Euclidean Distance Formula Research Articles

Solar Energy Forecasting in Short Term Based on the ASO-BPNN Model

Accurate forecasting of short-term photovoltaic power output is vital for enhancing the operation efficiency of photovoltaic (PV) power stations and ensuring the safety and stable operation of grid-connected PV plants. Therefore, a short-term power forecasting model based on a backpropagation neural network with atom search optimization optimizes the weights and thresholds. Meanwhile, the Pearson correlation coefficient formula is introduced to screen the key meteorological factors and eliminate redundant factors, i.e., total irradiance, temperature, humidity, and direct irradiance are taken as the input of the prediction model. Moreover, the Euclidean distance formula is used to establish a customized training set for each test data which improves the dependability of the training set. Lastly, with the simulations of actual data from a solar farm in Yunnan, China, it is verified that the proposed ASO-BPNN model is competent to forecast the PV power generation.

Implementation of Facial Landmarks Detection Method for Face Follower Mobile Robot

This paper presents a new technique for facesrecognition based on auto-extracted facial marks. Our landmarks are those related to the outer corner of the nose. With extracted landmarks, a triplet of areas and their associated geometric invariance are formed. Where later the points on the outer corners of the eyes and nose will be connected with lines that will form a triangle. Later the line length will be calculated using the Euclidean Distance formula so that the area value of the triangle can be obtained. Then the data obtained will be trained using the Support Vector Machine algorithm so that they can recognize faces. And later the system will be implanted into a mobile robot with raspberry.

Virtual interaction algorithm of cultural heritage based on multi feature fusion

During the traditional cultural heritage virtual interaction algorithm in the interaction action recognition, the database is too single, resulting in low recognition accuracy, recognition time-consumer and other issues. Therefore, this paper introduces the multi feature fusion method to optimize the cultural heritage virtual interaction algorithm. Kinect bone tracking technology is applied to identify the movement of the tracking object, 20 joints of the human body are tracked, and interactive action recognition is realized according to the fingertip candidate points. In order to carry out the judgment virtual interactive operation of subsequent recognition actions, a multi feature fusion database is established. The mean shift is used to derive the moving mean of the target’s action position and to track the interactive object. The Euclidean distance formula is used to train samples of multi feature fusion database data to realize the judgment of recognition action and virtual interaction. In order to verify the feasibility of the research algorithm, the virtual interactive script of ink painting in a cultural heritage museum is used to simulate the research algorithm, and a comparative experiment is designed. The experimental results show that the proposed algorithm is superior to the traditional virtual interactive algorithm in recognition accuracy and efficiency, which proves the feasibility of this method.

Indoor Localization System Based on Mobile Access Point Model MAPM Using RSS With UWB-OFDM

Indoor tracking is one of the most attractive topics in communication and information technology. Indoor localization mechanisms can help people for navigating in complex environments. Those with complex structures such as airports, shopping malls, hospitals, and others have a massive population (Crowdsourcing) that blocks the visibility (NLOS) between the access points and the users. Accordingly, we present the mobile access point model MAPM as a new algorithm for positioning users indoors based on the mathematical model of received signal strength RSS using UWB-OFDM. MAPM participates in crowdsourcing indoors by using users as mobile access points (MAP). That may decrease the use of several static access points (SAP) indoors and increase the localization precision. First, we use ultra-wideband UWB with orthogonal frequency division multiplexing OFDM as a communication gadget between the users and the system. Those have good quality in terms of accuracy, time response, energy consumption, and efficiency against interference. Second, we measure the received signal strength then, we estimate the distance between users and the access points using the mathematical model of RSS. These can be more adapted to changing environments and device heterogeneity than RSSI fingerprints. Third, we calculate the position information by using the Euclidean distance formula. In this way, we can reduce the effect of most of the problems on the indoor positioning system. We simulate the proposed algorithm in a platform based on three tools, MATLAB for system information processing, MYSQL as a system database, and a control interface coded in Java. In the given simulation results, we find that the average MAPM error in the case of 30 users is 10.19 cm, and the detection rate has a value of 86.66%.

