Phenetic Research Articles

Different variable selection and model updating strategies about sex classification of silkworm pupae

When the model was applied to discriminate the sex of silkworm pupae of new species, the accuracy was not satisfied. Rebuilding the model need abundant samples and was time consuming. Updating the original model with few samples was usually used, which could also gave high performance. Hence, different model updating strategies were explored via visible (VIS)/near-infrared (NIR) hyperspectral imaging (HSI) spectroscopy in this paper. The calibration model including 150 samples was established on two species (221B-403, 223B-404) and the prediction set had 50 samples. Different variable selection methods including uninformative variable elimination (UVE) and synergy interval-partial least-squares (SiPLS) were adopted. Then partial least squares-discriminant analysis (PLS-DA) and extreme learning machine (ELM) were used to build the model. The best performance were given by UVE-PLSDA and SiPLS-PLSDA models with the accuracy of 98%. When SiPLS-PLSDA model was explored to discriminate the sex of new species “9312-shanheB”, the accuracy was just 70.83%. Different sample selecting methods, containing Kennard Stone (KS) algorithm, Manhattan distance, Euclidean distance and Chebyshev distance, were used to update the original calibration model. The updated SiPLS-PLSDA model based on KS gave the highest performance with 100% when used to discriminate the sex of silkworm pupa with different species in the same year. In addition, the updated model reached the accuracy of 94.44% when used to discriminate the sex of silkworm pupa with different species in different year. It indicated that the proposed updating strategy could be further effectively explored to differentiate the sex of other new species.

Classification of major depression disorder via using minimum spanning tree of individual high-order morphological brain network

BackgroundMajor depressive disorder (MDD) is an overbroad and heterogeneous diagnosis with no reliable or quantifiable markers. We aim to combine machine-learning techniques with the individual minimum spanning tree of the morphological brain network (MST-MBN) to determine whether the network properties can provide neuroimaging biomarkers to identify patients with MDD. MethodEight morphometric features of each region of interest (ROI) were extracted from 3D T1 structural images of 106 patients with MDD and 97 healthy controls. Six feature distances of the eight morphometric features were calculated to generate a feature distance matrix, which was defined as low-order MBN. Further linear correlations of feature distances between ROIs were calculated on the basis of low-order MBN to generate individual high-order MBN. The Kruskal's algorithm was used to generate the MST to obtain the core framework of individual low-order and high-order MBN. The regional and global properties of the individual MSTs were defined as the feature. The support vector machine and back-propagation neural network was used to diagnose MDD and assess its severity, respectively. ResultThe low-order and high-order MST-MBN constructed by cityblock distance had the excellent classification performance. The high-order MST-MBN significantly improved almost 20 % diagnostic accuracy compared with the low-order MST-MBN, and had a maximum R2 value of 0.939 between the predictive and true Hamilton Depression Scale score. The different group-level connectivity strength mainly involves the central executive network and default mode network (no statistical significance after FDR correction). ConclusionWe proposed an innovative individual high-order MST-MBN to capture the cortical high-order morphological correlation and make an excellent performance for individualized diagnosis and assessment of MDD.

Securely Computing the Manhattan Distance under the Malicious Model and Its Applications

Manhattan distance is mainly used to calculate the total absolute wheelbase of two points in the standard coordinate system. The secure computation of Manhattan distance is a new geometric problem of secure multi-party computation. At present, the existing research secure computing protocols for Manhattan distance cannot resist the attack of malicious participants. In the real scene, the existence of malicious participants makes it necessary to study a solution that can resist malicious attacks. This paper first analyzes malicious attacks of the semi-honest model protocol of computing Manhattan distance and then designs an advanced protocol under the malicious model by using the Goldwasser–Micali encryption system and Paillier encryption algorithm, and utilizing some cryptographic tools such as the cut-choose method and zero-knowledge proof. Finally, the real/ideal model paradigm method is used to prove the security of the malicious model protocol. Compared with existing protocols, the experimental simulation shows that the proposed protocol can resist malicious participant attacks while maintaining high efficiency. It has practical value.

