Discriminative Space Research Articles

Dynamic Target Tracking Method Based on Medical Imaging

The cross fusion of rehabilitation medicine and computer graphics is becoming a research hotspot. Due to the problems of low definition and unobvious features of the initial video data of medical images, the initial data is filtered and enhanced by adding image preprocessing, including image rotation and contrast enhancement, in order to improve the performance of the tracking algorithm. For the moving barium meal, the discrete point tracking and improved inter frame difference method are proposed; for the position calibration of tissues and organs, the Kernel Correlation Filter (KCF) and Discriminative Scale Space Tracker (DSST) correlation filtering method and the corresponding multi-target tracking method are proposed, and the experimental results show that the tracking effect is better. The two algorithms modify each other to further improve the accuracy of calibration and tracking barium meal flow and soft tissue organ motion, and optimize the whole swallowing process of moving target tracking model.

AKSESIBILITAS PENDIDIKAN GRATIS BAGI MASYARAKAT MISKIN PADA SEKOLAH SWASTA ISLAMIC BOARDING SCHOOL DI ACEH

The high interest of the Acehnese people towards education at private Islamic Boarding School schools, namely the integrated dayah, provides space for discrimination between students who are able and those who cannot. The purpose of this study was to examine access to policy and budget for the poor in obtaining education at integrated dayahs in Aceh. The research method uses a descriptive qualitative approach with data collection techniques by interview and documentation. The results found are in the formal legal aspect, accessibility from the central government is obtained by the poor, namely the existence of BOS and PIP, while the regional government of Aceh province is scholarship assistance for orphans, orphans, orphans and orphans but not specifically for the poor, while the internal Dayah policy is integrated is to determine their own policies such as the foster parent program, maximizing business entities implementing zakat mal dayah. In terms of budget sources, it can be seen from the APBN, DIPA and integrated Dayah internal finance.

Social Media Analysis and Strategic Recommendations for a Non-Profit Organization in Germany

Nowadays it is impossible to imagine life without social media - Facebook, Instagram and Co. have become important platforms for public discourse, political communication and opinion-forming.
 Not only for companies, but also for nonprofit organizations (NPO), networking via social media creates potential. On the one hand, they offer a cost-effective dialog opportunity to address many interested parties and new target groups. On the other hand, the interaction of high-quality content and strategically planned social media posts not only gains reach, but also members and donations for the organization. At the same time, social media opens up space for hate speech, discrimination and racism, which is why a strategy to steadfastly counter negative reactions online is becoming increasingly important for nonprofit organizations as well.
 The purpose of this paper is to examine how the regional nonprofit organization in the welfare sector – German Red Cross district association in Leipzig and the surrounding region – is targeting social media communications to achieve its established goals of recruitment and fundraising.
 Unlike previous studies that focus on single social media platforms, this study examines the use of multiple social media platforms. This study included a qualitative analysis. We used qualitative content analysis (Mayring, 2015) to gain in-depth findings into the social media work of the NPO and its competitors.
 In the first step, competitors of the NPO were selected for the analysis based on their activities on the social media profiles on Facebook, Instagram, Twitter and YouTube. For the selection of the competitors, own selection measures were chosen in order to make a suitable sample selection. Content categorization was used to interpret information within the social media profiles. The focus was on the textual and visual design of the social media accounts and individual posts of the competitors. For this purpose, the period of data collection included the months of June and September 2020. In summary, posts from 17 social media profiles were considered in the analysis, and we analyzed 21 Facebook posts, 12 Instagram posts, 15 tweets, and 20 YouTube videos.
 Based on the results, a strategic approach for the social media work of the non-profit organization could be developed in the form of recommendations for action. In addition, more donation campaigns are to be included in social media. Emotional storytelling leads to more interactions, which can generate a higher willingness to donate.

Class-specific discriminative metric learning for scene recognition

Metric learning aims to learn an appropriate distance metric for a given machine learning task. Despite its impressive performance in the field of image recognition, it may still not be discriminative enough for scene recognition because of the high within-class diversity and high between-class similarity of scene images. In this paper, we propose a novel class-specific discriminative metric learning method (CSDML) to alleviate these problems. More specifically, we learn a distinctive linear transformation for each class (or, equivalently, a Mahalanobis distance metric for each class), which allows to project the samples of that class into a corresponding low-dimensional discriminative space. The overall aim is to simultaneously minimize the Euclidean distances between the projections of samples of the same class (or, equivalently, the Mahalanobis distances between these samples) and maximize the Euclidean distances between the projections of samples of different classes. Additionally, we incorporate least squares regression into the optimization problem, rendering class-specific metric learning more flexible and better suited to tackle scene recognition. Experimental results on four benchmark scene datasets demonstrate that the proposed method outperforms most of the state-of-the-art approaches.

Проблемы реализации охранительной функции государства в сфере защиты прав человека в цифровом пространстве

Digitalization of all spheres of life of society and the state has actualized the problems that arise when the state implements its protective function in the field of human rights protection in conditions. The special signi-ficance of these issues is due to the consolidation in the Constitution of the Russian Federation of ensuring the security of the individual, society and the state in the application of information technologies, the circulation of digital data as an independent subject of the Russian Federation in the field of defense and security. The purpose of this study was to substantiate the hypothesis of the need for the state to take systemic measures aimed at ensuring the digital security of the individual, society and the state. The methodological basis of the study was the dialectical method of cognition of the considered socio-legal phenomena. In addition, when writing the article, the following methods were used: the logical method used in determining the sequence of presentation of the material and the formulation of conclusions, the method of system analysis, the method of modeling, the structural and functional method, as well as the method of referring to the conclusions of the theory of human rights. The paper analyzes the main directions of the implementation of the protective function of the state in this area, to which the author refers: ensuring the safety of personal data of citizens obtained as a result of information exchange, and the exclusion of their use for illegal purposes; compliance with labor and other social rights of citizens in the conditions of their involvement in new digital forms of economic activity, in particular, when interaction with digital platforms; gradual and reasonable introduction of digital document management while preserving its traditional forms; ensuring the digital sovereignty of the state and taking measures to prevent the use of the digital information space for discrimination against Russian citizens, disinformation and destructive activities. The author substantiates the need for specific measures that the state can and should take as part of the implementation of its protective function to neutralize and reduce risks in the field of ensuring and protecting human rights in the digital space. The results of the conducted research can be applied in standard-setting and law enforcement activities in the field of implementation of the state policy on ensuring digital security, as well as in further scientific research in this area of law.

Latent Discriminative Space with Inline Constraints Cross-Modal Hashing

Latent Discriminative Space with Inline Constraints Cross-Modal Hashing

Deep learning for prediction of depressive symptoms in a large textual dataset

Depression is a common illness worldwide with potentially severe implications. Early identification of depressive symptoms is a crucial first step towards assessment, intervention, and relapse prevention. With an increase in data sets with relevance for depression, and the advancement of machine learning, there is a potential to develop intelligent systems to detect symptoms of depression in written material. This work proposes an efficient approach using Long Short-Term Memory (LSTM)-based Recurrent Neural Network (RNN) to identify texts describing self-perceived symptoms of depression. The approach is applied on a large dataset from a public online information channel for young people in Norway. The dataset consists of youth’s own text-based questions on this information channel. Features are then provided from a one-hot process on robust features extracted from the reflection of possible symptoms of depression pre-defined by medical and psychological experts. The features are better than conventional approaches, which are mostly based on the word frequencies (i.e., some topmost frequent words are chosen as features from the whole text dataset and applied to model the underlying events in any text message) rather than symptoms. Then, a deep learning approach is applied (i.e., RNN) to train the time-sequential features discriminating texts describing depression symptoms from posts with no such descriptions (non-depression posts). Finally, the trained RNN is used to automatically predict depression posts. The system is compared against conventional approaches where it achieved superior performance than others. The linear discriminant space clearly reveals the robustness of the features by generating better clustering than other traditional features. Besides, since the features are based on the possible symptoms of depression, the system may generate meaningful explanations of the decision from machine learning models using an explainable Artificial Intelligence (XAI) algorithm called Local Interpretable Model-Agnostic Explanations (LIME). The proposed depression symptom feature-based approach shows superior performance compared to the traditional general word frequency-based approaches where frequency of the features gets more importance than the specific symptoms of depression. Although the proposed approach is applied on a Norwegian dataset, a similar robust approach can be applied on other depression datasets developed in other languages with proper annotations and symptom-based feature extraction. Thus, the depression prediction approach can be adopted to contribute to develop better mental health care technologies such as intelligent chatbots.