Regional‐based multi‐module spatial–temporal networks predicting city‐wide taxi pickup/dropoff demand from origin to destination

AbstractTaxi demand forecasting from origin to destination (OD) is an important component in managing public transportation needs on a city‐wide scale. Accurate taxi demand forecasting may provide several benefits, including economic and traffic flow optimization. However, due to complicated spatial–temporal connections and irregular distant locations, predicting taxi demand becomes difficult. To address these issues, we proposed a novel architecture of multi‐module spatial–temporal networks to collectively predict city‐wide OD taxi demand. In our work to deal with adjacent areas in a city, we employed the 3D convolutional neural networks to extract the spatial–temporal dependencies and learn the OD taxi demand pattern. To handle remote areas, we created an attention‐based auto encoder‐decoder, in which the input of the set of convolutional layers creates a feature matrix. The feature matrix embeds the spatial–temporal correlation jointly and passing through the encoder layer. We encode the spatial–temporal features with the help of pooling layer, then flatten layer used the back‐propagation method to decode the weight matrix. We apply the normalization function to determine the demand pattern influences. The influence vector we compute with the Euclidean distance formula to determine the similarity of all distant regions. Finally, we use the attention mechanism to calculate the attention weight score for each region that its neighbour impacted. Then we used long short‐term memory, we captured the significant relationship of spatial–temporal dependencies with external factors. We train our model simultaneously to forecast city‐wide taxi services OD. We have performed comprehensive experiments and large‐scale dataset comparisons that reveal the taxi demand prediction problem.

Accurate Segmentation for Low Resolution Satellite images by Discriminative Generative Adversarial Network for Identifying Agriculture Fields

Agricultural field identification is still a difficult issue because of the poor resolution of satellite imagery. Monitoring remote harvest and determining the condition of farmlands rely on the digital approach agricultural applications. Therefore, high-resolution photographs have obtained much more attention since they are more efficient in detecting land cover components. In contrast, because of low-resolution repositories of past satellite images used for time series analysis, wavelet decomposition filter-based analysis, free availability, and economic concerns, low-resolution images are still essential. Using low-resolution Synthetic Aperture Radar (SAR) satellite photos, this study proposes a GAN strategy for locating agricultural regions and determining the crop's cultivation state, linked to the initial or harvesting time. An object detector is used in the preprocessing step of training, followed by a transformation technique for extracting feature information and then the GAN strategy for classifying the crop segmented picture. After testing, the suggested algorithm is applied to the database's SAR images, which are further processed and categorized based on the training results. Using this information, the density between the crops is calculated. After zooming in on SAR photos, the crop condition may be categorized based on crop density and crop distance. The Euclidean distance formula is used to calculate the distance. Finally, the findings are compared to other existing approaches to determine the proposed technique's performance using reliable measures.

Simulasi dalam Optimalisasi Pengadaan Barang menggunakan Metode K-Mean Clustering

Products provided by a store have an influence on store sales. Consumers will be attracted to stores that provide products according to their wants and needs. The purpose of this research is to find out what ornamental flower products are most in demand by consumers, in demand by consumers and less desirable to consumers. Keywords: inventory of goods, K-Mean Clustering, Data Mining, cluster, optimal. Store managers can get information about goods that have been depleted of inventory stock to be updated immediately. The method used in this study is the K-Mean Clustering method which belongs to one of the branches of Data Mining. The data used in the study is data from January 2020 to December 2020 as many as 100 pieces taken from naafilah official shop, Padang. The data variables used in the entry of goods are the year, product name, price and amount sold. Furthermore, the data is processed using Rapid Miner software. The first stage of processing is to determine the value of clusters randomly, in this study researchers divided the cluster values into 3 groups. Next, the centroid value of each group will be determined. Centroid is derived from the minimum value, middle value and maximum value of the data provided. Then, the cluster process is calculated using the euclidean distance formula. Cluster calculations are done by calculating the closest distance to the data. The final result of this study is to find out the best-selling, best-selling and less-selling ornamental flowers, so that sellers can optimize the provision of ornamental flowers for the future.

