Phenetic Research Articles

A hybrid recommender system using topic modeling and prefixspan algorithm in social media

AbstractRoute schema is difficult to plan for tourists, because they demand to pick points of interest (POI) in unknown areas that align with their preferences and limitations. This research proposes a novel personalized method for POI route recommendation that employs contextual data. The proposed approach enhances the existing methods by considering user preferences and multifaceted tourism contexts. Due to the sparsity of the data, the proposed method employs two-level clustering (DBSCAN based on the Manhattan distance) that reduces the time to discover POI. In specific, this approach utilizes the following: first, a topic pattern model is employed to discover the users’ attraction diffusion while improving the user–user similarity model using a novel asymmetric schema. Second, it has used explicit demographic information to alleviate the cold start issue, and third, it proposes a new strategy for assessing user preferences and also combined the context parameters in the form of a vector model with the Term Frequency Inverse Document Frequency technique to find contexts’ similarity. Furthermore, our framework discovers a list of optimal candidate trips by involving personalized POIs in sequential patterns’ mining (SPM); also, it used an adjusted forgotten function to involve the date context of each trip. Based on two datasets (Flickr and Gowalla), our methodology beats other prior approaches in F-score, RMSE, MAP, and NDCG factors in the experimental evaluation.

Total-body low-dose CT image denoising using a prior knowledge transfer technique with a contrastive regularization mechanism.

Reducing the radiation exposure experienced by patients in total-body computed tomography (CT) imaging has attracted extensive attention in the medical imaging community. A low radiation dose may result in increased noise and artifacts that greatly affect the subsequent clinical diagnosis. To obtain high-quality total-body low-dose CT (LDCT) images, previous deep learning-based research works developed various network architectures. However, most of these methods only employ normal-dose CT (NDCT) images as ground truths to guide the training process of the constructed denoising network. As a result of this simple restriction, the reconstructed images tend to lose favorable image details and easily generate oversmoothed textures. This study explores how to better utilize the information contained in the feature spaces of NDCT images to guide the LDCT image reconstruction process and achieve high-qualityresults. We propose a novel intratask knowledge transfer (KT) method that leverages the knowledge distilled from NDCT images as an auxiliary component of the LDCT image reconstruction process. Our proposed architecture is named the teacher-student consistency network (TSC-Net), which consists of teacher and student networks with identical architectures. By employing the designed KT loss, the student network is encouraged to emulate the teacher network in the representation space and gain robust prior content. In addition, to further exploit the information contained in CT scans, a contrastive regularization mechanism (CRM) built upon contrastive learning is introduced. The CRM aims to minimize and maximize the L2 distances from the predicted CT images to the NDCT samples and to the LDCT samples in the latent space, respectively. Moreover, based on attention and the deformable convolution approach, we design a dynamic enhancement module (DEM) to improve the network capability to transform input informationflows. By conducting ablation studies, we prove the effectiveness of the proposed KT loss, CRM, and DEM. Extensive experimental results demonstrate that the TSC-Net outperforms the state-of-the-art methods in both quantitative and qualitative evaluations. Additionally, the excellent results obtained for clinical readings also prove that our proposed method can reconstruct high-quality CT images for clinicalapplications. Based on the experimental results and clinical readings, the TSC-Net has better performance than other approaches. In our future work, we may explore the reconstruction of LDCT images by fusing the positron emission tomography (PET) and CT modalities to further improve the visual quality of the reconstructed CTimages.

A computer vision-aided analysis of facial similarities in Song dynasty imperial portraits

Similarity between faces in portraiture is incredibly informative for art historical questions involving the sitter's identity, as well for setting a painting in its historical context to understand why someone was depicted a certain way. A set of royal portraits from Song dynasty, China, has been the subject of rich art historical scholarship. Here, I demonstrate the usefulness of computer vision-based quantitative metrics in complementing existing rich subjective evaluations. Working with the portrait set, I show that L2 distances generated by OpenFace support the accepted hypothesis that emperor Lizong is depicted in Listening to the Wind in the Pines. I then use the technique to gain insight into whether the zither player in Listening to the Zither resembles emperor Huizong and why that might be, as well as what degrees of similarity between emperor portraits in the set may mean in terms of metaphorical inclusion or exclusion from the lineage. I then extend discussions on metaphorical inclusion to women in this set by exploring spousal similarity. Fascinating mysteries surrounding posthumous portraiture float amidst confounding factors in the clouds of memory, and this study shows the promise of using computer vision-based techniques as complements to subjective analyses in exploring these mysteries.

