Euclidean Distance Calculation Research Articles

Dengue NS1 interaction with lipids alters its pathogenic effects on monocyte derived macrophages.

While dengue NS1 antigen has been shown to be associated with disease pathogenesis in some studies, it has not been linked in other studies, with the reasons remaining unclear. NS1 antigen levels in acute dengue are often associated with increased disease severity, but there have been a wide variation in results based on past dengue infection and infecting dengue virus (DENV) serotype. As NS1 engages with many host lipids, we hypothesize that the type of NS1-lipid interactions alters its pathogenicity. Primary human monocyte derived macrophages (MDMs) were co-cultured with NS1 alone or with HDL, LDL, LPS and/or platelet activating factor (PAF) from individuals with a history of past dengue fever (DF=8) or dengue haemorrhagic fever (DHF=8). IL-1β levels were measured in culture supernatants, and gene expression analysis carried out in MDMs. Monocyte subpopulations were assessed by flow cytometry. Hierarchical cluster analysis with Euclidean distance calculations were used to differentiate clusters. Differentially expressed variables were extracted and a classifier model was developed to differentiate between past DF and DHF. Significantly higher levels of IL-1β were seen in culture supernatants when NS1 was co-cultured with LDL (p=0.01), but with lower levels with HDL (p=0.05). MDMs of those past DHF produced more IL-1β when NS1 with PAF (p=0.02). MDMs of individuals with past DHF, were significantly more likely to down-regulate RPLP2 gene expression when macrophages were co-cultured with either PAF alone, or NS1 combined with PAF, or NS1 combined with LDL. When NS1 was co-cultured with PAF, HDL or LDL two clusters were detected based on IL10 expression, but these did not differentiate those with past DF or DHF. As RPLP2 is important in DENV replication and in regulating cellular stress responses and immune responses and IL-10 is associated with severe disease, it would be important to further explore how differential expression of RPLP2 and IL-10 could lead to disease pathogenesis based on NS1 and lipid interactions.

Inverse design of two-function transmission-type reconfigurable polarization control metasurfaces based on deep learning

Compared with single-function metasurfaces, the design difficulty of multi-function metasurfaces increases significantly. This paper introduces an inverse design method based on deep learning to address this challenge. By this method, a transmission-type reconfigurable polarization control metasurface (TRPCM) with two functions is rapidly designed. The network model used in the method consists of an electromagnetic parameter reconstruction network model and an inverse prediction network model. The combination of the two models can solve the problem of difficulty in defining high-dimensional inputs in traditional inverse design, and achieve accurate prediction of metasurface structure parameters under given design targets. To optimize the hyperparameters of the neural network model, a genetic algorithm was introduced. To solve the non-uniqueness problem of inverse design, a method for eliminating similar data by calculating Euclidean Distance was introduced. Both schemes further improve the predictive performance of the proposed network model. Finally, six design targets were set based on the TRPCM. The structural parameters of the metasurface were successfully predicted using two neural network models and achieved the required performance. On this basis, a set of parameters was selected for experimental validation. By controlling the ON or OFF of the PIN diodes, the fabricated metasurface achieves two functions: linear-to-circular polarization conversion and linear polarization maintenance in the range of 2–3.6 GHz. Study results show that the inverse design scheme proposed in the paper is feasible and practical for solving the rapid optimization design of complex multi-function metasurfaces.

A geometric modelling approach to estimate apple fruit size by means of LiDAR 3D point clouds

ABSTRACT Remote sensing in agriculture aims to search new methods to monitor fruit at the tree, thus improving the estimation of yield-related variables. Light detection and range (LiDAR) scanning was introduced to obtain geometric and radiometric information from fruit surfaces by means of 3D point clouds. A geometric model to estimate apple size by means of segmented 3D point cloud of fruit is proposed in the present study. The model consists in the approximation of 3D point clouds to a reference shape given by 2D Fourier series expansion. Each point cloud was approximated to its reference shape using an iterative error minimization routine. The geometric model was applied to laboratory and field data of spheres and apples during fruit growth, ranging from 60 to 151 days after full bloom (DAFB). An overall RMSE between measured and predicted fruit radius of 20.1, 76.8, and 119.1% was found for the geometric model, mean, and maximum Euclidean distance approaches, respectively, including all studied growth periods in field conditions. Moreover, the linear regression on measured and predicted values showed considerably improved coefficient of determination ( R 2 ) of the geometric model in comparison to Euclidean distance calculations with R 2 values of 0.76 and 0.49 for laboratory and field scanned apples, respectively. The data processing method enables fruit monitoring and their application of terrestrial LiDAR sensing in precise orchard management.