Constrained mutual convex cone method for image set based recognition

In this paper, we propose convex cone-based frameworks for image-set classification. Image-set classification aims to classify a set of images, usually obtained from video frames or multi-view cameras, into a target object. To accurately and stably classify a set, it is essential to accurately represent structural information of the set. There are various image features, such as histogram-based features and convolutional neural network features. We should note that most of them have non-negativity and thus can be effectively represented by a convex cone. This leads us to introduce the convex cone representation to image-set classification. To establish a convex cone-based framework, we mathematically define multiple angles between two convex cones, and then use the angles to define the geometric similarity between them. Moreover, to enhance the framework, we introduce two discriminant spaces. We first propose a discriminant space that maximizes gaps between cones and minimizes the within-class variance. We then extend it to a weighted discriminant space by introducing weights on the gaps to deal with complicated data distribution. In addition, to reduce the computational cost of the proposed methods, we develop a novel strategy for fast implementation. The effectiveness of the proposed methods is demonstrated experimentally by using five databases.

Dynamic Time Warping-Based Features With Class-Specific Joint Importance Maps for Action Recognition Using Kinect Depth Sensor

This paper proposes a novel 3D action recognition technique that uses time-series information extracted from depth image sequences for use in systems of human daily activity monitoring. To this end, each action is represented as a multi-dimensional time series, where each dimension represents the position variation of one skeleton joint over time. The time series is then mapped onto a vector space using Dynamic Time Warping (DTW) distance. Furthermore, to employ the correlation-distinctiveness relationship of the sequences in recognition, this vector space is remapped onto a discriminative space using the regularized Fisher method, where final decisions about the actions are made. Unlike other available methods, the time-warping used in the mapping strategy makes the feature space robust to temporal variations of the motion sequences. Moreover, our method eliminates the need for a complicated design method for extracting the static and dynamic information of a motion sequence. Furthermore, most existing methods treat all skeletal joints identically for different actions, while some joints are more discriminative to distinguish a specific action. Thanks to the nature of the proposed features, we propose to use a separate set of discriminative joints, called joint importance map for each class of action. Evaluation results on four well-known datasets, TST, UTKinect, UCFKinect, and NTU RGB+D show competitive performance with the state-of-the-art methods in human action recognition.

IEEE Access Special Section Editorial: Feature Representation and Learning Methods With Applications in Large-Scale Biological Sequence Analysis

Machine learning has been widely applied in the fields of biomedicine, computational biology, bioinformatics, image processing, and so on. The performance of machine learning methods mainly relies on feature representation that is the mapping from various types of raw data (i.e., image and genomic data) to a discriminant high-dimensional data space, bridging the raw data with the input of learning/inference algorithms. A good representation is often one that captures the discriminative information from the data and supports effective machine learning. However, over the last few decades, most representation learning approaches are labor-intensive and heavily dependent on the professional knowledge of researchers (dependent on handcrafted feature engineering). To conduct more novel applications in bioinformatics and biomedicine, the weakness of current learning algorithms should be overcome by developing novel feature representation learning algorithms, including supervised representation learning algorithms that are learning features from labeled data, unsupervised feature representation strategies that are learning feature representatives from unlabeled data, and deep feature representation learning algorithms that are learning representative features from data using deep learning architectures.

Visual Object Multimodality Tracking Based on Correlation Filters for Edge Computing