An Integrated machine learning and DEA-predefined performance outcome prediction framework with high-dimensional imbalanced data

In performance evaluation, emerging studies utilize machine learning to increase the interpretability and robustness of data envelopment analysis (DEA), a non-parametric tool for assessing the relative performance of decision-making units (DMUs). In these studies, the machine learning dynamics typically do not replicate the DEA process in terms of directly labeling DMUs based on their relative performance. Practically, there is no standardized methodological framework that serves this purpose. We propose a data-driven and computationally efficient system that imitates DEA and predicts performance outcomes, which are grouped into several classes. First, a DEA composite index was constructed, and the subsequent DEA scores were labeled as the good, the acceptable, and the underperforming classes. Next, synthetic minority oversampling technique (SMOTE) with Manhattan distance metric was used to solve class imbalance in the labeled, high-dimensional dataset. The framework was built using different classifiers, including random forest, support vector machine, and logistic regression, to verify that the framework is not model-dependent. They achieved comparable recall rates (82.70%–95.39%). Moreover, the impacts of contextual variables on DMU performance were unveiled using model-based feature selection and logistic regression. The framework was tested on a banking dataset and an independent dataset containing the electronics, service, and retail industries.

Asymptomatic carotid stenosis is associated with both edge and network reconfigurations identified by single-subject cortical thickness networks.

Patients with asymptomatic carotid stenosis, even without stroke, are at high risk for cognitive impairment, and the neuroanatomical basis remains unclear. Using a novel edge-centric structural connectivity (eSC) analysis from individualized single-subject cortical thickness networks, we aimed to examine eSC and network measures in severe (> 70%) asymptomatic carotid stenosis (SACS). Twenty-four SACS patients and 24 demographically- and comorbidities-matched controls were included, and structural MRI and multidomain cognitive data were acquired. Individual eSC was estimated via the Manhattan distances of pairwise cortical thickness histograms. In the eSC analysis, SACS patients showed longer interhemispheric but shorter intrahemispheric Manhattan distances seeding from left lateral temporal regions; in network analysis the SACS patients had a decreased system segregation paralleling with white matter hyperintensity burden and recall memory. Further network-based statistic analysis identified several eSC and subgraph features centred around the Perisylvian regions that predicted silent lesion load and cognitive tests. We conclude that SACS exhibits abnormal eSC and a less-optimized trade-off between physical cost and network segregation, providing a reference and perspective for identifying high-risk individuals.

IMPLEMENTASI K-MEDOIDS DAN MODEL WEIGHTED-LENGTH RECENCY FREQUENCY MONETARY (W-LRFM) UNTUK SEGMENTASI PELANGGAN DILENGKAPI GUI R

The k-medoids algorithm is a partition-based clustering algorithm that groups n objects as much as k clusters. The algorithm uses medoids as the center point (partition) of the cluster. Medoids are actual objects that are randomly selected as the most centered object in a cluster so that the k-medoids algorithm is robust against outliers. Grouping objects in cluster analysis based on similarities between objects. Measurement of similarity between objects can use the euclidean and manhattan distances. The use of distance in cluster analysis can affect cluster results. Validation of cluster results using internal validation, namely the silhouette index. The Weighted-Length Recency Frequency Monetary (W-LRFM) model is a model that applies the relative importance (weight) of the LRFM model according to the importance of each variable in the LRFM model. LRFM model is a model used for customer segmentation based on customer behavior which consists of variables length, recency, frequency, and monetary. The relative importance (weight) of the W-LFRM model uses the Analytics Hierarchical Process (AHP) method. The W-LRFM model is used to calculate the Customer Lifetime Value (CLV) of each cluster. The implementation of k-medoids and the W-LFRM model in this study are used for customer segmentation based on the length, recency frequency, and monetary variable. The formation of these variables is the result of transformation of customer behavior data such as transaction id, date of purchase, and a total amount of 41,073 rows into variable length, recency, frequency, and monetary as much as 5,108 rows. The criteria of the best cluster formed are k = 2 using the manhattan distance with the average of coefficient values = 0.62. The weights on the W-LRFM model produced based on the AHP method are 0.16, 0.29, 0.47, and 0.08 for the variable length, recency, frequency, and monetary. CLV formed from two clusters, namely 0.158 and 0.499. CLV in the second cluster is bigger so that the second cluster becomes the main priority in the marketing strategy. The second cluster has the characteristics 0.29, 0.47, and 0.08 for the variable length, recency, frequency, and monetary. The second cluster has the characteristics means a loyal customer group. The first cluster has characteristics means a potential customer group. This research is assisted by using Graphical User Interface (GUI) R to facilitate analysis