A screening method for decoloration of xenobiotic dyes by fungi

Wood degrading fungi are often screened for their ability to degrade xenobiotics such as dyes. Dye decoloration by these fungi on solid media could until now only be assessed qualitatively. We here describe a fast quantitative method to screen for dye decoloration on such media. Decoloration of crystal violet (CV), malachite green (MG), orange G (OG), rose bengal (RB) and remazol brilliant blue R (RBBR) by 124 isolates of the basidiomycete Schizophyllum commune was quantified with a flatbed scanner and the CIE-L*a*b* model. Colour and intensity changes were calculated with the Euclidean distance formula. More than 10 strains showed high MG decoloration. Isolates 136, 140 and 213 showed superior CV decoloration, while OG was most effectively decolorized by isolates 183, 216 and 227. Six strains showed high RB decoloration with isolate 216 being superior. The latter strain was also highly active on RBBR together with isolates 177 and 227. Together, dye decoloration was highly variable between the 124 isolates but strain 216 showed high activity on 3 out of 5 dyes. The fast screening method described in this paper enables identification of strains effectively decolorizing dyes.

Classification of skin cancer images by applying simple evolving connectionist system

<span id="docs-internal-guid-eea5616b-7fff-5d26-eeb4-1d8c084ec93d"><span>Simple evolving connectionist system (SECoS) is one of data mining classification techniques that recognizing data based on the tested and the training data binding. Data recognition is achieved by aligning testing data to trained data pattern. SECoS uses a feedforward neural network but its hidden layer evolves so that each input layer does not perform epoch. SECoS distance has been modified with the normalized Euclidean distance formula to reduce error in training. This paper recognizes skin cancer by classifying benign malignant skin moles images using SECoS based on parameter combinations. The skin cancer classification has learning rate 1 of 0.3, learning rate 2 of 0.3, sensitivity threshold of 0.5, error threshold of 0.1 and MAPE is 0.5184845 with developing hidden node of 23. Skin cancer recognition by applying modified SECoS algorithm is proven more acceptable. Compared to other methods, SECoS is more robust to error variations.</span></span>

Fast fully automatic detection, classification and 3D reconstruction of pulmonary nodules in CT images by local image feature analysis

This study develops a computer-aided diagnosis (CAD) system for automatic detection and classification of pulmonary nodules in lung computed tomography (CT) images, which can simultaneously detect and classify ground-glass opacity (GGO), part-solid, and solid nodules. From the morphological feature and local image features of pulmonary nodules, a total of ten features were selected for artificial neural network (ANN) training and testing, to ensure the system can detect and classify pulmonary nodules. Then, the cross-sectional area of each slice of pulmonary nodule was extracted. The response evaluation criteria in solid tumor (RECIST) value was obtained using the Euclidean distance formula, and the number of pixels of the maximum cross-sectional area was counted for area computation. The nodule volume and 3D reconstruction was obtained using the marching cube algorithm and Riemann integral formula. The sensitivity of system detection and classification were 93.13% and 92.70%, respectively. The proposed system can detect GGO, part-solid, and solid nodules, and takes only 0.1 s to process a single image. This study used the clay model imitating pulmonary nodule morphology as physical samples. Each physical sample underwent three CT. The average difference between the physical volume and the volume derived from this study was 0.37%. The detection and classification results of the system enhanced the clinical detection of missing nodules. 3D reconstruction and volume information of the nodules can give their volume doubling time and growth rate when the patient undergoes CT for the second time, thus enhancing the effect of diagnosis and treatment.

Health Evaluation Method of Supercapacitor Based on Data Mining

With the wide application of super capacitor energy storage system as energy storage device on urban rail trains, the problem of its safe operation has attracted great attention. In order to ensure the reliability of the supercapacitor energy storage system, it is necessary to evaluate its health effectively. In view of the fact that the existing model-based supercapacitor evaluation methods are difficult to establish a reasonable and accurate model and the parameter estimation is complex, a data-driven supercapacitor health evaluation method is proposed. In this method, based on the data of voltage, current, temperature and external characteristic parameters of charge and discharge of supercapacitor, the weighted Euclidean distance formula is introduced, the mixed weighted Euclidean distance is calculated, and the comprehensive evaluation index of supercapacitor health state is obtained. It can quickly and effectively evaluate the health status of supercapacitors.

