Anti-balance Load Control System Applied to an Overhead Crane Prototype Activated by Voice Commands

Bernardo, Christofer; Lima, Luis E. M.

doi:10.1109/tla.2021.9448318

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As one of the most popular topics, Keyword Spotting (KWS) problems have been solved using several methods. One of the most popular methods is using Artificial Neural Networks (ANN) [6]- [8]. The recent success of Deep Learning (DL) methods in other topics, such as image classification [9]- [12], medical signal analysis [13]- [16], and weather forecasting [17], [18] has inspired researchers to apply Deep Learning methods to KWS problems.…”

Section: A Abstractpotting Methodsmentioning

confidence: 99%

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Syafalni,

Amadeus,

Sutisna

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Keyword Spotting (KWS) is the task of recognizing spoken command words from a database. With recent application human-machine interactions, KWS systems require real-time performance, where edge computing is a preferable option. To allow KWS systems to work on fast and real-time implementation, a low-complexity yet high-accurate AI model is mandatory. In this paper, we propose a comprehensive voice command recognition system design and its hardware implementation. The proposed AI model considered in this system is SpectroNet-based and an efficient hybrid CNN-LSTM architecture with low complexity. Jetson Xavier NX is an edge device because of its strong computational power as an embedded device. The implementation result shows the proposed method offers quite good in terms of accuracy, indicated by no accuracy drop between the model implemented in PC and Jetson Xavier. However, the inference time is quite high, which is 180 ms/step. To improve the speed of the system, the TensorRT library is used to further optimize the model. Optimization of the model is found effective, reducing 59.35% of the total operation performed in SpectroNet when FP32 precision is used, and 59.63% when FP16 precision is used. The model is also sped up by 45% if FP32 precision mode is used and 62% if FP16 precision mode is used. However, there is a slight accuracy drop of 2.68% if FP32 precision mode is used and 4.84% if FP16 precision mode is used. This slight drop in accuracy is considered negligible compared to the performance boost that TensorRT gives. The work is useful for intelligent control systems such as smart vehicles, smartphones, computers, and smart communications.

show abstract

Section: A Abstractpotting Methodsmentioning

confidence: 99%

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Syafalni,

Amadeus,

Sutisna

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Identification of the problem found that the current home security system is still incomplete and does not provide a comfortable security system when leaving or occupying the house [15] [16].…”

Section: Methods Identify the Problemmentioning

confidence: 99%

“…The main point of this research is how to design a home door security product that consumers need according to their wishes using a QFD method [16] [17].…”

Section: Problem Statementmentioning

confidence: 99%

Design of Smart Locker Door Using Quality Function Deployment Based on ATMega 2560 Microcontroller

Filhaq,

Aprianto,

Alfianto

2023

JURIT

View full text Add to dashboard Cite

Smart Locker system to provide more security for the house that is a place to live to avoid losses and negative impacts of criminal case actions with incrimination. This study designed door security with a door bar control system that can be done from outside the house using Android and a keypad so that the bar behind the door automatically closes and opens according to the password code command entered by the user or homeowner. Consumer desires home security systems using the QFD (Quality Function Deployment) method. The QFD method will conclude that a better door security product design is needed, with home security system updates as needed. Consumers need thirteen dimensions with three priorities with the highest value, namely securing the door of the house with a shape that matches the door with a rating of 4.55, Securing the door of the house has an alarm system with a rating of 4.50, Securing the door of the house is easy to use for the owner. The intelligent locker design is based on ATMega 2560 Microcontroller, which functions to program other components so that they can work according to the data that has been inputted

show abstract

Digit-Number Speech-Recognition using Spectrogram-Based Convolutional Neural Network

Amadeus

Sutisna

Adiono

2022

2022 International Symposium on Electronics and Smart Devices (ISESD)

View full text Add to dashboard Cite

Anti-balance Load Control System Applied to an Overhead Crane Prototype Activated by Voice Commands

Cited by 3 publications

References 11 publications

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Design of Smart Locker Door Using Quality Function Deployment Based on ATMega 2560 Microcontroller

Digit-Number Speech-Recognition using Spectrogram-Based Convolutional Neural Network

Contact Info

Product

Resources

About