Privacy Preserving Image Retrieval Using Multi-Key Random Projection Encryption and Machine Learning Decryption

Homomorphic Encryption (HE), Multiparty Computation (MPC), Differential Privacy (DP) and Random Projection (RP) have been used in privacy preserving computing. The main benefit of the random projection approach is the lighter time and space complexity compared to the other available techniques. However, RP is typically used in a symmetric encryption mode, with one random projection matrix single key, making it vulnerable to attacks. An enhanced multi-key RP approach is proposed in this paper where a set of N random matrices are used as projection keys. Moreover, a randomly chosen one is used for each new query. Machine learning models are trained to perform specific vector operations on the randomly projected vectors and produce another randomly projected results vector. Another machine learning model is trained to decrypt the final result at the user’s side. The proposed system is shown to offer privacy against known plaintext and cipher-only attacks while preserving Euclidean distance calculations accuracy in the randomly projected domain which are demonstrated on the COREL 1K image retrieval task. Results show that the cyphertext space took sixteen times less than the ciphertext done with homomorphic encryption, and the computation of distance using random projection was 8 times faster than homomorphic encryption distance calculation.

Abstract 4980: Genomic and clinical characteristics of advanced pancreatobiliary cancer, stratified by KRAS mutation status

Abstract Mutations in KRAS are common in pancreatobiliary cancer, occurring in 90% of advanced pancreatic ductal adenocarcinomas (PDAC) and 20% of advanced cholangiocarcinomas (CCA). We analyzed clinico-genomic databases to evaluate the hypothesis that KRAS mutation status defines subsets of PDAC and CCA with similar genomic characteristics and clinical behavior. Using the genomic data of PDAC and CCA from AACR Project GENIE Cohort version 14.0-public, we analyzed the genomic landscape of four cohorts of pancreatobiliary cancer: KRAS mutated PDAC, KRAS wild-type PDAC, KRAS mutated CCA, and KRAS wild-type CCA. Excluding KRAS mutations, there were 53 gene alterations observed in >2.5% of cases in at least one of the four cohorts. The three most common gene alterations in each cohort were; TP53, SMAD4, and CDKN2A mutations (KRAS mutated PDAC), TP53, ARID1A, and SMAD4 mutations (KRAS wild-type PDAC), TP53 mutation, CDKN2A deletion and SMAD4 mutation (KRAS mutated CCA), and TP53, ARID1D and IDH1 mutations. (KRAS wild-type CCA) The similarity of gene alteration patterns was evaluated by principal component analysis (PCA) 3D plot and calculation of average Euclidean distance. The PCA plot suggested heterogeneous genomic profiles in KRAS wild-type CCA in contrast to relatively monotonous profiles in KRAS mutated PDAC. The average Euclidean distance between KRAS mutated CCA and KRAS wild-type CCA was significantly longer than that between KRAS mutated CCA and KRAS mutated PDAC (2.00 vs. 1.89, p < 0.001), suggesting that KRAS mutated CCA is more genomically related to KRAS mutated PDAC than KRAS wild-type CCA. The average Euclidean distance between KRAS mutated PDAC and KRAS wild-type PDAC was significantly shorter than that between KRAS wild-type CCA and KRAS wild-type PDAC. To compare the clinical characteristics of the four cohorts, we evaluated the data of patients with stage IV pancreatobiliary cancer, using cBioPortal. The number of cases in each cohort was 1544 (KRAS mutated PDAC), 121 (KRAS wild-type PDAC), 91 (KRAS mutated CCA), and 459 (KRAS wild-type CCA). Median overall survival (OS) was 14.7, 21.5, 10.7, and 15.4 months, respectively. Compared to KRAS wild-type CCA, KRAS mutated CCA had a significantly shorter OS (hazard ratio [HR] = 1.45, 95% confidence interval [CI] = 1.12 - 1.89). The OS of KRAS mutated CCA was shorter than KRAS mutated PDAC (HR 1.32, 95% CI 1.03 - 1.68). KRAS wild-type PDAC had a significantly longer OS compared to KRAS mutated PDAC. (HR 0.72, 95% CI 0.57 - 0.92) In conclusion, KRAS mutated CCA has a poor OS and a genomic landscape distinct from KRAS wild-type CCA; it is genomically more similar to KRAS mutated PDAC. KRAS wild-type PDAC has a better OS than KRAS mutated PDAC, though it was not genomically similar to KRAS wild-type CCA. Therapeutic approaches stratified by KRAS mutation status should be considered for pancreaticobiliary cancers. Citation Format: Hirotaka Miyashita, Parth S. Shah, Gabriel A. Brooks. Genomic and clinical characteristics of advanced pancreatobiliary cancer, stratified by KRAS mutation status [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4980.

