications

References 25 publications

Epilepsy Identification using Hybrid CoPrO-DCNN Classifier

Epilepsy Identification using Hybrid CoPrO-DCNN Classifier

Clinical investigations to calculate nuchal translucency using F-LNET

Utilizing Information and Communication Technology in Scalable Management Strategies for Teacher Development

Contact Info

Product

Resources

About