Emotion Recognition Robust to Indoor Environmental Distortions and Non-targeted Emotions Using Out-of-distribution Detection

The rapid development of machine learning on acoustic signal processing has resulted in many solutions for detecting emotions from speech. Early works were developed for clean and acted speech and for a fixed set of emotions. Importantly, the datasets and solutions assumed that a person only exhibited one of these emotions. More recent work has continually been adding realism to emotion detection by considering issues such as reverberation, de-amplification, and background noise, but often considering one dataset at a time, and also assuming all emotions are accounted for in the model. We significantly improve realistic considerations for emotion detection by (i) more comprehensively assessing different situations by combining the five common publicly available datasets as one and enhancing the new dataset with data augmentation that considers reverberation and de-amplification, (ii) incorporating 11 typical home noises into the acoustics, and (iii) considering that in real situations a person may be exhibiting many emotions that are not currently of interest and they should not have to fit into a pre-fixed category nor be improperly labeled. Our novel solution combines CNN with out-of-data distribution detection. Our solution increases the situations where emotions can be effectively detected and outperforms a state-of-the-art baseline.

Perilaku Petani Terhadap Adopsi Teknologi M-Bio untuk Pengembangan Usahatani Agroforestri

This study aims to determine the behavior of farmers in adopting M-Bio technology for the development of agroforestry farming. The research method is a survey with data collection techniques: observation and in-depth interviews with respondents. Research variables include farmer behavior towards the implementation of counseling and training as well as farmer behavior towards the adoption of M-Bio Technology. The research was conducted in Setiawaras Village in the Cipigan Insan Mandiri and Dadap Sari farmer groups from July to October 2020. The data analysis used was descriptive analysis with a Likert scale with scores of 1, 2, 3, 4, and 5 then measured by weighted values. The data distribution was converted into a ratio scale with a score between 0–100. Furthermore, the scores are grouped into: (1) Very Low: 0–20; (2) Low: 21 - 40; (3) Moderate: 41–60; (4) Height: 61–80; and (5) Very High: 81-100. The results showed that the behavior of farmers towards the implementation of counseling and training on M-Bio technology with all its indicators (presentation and practice, attention, comprehensiveness, results and retention) had a score between 80 - 100 so all of them were categorized as very high. Likewise, the behavior of farmers towards the adoption of M-Bio technology for the development of agroforestry farming along with all its indicators concerning cognitive, apective, and conative aspects has a score between 80 - 100 so that all of them are also categorized as very high. Abstrak Penelitian bertujuan untuk mengetahui perilaku petani dalam adopsi teknologi M-Bio untuk pengembangan usahatani agroforestri. Metode penelitian adalah survey dengan teknik pengumpulan data : observasi dan wawancara mendalam dengan responden. Varibel penelitian mencakup perilaku petani terhadap pelaksanaan penyuluhan dan pelatihan serta perilaku petani terhadap adopsi Teknologi M-Bio. Penelitian dilaksanakan di Desa Setiawaras pada kelompok tani Cipigan Insan Mandiri dan Dadap Sari dari bulan Juli sampai Oktober 2020. Analisis data yang digunakan adalah analisis deskriptif dengan skala likert skor 1, 2, 3, 4, dan 5 kemudian diukur dengan nilai tertimbang. Sebaran data diubah menjadi skala rasio dengan skor antara 0–100. Selanjutnya, skor dikelompokkan menjadi : (1) Sangat Rendah:0–20; (2) Rendah:21 – 40; (3) Sedang:41–60; (4) Tinggi:61–80; dan (5) Sangat Tinggi: 81-100. Hasil penelitian menunjukkan bahwa perilaku petani terhadap pelaksanaan penyuluhan dan pelatihan teknologi M-Bio dengan seluruh indikatornya (presentasi dan praktek, atensi, komprehensif, hasil dan retensi) memiliki skor antara 80 – 100 sehingga semuanya terkategori sangat tinggi. Demikian juga dengan perilaku petani terhadap adopsi teknologi M-Bio untuk pengembangan usahatani agroforestri beserta seluruh indikatornya yang menyangkut aspek kognitif, apektif, dan konatif memiliki skor antara 80 – 100 sehingga semuanya juga terkategori sangat tinggi.

Pruning Growing Self-Organizing Map Network for Human Physical Activity Identification

Human physical activity identification based on wearable sensors is of great significance to human health analysis. A large number of machine learning models have been applied to human physical activity identification and achieved remarkable results. However, most human physical activity identification models can only be trained based on labeled data, and it is difficult to obtain enough labeled data, which leads to weak generalization ability of the model. A Pruning Growing SOM model is proposed in this paper to address the limitations of small-scale labeled dataset, which is unsupervised in the training stage, and then only a small amount of labeled data is used for labeling neurons to reduce dependency on labeled data. In training stage, the inactive neurons in network can be deleted by pruning mechanism, which makes the model more consistent with the data distribution and improves the identification accuracy even on unbalanced dataset, especially for the action categories with poor identification effect. In addition, the pruning mechanism can also speed up the inference of the model by controlling its scale.