An investigation into real-time surface crack classification and measurement for structural health monitoring using transfer learning convolutional neural networks and Otsu method

This study introduces a pioneering system for real-time classification and measurement of concrete surface cracks, a crucial aspect of Structural Health Monitoring (SHM). We harness the power of transfer learning (TL) in Convolutional Neural Networks (CNNs), including renowned models such as MobileNetV2, EfficientNetV2, InceptionV3, and ResNet50. Notably, our model excels, particularly with TL MobileNetV2, achieving remarkable results – a 99.87% accuracy rate, 99.74% recall, 100% precision, and an impressive 99.87% F1-score. Incorporating the Otsu method for image segmentation, our system accurately assesses individual crack sizes. To refine measurements, Euclidean distance calculations and a 'pixel per inch' technique, accounting for video resolution, ensure millimeter-level width estimations. Precision is validated through manual experiments using a vernier caliper, specifically the Mitutoyo Absolute Digital Caliper. This tool ensures high accuracy, with an error margin of ±0.2 mm to ±0.3 mm, making it efficient for detailed measurements. Despite these promising outcomes, it is crucial to acknowledge inherent limitations. These include dependence on image quality, challenges in generalization, sensitivity to training data, assumption of linear crack width calculation, resolution dependency, and other factors. These limitations underscore the need for further refinement in our proposed classification model and measurement technique. This research represents a significant advancement in the SHM field, catering to early detection and timely maintenance requirements essential for infrastructure safety and longevity. As the field increasingly prioritizes rapid detection, our model presents a versatile solution that enhances the potential of Structural Health Monitoring.

Electric field simulation and appropriate electrode positioning for optimized transcranial direct current stimulation of stroke patients: an in Silico model

Transcranial Direct Current Stimulation (tDCS) has benefits for motor rehabilitation in stroke patients, but its clinical application is limited due to inter-individual heterogeneous effects. Recently, optimized tDCS that considers individual brain structure has been proposed, but the utility thereof has not been studied in detail. We explored whether optimized tDCS provides unique electrode positions for each patient and creates a higher target electric field than the conventional approach. A comparative within-subject simulation study was conducted using data collected for a randomized controlled study evaluating the effect of optimized tDCS on upper extremity function in stroke patients. Using Neurophet tES LAB 3.0 software, individual brain models were created based on magnetic resonance images and tDCS simulations were performed for each of the conventional and optimized configurations. A comparison of electrode positions between conventional tDCS and optimized tDCS was quantified by calculation of Euclidean distances. A total of 21 stroke patients were studied. Optimized tDCS produced a higher electric field in the hand motor region than conventional tDCS, with an average improvement of 20% and a maximum of 52%. The electrode montage for optimized tDCS was unique to each patient and exhibited various configurations that differed from electrode placement of conventional tDCS. Optimized tDCS afforded a higher electric field in the target of a stroke patient compared to conventional tDCS, which was made possible by appropriately positioning the electrodes. Our findings may encourage further trials on optimized tDCS for motor rehabilitation after stroke.

