An instance-based physical violence detection algorithm for school bullying prevention

Author(s):  
Liang Ye ◽  
Hany Ferdinando ◽  
Tapio Seppanen ◽  
Tuija Huuki ◽  
Esko Alasaarela
2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Liang Ye ◽  
Hany Ferdinando ◽  
Tapio Seppänen ◽  
Esko Alasaarela

School bullying is a serious problem among teenagers, causing depression, dropping out of school, or even suicide. It is thus important to develop antibullying methods. This paper proposes a physical bullying detection method based on activity recognition. The architecture of the physical violence detection system is described, and a Fuzzy Multithreshold classifier is developed to detect physical bullying behaviour, including pushing, hitting, and shaking. Importantly, the application has the capability of distinguishing these types of behaviour from such everyday activities as running, walking, falling, or doing push-ups. To accomplish this, the method uses acceleration and gyro signals. Experimental data were gathered by role playing school bullying scenarios and by doing daily-life activities. The simulations achieved an average classification accuracy of 92%, which is a promising result for smartphone-based detection of physical bullying.


2021 ◽  
Vol 13 (4) ◽  
pp. 628
Author(s):  
Liang Ye ◽  
Tong Liu ◽  
Tian Han ◽  
Hany Ferdinando ◽  
Tapio Seppänen ◽  
...  

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%.


Author(s):  
Sergazy Narynov ◽  
Zhandos Zhumanov ◽  
Aidana Gumar ◽  
Mariyam Khassanova ◽  
Batyrkhan Omarov

2016 ◽  
Vol 4 (2) ◽  
pp. 142-164 ◽  
Author(s):  
Peter K. Smith

Following some background studies on the nature of school bullying, its prevalence, and the negative consequences it can have, this article reviews the history of anti-bullying interventions over the last 30 years. It considers several major programmes in detail, such as the Olweus Bullying Prevention Program, KiVa, Steps to Respect, and Friendly Schools. The nature and evaluation of the interventions is discussed, followed by a review of meta-analyses of the programmes effectiveness. Issues considered are the effect at different ages; components of interventions; work with peers; disciplinary methods, non-punitive and restorative approaches; challenges regarding cyberbullying; the role of parents; the role of teachers and teacher training; set menu versus à la carte approaches; sustainability of interventions and societal context. Conclusions show that interventions have had some success, with traditional bullying. However, further progress is needed in strengthening theoretical underpinnings to interventions, and in tackling cyberbullying.


Author(s):  
Y. Lytvynenko

At present, in the Ukrainian society, there is a gradual transition from the "interest" of bullying problems to implement a practical program to counteract bullying in the school environment. Programs are being implemented with support the MES of Ukraine using conflicting functionality, changing and navigating non-violent behavior and civic attitudes. The results of the empirical study made it possible to pay attention to the need to change approaches when using bullying prevention technology among adolescents. In particular, it was determined that not only forms of preventive training play a major role in preventing bullying, but the use of techniques, methods, ways of information submission by the subjects who carry it out, and features of interpersonal interaction with adolescents. Often, they have signs of prejudice and stigma that provoke aggression and bullying cases.


Author(s):  
Ariel A. Williamson ◽  
Nancy G. Guerra ◽  
Noel L. Shadowen

This chapter conceptualizes school-based, peer-to-peer bullying as a coercive relational process, in which bullies instrumentally use aggressive interpersonal tactics to influence, change, or dominate others in order to attain desired outcomes. We explain how this coercive process occurs on multiple levels, both within the bully-victim dyad and within the peer group context. We then discuss how the nature and desired outcomes of bullying change according to school setting and developmental period, drawing on empirical research that highlights the increasingly sexualized nature of bullying during early adolescence. Finally, we link sexual harassment and bullying behaviors during adolescence to risk for involvement in coercive relationships and processes in adulthood, and review the implications of this work for evidence-based bullying prevention programs.


Author(s):  
Leslee A. Fisher ◽  
Lars Dzikus

Bullying is a growing problem in sport and performance settings. Bullying falls under the umbrella of “athlete maltreatment,” which includes any form of harm and all relationships where harm could occur in sport and performance. Specifically, bullying is defined as repeated hostile and deliberate behavior from one person (the perpetrator) to another (the target) with the intent to harm or threaten harm to the target; it is marked by an imbalance of power. Often, after extreme bullying, the target feels terrorized. Athlete maltreatment in sport and performance has been categorized into one of two forms: relational maltreatment and nonrelational maltreatment. Bullying is a relational problem. In particular, sport and performance bullying can occur from coach to player, parent to player, or player to player, and often takes the form of (1) making unreasonable performance demands of the target, (2) repeated threats to restrict or remove the target’s privileges or opportunities, (3) screaming or yelling directed at the target that is unwarranted, (4) repeated and continual criticism of the target’s abilities, (5) discounting or denying the target’s accomplishments, (6) blaming the target for his or her mistakes, (7) threats of and/or actual physical violence toward the target, and (8) social media or e-mail messages with threats or insults toward the target. Sport and performance organizations should develop and implement antibullying policies. Six potential steps toward policy development and implementation include: (1) defining bullying behaviors, (2) referring to existing “best-practice” bullying policies, (3) specifically outlining the reporting of bullying incidents, (4) outlining clearly investigation and disciplinary actions to be taken, (5) outlining specific assistance for bullying targets, and (6) including prevention and training procedures. In the meantime, coaches as well as parents and players can recognize that they are role models for everyone with whom they come into contact in sport and performance settings. Coaches, parents, and players can also accept responsibility for creating a respectful and safe sport and performance environment, have a pre-season meeting to discuss antibullying policy, foster open and honest communication, accept critical feedback, not engage or allow bullying behavior themselves, create acceptable boundaries between themselves and others, and teach players to trust their instincts when things do not feel right. More advanced bullying prevention and training procedures can then take place.


Sign in / Sign up

Export Citation Format

Share Document