IoT based Face Recognition for Smart Applications using Machine Learning

Pandimurugan, V.; Jain, Anmol; Sinha, Yash

doi:10.1109/iciss49785.2020.9316089

Cited by 18 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [23,24] constructed a smart home system with the ability to record offline and online attendance as well as detect offenders via an image recognition algorithm. Due to significant shifts in life caused by the pandemic, most previously offline jobs and services are now going online, with rapid digitization in the fields of education, home automation, and security.…”

Section: Literature Reviewmentioning

confidence: 99%

Smart Home IoT Privacy and Security Preservation via Machine Learning燭echniques

Almutairi¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The development and use of Internet of Things (IoT) devices have grown significantly in recent years. Advanced IoT device characteristics are mainly to blame for the wide range of applications that may now be achieved with IoT devices. Corporations have begun to embrace the IoT concept. Identifying true and suitable devices, security faults that might be used for bad reasons, and administration of such devices are only a few of the issues that IoT, a new concept in technological progress, provides. In some ways, IoT device traffic differs from regular device traffic. Devices with particular features can be classified into categories, irrespective of their function or performance. Ever-changing and complex environments, like a smart home, demand this classification scheme. A total of 41 IoT devices were employed in this investigation. To build a multiclass classification model, IoT devices contributed 13 network traffic parameters. To further preprocess the raw data received, preprocessing techniques like Normalization and Dataset Scaling were utilized. Feature engineering techniques can extract features from the text data. A total of 117,423 feature vectors are contained in the dataset after stratification, which are used to further improve the classification model. In this study, a variety of performance indicators were employed to show the performance of the logiboosted algorithms. Logi-XGB scored 80.2% accuracy following application of the logit-boosted algorithms to the dataset for classification, whereas Logi-GBC achieved 77.8% accuracy. Meanwhile, Logi-ABC attained 80.7% accuracy. Logi-CBC, on the other hand, received the highest Accuracy score of 85.6%. The accuracy of Logi-LGBM and Logi-HGBC was the same at 81.37% each. Our suggested Logi-CBC showed the highest accuracy on the dataset when compared to existing Logit-Boosted Algorithms used in earlier studies.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Smart Home IoT Privacy and Security Preservation via Machine Learning燭echniques

Almutairi¹

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…In [8], the study aimed to develop an an intelligent home system that could track attendance both digital and physical, and identify suspects using an computer vision algorithm. People's lives have undergone significant changes as a result of the pandemic, resulting in a shift of numerous professions and services from offline to online platforms.…”

Section: Related Workmentioning

confidence: 99%

Enhancing security in smart homes with IoT using logit-boosted techniques

Rahim,

Zhong,

Ahmad

2023

Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023)

View full text Add to dashboard Cite

The utilization and advancement of Internet of Things (IoT) gadgets have noticeably increased in recent times. Various sectors, including intelligent homes, healthcare, sports analysis, and different industries, use IoT devices. Traffic is a crucial aspect of IoT devices, and it differs from conventional device traffic in several ways. This investigation employed 41 Internet of Things (IoT) devices. A machine learning model was developed that can classify IoT devices into multiple categories based on 13 different network traffic features. The raw data that was gathered was preprocessed using techniques like standardization and scaling techniques of the dataset. Algorithms for feature selecting can be utilized to extract characteristics from textual data. Following stratification, The dataset contains 106,234 sets of features that were utilized to enhance the predictive model. This research employed various evaluation metrics to demonstrate the effectiveness of the logistic-boosted algorithms. In this research, collaborative machine learning methods were utilized as a starting point to develop an intrusion detection system (IDS) that can identify abnormal network traffic. The principal aim of this investigation is to identify attacks and abnormalities within a Smart Home IoT setting. We have introduced a new technique for constructing Logit-Boosted algorithm, namely Logi-CatBoost Classifier. Once the logitboosted algorithm was employed to classify the dataset, Logi-CBC performed the best, with an accuracy of 88.70%. We suggested Logi-CBC algorithm achieved the top precision among previously used Logit-Boosted algorithms in past studies on the same dataset.

show abstract

“…Furthermore, it is more challenging to identify faces when auxiliary features like a person's hair fringe, eyes, and makeup are present. The facial expression is also influenced by the clarity of pictures of faces and the trajectory and brightness of light sources [2]. Depending upon the person's face complexity, variations in the output of the facial tracking pro exist.…”

Section: Introductionmentioning

confidence: 99%

“…Person identification and tracking techniques in video clips have started to use DL architecture as a hotspot for target-tracking research. Before deep learning methodologies, conventional feature extraction techniques like principal component analysis (PCA), kernel-PCA (K-PCA), fisher linear discriminant analysis (FLDA), independent component analysis (ICA), and many more were tested by researchers [2], [3]. It gave good results, but execution time was more timeconsuming and limited for images.…”

Section: Introductionmentioning

confidence: 99%

Framework for multiple person identification using YOLOv8 detector: a transfer learning approach

Jayaram,

Vedagiri,

Ramachandra

2024

IJECE

View full text Add to dashboard Cite

Video surveillance extensively uses person detection and tracking technology based on video. The majority of person detection and classification techniques currently in use encounter challenges in video sequences brought on by occlusion, ambient lighting, and variations in human facial position. This paper proposed an effective person identification and classification system based on deep learning, which comprises a you only look once at version 8 (YOLOv8) detection and classification model, to classify human faces in video sequences accurately. This work proposes a new staff-detection and classification (S-DEC) dataset for comprehensive performance evaluation. visual tracker benchmark (VTB) standard database is used for performance comparison with the proposed S-DEC dataset. The proposed technique achieved 98.67% precision accuracy. For the S-DEC dataset, the system gave 94.67% accuracy in identifying facial images from a video sequence of 38 people addressing the pose variation occlusion challenge. Earlier methods used to provide approximately 85% to 90% results taking more execution time. Many existing techniques were successful in detecting people only-identification of the detected person has been done in limited papers. The proposed method uses the cross-stage partial connections (CSPDarknet53) model, integrated with YOLOv8, to achieve faster results. The proposed framework took 35 minutes to train a deep learning model. A testing time of 2 minutes ensured that the proposed framework outplayed other existing methodologies and successfully identified extra information about the detected person.

show abstract

IoT based Face Recognition for Smart Applications using Machine Learning

Cited by 18 publications

References 7 publications

Smart Home IoT Privacy and Security Preservation via Machine Learning燭echniques

Smart Home IoT Privacy and Security Preservation via Machine Learning燭echniques

Enhancing security in smart homes with IoT using logit-boosted techniques

Framework for multiple person identification using YOLOv8 detector: a transfer learning approach

Contact Info

Product

Resources

About