Automatic Clustering of Students by Level of Situational Interest Based on Their EEG Features

The usage of physiological measures in detecting student’s interest is often said to improve the weakness of psychological measures by decreasing the susceptibility of subjective bias. The existing methods, especially EEG-based, use classification, which needs a predefined class and complex computational to analyze. However, the predefined classes are mostly based on subjective measurement (e.g., questionnaires). This work proposed a new scheme to automatically cluster the students by the level of situational interest (SI) during learning-based lessons on their electroencephalography (EEG) features. The formed clusters are then used as ground truth for classification purposes. A simultaneous recording of EEG was performed on 30 students while attending a lecture in a real classroom. The frontal mean delta and alpha power as well as the frontal alpha asymmetry metric served as the input for k-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithms. Using the collected data, 29 models were trained within nine domain classifiers, then the classifiers with the highest performance were selected. We validated all the models through 10-fold cross-validation. The high SI group was clustered to students having lower frontal mean delta and alpha power together with negative Frontal Alpha Asymmetry (FAA). It was found that k-means performed better by giving the maximum performance assessment parameters of 100% in clustering the students into three groups: high SI, medium SI and low SI. The findings show that the DBSCAN had reduced the performance to cluster dataset without the outlier. The findings of this study give a promising option to cluster the students by their SI level, as well as address the drawbacks of the existing methods, which use subjective measures.

Business Circle Identification and Spatiotemporal Characteristics in the Main Urban Area of Yiwu City Based on POI and Night-Time Light Data

The activity of the urban night-time economy is one of the most important indicators reflecting the prosperity of an urban economy. The business circle is an important carrier of urban commercial activities and the core area of urban nightlife. This paper takes the main urban area of Yiwu city as the research object. Based on POI data and night-time light remote sensing data, two-factor mapping, kernel density analysis, DBSCAN clustering, and local contour tree methods are adopted to identify the business circle structure of the main urban area of Yiwu city and analyse the relationship between business circle characteristics and the night-time economy. The following conclusions can be drawn. (1) The spatial superimposition relationship between the night-time remote sensing data and points of interest (POI) data in the main urban area of Yiwu city is good, and the overall coupling results show obvious circle structure characteristics. (2) The spatial distribution of different business combinations has obvious regularity: comprehensive shopping business shows a multicentre distribution pattern and has a hierarchical feature. In contrast, professional food and beverage and leisure and entertainment businesses are close to urban residential areas, and different groups of people live in different places with their own characteristics. (3) From 2015 to 2019, the brightness value of each business circle showed a continuously increasing trend. In 2020, due to the impact of COVID-19, most of them declined. (4) Overall, the difference in business circle tiers reflects the difference in the level of night-time economic activities.

Enabling Automatic Detection of Anomalies in Wastewater: A Highly Simplified Approach to Defining “Normal” in Complex Chemical Mixtures

Wastewater treatment demands management of influent conditions to stabilize biological processes. Generally wastewater collection systems lack advance warning of approaching water parcels with anomalous characteristics, which could then be diverted for testing or pre-treatment. A major challenge in achieving this goal is identifying anomalies against the complex chemical background of wastewaters. This work evaluates unsupervised clustering methods to characterize “normal” wastewater characteristics, using >17 months of 10-min resolution absorbance spectrometry data collected at an operating wastewater treatment facility. Comparison of results using K-means, GMM, Hierarchical, and DBSCAN clustering shows minimal intra-cluster variability achieved using K-means. The four K-means clusters include three representing 99% of samples, with the remaining cluster (<0.3% of samples) representing atypical measurements, demonstrating utility in identifying both underlying modalities of wastewater characteristics and outliers. K-means clustering provides a better separation than grouping based on factors such as month, precipitation, or flow (with 25% overlap at 1-σ level, compared to 93, 93, and 83%, respectively) and enables identification of patterns that are not visible in factor-driven grouping, e.g., shows that summer and November months have a characteristic type of behavior. When evaluated with respect to wastewater influent changes occurring during the SARS-CoV-2 pandemic, the K-means approach shows a distinct change in strength of diurnal patterns when compared to non-pandemic periods during the same season. This method may therefore be useful both as a tool for fast anomaly detection in wastewaters, contributing to improved infrastructure resilience, as well for providing overall analysis of temporal patterns in wastewater characteristics.