Coastal Batik Motifs Identification Using K-Nearest Neighbor Based on The Grey Level Co-occurrence Method

Indonesia is a country rich in natural, cultural, and tourism resources. One of the famous human cultural heritage in Indonesia is batik. Batik has unique motifs that are very diverse so it is difficult to recognize the in certain classes. This research was conducted to classify coastal batik, especially Tegal batik, Pekalongan batik, and Cirebon batik so that it can help facilitate the introduction and understanding of coastal batik when compared to another batik, such as Yogyakarta batik. The method used is Grey Level Co-occurrence Matrices to extract texture features, while, to determine the proximity of the test image to the training data using the K-Nearest Neighbor method, the calculation of the distance to be used is the Euclidean Distance and Manhattan Distance based on the texture characteristics of the batik image obtained. In this study, the highest score was obtained at 64% for Euclidean Distance and 66% for Manhattan Distance at k=15

The Fifteen Puzzle—A New Approach through Hybridizing Three Heuristics Methods

The Fifteen Puzzle problem is one of the most classical problems that has captivated mathematics enthusiasts for centuries. This is mainly because of the huge size of the state space with approximately 1013 states that have to be explored, and several algorithms have been applied to solve the Fifteen Puzzle instances. In this paper, to manage this large state space, the bidirectional A* (BA*) search algorithm with three heuristics, such as Manhattan distance (MD), linear conflict (LC), and walking distance (WD), has been used to solve the Fifteen Puzzle problem. The three mentioned heuristics will be hybridized in a way that can dramatically reduce the number of states generated by the algorithm. Moreover, all these heuristics require only 25 KB of storage, but help the algorithm effectively reduce the number of generated states and expand fewer nodes. Our implementation of the BA* search can significantly reduce the space complexity, and guarantee either optimal or near-optimal solutions.

Freeze-Tag is NP-hard in 3D with L1 distance

The Freeze-Tag Problem (FTP) is the task of scheduling the activation of a robot swarm. The input consists of the initial locations of a set of mobile robots in some metric space. A single robot is initially “active” while the others are initially “frozen”. Active robots can move at unit speed, and upon reaching the location of a frozen robot, the latter is activated. The goal is to activate all the robots within the minimum time, minimizing the so-called makespan of the schedule. The complexity of this problem in Euclidean spaces was open until 2017, when Abel et al. [1] proved that FTP is NP-hard in the Euclidean plane with L2 distance. During that same year, Demaine and Rudoy [2] showed that it is also NP-hard in 3D Euclidean space with Lp distance for any p > 1, but left open the case with p = 1. This paper closes this gap and shows that FTP is indeed NP-hard in 3D Euclidean space with L1 distance. Furthermore, the hardness result holds in the strong sense, such that every coordinate is a rational bounded by a polynomial in the instance size.

A Novel Fusion System Based on Iris and Ear Biometrics for E-exams

With the rapid spread of the coronavirus epidemic all over the world, educational and other institutions are heading towards digitization. In the era of digitization, identifying educational e-platform users using ear and iris based multimodal biometric systems constitutes an urgent and interesting research topic to preserve enterprise security, particularly with wearing a face mask as a precaution against the new coronavirus epidemic. This study proposes a multimodal system based on ear and iris biometrics at the feature fusion level to identify students in electronic examinations (E-exams) during the COVID-19 pandemic. The proposed system comprises four steps. The first step is image preprocessing, which includes enhancing, segmenting, and extracting the regions of interest. The second step is feature extraction, where the Haralick texture and shape methods are used to extract the features of ear images, whereas Tamura texture and color histogram methods are used to extract the features of iris images. The third step is feature fusion, where the extracted features of the ear and iris images are combined into one sequential fused vector. The fourth step is the matching, which is executed using the City Block Distance (CTB) for student identification. The findings of the study indicate that the system’s recognition accuracy is 97%, with a 2% False Acceptance Rate (FAR), a 4% False Rejection Rate (FRR), a 94% Correct Recognition Rate (CRR), and a 96% Genuine Acceptance Rate (GAR). In addition, the proposed recognition system achieved higher accuracy than other related systems.