Garbage Classification Using Ensemble DenseNet169

Garbage is a big problem for the sustainability of the environment, economy, and society, where the demand for waste increases along with the growth of society and its needs. Where in 2019 Indonesia was able to produce 66-67 million tons of waste, which is an increase from the previous year of 2 to 3 million tons of waste. Waste management efforts have been carried out by the government, including by making waste sorting regulations. This sorting is known as 3R (reduce, reuse, recycle), but most people do not sort their waste properly. In this study, a model was developed that can sort out 6 types of waste including: cardboard, glass, metal, paper, plastic, trash. The model was built using the transfer learning method with a pretrained model DenseNet169. Where the optimal results are shown for the classes that have been oversampling previously with an accuracy of 91%, an increase of 1% compared to the model that has an unbalanced data distribution. The next model optimization is done by applying the ensemble method to the four models that have been oversampled on the training dataset with the same architecture. This method shows an increase of 3% to 5% while the final accuracy on the test of dataset is 96%.

Facilitative Parenting of Adolescent Self Disclosure

This study aims to find out empirically whether there is a relationship between facilitative parenting and adolescent self-disclosure. The hypothesis used is that there is a positive relationship between facilitative parenting and adolescent self-disclosure. Where the higher the level of concern, the higher the level of self-disclosure of adolescents when they are high and concern is low, the lower the self-disclosure of adolescents. The research subjects were students living with their parents, female and male and aged 15-18 years. The number of research subjects was 82 people, consisting of 35 women and 27 men. The adolescent self-disclosure scale that based on the theory of Buhrmester & Prager in Bauminger (2008). Parenting scale based on theory and Grolnick (2009). Method of data analysis using product moment correlation technique. The results of the analysis have a normal data distribution with a linear correlation. While the correlation coefficient between maternal parenting and adolescent self-disclosure to mothers is 0.494 and p = 0.000 (p <0.05) with an effective contribution of 0.244. While the father's self-disclosure analysis obtained the results of 0.727 and p = 0.000 (p <0.05) with an effective contribution of 0.529

A Deep Transfer NOx Emission Inversion Model of Diesel Vehicles with Multisource External Influence

By installing on-board diagnostics (OBD) on tested vehicles, the after-treatment exhaust emissions can be monitored in real time to construct driving cycle-based emission models, which can provide data support for the construction of dynamic emission inventories of mobile source emission. However, in actual vehicle emission detection systems, due to the equipment installation costs and differences in vehicle driving conditions, engine operating conditions, and driving behavior patterns, it is impossible to ensure that the emission monitoring data of different vehicles always follow the same distribution. The traditional machine learning emission model usually assumes that the training set and test set of emission test data are derived from the same data distribution, and a unified emission model is used for estimation of different types of vehicles, ignoring the difference in monitoring data distribution. In this study, we attempt to build a diesel vehicle NOx emission prediction model based on the deep transfer learning framework with a few emission monitoring data. The proposed model firstly uses Spearman correlation analysis and Lasso feature selection to accomplish the selection of factors with high correlation with NOx emission from multiple sources of external factors. Then, the stacked sparse AutoEncoder is used to map different vehicle working condition emission data into the same feature space, and then, the distribution alignment of different vehicle working condition emission data features is achieved by minimizing maximum mean discrepancy (MMD) in the feature space. Finally, we validated the proposed method with the diesel vehicle OBD data that were collected by the Hefei Environmental Protection Bureau. The comprehensive experiment results show that our method can achieve the feature distribution alignment of emission data under different vehicle working conditions and improve the prediction performance of the NOx inversion model given a little amount of NOx emission monitoring data.

VDPC: Variational Density Peak Clustering Algorithm

<div>Clustering is an important unsupervised knowledge acquisition method, which divides the unlabeled data into different groups \cite{atilgan2021efficient,d2021automatic}. Different clustering algorithms make different assumptions on the cluster formation, thus, most clustering algorithms are able to well handle at least one particular type of data distribution but may not well handle the other types of distributions. For example, K-means identifies convex clusters well \cite{bai2017fast}, and DBSCAN is able to find clusters with similar densities \cite{DBSCAN}. </div><div>Therefore, most clustering methods may not work well on data distribution patterns that are different from the assumptions being made and on a mixture of different distribution patterns. Taking DBSCAN as an example, it is sensitive to the loosely connected points between dense natural clusters as illustrated in Figure~\ref{figconnect}. The density of the connected points shown in Figure~\ref{figconnect} is different from the natural clusters on both ends, however, DBSCAN with fixed global parameter values may wrongly assign these connected points and consider all the data points in Figure~\ref{figconnect} as one big cluster.</div>