AI assisted Edge Vision for Violence Detection in IoT based Industrial Surveillance Networks

Abstract:Since the 1950s, national networks for the surveillance of influenza have been progressively implemented in several countries. New epidemiological arguments have triggered changes in order to increase the sensitivity of existent early warning systems and to strengthen the communications between European networks. The WHO project CARE Telematics, which collects clinical and virological data of nine national networks and sends useful information to public health administrations, is presented. From the results of the 1993-94 season, the benefits of the system are discussed. Though other telematics networks in this field already exist, it is the first time that virological data, absolutely essential for characterizing the type of an outbreak, are timely available by other countries. This argument will be decisive in case of occurrence of a new strain of virus (shift), such as the Spanish flu in 1918. Priorities are now to include other existing European surveillance networks.

Download Full-text

Adaptive Resource Management in Application to Surveillance Networks using Stochastic Methodologies

i-manager’s Journal on Software Engineering ◽

10.26634/jse.5.1.1201 ◽

2010 ◽

Vol 5 (1) ◽

pp. 1-6

Author(s):

Charles C. Castello ◽

Jeffrey Fan

Keyword(s):

Resource Management ◽

Adaptive Resource Management ◽

Surveillance Networks ◽

Adaptive Resource

Download Full-text

A survey of video violence detection

Cyber-Physical Systems ◽

10.1080/23335777.2021.1940303 ◽

2021 ◽

pp. 1-24

Author(s):

Huiling Yao ◽

Xing Hu

Keyword(s):

Violence Detection

Download Full-text

A dataset for automatic violence detection in videos

Data in Brief ◽

10.1016/j.dib.2020.106587 ◽

2020 ◽

Vol 33 ◽

pp. 106587

Author(s):

Miriana Bianculli ◽

Nicola Falcionelli ◽

Paolo Sernani ◽

Selene Tomassini ◽

Paolo Contardo ◽

...

Keyword(s):

Violence Detection

Download Full-text

Harnessing high-level concepts, visual, and auditory features for violence detection in videos

Journal of Visual Communication and Image Representation ◽

10.1016/j.jvcir.2021.103174 ◽

2021 ◽

pp. 103174

Author(s):

Bruno M. Peixoto ◽

Bahram Lavi ◽

Zanoni Dias ◽

Anderson Rocha

Keyword(s):

Violence Detection ◽

High Level ◽

Auditory Features

Download Full-text

Deep Neural Network for Gender-Based Violence Detection on Twitter Messages

Mathematics ◽

10.3390/math9080807 ◽

2021 ◽

Vol 9 (8) ◽

pp. 807

Author(s):

Carlos M. Castorena ◽

Itzel M. Abundez ◽

Roberto Alejo ◽

Everardo E. Granda-Gutiérrez ◽

Eréndira Rendón ◽

...

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Gender Violence ◽

Strategic Decision ◽

Learning Approaches ◽

Gender Based Violence ◽

Data Set ◽

Violence Detection ◽

Governmental Institutions ◽

Gender Based

The problem of gender-based violence in Mexico has been increased considerably. Many social associations and governmental institutions have addressed this problem in different ways. In the context of computer science, some effort has been developed to deal with this problem through the use of machine learning approaches to strengthen the strategic decision making. In this work, a deep learning neural network application to identify gender-based violence on Twitter messages is presented. A total of 1,857,450 messages (generated in Mexico) were downloaded from Twitter: 61,604 of them were manually tagged by human volunteers as negative, positive or neutral messages, to serve as training and test data sets. Results presented in this paper show the effectiveness of deep neural network (about 80% of the area under the receiver operating characteristic) in detection of gender violence on Twitter messages. The main contribution of this investigation is that the data set was minimally pre-processed (as a difference versus most state-of-the-art approaches). Thus, the original messages were converted into a numerical vector in accordance to the frequency of word’s appearance and only adverbs, conjunctions and prepositions were deleted (which occur very frequently in text and we think that these words do not contribute to discriminatory messages on Twitter). Finally, this work contributes to dealing with gender violence in Mexico, which is an issue that needs to be faced immediately.

Download Full-text

Campus Violence Detection Based on Artificial Intelligent Interpretation of Surveillance Video Sequences

Remote Sensing ◽

10.3390/rs13040628 ◽

2021 ◽

Vol 13 (4) ◽

pp. 628

Author(s):

Liang Ye ◽

Tong Liu ◽

Tian Han ◽

Hany Ferdinando ◽

Tapio Seppänen ◽

...

Keyword(s):

Neural Network ◽

Recognition Accuracy ◽

Role Playing ◽

School Bullying ◽

Image Features ◽

Campus Violence ◽

Surveillance Video ◽

Acoustic Features ◽

Mel Frequency Cepstral Coefficients ◽

Violence Detection

Campus violence is a common social phenomenon all over the world, and is the most harmful type of school bullying events. As artificial intelligence and remote sensing techniques develop, there are several possible methods to detect campus violence, e.g., movement sensor-based methods and video sequence-based methods. Sensors and surveillance cameras are used to detect campus violence. In this paper, the authors use image features and acoustic features for campus violence detection. Campus violence data are gathered by role-playing, and 4096-dimension feature vectors are extracted from every 16 frames of video images. The C3D (Convolutional 3D) neural network is used for feature extraction and classification, and an average recognition accuracy of 92.00% is achieved. Mel-frequency cepstral coefficients (MFCCs) are extracted as acoustic features, and three speech emotion databases are involved. The C3D neural network is used for classification, and the average recognition accuracies are 88.33%, 95.00%, and 91.67%, respectively. To solve the problem of evidence conflict, the authors propose an improved Dempster–Shafer (D–S) algorithm. Compared with existing D–S theory, the improved algorithm increases the recognition accuracy by 10.79%, and the recognition accuracy can ultimately reach 97.00%.

Download Full-text