Clustering models for hospitals in Jakarta using fuzzy c-means and k-means

After facing the COVID-19 pandemic, national and local governments in Indonesia realized a gap in the distribution of health care and human health practitioners. This research proposes two unsupervised learning methods, K-Means and Fuzzy C-Means (FCM), for clustering a list of hospital data in Jakarta, Indonesia, which contains information about the number of its human health resources. The datasets used in this study were obtained from the website the Ministry of the Health Republic of Indonesia provided through the content scraping method. The result shows that implementing K-Means and FCM clustering results in the same number of clusters. Nevertheless, both results have different areas and proportions that can be observed by three distance metrics, such as Hamming, Euclidean, and Manhattan distance. By using the clustering result using the K-Means algorithm, the hospital list was separated into three clusters with a proportion of 84.82%, 14.66%, and 0.52% for clusters 0, 1, and 2, respectively. Meanwhile, using the FCM algorithm, the hospital list was separated into three clusters with a proportion of 17.80%, 73.82%, and 8.38% for clusters 0, 1, and 2, respectively. To the best of our knowledge, this is the first discussion of clustering healthcare facilities in Indonesia, especially hospitals, based on their health professionals.

Automatic quantitative assessment of English writing proficiency based on multi-feature fusion

In the existing quantitative evaluation methods of English writing level, the accuracy of feature extraction is low and the error is high. An automatic quantitative evaluation method of English writing level based on multi-feature fusion is put forward. By using vector space model and Jekard similarity coefficient to determine the cosine similarity of English text, the features of English text are extracted by Manhattan distance. Through kernel function, the multi-feature fusion of English writing text is realised. The multivariate linear regression model is used to determine the feature weight of English text and to quantitatively process the feature data. The automatic quantitative evaluation model of English writing level is constructed to complete the automatic quantitative evaluation of English writing level. The experimental results show that the accuracy of the proposed automatic quantitative evaluation method is always higher than 90 and the minimum error of text feature extraction is about 2%.

Machine learning based text neck syndrome detection using Microsoft Kinect sensor

Text Neck Syndrome is repeated stress injury to the neck, or it is a pain encountered in the neck due to excessive usage of handheld devices for a prolonged period. In this paper, we have used the Microsoft Kinect sensor to create the dataset for normal and abnormal sitting postures by obtaining 3D skeletal coordinates of people. Features are extracted from the data collected from the Kinect sensor data based on the various parameters like Minkowski distance, Euclidean distance, Manhattan distance, etc. Then we have applied different machine learning algorithms, namely, K-nearest neighbours, Random forest, Support vector machine, Logistic and Linear Regression, to classify them. The performance of various algorithms is analysed. The best testing accuracy achieved is 92.85% by using Random Forest and Support Vector Machine algorithms.

Assessing the efficacy of social distancing as a weapon against COVID-19 using Manhattan distance and AI-based deep learning models

Assessing the efficacy of social distancing as a weapon against COVID-19 using Manhattan distance and AI-based deep learning models

A Clustering Algorithm of Electronic Boundary Points for Cadastral Blocks

The coordinates of boundary points of a number of cadastral blocks can be obtained by electronic boundary points automatically, while the automation of data processing of coordinates needs to be improved. This paper focuses on the automatic clustering of electronic boundary point coordinates and analyses the location distribution and angle characteristics of cadastral blocks with real coordinates data from 6 villages. In this paper, a strategy is proposed that one boundary point of every cadastral block should be marked and Manhattan distance between points should be used as the similarity measure. A clustering algorithm of electronic boundary points for cadastral blocks is designed with the combination of K-means algorithm. The simulation results show the clustering accuracy of the algorithm can be above 0.9 when the number of cadastral blocks is more than 100, and it can be improved as the number of cadastral blocks is controlled within 25. This study provides a reference for optimization of existing electronic boundary points system and automation technology of the cadastral survey.

