Rakshak: A Child Identification Software for Recognizing Missing Children Using Machine Learning-Based Speech Clarification

Rakshak: A Child Identification Software for Recognizing Missing Children Using Machine Learning-Based Speech Clarification

Ashutosh Dixit, Preeti Sethi, Puneet Garg
Copyright: © 2022 |Pages: 15
DOI: 10.4018/IJKBO.299968
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Almost every country in the world is facing the issue of child trafficking. Besides abduction, children below 10 years sometimes get missed from their homes or other locations due to many reasons. following the criminal record, many of the abducted or missed children got received by police officials where majorly officials face difficulty to get correct information as the founded children are not in their normal state in general due to fear factor or less trust. It is also observed that such children also usually start stammering due to uncontrolled emotions. In this kind of situation, Police officials would not get the exact information of founded children and unable to contact their respective guardians. This paper proposes a possible solution “Rakshak” for this kind of difficult situation. The Rakshak is Machine Learning based software which inputs the recorded voice of such children by police officials and returns the voice as well as text output after being corrected by various techniques of the Rakshak.
Article Preview
Top

1. Introduction

Child Kidnapping is one of the most hated crimes globally. The person who commits such a crime deserves the hardest punishment. But, despite the strict laws imposed by almost every country, the graph of abducted child crime is on increasing phase day-by-day (Gurung, 2020). This abducted child is usually forcefully dragged into the organized business of begging, pick-pocketing, prostitution, etc. Some International Gangs extract human organs from abducted child and sells them at high rates (Boruah & Roy, 2021). Article 23 in Indian Constitution strictly prohibits human trafficking and forced labor. India is also putting hard efforts into stopping this crime in the country, but, results are not in favor of these efforts. Department of State, United States has placed India in the category of Tier-II Country due to the absence of considerable results against Child Trafficking (Beyrer, 2004).

Total 63,407 children went missing in the year 2016 in India, according to the latest data from the National Crime Records Bureau (Joshi, 2016), which translates to an average of 174 every day and it is more shocking that more than 51% of missing children was a girl child. Indian Police are doing great efforts to overcome this social and legal menace. According to IndiaSpend (Chaitanya, 2015), the five prime purposes of Human Trafficking have been depicted in Figure 1.

Figure 1.

Top five purposes of Human Trafficking (source: IndiaSpend)

IJKBO.299968.f01

According to the National Crime Records Bureau’s updated data for 2020, Delhi reported 3,770 minors (aged below 18) being hijacked -- the highest across 19 metropolitan cities with a citizens of more than two million.Bengaluru reported 654 such cases and Kolkata 266. The number of cases in Mumbai and Chennai was 1,150 and 14 respectively, according to the NCRB article that was released recently. According to the wise cracked of Delhi data, 69 cases involved children below the age of six. The number of cases registered in the age bracket of 6-12 and 12-16 stood at 368 and 1,929 respectively. Around 1,404 cases involved minors in the age group of 16-18 years. Cornerwise, most victims were girls. A total of 2,749 girls were hijacked and 1,021 victims were boys, according to the data.

According to Delhi Police data, between January 1 and December 31, 2019, 5412 children were reported missing, of which 3336 were traced --a recovery rate of 61.64%. In 2020, at least 4297 children were reported missing, while 4052 were recovered – a recovery rate of 94.29% and an improvement of 32.65 percentage points compared to 2019. These cases included those in which kidnapping/abduction cases were registered and those in cases were not registered, but children were reported missing.

One of the major problems which the police officials face is gathering/extracting personal details from the recovered child. In general, when a kidnapped child is recovered by police, he is not in the state of explaining his details due to fear factors or any other reasons. Sometimes, Police officers make that child comfortable by their sober counseling but it is not always possible and easy to do the same.

To make this inquiry convenient and general, novel software named Rakshak has been proposed. Rakshak is software that will surely be helpful to understand the statements of recovered toddlers who are not able to properly speak. It is based on Machine Learning techniques for error detection and correction in Text.

Top

2. Existing Word Error Detection Techniques

The two main methods used for the wrong word website are n-gram checking and word reference search. IV-grams are suffix effects of n letters of words or strings, where n is generally one, two, or three. The grammatical characters made up of a single letter are known as single or single letters. Two n-grams are called a digram or a bigram. And the three letters n are like trigrams. Typically n-gram strategies for identifying fatal errors by parsing every n-gram in a data set and finding it in a pre-built table of n-gram insights to discover or repeat the truth.

Complete Article List

Search this Journal:
Reset
Volume 14: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 13: 1 Issue (2023)
Volume 12: 4 Issues (2022): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing