Pattern Co-occurrence Research Articles

Re-construction of original face images from plastic surgery images using harmony search algorithm and IRBFN model

Face Reconstruction is the only biometric that allows you to perform passive identification in one to many environments. By changing the geometry and texture of the facial region, there can be an increased intraclass variability between images of an individual before and after surgery. Even so, the nonlinear changes caused by plastic surgery have a hard time being modelled by facial reconstruction systems. An algorithm for plastic surgery face reconstruction is presented here, that uses Harmony Search to confront the challenges involved. A non-disjoint algorithm generates the face granules, each representing different information with varying resolutions and sizes. A Scale-Invariant Feature Transform (SIFT) and Co-occurrence of Adjacent Local Binary Patterns were applied to extract discriminating information from granules of face images. As the concluding step, we used Harmony Search Method (HSM) to combine the various responses to attain the optimal solution. Finally Improved Radial Basis Function Network (IRBFN) algorithm is used for feature matching. The feature matching predict, where the face is recognized or not. The modified method, proposed in this work, has the better performance in classifying more images with higher accuracy. An obtained sensitivity of 100 % and specificity of 97.5 % was achieved by the proposed classifier. The results proved that it is possible to use the developed algorithms understand different pre and post surgical image conditions, evaluate their strength and future development trends, and provide all-facial features basis for detection of pre and post surgical images.

Non-parametric style transfer: Correlation-aware exact distribution matching

Early feed-forward neural methods of arbitrary image style transfer utilized the encoded feature map up to its second-order statistics, i.e., mean and variance (or covariance) of the encoded feature map. Recent methods have begun to utilize feature statistics beyond the 2nd-order statistics, e.g., a higher-order moment, slicing-based method, and histogram matching for better style representation. However, even in the distribution matching of the latest method, considering the channel-correlation and the order of duplicated values in the feature map is missing. This resulted in insufficient style transfer or artifacts on style-transferred images e.g., unexpected color or pattern co-occurrence, skewed color or style pattern into one side, noise between background and foreground, etc. In this work, we show how to make a feature transform layer to consider both channel-correlation and duplicated values in the feature map for exact feature distribution matching in style transfer. Our experimental results prove that the stylized images obtained with our method are more similar to the target style images qualitatively without losing content clearness and superior to the existing methods quantitatively in all possible style measures, e.g., 0.0311 lower sliced Wasserstein distance than the previous method and the most favored choice with 25.54% preference.

Integrated Color and Intensity MSF Scheme for Image Retrieval Systems

Markov Stationary Features (MSF) based on homogeneous Markov chain model, for content-based image analysis, is getting popularity nowadays. It not only considers the distribution of colors, just as the histogram method does, but also characterizes the spatial co-occurrence of histogram patterns. However, handling a large-scale database of images with a degree of heterogeneity, a simple MSF method is not sufficient to discriminate the images as one requires. In this paper, an Integrated Color and Intensity MSF (ICI-MSF) based on non-homogeneous Markov Chain is proposed to overcome this shortcoming. By incorporating spatial co-occurrence of image intensities with the spatial co-occurrence information of colors and exploiting time inhomogeneous Markov chain concept, it is possible to improve certain aspects of the existing methods. Without compromising effectiveness and robustness, the method proposed in this paper keeps the feature level simplicity. Widely recognized databases namely WANG1000 and Corel10800, are used to evaluate and compare the performance of the proposed algorithm with the existing methods. The experimental results justify the effectiveness of the proposed method.

Joint Developmental Trajectories of Likability and Popularity: Associations with Social Behavior among Chinese Adolescents.

The beginning of secondary school is a critical time point of adolescents' development as they entered a new peer context in which social status was re-established. As the key indicators of social status, likability and popularity co-occur but also display distinct developmental trajectories over time. Nevertheless, little is known about the joint developmental trajectories of likability and popularity among adolescents and how identified trajectories are associated with important social behavior. The current study examined the joint developmental trajectories of likability and popularity among Chinese adolescents and their associations with social behavior (prosocial behavior, aggression, and peer victimization) over time. A total of 1509 Chinese 7th grade students (53.6% male, Mage = 13.1, SD = 0.67) participated in self-report and peer nomination assessments on three occasions at 6-month intervals. Parallel process latent growth mixture models revealed four distinct trajectories of likability and popularity: social status decreasing, average, high social status, and social status increasing. The high social status group showed the highest levels of prosocial behavior, the lowest levels of peer victimization, and higher aggression than the average group. The social status decreasing group and social status increasing group exhibited the lower prosocial behavior as well as the higher aggression and peer victimization compared to the average group over time. The findings highlight the co-occurrence but diversity of developmental patterns of likability and popularity in adolescence.