Анализ структурной организации сообщества крупных хищных птиц Ремдовского заказника

Анализ структурной организации сообщества крупных хищных птиц Ремдовского заказника

A Novel Approach to Design Distribution Preserving Framework for Big Data

In several fields like financial dealing, industry, business, medicine, et cetera, Big Data (BD) has been utilized extensively, which is nothing but a collection of a huge amount of data. However, it is highly complicated along with time-consuming to process a massive amount of data. Thus, to design the Distribution Preserving Framework for BD, a novel methodology has been proposed utilizing Manhattan Distance (MD)-centered Partition Around Medoid (MD–PAM) along with Conjugate Gradient Artificial Neural Network (CG-ANN), which undergoes various steps to reduce the complications of BD. Firstly, the data are processed in the pre-processing phase by mitigating the data repetition utilizing the map-reduce function; subsequently, the missing data are handled by substituting or by ignoring the missed values. After that, the data are transmuted into a normalized form. Next, to enhance the classification performance, the data’s dimensionalities are minimized by employing Gaussian Kernel (GK)-Fisher Discriminant Analysis (GK-FDA). Afterwards, the processed data is submitted to the partitioning phase after transmuting it into a structured format. In the partition phase, by utilizing the MD-PAM, the data are partitioned along with grouped into a cluster. Lastly, by employing CG-ANN, the data are classified in the classification phase so that the needed data can be effortlessly retrieved by the user. To analogize the outcomes of the CG-ANN with the prevailing methodologies, the NSL-KDD openly accessible datasets are utilized. The experiential outcomes displayed that an efficient result along with a reduced computation cost was shown by the proposed CG-ANN. The proposed work outperforms well in terms of accuracy, sensitivity and specificity than the existing systems.

Vesicular self-assembly of copolymer-grafted nanoparticles with anisotropic shapes.

Plasmonic nanovesicles show broad applications in areas such as cancer theranostics and drug delivery, but the preparation of nanovesicles from shaped nanoparticles remains challenging. This article describes the vesicular self-assembly of shaped nanoparticles, such as gold nanocubes grafted with amphiphilic block copolymers, in selective solvents. The nanocubes assembled within the vesicular membranes exhibit two distinctive packing modes, namely square-like and hexagonal packing, depending on the relative dimensions of the copolymer ligands and nanocubes. The corresponding optical properties of the plasmonic nanovesicles can be tuned by varying the length of the grafted copolymers and the size of the nanocubes. This work provides guidance for the fabrication of functional plasmonic vesicles for applications in catalysis, nanomedicines and optical devices.

Optimization Reinforced PID-Sliding Mode Controller for Rotary Inverted Pendulum

The control of a rotary inverted pendulum (RIP) is challenging because it is an underactuated, highly sensitive, and unsteady system. Sliding mode control (SMC) is a nonlinear control method with high-frequency switching control. Designing a proportional integral derivative (PID) controller for a RIP is challenging due to its nonlinearity and instability in open-loop characteristics. The primacy of the SMC over the PID is the stability of the closed-loop. Hybrid control of a PID-SMC controller can provide better performance because this technique demonstrates less chatter, higher precision, no oscillation, and adequate gain tuning. To achieve gain tuning, the PID and SMC parameters must be optimized. Thus, this paper proposed a congruently tuned control strategy (CTCS) to fine-tune the controller parameters. The proposed strategy uses an improved whale optimization algorithm (WOA), i.e., the modified Manhattan distance updated WOA (MMD-WOA) to identify effective coefficient values for the sliding surface to reduce tracking errors while reaching the desired position. The proposed CTCS for a RIP with the MMD-WOA was implemented, and the results are very promising.

Habituation deficit study in patients with episodic migraine thru nociceptive blink reflex

Lack of habituation is the most reproducible interictal neurophysiological phenomenon in episodic migraine. The aim of this study is to evaluate the habituation phenomenon by examining the nociceptive blink reflex in patients with episodic migraine. We conducted a cross-sectional observational case-control study. Patients with episodic migraine were selected consecutively and studied during the interictal phase. The nociceptive blink reflex was examined and a study was conducted comparing symmetry, analysis of the Euclidean distances and assessment of latency prolongation between stimulation blocks. Thirty-one patients and 16 healthy controls were included, their mean ages being 32.25 and 32.35 years, respectively. The controls displayed left-right symmetry. The Euclidean and Manhattan distances showed that the means of the block latencies of the groups are different and increase according to the number of blocks being compared. The means of the block latencies do not differ significantly in the migraine patient group, in contrast to what is seen in the healthy group. Habituation deficit was observed in the interictal phase in patients with episodic migraine compared to controls, as measured by the absence of latency prolongation in the nociceptive blink reflex.