Systematic Review of Methodologies for the Development of Embedded Systems

Embedded systems encompass software and hardware components developed in parallel. These systems have been the focus of interest for many scholars who emphasized development issues related to embedded systems. Moreover, they proposed different approaches for facilitating the development process. The aim of this work is to identify desirable characteristics of existing development methodologies, which provide a good foundation for development of new methodologies. For that purpose, systematic mapping methodology was applied to the area of embedded systems, resulting in a classification scheme, graphically represented by a multilayer conceptual network. Afterwards, the most significant clusters were identified, using the k-means algorithm and the squared Euclidean distance formula. Overall, the results provide guidelines for further research aiming to propose a holistic approach for the development of special case of embedded systems.

Assessment of Risk Levels of Mangrove Forest Due to Oil Spill in Muara Gembong, Bekasi Regency

Habitat risk assessment is critical to assess the state of an environment. This research was conducted with the aim to assessand map the risk value of Mangrove Forest due to the oil spill incident in the Muara Gembong Regency, Bekasi District, which previously polluted coastal areas, especially in the mangrove ecosystem. Risk assessment is carried out as an effort to mitigate disaster to have a better prevention strategy, especially in areas that have a higher risk. The method for assessing risk in the mangrove ecosystem in Muara Gembong uses Habitat Risk Assessment using the Euclidean Distance formula, which is divided into three risk classes: low, medium, high. The risk value in coastal areas prone to oil spills has a moderate risk value with a total area of 3.7 km2 because the mangrove ecosystem has good resilience, and low risk for the inner mangrove area of the coastal area has a low chance with an area of 2.85 km2. The risk value in the medium class is 1.02, and the risk value in the low rank is 0.11.

Study on accident propagation ability of chemical industry park based on mixture degree decomposition algorithm and accident propagation probability

AbstractIn order to better characterize the accident propagation mechanism in chemical industry park (CIP), a method combining mixed degree decomposition (MDD) algorithm with accident propagation probability is proposed to measure the accident propagation ability of nodes in the accident chain network of CIP in this paper. First, the accident chain network model of CIP is established by using complex network theory and the nodes in the network model are layered according to the accident propagation ability based on the MDD algorithm. Second, the accident propagation probability value of each node in the network is defined and calculated according to the characteristic factors of the node itself. Finally, the result of MDD algorithm is combined with the accident propagation probability value by using Euclidean distance formula, the nodes with strong accident propagation ability in the accident chain network of CIP are determined. The case analysis shows that the method has higher discrimination, can effectively measure the accident propagation ability of nodes in the accident chain network of CIP, and better identify the nodes with strong propagation ability.

Gaussian Kernel Fuzzy C-Means Algorithm for Service Resource Allocation

With respect to the cluster problem of the evaluation information of mass customers in service management, a cluster algorithm of new Gaussian kernel FCM (fuzzy C-means) is proposed based on the idea of FCM. First, the paper defines a Euclidean distance formula between two data points and makes them cluster adaptively based on the distance classification approach and nearest neighbors in deleting relative data. Second, the defects of the FCM algorithm are analyzed, and a solution algorithm is designed based on the dual goals of obtaining a short distance between whole classes and long distances between different classes. Finally, an example is given to illustrate the results compared with the existing FCM algorithm.

Economic stimulus for COVID-19 pandemic and its determinants: evidence from cross-country analysis

Countries around the world are announcing stimulus packages in response to the COVID 19 pandemic. This research attempts to measure the extent and progress of stimulus packages by proposing a multidimensional index that standardizes governments' economic responses and allows us to examine the differences in economic policies from country to country. We apply the Euclidean distance formula to develop the new index and then identify the determinants of the economic stimulation of COVID-19 through beta-regression. The results show that Chile, Switzerland, Croatia, Sweden and the Netherlands responded more strongly to the COVID-19 pandemic, while the remaining countries responded slightly to the pandemic. Empirical results also indicate that most countries increased COVID-19 economic support, although not significantly. Finally, the results of the beta regression show that the median age of the population, the number of hospitals, beds per capita, the number of total COVID-19 cases, GDP, health care expenditure and the index of the severity of the government's response is significantly related to the level of the countries' stimulus packages.