In recent years, visual object tracking has become a very active research field which is mainly divided into the correlation filter-based tracking and deep learning (e.g., deep convolutional neural network and Siamese neural network) based tracking. For target tracking algorithms based on deep learning, a large amount of computation is required, usually deployed on expensive graphics cards. However, for the rich monitoring devices in the Internet of Things, it is difficult to capture all the moving targets in each device in real time, so it is necessary to perform hierarchical processing and use tracking based on correlation filtering in insensitive areas to alleviate the local computing pressure. In sensitive areas, upload the video stream to a cloud computing platform with a faster computing speed to perform an algorithm based on deep features. In this paper, we mainly focus on the correlation filter-based tracking. In the correlation filter-based tracking, the discriminative scale space tracker (DSST) is one of the most popular and typical ones which is successfully applied to many application fields. However, there are still some improvements that need to be further studied for DSST. One is that the algorithms do not consider the target rotation on purpose. The other is that it is a very heavy computational load to extract the histogram of oriented gradient (HOG) features from too many patches centered at the target position in order to ensure the scale estimation accuracy. To address these two problems, we introduce the alterable patch number for target scale tracking and the space searching for target rotation tracking into the standard DSST tracking method and propose a visual object multimodality tracker based on correlation filters (MTCF) to simultaneously cope with translation, scale, and rotation in plane for the tracked target and to obtain the target information of position, scale, and attitude angle at the same time. Finally, in Visual Tracker Benchmark data set, the experiments are performed on the proposed algorithms to show their effectiveness in multimodality tracking.

Cross-modal discriminant adversarial network

Cross-modal retrieval aims at retrieving relevant points across different modalities, such as retrieving images via texts. One key challenge of cross-modal retrieval is narrowing the heterogeneous gap across diverse modalities. To overcome this challenge, we propose a novel method termed as Cross-modal discriminant Adversarial Network (CAN). Taking bi-modal data as a showcase, CAN consists of two parallel modality-specific generators, two modality-specific discriminators, and a Cross-modal Discriminant Mechanism (CDM). To be specific, the generators project diverse modalities into a latent cross-modal discriminant space. Meanwhile, the discriminators compete against the generators to alleviate the heterogeneous discrepancy in this space, i.e., the generators try to generate unified features to confuse the discriminators, and the discriminators aim to classify the generated results. To further remove the redundancy and preserve the discrimination, we propose CDM to project the generated results into a single common space, accompanying with a novel eigenvalue-based loss. Thanks to the eigenvalue-based loss, CDM could push as much discriminative power as possible into all latent directions. To demonstrate the effectiveness of our CAN, comprehensive experiments are conducted on four multimedia datasets comparing with 15 state-of-the-art approaches.

Differentiation of endangered butter catfish, Ompok bimaculatus populations along the selected habitats of South-western Bangladesh: Evidence from morphological characters

The intraspecific morphological variations of the butter catfish, Ompok bimaculatus has been assessed from two fish farms viz., Chanchra Fish Farm, Jashore (CFFJ) and Fish Seed Complex, Khulna (FSCK) and two natural wetlands viz., Bohni beel, Gopalganj (BBG); Dakatia beel, Khulna (DBK) in the south-western part of Bangladesh. A total number of 80 samples were collected comprising 20 individuals from each sampling location. Five meristic characters, 18 morphometric characters and 21 truss-based morphometric characters were measured respectively. Meristic, morphometric and truss-based morphometric characters were exposed to one-way analysis of variance followed by Tukey-HSD post-hoc test at 5% significance level. Significant differences were observed in two meristic characters viz., CFR and PevFR, and five morphometric and four truss morphometric characters. However, morphometric and truss measurements showed highly intermingled among four populations in discriminant functions (DFs) analysis and discriminant space as well. DFs showed that 6-7, PrDL, HL, PSDL, 1-2, 4-6, FL, ED, 3-9, 5-6, SnL and 4-5 characters contributed 62.8% in first DF, while 2-9, HD, 1-9, 2-3, 2-6, 3-6, 3-4, LAB, 3-8, 9-10, IO and MXBLR characters contributed 20.6% in second DF, and the remaining characters contributed 16.6% in third DF. In cluster analysis, two distinct clusters were made, where BBG demonstrated a solitary group, and FSCK and CFFJ jointly shaped alternative clusters, while the DBK population found a subgroup with CFFJ. These results postulate the occurrence of intermingling populations of this species from four aquatic habitats. These morphological discrepancies play an important role in establishing proper decisions in order to achieve appropriate management and conservation as well as mass seed production for their future sustainability.

Sustainable Development of Polish Macroregions-Study by Means of the Kernel Discriminant Coordinates Method.

