Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network With Transfer Learning

Interpersonal violence, such as physical and sexual abuse, eve-teasing, bullying, and taking hostages, is a growing concern in our society. The criminals who directly or indirectly committed the crime often do not go into the trial for the lack of proper evidence as it is very tough to collect photographic proof of the incident. A subject's corneal reflection has the potentiality to reveal the bystander images. Motivated with this clue, a novel approach is proposed in the current paper that uses a convolutional neural network (CNN) along with transfer learning in identifying crime as well as recognizing the criminals from the corneal reflected image of the victim called the Purkinje image. This study found that off-the-shelf CNN can be fine-tuned to extract discriminative features from very low resolution and noisy images. The procedure is validated using the developed datasets comprising six different subjects taken at diverse situations. They confirmed that it has the ability to recognize criminals from corneal reflection images with an accuracy of 95.41%.

Development of Street Harassment Scale for Women in Universities

This study is aimed to discuss the manifestations of street harassment among women university students of Lahore. The initial phase of the study involved conducting semi-structured interviews. For this purpose, 20 women university students were interviewed and 19 items were generated. A list of 19 items was given to experts to assess content validity. After removing repetitive statements, 15 item scale was retained and validated by experts. The final 15 item scale was administered to 150 female participants. Factor analysis showed significant KMO value and Bartlett’s test of sphericity which indicated a significant correlation between the items with a few exceptions of weak loadings. Items 12 and 13 showed weak loadings, so these items were discarded and a 13 item scale was retained. Three-factor solutions were suggested through Principle Component Analysis via oblimin rotation and labeled as Behavioral, Verbal, and Eve Teasing. Confirmatory Factor Analysis was further done on a sample of 380 participants to confirm the factors obtained via Exploratory Factor Analysis which overall showed a strong construct validity of the scale and model fit after removal of three items. The final retained version of the scale consisted of 12 items. To assess the convergent validity of the indigenously developed scale, the Sexual Harassment Experience Questionnaire (Kamal & Tariq, 1998) was used as it assessed a similar construct. The correlation coefficient of the two scales was .49 (p < .01). Cronbach alpha value of the developed scale was .82 suggesting a strong inter-item correlation. There are myriad interventions on which the study sheds light.

DMRC Location Tracker and Alert System

It is a simple React-Native application used to get an alert before your destined metro station so that you can plan your journey accordingly without the fear of missing the destination. The purpose of this project is to design and construct a hand-held wireless tracking device so that the location of a person can be detected. Other than providing alert the application can also be used for women safety purpose. It focuses on one of the important problems of society that is eve-teasing. It makes the society to be aware of the misbehavior which is happening and to come forward for help. It enables women to be self-dependent and can handle any kind of unpredictable situation. It mainly shares the location based on GPS, (Global Positioning System). Pressing the SOS button it sends the emergency message with time and location to the emergency contacts and metro authorities. When the application triggers on the time of travelling it send the location to the emergency contacts with few images taken by the camera on spot, and a siren rings which gives immediate help.

The ebb and flow of ‘eve-teasing’ in the news: Front page coverage of street harassment of women in Bangladesh

Eve-teasing is a euphemism for street-based sexual harassment, which is a widespread issue across Bangladesh affecting the emotional, mental, and physical wellbeing of Bangladeshi women. The media can play a vital role by covering news and raising awareness of eve-teasing. Historically, the headlines in Bangladesh focused on more obvert forms of gender violence—rape, murder, acid attacks—framing eve-teasing as a mere nuisance, a fact of life in the country. How the media portrays eve-teasing in Bangladesh is a subject about which there is currently very little research. This content analysis of the two main national newspapers in Bangladesh assesses how the media reported street-based sexual harassment over the course of a seminal year—2010. It was during this year that the government of Bangladesh enacted the Family Violence Prevention and Protection Act in acknowledgement of the prevalence and seriousness of gender violence in the country. Similar acts had been passed by the governments of nearby countries India and Sri Lanka in 2005, and Nepal in 2008 (Fardosh, 2013). This study looks at how Bangladeshi newspapers covered ‘eve-teasing’ prominently (as front-page news), in a year when it was acknowledged as a serious issue, through the passing of a law by the Bangladeshi government.

Iot Based Emergency Security System for Women

In today’s era, women are progressing and scaling the peaks of success. However, there’s a significant hike in the number of crimes against women like molestation, eve-teasing, trafficking, etc. Also, there have been numerous attempts to ensure the safety of women ranging from the infamous mobile apps to the hefty belts &safety jackets,etc. However, it is not practical to carry such bulky systems and the victim may not be able to reach the smartphone without being noticed by the assaulter.This increases the risk factor. Therefore, to ensure the security of women, in this paper we propose an IOT based Emergency security system. This system includes a gsm, gps, raspberry pi, fingerprint module, camera module and IR led blasters. It aims at providing a dual security to the women with the help of panic button and fingerprint scanning device. Whenever a woman feels like she is in danger, she can manually switch on the system which will require her to scan her fingerprint for every 1 min. Practically, if she is in distress situation she would fail to scan and the camera module which is embedded in the woman’s pendant will start capturing images and live video. The GPS module will trace the exact location & GSM module will send emergency text messages to the specified contacts and alert the nearby police station. An additional provision of improved vision during night time using IR led blasters is incorporated in this system.

Understanding Women’s Access to Sanitation: A Study of the Slums in Delhi

Sanitation is an important basic right for a dignified living. About 130 million households lack toilets; even more than 72 per cent of the rural population defecate in open areas. The dearth of proper sanitation facilities is visible throughout the Indian sub-continent. Even the capital has failed to distance from this crisis. Lack of sanitation facilities causes pollution, health issues and, above all, security problems, especially for women. Women ought to go for open defecation that makes them more vulnerable towards crime. Rape, sexual assault or eve-teasing often take place in the silence of the night, and the screams of pain never come out. This paper highlights the poor sanitation facilities in slums and jhuggi jhopadi clusters in Delhi and its effect on people living there. A gender analysis framework has been used to get a wider perspective on the problems arising due to the lack of sanitation.