Search

This study provides a review of CNN's ensemble learning method for transfer learning by highlighting sections such as review studies, datasets, pre-trained models, transfer learning, ensemble learning, and performance. The results indicate that the trend of ensemble learning, transfer learning ensemble, and transfer learning is growing every year. In 2022, there will be 35 papers reviewed related to this topic in this study. Some datasets contain apparent information starting from the dataset name, total data points, dataset splitting, target dataset availability, and type classification. ResNet-50, VGG-16, InceptionV3, and VGG-19 are used in most papers as pre-trained models and transfer learning processes. 50 (90.1%) papers use ensemble learning, and 5 (9.1%) do without ensemble learning. The reviewed paper summarizes several performance measurements, including accuracy, precision, recall, f1-score, sensitivity, specificity, training accuracy, validation accuracy, test accuracy, training losses, validation losses, test losses, training time, and AUC, DSC. In the last section, 49 papers produce the best model performance using the proposed model, and 6 other papers use DenseNet, DeQueezeNet, Extended Yager Model, InceptionV3, and ResNet-152.

The convolutional neural network (CNN) is a technique that is often used in deep learning. Various models have been proposed and improved for learning on CNN. When learning with CNN, it is important to determine the optimal parameters. This paper proposes an optimization of CNN parameters using logarithm decreasing inertia weight (LogDIW). This paper is used two datasets, i.e., MNIST and CIFAR-10 dataset. The MNIST learning experiment, the CIFAR-10 dataset, compared its accuracy with the CNN standard based on the LeNet-5 architectural model. When using the MNIST dataset, CNN's baseline was 94.02% at the 5th epoch, compared to CNN's LogDIWPSO, which improves accuracy. When using the CIFAR-10 dataset, the CNN baseline was 28.07% at the 10th epoch, compared to the LogDIWPSO CNN accuracy of 69.3%, which increased the accuracy.

Copyright of Techno.com is the property of Universitas Dian Nuswantoro, Fakultas Ilmu Komputer and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Twitter is one of the social media that has the largest users in the world. Indonesia is one of the countries that has the 5th largest number of Twitter users in the world which causes a high possibility of conflict between Indonesian Twitter users due to emotional tension in tweets. In this paper, we will compare the BERT embedding method with CNN and LSTM. The results of this experiment are BERT-CNN has the best performance results which has an accuracy of 61% compared to BERT-LSTM. In the experiment several stages of data preprocessing, data cleaning, data spiting and data training were carried out and the results were evaluated using confusion metrics.

In this modern era, electrical energy plays a crucial role in human life, as it is essential for most household appliances. The number of appliances requiring electrical energy increases each year, meeting the growing needs of users. However, electricity consumers tend to forget this fact and only realize its importance when they receive a significantly increased monthly electricity bill or face problems caused by anomalies in electricity use. Such anomalies can lead to substantial losses, especially when electrical equipment is damaged or left switched on without awareness. To make better decisions in such situations, real-time and accurate information is necessary, which can be achieved through data analytics utilizing machine-learning and predictive analytics. The purpose of this paper is to introduce the CNN-LSTM method of data analytic modeling for power consumption data collected through an electric data logger, which can help predict future power usage and detect real-time anomalies in the power network. The proposed model was tested using hourly electricity consumption data, and the results showed that the CNNLSTM method outperformed the LSTM model. The CNN-LSTM model had a 29% smaller Mean Squared Error (MSE) score than the LSTM method.

In the digital era, preserving old documents to prevent damage is a significant challenge. One solution to this problem is to reconstruct damaged or lost documents using image processing and natural language processing technologies. This article discusses the design of a tool for correcting and reconstructing writing in old papers and documents that can be implemented on a mini PC. The tool uses state-of-the-art algorithms such as Convolutional Neural Network (CNN) for character recognition and Optical Character Recognition (OCR), as well as Image Inpainting and Sequence-to-Sequence (Seq2Seq) algorithms for document reconstruction. Test results show that this tool can recognize characters with high accuracy and reconstruct damaged or lost documents effectively.

Cacao pod's ideal harvesting time is when it is about to be ripe. Immature harvest would result in hard cacao beans not suitable for fermentation, while overripe cacao pods lead to fungal-infected, defective, and poor-quality yields. The demand for high-quality cacao products is expected to rise due to advancing technology in the present. Pre-harvesting needs to provide optimal identification of which amongst the pods are ripened enough and ready for the next stage of the cacao process. This paper recommends a technique to determine the ripeness of cacao. Nine hundred thirty-three cacao samples were used to collect thumping audio data at five different pod's exocarp locations. Each sound file is 1 second long, creating 4665 cacao sound file datasets at 16kHz sample rate and 16-bit audio bit depth. The process of the Mel-Frequency Cepstral Coefficient Spectogram was then applied to extract recognizable features for the training process. The deep learning method integrated was a convolutional neural network (CNN) to classify the cacao sound successfully. The experimental design model's output exhibits an accuracy of 97.50 % for the training data and 97.13 % for the validation data. While the overall accuracy mean of the classification system is 97.46 %, whether the cacao is unripe or ripe.

ABSTRAK Dalam tulisan ini, deteksi aktivitas suara disajikan pada smartphone secara realtime dengan jaringan saraf konvolusional. Pengurangan waktu komputasi adalah masalah dari studi sebelumnya. Meskipun telah menggunakan pendekatan machine learning, masih banyak kekurangan dari penelitian sebelumnya. Citra sinyal suara dihasikan oleh spektrogram energi log-mel, kemudian citra sinyal suara diinputkan ke dalam deep learning CNN untuk mengklasifikasi suara manusia dan derau. HiVAD mengungguli persentase metode VAD lainnya yaitu G729B, Sohn, dan RF dari hasil tes yang ditunjukkan dengan akurasi rata-rata SHR sebesar 15,89%, 28,98%, 42,13% pada tingkat 0dB, 8,67%, 16,29%, 17,63% pada tingkat 5 dB, dan 1,35%, 7,72%, 5,14% pada tingkat 10 dB. Selain itu, mekanisme Multi-threading memungkinkan komputasi yang efisien untuk waktu secara realtime. Penelitian ini menunjukkan bahwa arsitektur CNN pada HiVAD secara signifikan meningkatkan akurasi deteksi aktivitas suara. Kata kunci: aplikasi VAD, voice detection, deep learning, CNN ABSTRACT In this paper, the detection of sound activity is presented on smartphones in realtime with convolutional neural networks. Reduced computing time is a problem from previous studies. Despite the use of machine learning approaches, there are still many shortcomings from previous research. A log-mel energy spectrogram narrates the sound signal image. Then the sound signal image is inputted into CNN's deep learning to classify the human voice and noise. HiVAD outperformed the percentage of other VAD methods, namely G729B, Sohn, and RF from the test results shown with an average SHR accuracy of 15.89%, 28.98%, 42.13% at 0dB, 8.67%, 16.29% ,17.63% at 5 dB, and 1.35%, 7.72%, 5.14% at 10 dB. In addition, the Multi-threading mechanism enables efficient computing for real-time. This study shows that CNN's architecture on HiVAD significantly improves the accuracy of sound activity detection. Keywords: VAD App, voice detection, deep learning, CNN