A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning

Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F1-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance.

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.

Approach for Multi-Label Text Data Class Verification and Adjustment Based on Self-Organizing Map and Latent Semantic Analysis

In this paper, a new approach has been proposed for multi-label text data class verification and adjustment. The approach helps to make semi-automated revisions of class assignments to improve the quality of the data. The data quality significantly influences the accuracy of the created models, for example, in classification tasks. It can also be useful for other data analysis tasks. The proposed approach is based on the combination of the usage of the text similarity measure and two methods: latent semantic analysis and self-organizing map. First, the text data must be pre-processed by selecting various filters to clean the data from unnecessary and irrelevant information. Latent semantic analysis has been selected to reduce the vectors dimensionality of the obtained vectors that correspond to each text from the analysed data. The cosine similarity distance has been used to determine which of the multi-label text data class should be changed or adjusted. The self-organizing map has been selected as the key method to detect similarity between text data and make decisions for a new class assignment. The experimental investigation has been performed using the newly collected multi-label text data. Financial news data in the Lithuanian language have been collected from four public websites and classified by experts into ten classes manually. Various parameters of the methods have been analysed, and the influence on the final results has been estimated. The final results are validated by experts. The research proved that the proposed approach could be helpful to verify and adjust multi-label text data classes. 82% of the correct assignments are obtained when the data dimensionality is reduced to 40 using the latent semantic analysis, and the self-organizing map size is reduced from 40 to 5 by step 5.

New Aspects and an Artificial Intelligence Approach for the Detection of Cervical Abnormalities

The COVID-19 pandemic has challenged health systems worldwide by decreasing their reserves and effectiveness. In this changing landscape, the urge for reallocation of financial and human resources represents a top priority. In screening, effectiveness and efficiency are most relevant. In the quest against cervical cancer, numerous molecular ancillary techniques detecting HPV DNA or mRNA or other related biomarkers complement morphological assessment by the Papanicolaou test. However, no technique is perfect as sensitivity increases at the cost of specificity. Various approaches try to resolve this issue by incorporating several examination results, such as artificial intelligence are proposed. In this study, 1,258 cases with a complete result dataset for cytology, HPV DNA, HPV mRNA, and p16 were used to evaluate the performance of a self-organizing map (SOM), an unsupervised artificial neural network. The results of the SOM application were encouraging since it is capable of producing maps discriminating the necessary tests and has improved performance.

Information Extraction from Agricultural and Weather Domain using Deep Learning Approach

India is an agricultural region and the economy of the country depends upon agriculture. Change in climatic parameters (like rainfall, soil, etc) directly affect the growth of crops. This parameter has an unswerving effect on the quantity of food production. Information extraction from the agricultural domain through rainfall prediction has been one of the most challenging issues around the world in recent years because of climatic changes. To evaluate the feasibility of rain by employing some data analytics and machine learning techniques are developed. This paper proposes an enhanced deep learning-based approach known as Deep Regression Network (DRN). The proposed DRN is a 6-layer deep neural network. The proposed algorithm trains and tests on the agricultural corpus, collected from Dehradun (India) region. The experimental outcomes state that the proposed DRN method attained a prediction accuracy approx 86.56%. The comparative analysis shows that the proposed method outperformed existing methods like Ensemble Neural Network, Naïve Bayes, KNN, and Weighted Self-Organizing Map.

Implementasi Self Organizing Map dalam Pengelompokkan Kabupaten di Jawa Barat Berdasarkan Kasus Covid-19

Covid-19 adalah penyakit menular yang disebabkan oleh jenis coronavirus. Penyakit menular baru yang disebabkan oleh sindrom pernafasan akut yang parah corona virus 2 (SARS-CoV-2), menyebar pesat ke beberapa negara di seluruh dunia termasuk negara Indonesia. Provinsi Jawa Barat merupakan salah satu provinsi sebagai penyumbang terbesar kasus covid-19 di Indonesia. Penelitian ini bertujuan untuk mengelompokkan wilayah kabupaten/kota di Provinsi Jawa Barat menurut perkembangan kasus covid-19. Metode yang digunakan dalam proses pengelompokan ini adalah metode Self Organizing Map (SOM). SOM merupakan perangkat visualisasi dan analisis untuk data berdimensi tinggi dan dalam pengelompokannya tidak diperlukan uji asumsi. Data sekunder yang digunakan pada penelitian ini adalah 5 variabel pada 27 kabupaten/kota di Provinsi Jawa Barat dari tanggal 1 Agustus 2020 sampai dengan 22 Juni 2021 yang bersumber dari Pusat Informasi dan Koordinasi Covid-19 Provinsi Jawa Barat. Berdasarkan hasil analisis menggunakan SOM diperoleh sebanyak dua cluster yang masing-masing memiliki karakteristik yang berbeda-beda untuk mengelompokkan 27 kabupaten/kota di Provinsi Jawa Barat. Cluster yang terbentuk meliputi cluster 1 yang terdiri dari 2 kota yaitu kota Depok dan kota Bekasi memiliki tingkat kasus covid-19 yang tertinggi, sedangkan Cluster 2 terdiri dari 25 kabupaten/kota di Jawa Barat dengan tingkat kasus covid-19 terendah.