Identifying, exploring, and interpreting time series shapes in multivariate time intervals

We introduce a concept of episode referring to a time interval in the development of a dynamic phenomenon that is characterized by multiple time-variant attributes. A data structure representing a single episode is a multivariate time series. To analyse collections of episodes, we propose an approach that is based on recognition of particular patterns in the temporal variation of the variables within episodes. Each episode is thus represented by a combination of patterns. Using this representation, we apply visual analytics techniques to fulfil a set of analysis tasks, such as investigation of the temporal distribution of the patterns, frequencies of transitions between the patterns in episode sequences, and co-occurrences of patterns of different variables within same episodes. We demonstrate our approach on two examples using real-world data, namely, dynamics of human mobility indicators during the COVID-19 pandemic and characteristics of football team movements during episodes of ball turnover.

Voice spoofing detector: A unified anti-spoofing framework

Voice controlled systems (VCS) in Internet of Things (IoT), speaker verification systems, voice-based biometrics, and other voice-assistant-enabled systems are vulnerable to different spoofing attacks i.e., replay, cloning, cloned-replay, etc. VCS are not only susceptible to these attacks in a non-network environment, but they are also vulnerable to multi-order spoofing attacks in networked IoT. Additionally, deepfakes with artificially generated audio pose a great threat to the all systems having voice-interfaces. Most of the existing countermeasures against these voice spoofing attacks work for only one specific attack (e.g. voice replay) and fail to generalize this for other classes of spoofing attacks. Additionally, generalization is also crucial for cross-corpora evaluation. Thus, there exists a need to develop a unified voice anti-spoofing framework capable of detecting multiple spoofing attacks. This work presents a unified anti-spoofing framework that uses novel (ATCoP-GTCC) features to combat the variety of voice spoofing attacks. The proposed novel acoustic-ternary co-occurrence patterns (ATCoP) encode the co-occurrence of similar patterns between the center and neighboring samples. Our experiments demonstrate that ATCoP can better capture the microphone induced distortions in replays, unnatural prosody and algorithmic artifacts in cloned samples, and both the distortions and artifacts in cloned-replays including compression on multi-hop attacks in the spoofing samples. The performance of ATCoP could be further enhanced by the Gammatone cepstral coefficients. To evaluate the effectiveness of the proposed anti-spoofing system for multi-order replay and cloned-replay attacks detection, we created a diverse voice spoofing detection corpus (VSDC) containing multi-order replay and cloned-replay audios against the bonafide and cloned audio recordings, respectively. Experimental results obtained on VSDC, ASVspoof 2019, Google’s LJ Speech, and YouTube deepfakes datasets illustrate the effectiveness of the proposed system in terms of accurate detection for a variety of voice spoofing attacks.

Long-Term Compost Amendment Changes Interactions and Specialization in the Soil Bacterial Community, Increasing the Presence of Beneficial N-Cycling Genes in the Soil

Significant differences in the microbial community and diversity in soil have been observed due to organic farming, but little research has been performed for exploring microbial functionality and the co-occurrence of patterns among microbial taxa. In this work, we study soil 16S rDNA amplicons from two long-term organic farming systems (Org_C and Org_M) and a conventional system (Conv) to decipher the differences in microbial interaction and network organization and to predict functional genes (principally related to the N cycle). In general, the network organizations were different in all cropping systems due to agricultural management. Org_C showed the highest negative interactions and modularity and the most altered bacterial niches and interactions, which led to an increase in generalist species that stabilize the bacterial community and improve the response of the soil to adverse conditions. These changes altered the predicted functionality of the bacterial community; Org_C showed higher referred numbers of nitrogen fixation genes, a decrease in the N2O emission genes and could favor the uptake of environmental CO2. Thus, long-term compost amendment application has significant benefits for the farmer and the environment, since prolonged application can reduce the use of fertilizers and pesticides and could create a more stable soil, which could resist the effects of climate change.

