• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.900-901
• /
• 2023

본 연구는 TFLite 기반의 경량화 AI 모델을 활용하여 쓰레기의 자동 분리수거 시스템을 구축하는 방법을 제안한다. 제안된 시스템은 객체 인식 기술을 활용해 쓰레기를 정확하게 분류하며, 테스트 결과 평균 90.33%의 mAP 성능을 나타낸다. Label 수와 데이터셋의 한계가 존재하지만, 본 연구를 확장하고 개선함으로써 자동 분리수거의 효율성을 더욱 높일 수 있을 것으로 기대된다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.179-186
• /
• 2023

For the future prosperity of any society, the sound growth of children is essential. Autism Spectrum Disorder (ASD) is a neurobehavioral disorder which has an impact on social interaction of autistic child and has an undesirable effect on his learning, speaking, and responding skills. These children have over or under sensitivity issues of touching, smelling, and hearing. Its symptoms usually appear in the child of 4- to 11-year-old but parents did not pay attention to it and could not detect it at early stages. The process to diagnose in recent time is clinical sessions that are very time consuming and expensive. To complement the conventional method, machine learning techniques are being used. In this way, it improves the required time and precision for diagnosis. We have applied TFLite model on image based dataset to predict the autism based on facial features of child. Afterwards, various machine learning techniques were trained that includes Logistic Regression, KNN, Gaussian Naïve Bayes, Random Forest and Multi-Layer Perceptron using Autism Spectrum Quotient (AQ) dataset to improve the accuracy of the ASD detection. On image based dataset, TFLite model shows 80% accuracy and based on AQ dataset, we have achieved 100% accuracy from Logistic Regression and MLP models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.93-98
• /
• 2021

Due to the development of deep learning and AI, the scale of the model has grown, and it has been integrated into other fields to blend into our lives. However, in environments with limited resources such as embedded devices, it is exist difficult to apply the model and problems such as power shortages. To solve this, lightweight methods such as clouding or offloading technologies, reducing the number of parameters in the model, or optimising calculations are proposed. In this paper, quantization of learned models is applied to ONNX models used in various framework interchange formats, neural network structure and inference performance are compared with existing models, and various module methods for quantization are analyzed. Experiments show that the size of weight parameter is compressed and the inference time is more optimized than before compared to the original model.