Tourism Destination Grouping Systems With Partitioning Clustering Method from Geotagged Photo using Android

This application is focused on grouping photos that have information about the location of the photo. To get the location of the nearest tourism destination is by taking the location coordinate value from the uploaded photo then grouping it with a maximum distance of 1 kilometer. The main location for data collection is in Gunung Kidul Regency. This application uses Android for its development. For data processing and transforming scripts into the JSON file uses PHP and for storing the data uses MySQL.The metadata of the photo contains detail information about the photo. In the application shown the few information of its metadata such as the date and time took, image size and resolution, camera maker and model, also coordinate latitude and longitude. The location and metadata values will be shown in the application and stored in the database. Partitioning Clustering method used to find the nearest place within the 1 km radius. First of all by taking the coordinates value from an uploaded photo and stored to a database. The coordinate must be converted from Degree Minute Second Format into Latitude and Longitude Coordinate. After that, the calculation process starting with uses the Euclidean Distance formula to get the nearest distance of the attractions. To display the nearest location, sorting the result values from a minimum value to the maximum value as the final result. The application could be a reference for tourists who will visit Gunung Kidul Regency.

Customer segmentation for churn management by using ant colony algorithm

It is extremely important for companies to set customer priorities and act in line with these priorities. The ant colony algorithm is used to perform customer segmentation. To do this, the shortest path approach was chosen. Besides, clustering is done by the Euclidean distance formula in the ant colony algorithm. The customer segmentation attributes are mostly related to the satisfaction factors, but some of them were eliminated by using ranker. These results are mostly related to the customer’s income, tenure, equip call card and reside. These attributes are the most important satisfaction factors not to lose customers as expected. There are many reasons in changing GSM operator for subscribers, and it is very important for companies to predict if subscriber will change GSM operator or not. For this reason, companies that give GSM services have to monitor subscribers’ behaviour and predict one step forward. In this study, changing subscribers’ GSM operator will be predicted by using data mining techniques.
 Keywords: Ant colony, churn management, customer segmentation, data mining.
 Categories: I.2.1, I.2

Analisis K-Means Clustering pada Data Sepeda Motor

K-Means is a data mining algorithm that can be used to grouping or clustering data. This research using k-means for clustering the data of motorcycle based on consumer needs. The dataset used in this research is Honda and Yamaha motorcycle which taken from the dialers in Dewantara District, Aceh. The data tested by grouping 300 data of motorcycle with different attributes into 3 clusters, which are cheap, normal, and expensive. The distribution of the data we separate it using 45 data in 15 times of test. Each test used 3 different data randomly selected on each test. To calculate the distance of each motorcycle data that have been inputted to each centroid, we used the Euclidean Distance formula. Data in this cluster system can be used as a recommendation for users in selecting the motorcycle that they interest the most. The results of the performance on each test finished in 15 times shown that the average value of Precision by 76%, Recall by 76% and the accuracy by 81%.

Reduced Reference Image Quality Assessment Technique Based on DWT and Path Integral Local Binary Patterns

In the prevailing technological advancements, image and video services are one of the primary concerns of researches around the world. The transmission of multimedia contents involved various types of attenuations such as blurring, ringing, contrast, and blocking. To evaluate the quality of the image or video, researchers presented various quality assessment techniques, including subjective and objective assessments. In this article, a robust reduced reference image quality assessment technique based on the objective assessment is presented, which considers the extracted features of the underlying image to evaluate its quality. The proposed method uses a discrete wavelet transform-based path integral local binary pattern histogram as extracted features. These features of the reference and testing image are compared by a Euclidean distance formula to generate a single value to evaluate the quality of the image. The qualitative and quantitative analysis of the proposed method is carried on three different image datasets, namely LIVE, TID2013, and CSIQ. The experimental results of the proposed method indicate that it produces robust performance in terms of performance evaluation metrics as compared with state-of-the-art methods.