A Joint Stacked Autoencoder Approach with Silhouette Information for Industrial Fault Detection

Due to the growing complexity of industrial processes, it is no longer adequate to perform precise fault detection based solely on the global information of process data. In this study, a silhouette stacked autoencoder (SiSAE) model is constructed for process data by considering both global/local information and silhouette information to depict the link between local/cross-local. Three components comprise the SiSAE model: hierarchical clustering, silhouette loss, and the joint stacked autoencoder (SAE). Hierarchical clustering is used to partition raw data into many blocks, which clarifies the information’s characteristics. To account for silhouette information between data, a silhouette loss function is constructed by raising the inner block’s data distance and decreasing the distance of the cross-center block. Each data block has a properly sized SAE model and is jointly trained via silhouette loss to extract features from all available data. Using the Tennessee Eastman (TE) benchmark and semiconductor industrial process data, the proposed method is validated. Comparative tests on the TE benchmark indicate that the average rate of fault identification increases from 75.8% to 83%, while the average rate of false detection drops from 4.6% to 3.9%.

KLASIFIKASI KABUPATEN/KOTA DI INDONESIA BERDASARKAN TINGKAT KEDALAMAN DAN KEPARAHAN KEMISKINAN MENGGUNAKAN NAÏVE BAYES CLASSIFIER DAN K-NEAREST NEIGHBOR

Poverty is a complex problem, because it involves many other fields. Indonesia as a developing country with 514 districts/cities so far has not been able to solve the problem of poverty. The poverty level can be seen from the value of the poverty depth index and the poverty severity index. It is necessary to classify it, to find out which districts/cities have a high or low poverty rate seen from the two index values. The poverty rate can also be influenced by several factors such as the number of poor people, the percentage of poor people, adjusted per capita expenditure, and the average length of schooling. In this study, the classification is carried out using the Naïve Bayes Classifier and K-nearest Neighbor methods. Both methods are carried out by dividing the training data and testing data by 60%: 40%, 70%:30%, and 80%:20%. In addition, samples were randomized using the functions set.seed(6), set.seed(99), and set.seed(123). In K-nearest Neighbor using the number of neighbors k = 3, k = 5, k = 7, and k = 9 with Euclid distance and Manhattan distance. The results of the analysis with both methods obtained that the Naïve Bayes Classifier method is better used than the K-nearest Neighbor. The results of the highest average accuracy on the poverty depth index and poverty severity index occur in the data splitting of 60%: 40% with an average accuracy of 89.47% and 87.80%, respectively.

Odd-Distance Sets and Right-Equidistant Sequences in the Maximum and Manhattan Metrics

Odd-Distance Sets and Right-Equidistant Sequences in the Maximum and Manhattan Metrics

Smoothing and adaptation of shifted Pólya tree ensembles

Recently, S. Arlot and R. Genuer have shown that a random forest model outperforms its single-tree counterpart in estimating α-Hölder functions, 1≤α≤2. This backs up the idea that ensembles of tree estimators are smoother estimators than single trees. On the other hand, most positive optimality results on Bayesian tree-based methods assume that α≤1. Naturally, one wonders whether Bayesian counterparts of forest estimators are optimal on smoother classes, just as observed with frequentist estimators for α≤2. We focus on density estimation and introduce an ensemble estimator from the classical (truncated) Pólya tree construction in Bayesian nonparametrics. Inspired by the work mentioned above, the resulting Bayesian forest estimator is shown to lead to optimal posterior contraction rates, up to logarithmic terms, for the Hellinger and L1 distances on probability density functions on [0;1) for arbitrary Hölder regularity α>0. This improves upon previous results for constructions related to the Pólya tree prior, whose optimality was only proven when α≤1. Also, by adding a hyperprior on the trees’ depth, we obtain an adaptive version of the prior that does not require α to be specified to attain optimality.