Unsupervised Wavelet-Feature Correlation Ratio Markov Clustering Algorithm for Remotely Sensed Images

The spectrums of one type of object under different conditions have the same features (up, down, protruding, concave) at the same spectral positions, which can be used as primary parameters to evaluate the difference among remotely sensed pixels. The wavelet-feature correlation ratio Markov clustering algorithm (WFCRMCA) for remotely sensed data is proposed based on an accurate description of abrupt spectral features and an optimized Markov clustering in the wavelet feather space. The peak points can be captured and identified by applying a wavelet transform to spectral data. The correlation ratio between two samples is a statistical calculation of the matched peak point positions on the wavelet feature within an adjustable spectrum domain or a range of wavelet scales. The evenly sampled data can be used to create class centers, depending on the correlation ratio threshold at each Markov step, accelerating the clustering speed by avoiding the computation of Euclidean distance for traditional clustering algorithms, such as K-means and ISODATA. Markov clustering applies several strategies, such as a simulated annealing method and gradually shrinking the clustering size, to control the clustering convergence. It can quickly obtain the best class centers at each clustering temperature. The experimental results of the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Thermal Mapping (TM) data have verified its acceptable clustering accuracy and high convergence velocity.

The closer, the better – How perceived ideological proximity between parties affects the emergence of coalition preferences

ABSTRACT While coalition governments have been studied extensively, there remains a lack of understanding of how coalition preferences emerge and what factors are the most influential. Utilising coalition formation theories, this study posits that voters tend to prefer coalitions with a narrower range of ideological differences between 1.) the parties involved and 2.) between the voter and the party perceived to have the greatest ideological distance from the individual. Previous studies have mainly concentrated on a general left-right ideological dimension or specific issue dimensions, despite the fact that some of the countries analysed are characterized by a two-dimensional political space. Using Germany as a case study that exemplifies this inherent two-dimensionality, this analysis adopts a nuanced approach by employing the calculation of Euclidean distance based on socio-economic and socio-cultural measures. This approach aims to explain the formation of coalition preferences leading up to the federal election in 2021. Our results show how strongly the perceived ideological distance of parties contributes to developing preferences for a specific coalition option, even when controlling for party evaluation and socio-demographics. For this reason, they have important implications for the understanding of the emergence of coalition preferences and party competition.

Remaining useful life prediction based on a PCA and similarity methods

Aircraft engine failures or damages not only incur substantial financial losses but also present risks of injuries or even fatalities. Hence, it is of utmost importance to devise an effective method to predict potential failures in advance, thereby mitigating accidents and minimizing losses. This paper proposes a novel approach that combines a principal component analysis (PCA) with similarity methods to establish a degradation trajectory database and predict the remaining useful life (RUL) of new engines by identifying similar trajectories. Firstly, the data dimensionality is reduced using a PCA to create a health indicator. The validity of the reduced data is confirmed by calculating the Spearman correlation coefficient between the health indicator and the system RUL. During the similarity comparison process, the Manhattan distance is employed for the similarity calculation, and parameter optimization is performed on the length of selected time segments and the number of chosen similar trajectories to optimize the similarity of RUL prediction model, resulting in the optimal prediction results among all engine test sets. Notably, this paper introduces the feasibility of employing the Manhattan distance in similarity method-based prediction, which is superior to the commonly used Euclidean distance calculation method found in most literature. This finding offers innovative ideas and perspectives for advancing RUL prediction methodologies. By adopting the proposed approach, the occurrence of accidents and losses associated with aircraft engine failures can be substantially reduced, leading to enhanced safety and economic benefits.

Parallel Density‐Based Spatial Clustering with Dual‐Functional Memristive Crossbar Array

AbstractAnalog and digital switching performances in a Ta/HfO2/RuO2 (THR) memristor are studied to implement a density‐based spatial clustering of applications with noise (DBSCAN) algorithm in a low‐power, parallel‐computing memristor crossbar structure. In the analog mode THR memristor, more than 256 states can be stored through a fine‐tuning process with a denoising scheme. The analog mode crossbar array facilitates Euclidean distance calculation between any points in the given graphic dataset. In the digital mode, the on/off ratio of more than three orders of magnitude between the binary states is achieved, providing functionality to cluster the data points with a reduced number of operations. The parallel computing capacity of the adopted crossbar decreases the time complexity of the original DBSCAN from O(n2) to O(n). Through array‐level simulations, the effectiveness of hardware functionality is validated using representative synthetic datasets and single‐cell RNA sequences datasets.

