Claim Missing Document
Check
Articles

Found 2 Documents
Search

Child drowning prevention: GPS and LoRa based emergency alert system Enam, Md. Rayef; Ghosh, Subhasish; Sarker, Dr. M. Mesbahuddin
The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i4.3277

Abstract

UNICEF recently published in the "Country Office Report 2021" about the mortality of children in Bangladesh, "Every day, 30 children die from drowning – Bangladesh's second leading cause of under-five mortality. Drowning is preventable, and most cases occur within a child's home community." Bangladesh is a country of rivers, which means Bangladesh called a riverine country located in South Asia. The Center for Injury Prevention and Research conducted a survey, Around 19000 people of (all types of ages) drown every year in Bangladesh. Among them, 14500 which mean 77% are children. In our research, the emergency alert system is designed to be cost-effective and user-friendly for village communities in Bangladesh. The system is divided into two components: the kid is equipped with the transmitter, and the receiver is placed at home. The transmitter and receiver both use a LoRa transmission module that can communicate accurately within a 300-meter range (coverage up to 10 Kilometers) and can transmit 256 bytes of data. The transmitter collects geolocation data using a GPS module and sends the data to the receiver using the LoRa module. The receiver module is configured by setting up the geolocation of risky places. The receiver will send SMS or buzzing the receiver to alert the parents when the transmitter or kid is nearby risky places. The Equirectangular approximation method calculates the distance between children's positions from risky areas. Additionally, the transmitter and receiver may communicate encrypted messages using AES 128-bit symmetric encryption technology compatible with Arduino Nano controller. Thus, our emergency alert system can save children from drowning in the home environment.
Attention-based CNN-BiGRU for Bengali Music Emotion Classification Ghosh, Subhasish; Riad , Md. Omar Faruk
The Indonesian Journal of Computer Science Vol. 11 No. 3 (2022): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v11i3.3111

Abstract

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. To extract meaningful knowledge, however, past studies' shortcomings of low accuracy and overfitting have to be addressed. We have proposed a model combining Conv1D, Bi-GRU and the Bahdanau attention mechanism for music emotion classification of our Bengali music dataset. The model integrates distinct MFCCs wav preprocessing methods with deep learning methods and attention-based methods. The attention mechanism has increased the accuracy of the proposed classification model. The music is finally classified into one of the four emotion classes: Angry, Happy, Relax, Sad. The proposed Conv1D+BiGRU+Attention model is validated as more effective and efficient at classifying emotions in the Bengali music dataset than baseline methods, according to comparisons with baseline models. For our Bengali music dataset, the performance of our proposed model is 95%.