A Novel Error Criterion of Fundamental Matrix Based on Principal Component Analysis

Estimating the fundamental matrix (FM) using the known corresponding points is a key step for three-dimensional (3D) scene reconstruction, and its uncertainty directly affects camera calibration and point-cloud calculation. The symmetric epipolar distance is the most popular error criterion for estimating FM error, but it depends on the accuracy, number, and distribution of known corresponding points and is biased. This study mainly focuses on the error quantitative criterion of FM itself. First, the calculated FM process is reviewed with the known corresponding points. Matrix differential theory is then used to derive the covariance equation of FMs in detail. Subsequently, the principal component analysis method is followed to construct the scalar function as a novel error criterion to measure FM error. Finally, three experiments with different types of stereo images are performed to verify the rationality of the proposed method. Experiments found that the scalar function had approximately 90% correlation degree with the Manhattan norm, and greater than 80% with the epipolar geometric distance. Consequently, the proposed method is also appropriate for estimating FM error, in which the error ellipse or normal distribution curve is the reasonable error boundary of FM. When the error criterion value of this method falls into a normal distribution curve or an error ellipse, its corresponding FM is considered to have less error and be credible. Otherwise, it may be necessary to recalculate an FM to reconstruct 3D models.

Selection of Soybean Genotypes under Drought and Saline Stress Conditions Using Manhattan Distance and TOPSIS.

The search for soybean genotypes more adapted to abiotic stress conditions is essential to boost the development and yield of the crop in Brazil and worldwide. In this research, we propose a new approach using the concept of distance (or similarity) in a vector space that can quantify changes in the morphological traits of soybean seedlings exposed to stressful environments. Thus, this study was conducted to select soybean genotypes exposed to stressful environments (saline or drought) using similarity based on Manhattan distance and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. TOPSIS is a multi-criteria decision method for selecting the best alternative using the concept of distance. The use of TOPSIS is essential because the genotypes are not absolutely similar in both treatments. That is, just the distance measure is not enough to select the best genotype simultaneously in the two stress environments. Drought and saline stresses were induced by exposing seeds of 70 soybean genotypes to -0.20 MPa iso-osmotic solutions with polyethylene glycol-PEG 6000 (119.6 g L-1) or NaCl (2.36 g L-1) for 14 days at 25 °C. The germination rate, seedling length, and seedling dry matter were measured. We showed here how the genotypic stability of soybean plants could be quantified by TOPSIS when comparing drought and salinity conditions to a non-stressful environment (control) and how this method can be employed under different conditions. Based on the TOPSIS method, we can select the best soybean genotypes for environments with multiple abiotic stresses. Among the 70 tested soybean genotypes, RK 6813 RR, ST 777 IPRO, RK 7214 IPRO, TMG 2165 IPRO, 5G 830 RR, 98R35 IPRO, 98R31 IPRO, RK 8317 IPRO, CG 7464 RR, and LG 60177 IPRO are the 10 most stable genotypes under drought and saline stress conditions. Owing to high stability and gains with selection verified for these genotypes under salinity and drought conditions, they can be used as genitors in breeding programs to obtain offspring with higher resistance to antibiotic stresses.

Tensor Affinity Learning for Hyperorder Graph Matching

Hypergraph matching has been attractive in the application of computer vision in recent years. The interference of external factors, such as squeezing, pulling, occlusion, and noise, results in the same target displaying different image characteristics under different influencing factors. After extracting the image feature point description, the traditional method directly measures the feature description using distance measurement methods such as Euclidean distance, cosine distance, and Manhattan distance, which lack a sufficient generalization ability and negatively impact the accuracy and effectiveness of matching. This paper proposes a metric-learning-based hypergraph matching (MLGM) approach that employs metric learning to express the similarity relationship between high-order image descriptors and learns a new metric function based on scene requirements and target characteristics. The experimental results show that our proposed method performs better than state-of-the-art algorithms on both synthetic and natural images.

On the consistency of incomplete U-statistics under infinite second-order moments

We derive a consistency result, in the L1-sense, for incomplete U-statistics in the non-standard case where the kernel at hand has infinite second-order moments. Assuming that the kernel has finite moments of order p(≥1), we obtain a bound on the L1 distance between the incomplete U-statistic and its Dirac weak limit, which allows us to obtain, for any fixed p, an upper bound on the consistency rate. Our results hold for most classical sampling schemes that are used to obtain incomplete U-statistics.

On the Challenges of Generating Pixel Art Character Sprites Using GANs

We pose the problem of generating pixel art character sprites facing one side (e.g., right), given their images facing another one (e.g., front), as an image-to-image translation task and investigate the use of the Pix2Pix architecture to solve it. Aiming to improve the results over unseen data, we propose and investigate two architecture modifications: (a) representing images using color palettes and (b) adding a histogram loss term to the generator. We compared the results qualitatively and quantitatively using FID and L1 distances between the generated and target images. Results indicate that representing images with color palettes encourages overfitting, and the histogram loss leads to slightly improved results.