CACHE DATA REPLACEMENT POLICY BASED ON RECENTLY USED ACCESS DATA AND EUCLIDEAN DISTANCE

Data access management in web-based applications that use relational databases must be well thought out because the data continues to grow every day. The Relational Database Management System (RDBMS) has a relatively slow access speed because the data is stored on disk. This causes problems with decreased database server performance and slow response times. One strategy to overcome this is to implement caching at the application level. This paper proposed SIMGD framework that models Application Level Caching (ALC) to speed up relational data access in web applications. The ALC strategy maps each controller and model that has access to the database into a node-data in the in-Memory Database (IMDB). Not all node-data can be included in IMDB due to limited capacity. Therefore, the SIMGD framework uses the Euclidean distance calculation method for each node-data with its top access data as a cache replacement policy. Node-data with Euclidean distance closer to their top access data have a high priority to be maintained in the caching server. Simulation results show at the 25KB cache configuration, the SIMGD framework excels in achieving hit ratios compared to the LRU algorithm of 6.46% and 6.01%, respectively.

Quantitative Representativeness and Constituency of the Long-Term Agroecosystem Research Network and Analysis of Complementarity with Existing Ecological Networks

Studies conducted at sites across ecological research networks usually strive to scale their results to larger areas, trying to reach conclusions that are valid throughout larger enclosing regions. Network representativeness and constituency can show how well conditions at sampling locations represent conditions also found elsewhere and can be used to help scale-up results over larger regions. Multivariate statistical methods have been used to design networks and select sites that optimize regional representation, thereby maximizing the value of datasets and research. However, in networks created from already established sites, an immediate challenge is to understand how well existing sites represent the range of environments in the whole area of interest. We performed an analysis to show how well sites in the USDA Long-Term Agroecosystem Research (LTAR) Network represent all agricultural working lands within the conterminous United States (CONUS). Our analysis of 18 LTAR sites, based on 15 climatic and edaphic characteristics, produced maps of representativeness and constituency. Representativeness of the LTAR sites was quantified through an exhaustive pairwise Euclidean distance calculation in multivariate space, between the locations of experiments within each LTAR site and every 1 km cell across the CONUS. Network representativeness is from the perspective of all CONUS locations, but we also considered the perspective from each LTAR site. For every LTAR site, we identified the region that is best represented by that particular site—its constituency—as the set of 1 km grid locations best represented by the environmental drivers at that particular LTAR site. Representativeness shows how well the combination of characteristics at each CONUS location was represented by the LTAR sites’ environments, while constituency shows which LTAR site was the closest match for each location. LTAR representativeness was good across most of the CONUS. Representativeness for croplands was higher than for grazinglands, probably because croplands have more specific environmental criteria. Constituencies resemble ecoregions but have their environmental conditions “centered” on those at particular existing LTAR sites. Constituency of LTAR sites can be used to prioritize the locations of experimental research at or even within particular sites, or to identify the extents that can likely be included when generalizing knowledge across larger regions of the CONUS. Sites with a large constituency have generalist environments, while those with smaller constituency areas have more specialized environmental combinations. These “specialist” sites are the best representatives for smaller, more unusual areas. The potential of sharing complementary sites from the Long-Term Ecological Research (LTER) Network and the National Ecological Observatory Network (NEON) to boost representativeness was also explored. LTAR network representativeness would benefit from borrowing several NEON sites and the Sevilleta LTER site. Later network additions must include such specialist sites that are targeted to represent unique missing environments. While this analysis exhaustively considered principal environmental characteristics related to production on working lands, we did not consider the focal agronomic systems under study, or their socio-economic context.