Seam-Carved Image Tampering Detection Based on the Cooccurrence of Adjacent LBPs

Seam carving has been widely used in image resizing due to its superior performance in avoiding image distortion and deformation, which can maliciously be used on purpose, such as tampering contents of an image. As a result, seam-carving detection is becoming crucially important to recognize the image authenticity. However, existing methods do not perform well in the accuracy of seam-carving detection especially when the scaling ratio is low. In this paper, we propose an image forensic approach based on the cooccurrence of adjacent local binary patterns (LBPs), which employs LBP to better display texture information. Specifically, a total of 24 energy-based, seam-based, half-seam-based, and noise-based features in the LBP domain are applied to the seam-carving detection. Moreover, the cooccurrence features of adjacent LBPs are combined to highlight the local relationship between LBPs. Besides, SVM after training is adopted for feature classification to determine whether an image is seam-carved or not. Experimental results demonstrate the effectiveness in improving the detection accuracy with respect to different scaling ratios, especially under low scaling ratios.

Representation based on ordinal patterns for seizure detection in EEG signals

EEG signals carry rich information about brain activity and play an important role in the diagnosis and recognition of epilepsy. Numerous algorithms using EEG signals to detect seizures have been developed in recent decades. However, most of them require well-designed features that highly depend on domain-specific knowledge and algorithm expertise. In this study, we introduce the unigram ordinal pattern (UniOP) and bigram ordinal pattern (BiOP) representations to capture the different underlying dynamics of time series, which only assumes that time series derived from different dynamics can be characterized by repeated ordinal patterns. Specifically, we first transform each subsequence in a time series into the corresponding ordinal pattern in terms of the ranking of values and consider the distribution of ordinal patterns of all subsequences as the UniOP representation. Furthermore, we consider the distribution of the cooccurrence of ordinal patterns as the BiOP representation to characterize the contextual information for each ordinal pattern. We then combine the proposed representations with the nearest neighbor algorithm to evaluate its effectiveness on three publicly available seizure datasets. The results on the Bonn EEG dataset demonstrate that this method provides more than 90% accuracy, sensitivity, and specificity in most cases and outperforms several state-of-the-art methods, which proves its ability to capture the key information of the underlying dynamics of EEG time series at healthy, seizure-free, and seizure states. The results on the second dataset are comparable with the state-of-the-art method, showing the good generalization ability of the proposed method. All performance metrics on the third dataset are approximately 89%, which demonstrates that the proposed representations are suitable for large-scale datasets.

Learning Word-pair Embeddings from Co-occurrences of Word Pairs and Lexico-syntactic Patterns to Recognize Semantic Relations between Nouns

Learning Word-pair Embeddings from Co-occurrences of Word Pairs and Lexico-syntactic Patterns to Recognize Semantic Relations between Nouns

Multi-label charge predictions leveraging label co-occurrence in imbalanced data scenario

Charge prediction is to predict associated charges based on fact descriptions and plays a significant role in legal aid systems. It is a fundamental and challenging task to automatically predict charges in the multi-label classification paradigm, which is fit to real applications. Existing works either focus on balanced data scenario and multiple charges or few-shot charges with a single label. Moreover, previous models utilize special initialization with label patterns to improve the performance of the multi-label classification task, which is only applicable when there is less training data, resulting in poor robustness. To this end, a multi-task convolutional neural network combined with bidirectional long short-time memory leveraging label co-occurrence framework, called CBLLC, is introduced to predict multiple charges with article information on imbalanced data occasion. We develop a new learning mechanism to train the framework of charge and article patterns when there is a lot of training data, increasing its robustness. In CBLLC, the data preprocessing process serves to aid the training in a more generalized manner and reduce overfitting. A salient word annotation is introduced to deal with few-shot charges. A better classification result is obtained with processed data and improves the generality of the model. Experimental results of Chinese AI and Law Challenge test set show the superiority of our proposed method compared with the state-of-the-art methods. In particular, a macro-F1 score of 92.9% for charges and 86.6% for articles is achieved with co-occurrence of charges and patterns of articles.