Performance Comparison of Spectral Distance Calculation Methods.

Circular dichroism (CD) spectroscopy is a widely used technique for assessing the higher-order structure (HOS) of biopharmaceuticals, including antibody drugs. Since the International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use established quality control guidelines, objective evaluation of spectral similarity has been required in order to assess structural comparability. Several spectral distance quantification methods and weighting functions to increase sensitivity have been proposed, but not many reports have compared their performance for CD spectra. We constructed comparison sets that combine actual spectra and simulated noise and performed a comprehensive performance evaluation of each spectral distance calculation method and weighting function under conditions that consider spectral noise and fluctuations from pipetting errors. The results showed that using the Euclidean distance or Manhattan distance with Savitzky-Golay noise reduction is effective for spectral distance assessment. For the weighting function, it is preferable to combine the spectral intensity weighting function and the noise weighting function. In addition, the introduction of the external stimulus weighting function should be considered to improve the sensitivity. It is crucial to select the weighting function based on the balance between spectral changes and noise distributions for robust, sensitive antibody HOS similarity assessment.

Sliding window based ON/OFF flow watermarking on Tor

To analyze traffic in the anonymity network, an active network flow watermark scheme, the ON/OFF watermarking, is proposed to embed timing information into the network flow. This scheme exploits a technique that drops packets at prescribed time intervals to create a watermark sequence at the sending side of a flow, then extracts inter-packet delay at the receiving side, and computes the L1 distance between generated sequences to identify the network flow. A sliding window based L1 distance computation algorithm is proposed to detect flow watermark at a low overhead. Experimental results demonstrate that this timing-based flow watermarking scheme can identify watermarks efficiently and is resistant to timing disturbances in Tor.

Efficient Classification Techniques in Classifying Human Intestinal Parasite Ova

Helminth parasites live in the human body and can cause serious health problems that will lead to cancer and may cause death in patients. These parasitic helminths congregate in the intestines to mate and produce ova. Therefore, early identification screening is necessary to prevent the spread of helminth parasites throughout the body. A manual microscopic feces test is still the most often used approach for helminth detection. As a result, the purpose of this research is to investigate the effectiveness of three classifiers in classifying four types of human intestinal parasite ova. Three classifier techniques used are k-Nearest Neighbourhood (k-NN), Support Vector Machine (SVM), and Ensemble classifier. There are four types of helminth ova which are Ascaris Lumbricoides Ova (ALO), Enterobius Vermicularis Ova (EVO), Hookworm Ova (HWO), and Trichuris Trichiura Ova (TTO). A total of 664 helminth parasite ova images were analyzed, consisting of 166 images from each helminth species. The Linear kernel function from the SVM classifier has obtained the highest accuracy performance reaching 92.23%. Followed by Cityblock distance from the k-NN classifier with an accuracy of 91.16% and AdaBoostM2 from the Ensemble classifier with an accuracy of 89.94%.

Image processing for maturity classification of tomato using otsu and manhattan distance methods

Currently, image processing-based systems have been widely applied in various fields, one of which is agriculture. The system can be used to classify fruit maturity. Tomato is one of the agricultural products consumed by the community. Therefore, the requirement for ripe tomatoes increases. In this work, the classification method based on image processing for grading the maturity level of tomato was developed to distinguish tomato into three classes: unripe, half-ripe, and ripe. Classification is carried out based on the skin color of the tomato. The method required five main processes; initially, the detection of the region of interest (ROI) applied using the Otsu method followed by the conversion of RGB to HSV color space. Afterward, segmentation with Otsu thresholding on the S channel of the HSV color space was implemented. Subsequently, the extraction of the mean, median, max, and min features on each channel from the YIQ color space; therefore, a total number of 12 features was produced. Finally, the K-nearest neighbor (KNN) method using Manhattan distance is applied with the values of k = 1, 3, 5, 7, and 9. The dataset used consists of 90 images of tomatoes (30 raws, 30 half-ripes, and 30 ripes), where the dataset is divided into two types, including 54 images as training data and 36 images as testing data. The evaluation results were able to achieve the highest accuracy value of 0.9722.