WEBSITE REKOMENDASI DAN KLASIFIKASI LAGU MENGGUNAKAN METODE WEIGHTED K-NEAREST NEIGHBOR

As the years went by, music has become one of the most evolving aspects of human history. There is a load of musical development around the globe, especially in music genres. Due to these differences and developments, a design was created to be able to make song recommendations according to the genre types and classifications of music or song. The data that is processed as training data is in the form of song metadata with various music features sourced from Spotify. Song recommendations are performed using the Euclidean Distance calculation between musical features or songs, while song classification is carried out using the Weighted K-Nearest Neighbor (WKNN) method calculation through audio wave type file analysis which then takes the musical features and calculates them based on the existing song or music data. The end result of this process is the genre class label. There is also a classification evaluation calculation using a confusion matrix. With the design of this system, it is hoped that the user will be able to search for song recommendations that have similarities to the song chosen by the user and classify genres according to the user's input song.

Modified K-Nearest Neighbor Web Based Chatbot as Service and Academic Information School

At a time when everything is done on an Online basis starting from office activities, teaching and learning activities especially administrative activities school. Where in the activity, aninformant needs to be can serve academic and non-academic information needs for para parents of students and other parties. Chatbot is one of the means to overcome these needs by presentingfeatures that allows for someone to ask when and where. Therefore, in the conclusion that chatbot can be a public means especially on schools - schools that can implement their uses as one school information sources other than the school's business. This Chatbot made using the Modified K-Nearest Neighbor method or can be briefed MKNN. MKNN is the latest version of the previous method, K-Nearest Neighbor where in the application MKNN method does the process additional after Euclidean Distance calculation, Weight Voting. Premise from the weight voting method itself is the biggestweight calculation, so chatbot will calculate the value of the shortest distance to the database from the chatbot then after completion, the chatbot will calculate the value weight or information from that distance so that the results that can be from this are the shortestdistance to the data class that is being addressed by carrying the weight of information biggest or most. This is used to facilitate the deep chatbot determine the category of a database so that it can provide answers that more certain and accurate.

Hydrogel microenvironment contributes to chemical-induced differentiation of mesenchymal stem cells: single-cell infrared microspectroscopy characterization.

Stem cell microenvironment plays vital roles in directing cell proliferation and differentiation. Due to the tiny biochemical changes in the early stage of stem cell development, technical challenges to characterize the potential effects of environmental signals remain. In this work, we have introduced synchrotron radiation-based Fourier transform infrared microspectroscopy to evaluate the synergistic effects of physical and chemical factors on stem cell differentiation at the single-cell level. By using principal component analysis and cell-cell Euclidean distance calculation, the phenotypic heterogeneity changes during stem cell osteogenesis induced by lithium chloride or Wnt5a protein loaded in the polyvinyl alcohol (PVA) hydrogel were characterized in detail. The results demonstrated that PVA hydrogel could lead to the distinct effects between low-concentration lithium and wnt5a on human mesenchymal stem cells, suggesting a vital role of niche signals in Wnt pathway. These findings highlight the importance of microenvironment to the chemical-induced effects on stem cell differentiation and also provide a label-free, noninvasive method to sensitively identify the niche function in stem cell biology.

Research of the Ball Burnishing Impact over Cold-Rolled Sheets of AISI 304 Steel Fatigue Life Considering Their Anisotropy.

The present work focusses on the research of the plastic deformation accumulated effect obtained after two different plastic deformation treatments, over the fatigue life of AISI 304 austenitic stainless steel. The research is focused on ball burnishing as a finishing process to form specific, so-called "regular micro-reliefs" (RMRs) on a pre-rolled stainless-steel sheet. RMRs are formed using a CNC (Computerized Numerically Controlled) milling machine and toolpaths with the shortest unfolded length, generated by an improved algorithm, based on the Euclidean Distance calculation. The effect of the predominant tool trajectory direction during the ball burnishing process (which can be coinciding or transverse with the rolling direction), the magnitude of applied deforming force, and feed-rate is subjected to evaluation using Bayesian rule analyses of experimentally obtained results for the fatigue life of AISI 304 steel. The obtained results give us reason to conclude that the fatigue life of researched steel is increased when directions of pre-rolled plastic deformation and the tool movement during ball burnishing are coincident. It also been found that the magnitude of deforming force has a stronger impact over the fatigue life, than the feed-rate of the ball tool.