The aim of this study was to investigate if the macroregions of Poland are homogeneous in terms of the observed spatio-temporal data characterizing their sustainable development. So far, works related to the sustainable development of selected territorial units have been based on data relating to a specific year rather than many years. The solution to the problem of macroregion homogeneity goes through two stages. In step one, the original spatio-temporal data space (matrix space) was transformed into a kernel discriminant coordinates space. The obtained kernel discriminant coordinates function as synthetic measures of the level of sustainable development of Polish macroregions. These measures contain complete information on the values of 27 diagnostic features examined over 15 years. In the second step, cluster analysis was used in order to identify groups of homogeneous macroregions in the space of kernel discriminant coordinates. The agglomeration method and the Ward method were chosen as commonly used methods. By means of both methods, three super macroregions composed of homogeneous macroregions were identified. Within the kernel discriminant coordinates, the differentiating power of a selected set of 27 features characterizing the sustainable development of macroregions was also assessed. To this end, five different and most commonly used methods of discriminant analysis were used to test the correctness of the classification. Depending on the method, the classification errors amounted to zero or were close to zero, which proves a well-chosen set of diagnostic features. Although the data relate only to a specific country (Poland), the presented statistical methodology is universal and can be applied to any territorial unit and spatial-temporal dynamic data.

A Collaborative Dictionary Learning Model for Nasopharyngeal Carcinoma Segmentation on Multimodalities MR Sequences.

Nasopharyngeal carcinoma (NPC) is the most common malignant tumor of the nasopharynx. The delicate nature of the nasopharyngeal structures means that noninvasive magnetic resonance imaging (MRI) is the preferred diagnostic technique for NPC. However, NPC is a typically infiltrative tumor, usually with a small volume, and thus, it remains challenging to discriminate it from tightly connected surrounding tissues. To address this issue, this study proposes a voxel-wise discriminate method for locating and segmenting NPC from normal tissues in MRI sequences. The located NPC is refined to obtain its accurate segmentation results by an original multiviewed collaborative dictionary classification (CODL) model. The proposed CODL reconstructs a latent intact space and equips it with discriminative power for the collective multiview analysis task. Experiments on synthetic data demonstrate that CODL is capable of finding a discriminative space for multiview orthogonal data. We then evaluated the method on real NPC. Experimental results show that CODL could accurately discriminate and localize NPCs of different volumes. This method achieved superior performances in segmenting NPC compared with benchmark methods. Robust segmentation results show that CODL can effectively assist clinicians in locating NPC.

Fukunaga\u2013Koontz Convolutional Network with Applications on Character Classification

Several convolutional neural network architectures have been proposed for handwritten character recognition. However, most of the conventional architectures demand large scale training data and long training time to obtain satisfactory results. These requirements prevent the use of these methods in a broader range of applications. As an alternative to cope with these problems, we present a new convolutional network for handwritten character recognition based on the Fukunaga–Koontz transform (FKT). Our approach lies in the assumption that Fukunaga–Koontz convolutional kernels can be efficiently learned from subspaces and directly employed to produce high discriminant features in a shallow network architecture. When representing image classes by subspaces, the within-class separability is reduced, since the subspaces form clusters in a low-dimensional space. To increase the between-class separability, we compute a discriminative space from the training subspaces using FKT. By learning convolutional kernels from subspaces, it is possible to extract representative and discriminative features from an image with only a few parameters. Another contribution of the proposed network is the use of pooling layers, which further improves its performance. The proposed method, called Fukunaga–Koontz Network (FKNet), is suitable for solving practical problems, especially when training and processing times are constraints. Four publicly available handwritten character datasets are employed to evaluate the advantages of FKNet. In addition, we demonstrate the flexibility of the proposed method by experiments on LFW dataset.

Novel deep neural network based pattern field classification architectures

Field classification is a new extension of traditional classification frameworks that attempts to utilize consistent information from a group of samples (termed fields). By forgoing the independent identically distributed (i.i.d.) assumption, field classification can achieve remarkably improved accuracy compared to traditional classification methods. Most studies of field classification have been conducted on traditional machine learning methods. In this paper, we propose integration with a Bayesian framework, for the first time, in order to extend field classification to deep learning and propose two novel deep neural network architectures: the Field Deep Perceptron (FDP) and the Field Deep Convolutional Neural Network (FDCNN). Specifically, we exploit a deep perceptron structure, typically a 6-layer structure, where the first 3 layers remove (learn) a ‘style’ from a group of samples to map them into a more discriminative space and the last 3 layers are trained to perform classification. For the FDCNN, we modify the AlexNet framework by adding style transformation layers within the hidden layers. We derive a novel learning scheme from a Bayesian framework and design a novel and efficient learning algorithm with guaranteed convergence for training the deep networks. The whole framework is interpreted with visualization features showing that the field deep neural network can better learn the style of a group of samples. Our developed models are also able to achieve transfer learning and learn transformations for newly introduced fields. We conduct extensive comparative experiments on benchmark data (including face, speech, and handwriting data) to validate our learning approach. Experimental results demonstrate that our proposed deep frameworks achieve significant improvements over other state-of-the-art algorithms, attaining new benchmark performance.