PV-RCNN++: semantical point-voxel feature interaction for 3D object detection

Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing on informative areas to produce accurate 3D object detection results. This paper proposes a novel object detection network by semantical point-voxel feature interaction, dubbed PV-RCNN++. Unlike most of existing methods, PV-RCNN++ explores the semantic information to enhance the quality of object detection. First, a semantic segmentation module is proposed to retain more discriminative foreground keypoints. Such a module will guide our PV-RCNN++ to integrate more object-related point-wise and voxel-wise features in the pivotal areas. Then, to make points and voxels interact efficiently, we utilize voxel query based on Manhattan distance to quickly sample voxel-wise features around keypoints. Such the voxel query will reduce the time complexity from O(N) to O(K), compared to the ball query. Further, to avoid being stuck in learning only local features, an attention-based residual PointNet module is designed to expand the receptive field to adaptively aggregate the neighboring voxel-wise features into keypoints. Extensive experiments on the KITTI dataset show that PV-RCNN++ achieves 81.60\(\%\), 40.18\(\%\), 68.21\(\%\) 3D mAP on Car, Pedestrian, and Cyclist, achieving comparable or even better performance to the state-of-the-arts.

How does the structure of data impact cell-cell similarity? Evaluating how structural properties influence the performance of proximity metrics in single cell RNA-seq data.

Accurately identifying cell-populations is paramount to the quality of downstream analyses and overall interpretations of single-cell RNA-seq (scRNA-seq) datasets but remains a challenge. The quality of single-cell clustering depends on the proximity metric used to generate cell-to-cell distances. Accordingly, proximity metrics have been benchmarked for scRNA-seq clustering, typically with results averaged across datasets to identify a highest performing metric. However, the 'best-performing' metric varies between studies, with the performance differing significantly between datasets. This suggests that the unique structural properties of an scRNA-seq dataset, specific to the biological system under study, have a substantial impact on proximity metric performance. Previous benchmarking studies have omitted to factor the structural properties into their evaluations. To address this gap, we developed a framework for the in-depth evaluation of the performance of 17 proximity metrics with respect to core structural properties of scRNA-seq data, including sparsity, dimensionality, cell-population distribution and rarity. We find that clustering performance can be improved substantially by the selection of an appropriate proximity metric and neighbourhood size for the structural properties of a dataset, in addition to performing suitable pre-processing and dimensionality reduction. Furthermore, popular metrics such as Euclidean and Manhattan distance performed poorly in comparison to several lessor applied metrics, suggesting that the default metric for many scRNA-seq methods should be re-evaluated. Our findings highlight the critical nature of tailoring scRNA-seq analyses pipelines to the dataset under study and provide practical guidance for researchers looking to optimize cell-similarity search for the structural properties of their own data.

Sizing and Sitting of Battery Energy Storage Systems in Distribution Networks with Transient Stability Consideration

In this study, the capacity and location of battery energy storage systems (BESSs) in a distribution network were evaluated to increase the stability and reliability of power systems by applying the proposed transient stability indicators. The search capability of particle swarm optimization (PSO) combined with Pareto optimality in MATLAB R2019b was used to solve multi-objective problems in steady-state conditions, including active power loss, voltage deviation, and total operating cost. The BESS capacity and location were then derived using the Manhattan distance method. Subsequently, the BESS control model was constructed using the commercial software DIgSILENT PowerFactory 2021 to evaluate generator power smoothing and short-term voltage stability index during the transient response and determine the final capacity and location of BESS in distribution networks. Finally, the accuracy of the proposed method was verified by considering the daily load and solar power generation curves using the IEEE 33-bus radial power distribution network.

A New Method for Determining the Embedding Dimension of Financial Time Series Based on Manhattan Distance and Recurrence Quantification Analysis.

Identification of embedding dimension is helpful to the reconstruction of phase space. However, it is difficult to calculate the proper embedding dimension for the financial time series of dynamics. By this Letter, we suggest a new method based on Manhattan distance and recurrence quantification analysis for determining the embedding dimension. By the advantages of the above two tools, the new method can calculate the proper embedding dimension with the feature of stability, accuracy and rigor. Besides, it also has a good performance on the chaotic time series which has a high-dimensional attractors.