Physical security assessment with convolutional neural network transfer learning

Stubbs, Jaclynn J.; Birch, Gabriel C.; Woo, Bryana Lynn; Kouhestani, Camron G.

doi:10.1109/ccst.2017.8167800

Cited by 7 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In transfer learning, already known knowledge is extracted and is applied to new domain. If transfer learning is used on CNN, it is found that training time is significantly reduced as well as accuracy of detecting physical security related target is also high [43]. A more ideal physical security system would have a processing layer that eliminates the majority of nuisance alarms prior to presenting the information to an operator.…”

Section: Physical Security Systemmentioning

confidence: 99%

Review on effectiveness of deep learning approach in digital forensics

Ekhande

Patil

Kulhalli

2022

IJECE

View full text Add to dashboard Cite

<p><span>Cyber forensics is use of scientific methods for definite description of cybercrime activities. It deals with collecting, processing and interpreting digital evidence for cybercrime analysis. Cyber forensic analysis plays very important role in criminal investigations. Although lot of research has been done in cyber forensics, it is still expected to face new challenges in near future. Analysis of digital media specifically photographic images, audio and video recordings are very crucial in forensics This paper specifically focus on digital forensics. There are several methods for digital forensic analysis. Currently deep learning (DL), mainly convolutional neural network (CNN) has proved very promising in classification of digital images and sound analysis techniques. This paper presents a compendious study of recent research and methods in forensic areas based on CNN, with a view to guide the researchers working in this area. We first, defined and explained preliminary models of DL. In the next section, out of several DL models we have focused on CNN and its usage in areas of digital forensic. Finally, conclusion and future work are discussed. The review shows that CNN has proved good in most of the forensic domains and still promise to be better.</span></p>

show abstract

Section: Physical Security Systemmentioning

confidence: 99%

Review on effectiveness of deep learning approach in digital forensics

Ekhande

Patil

Kulhalli

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…Ada beberapa jenis keamanan, yaitu keamanan komputer dan keamanan fisik. Keamanan fisik adalah aspek yang paling mendasar dari sebuah keamanan, ini digunakan dalam kontrol fisik untuk melindungi tempat, situs kebudayaan, fasilitas, bangunan, atau aset lainnya yang berbentuk fisik [4]. Sama halnya dengan kesehatan, keamanan merupakan suatu aspek yang penting dalam kehidupan.…”

Section: Pendahuluanunclassified

Prototipe Sistem Keamanan Pintu Rumah Berbasis Single Board Computer (SBC)

Fikri

Hersyah

Novani

2020

chipset

View full text Add to dashboard Cite

Security is a very important need for everyone, one of the security that is needed is the safety of valuables both publicly and more especially at home. Due to the large number of thieves who came directly to the house, the door was forced open, and forgot to close the door, the theft cases increased. Therefore, a system that can detect movement in front of the door using a PIR sensor is designed, gives a warning when the door is forced open and can open or close the door automatically. This research uses the Telegram bot to send orders and receive notifications in the form of text or images. The PIR sensor will give notification when a movement is detected in front of the door, once detected it will turn on the LED light and take a picture of the movement, a warning from the system in the form of a buzzer. It will also serve as a warning when the door is forced open. When the user enters the open command via the Telegram bot, the door will open and close by itself. The error of the tested system is 0%, all components can work as expected.

show abstract

“…"Enhanced artificial intelligence" is the new frontier in the implementation of smart devices, which in turn opens up new possibilities for solving problems associated with security and video surveillance [1]. Various artificial intelligence techniques have resurfaced with great interest, one example being Deep Neural Networks (DNN), which perform well for identifying faces, vehicles, weapons, and other objects associated with a security system [2]. The preparation of the inputs, as well as their pre-processing, represent the challenge of correct selection for the good performance of a machine learning model [3].…”

Section: Introductionmentioning

confidence: 99%

Artificial vision techniques at the frontiers of video surveillance

Pérez-Escamilla

2023

JCT

View full text Add to dashboard Cite

The present work addresses the task of identifying a predatory behavior of robbery of homes or businesses. The proposed objective is the detection of blunt elements used in the commission of the crime, limiting the context to barrettes, covered faces, people and gates (doors or windows). The proposal addresses the task of object identification applying Single Shot Detectors (SSD). Due to its versatility and the physical resources applied, the structure of SSD ResNet50 V1 FPN 640x640 has been chosen from the TensorFlow Model Zoo to train and validate the classification. This has been built in five classes, for the training and validation set, an average of 50 annotations per class have been processed. Additionally, a support function was worked on in the detection of human activity. The evaluated model obtained a mA of 69% in the detection of objects and in the identification of criminal behavior it showed a performance of 69%.

show abstract

Physical security assessment with convolutional neural network transfer learning

Cited by 7 publications

References 10 publications

Review on effectiveness of deep learning approach in digital forensics

Review on effectiveness of deep learning approach in digital forensics

Prototipe Sistem Keamanan Pintu Rumah Berbasis Single Board Computer (SBC)

Artificial vision techniques at the frontiers of video surveillance

Contact Info

Product

Resources

About