Analisa Performa K-Means dan DBSCAN dalam Clustering Minat Penggunaan Transportasi Umum

Public transportation is one of the important modes of transportation and is the backbone of transportation in Indonesia. The development of public transportation is also supported by the government, this government support is evident in the national policy, namely the National Medium Term Development Plan (RPJMN). Although public transportation is an effective mode of transportation, it also has obstacles in its development, namely how to meet customer desires in choosing a mode of transportation. There are several variables that are the focus of this research, namely age, gender, income, cost, speed, comfort, safety, efficiency and flexibility. The search for influential variables will use the K-Means and DBSCAN clustering algorithms, these two algorithms are also compared to their performance to find a better algorithm. The results of the Silhouette Coefficient show that DBSCAN has a better performance with a value of 0.99 than K-Means with a value of 0.86. The variables that affect the interest in using public transportation are the most important ones related to cost, speed, comfort, safety, efficiency and flexibility.

IOT MODEL WITH MULTIMODAL NODE ALLOCATION AND THE METHOD OF USING MOBILE HEAD NODES FOR DATA COLLECTION

Рассмотрена задача организации движения головных узлов (ГУ) в сети интернета вещей (ИВ) при неоднородном (мультимодальном) распределении узлов в зоне обслуживания. Предложен метод кластеризации неоднородной сети, позволяющий выделить кластеры (отличающиеся плотностью узлов) и выбирать скорость движения ГУ в соответствии с плотностью в каждом кластере. Метод основан на использовании алгоритма кластеризации DBSCAN, позволяет повысить эффективность использования подвижных ГУ и может быть применен при организации сбора данных в сети ИВ. The paper is devoted to the problem of organizing the movement of head nodes in the Internet of Things (IoT) network with a heterogeneous (multimodal) distribution of nodes in the service area. A method for clustering a heterogeneous network is proposed, which makes it possible to distinguish clusters that differ in the density of nodes and select the speed of movement of the head node in accordance with the density in each cluster. The proposed method is based on the use of the DBSCAN clustering algorithm and makes it possible to increase the efficiency of the use of mobile head nodes. The method can be applied in organizing data collection in the IoT network.

Combining Daily Electricity Forecasts Based on DBSCAN and stacking Fusion

Background: Modern upgrades of power grids and a rapidly expanding economy complexify the uncertainties of electricity demand. Objective: The objective of the study is to have a more precise prediction on the demand side, which is beneficial in affirming the stable operation of the power system. Methods: This paper presents a combined electricity forecasting method based on the users clustering and stacking ensemble learning to mine underlying properties of different individual consumers. The preprocessed electricity consumption profiles are inputted into the DBSCAN clustering algorithm to obtain the clusters. The alternative models are tailored for different clusters in the stacking fusion framework for training and testing. Result: Experimental results on the operating data of Shandong Power Grid show that the proposed method has higher prediction accuracy and better generalization ability. Conclusion: The framework is of great significance for improving the level of power supply service.

A Quantification Method for Supraharmonic Emissions Based on Outlier Detection Algorithms

Based on outlier detection algorithms, a feasible quantification method for supraharmonic emission signals is presented. It is designed to tackle the requirements of high-resolution and low data volume simultaneously in the frequency domain. The proposed method was developed from the skewed distribution data model and the self-tuning parameters of density-based spatial clustering of applications with noise (DBSCAN) algorithm. Specifically, the data distribution of the supraharmonic band was analyzed first by the Jarque–Bera test. The threshold was determined based on the distribution model to filter out noise. Subsequently, the DBSCAN clustering algorithm parameters were adjusted automatically, according to the k-dist curve slope variation and the dichotomy parameter seeking algorithm, followed by the clustering. The supraharmonic emission points were analyzed as outliers. Finally, simulated and experimental data were applied to verify the effectiveness of the proposed method. On the basis of the detection results, a spectrum with the same resolution as the original spectrum was obtained. The amount of data declined by more than three orders of magnitude compared to the original spectrum. The presented method will benefit the analysis of quantification for the amplitude and frequency of supraharmonic emissions.