Implicit Bias and Discrimination

AbstractRecent social‐psychological research suggests that a considerable amount of, for example, racial and gendered discrimination may be connected to implicit biases: mental processes beyond our direct control or endorsement, that influence our behaviour toward members of socially salient groups. In this article I seek to improve our understanding of the phenomenon of implicit bias, including its moral status, by examining it through the lens of a theory of discrimination. In doing so, I also suggest ways to improve this theory of discrimination, by creating conceptual space for implicit bias discrimination. I explore two ways of distinguishing direct and indirect discrimination and spell out the resulting four different forms of discrimination. The resulting taxonomy provides some room for implicit bias discrimination. I also deal with four challenges to my proposal for capturing implicit bias within discrimination theory: the metaphysical challenge, the moral insignificance challenge, the causal connection challenge, and the challenge from irreducibly collective bias.

A Discriminative Projection and Representation-Based Classification Framework for Face Recognition

The sparse representation-based classifier (SRC) has been developed and verified as having great potential for real-world face recognition. In this paper, we propose a discriminative projection and representation-based classification (DPRC) method to enhance the discriminant ability of the SRC. The proposed method first obtains a discriminative projection matrix not only maximizing the ratio of the distance within interclass over the distance within intraclass, but also minimizing the linear approximation error within intraclass. Then it maps the original data onto the discriminative space, and adopts an SRC method to obtain the final solution. An inexact augmented Lagrangian method of multiplier is proposed for finding the optimal representation vector in our framework, and a proximal alternating minimization method is adopted to the iteration subproblems of the proposed method. The proposed method is proven to have the subsequence convergence property. Experimental results on Yale, ORL, and AR face image databases demonstrate that, compared with some existing feature extraction methods based on the SRC, the proposed DPRC method is more efficient.

Differentiation of intraspecific phenotypic plasticity of elongate glassy perchlet, Chanda nama: Insights into landmark-based truss morphometric and meristic variations.

Objective:Understanding intraspecific phenotypic plasticity is a prerequisite to fish stock identification and sustainable fisheries management. In this study, we assessed intraspecific phenotypic plasticity in terms of meristic and morphometric characters of wild populations of elongate glassy perchlet, Chanda nama from two different rivers, namely Madhumati River – Narail (MRN) and Tulshiganga River – Jaypurhat (TRJ), and an ox-bow lake, Jhapa Baor – Jashore (JBJ) in Bangladesh.Materials and Methods:In this study, six meristics, 15 conventional morphometrics, and 23-truss-based morphometrics were subjected to a one-way analysis of variance (ANOVA), followed by the Tukey-HSD test. The mean values of three meristic counts and nine conventional and 12 truss-based morphometrics demonstrated significant differences in the ANOVA test. Furthermore, principal component analysis (PCA) and discrimination function analysis (DFA) were performed separately using conventional and truss-based morphometric data.Results:In PCA analysis, four principal components were extracted and cumulatively demonstrated 51.848%. On the contrary, two discriminant functions (DF1, 63.5%; DF2, 36.5%) resulted from DFA analysis. In the bi-plot alignment from the discriminant space, all individuals were exceedingly separated among the three inhabitants. A dendrogram developed using conventional and truss morphometric characters confirmed that two clusters were formed among three populations. The TRJ population formed a distinct cluster, and the JBJ population formed a different cluster with a subcluster of MRN. In the discriminant function analysis, precise classification outcomes displayed 82% of individuals into their unique populations, whereas 66.9% of individuals were categorized as a cross-validated assemblage.Conclusion:The baseline information resulting from the current study would be useful for environmental studies and further conservation of glassy perchlet populations in Bangladesh.