Comparison Of K-nearest Neighbor (KNN) And Linear Discriminant Analysis (LDA) Algorithms For Mature Ajwa Date Fruit Classification

Currently, many applications of artificial intelligence in various fields of life, especially in image data, require digital image processing. One example of the use of digital images often encountered is image processing of fruit ripeness. Dates are a fruit in great demand by the people of Indonesia, and one of the most popular dates is the Ajwa date. The author is interested in developing previous research regarding identifying the ripeness of Ajwa Dates, where previous research used RGB color image processing with the HIS method. Therefore, the authors want to apply a different method, namely the K-Nearest Neighbor (K-NN) method and Linear Discriminant Analysis (LDA), in classifying the ripeness of the Ajwa Dates by applying a statistical feature algorithm. This research aims to develop a classification model for the maturity level of Ajwa Dates. Furthermore, it is expected to provide better classification results than the previous algorithm. The test results using the KNN method can produce higher accuracy than the LDA, where the KNN method is obtained from the calculation of the Euclidean distance k = 1 100% and Manhattan with a value of k = 1 and k = 2 worth 100%, but the minimum accuracy value is 53.33 % is found at k = 9 in the Euclidean distance calculation, while the LDA accuracy value can reach 93.33%.

Face Recognition of Indonesia’s Top Government Officials Using Deep Convolutional Neural Network

Facial recognition is a part of Computer Vision that is used to get facial coordinates from an image. Many algorithms have been developed to support Facial Detection such as Cascade Face Detection using Haar-Like features and AdaBoost to classify its Cascade and Convolutional Neural Network (CNN). Face recognition in this study uses the Deep Convolutional Neural Network (DCNN) method, and the output of this method is the measurement value of the face. In the model training process, Triplet Loss from Triplet Network Deep Metric Learning is used to get good face grouping results. The value of this face measurement will then be measured using the Euclidean distance calculation to determine the similarity of the input face from the dataset. This Research is using 6 images of Government officers in Indonesia to determine the accuracy of the model when there is a new picture of these officers inputted into the training machine. The result provides a 94% accuracy level with a variety of face positions and levels of brightness.

Virtual cleaning of works of art using a deep generative network: spectral reflectance estimation

Generally applied to a painting for protection purposes, a varnish layer becomes yellow over time, making the painting undergo an appearance change. Upon this change, the conservators start a process that entails removing the old layer of varnish and applying a new one. As widely discussed in the literature, helping the conservators through supplying them with the probable outcome of the varnish removal can be of great value to them, aiding in the decision making process regarding varnish removal. This help can be realized through virtual cleaning, which in simple terms, refers to simulation of the cleaning process outcome. There have been different approaches devised to tackle the problem of virtual cleaning, each of which tries to develop a method that virtually cleans the artwork in a more accurate manner. Although successful in some senses, the majority of them do not possess a high level of accuracy. Prior approaches suffer from a range of shortcomings such as a reliance on identifying locations of specific colors on the painting, the need to access a large set of training data, or their lack of applicability to a wide range of paintings. In this work, we develop a Deep Generative Network to virtually clean the artwork. Using this method, only a small area of the painting needs to be physically cleaned prior to virtual cleaning. Using the cleaned and uncleaned versions of this small area, the entire unvarnished painting can be estimated. It should be noted that this estimation is performed in the spectral reflectance domain and herein it is applied to hyperspectral imagery of the work. The model is first applied to a Macbeth ColorChecker target (as a proof of concept) and then to real data of a small impressionist panel by Georges Seurat (known as ‘Haymakers at Montfermeil’ or just ‘Haymakers’). The Macbeth ColorChecker is simulated in both varnished and unvarnished forms, but in the case of the ‘Haymakers’, we have real hyperspectral imagery belonging to both states. The results of applying the Deep Generative Network show that the proposed method has done a better job virtually cleaning the artwork compared to a physics-based method in the literature. The results are presented through visualization in the sRGB color space and also by computing Euclidean distance and spectral angle (calculated in the spectral reflectance domain) between the virtually cleaned artwork and the physically cleaned one. The ultimate goal of our virtual cleaning algorithm is to enable pigment mapping and identification after virtual cleaning of the artwork in a more accurate manner, even before the process of physical cleaning.