Klasifikasi Kelompok Usia Melalui Citra Wajah Berbasis Image Texture Analysis pada Sistem Automatic Video Filtering

Nowadays information technology makes it easier for everyone to access various information, this easiness harms minors, because it is possible to access adult content from the internet, television or mobile devices. The problem is the unavailability of the system for filtering and authentication to get information by the face. The face contains information related to personal characteristics such as age, etc. feature extraction is an important stage in the face recognition process. This study proposed local binary pattern (LBP) and gray level co-occurrence matrix (GLCM) as feature extraction to describe face feature, and we use artificial neural network to classify the human age, the experiment result after calculation with confusion matrix obtained average acceleration of 94.8%, precision of 93.7% and recall of 92.3%, it’s performance measure obtained proposed method can be described face feature it well, so that, the proposed method can be used as reference material to development video filtering system by age of the users in access information based on video especially pornography and violence content.

Coarse-to-Fine Deep Learning of Continuous Pedestrian Orientation Based on Spatial Co-Occurrence Feature

The continuous orientation estimation of a moving pedestrian is a crucial issue in autonomous driving that requires the detection of a pedestrian intending to cross a road. It is still a challenging task owing to several reasons, including the diversity of pedestrian appearances, the subtle pose difference between adjacent orientations, and similar poses with different orientations such as axisymmetric orientations. These problems render the task highly difficult. Recent studies involving convolutional neural networks (CNNs) have attempted to solve these problems. However, their performance is still far from satisfactory for application in intelligent vehicles. In this paper, we propose a CNN-based two-stream network for continuous orientation estimation. The network can learn representations based on the spatial co-occurrence of visual patterns among pedestrians. To boost estimation performance, we applied a coarse-to-fine learning approach that consists of two learning stages. We investigated continuous orientation performance on the TUD Multiview Pedestrian dataset and the KITTI dataset and compared them with the state-of-the-art methods. The results show that our method outperforms other existing methods.

Extraction of non-functional requirement using semantic similarity distance

Functional and non-functional requirements are important equally in software development. Usually, the requirements are expressed in natural languages. The functional and non-functional requirements are written inter-mixed in software requirement document. The extraction of requirement from the software requirement document is a challenging task. Most of the recent studies adopted a supervised learning approach for the extraction of non-functional requirements. However, there is a drawback of supervised learning such as training of model and retrain if the domain changed. The proposed approach manipulates the textual semantic of functional requirements to identify the non-functional requirements. The semantic similarity is calculated based on co-occurrence of patterns in large human knowledge repositories of Wikipedia. This study finds the similarity distance between the popular indicator keywords and requirement statements to identify the type of non-functional requirement. The proposed approach is applied to PROMISE “NFR dataset.” The performance of the proposed approach is measured in terms of precision, recall and F-measure. Furthermore, the research applies three pre-processing approaches (traditional, part of speech tagging and word augmentation) to increase the performance of NFR extraction. The proposed approach outperforms the results of existing studies.

An exploratory study on cooccurrence of design patterns and bad smells using software metrics

SummaryA design pattern is a general reusable solution to commonly recurring problems in software projects. Bad smells are symptoms existing in the source code that possibly indicate the presence of a structural problem that requires code refactoring. Although design pattern and bad smells be different concepts, literature has shown that they may be related and cooccur during the evolution of a software system. This paper presents an empirical study that investigates cooccurrences of design patterns and bad smells as well as identifies the main factors that contribute to the emergence of the relationship between them. We carried out a case study with five Java systems to: (1) investigate if the use of design pattern reduces bad smell occurrence, (2) identify cooccurrences of design patterns and bad smells, and (3) identify situations that contribute for the cooccurrence emergence. As the main result, we found that the application of design pattern not necessarily avoid bad smell occurrences. The results also show that some design patterns such as composite, factory method, and singleton, are intrinsically modular and might be useful in creating high‐quality systems. However, other design patterns such as adapter‐command, proxy, and state‐strategy, have presented high cooccurrence frequency with bad smells; therefore, they require attention in their implementation. Finally, via manual inspection in the components with cooccurrence, we found that the identified cooccurrences appeared due to poor planning and inadequate application of design patterns.

Elliptical local binary co-occurrence pattern for face image retrieval

Face image retrieval is considered as an active research field in computer vision. This paper describes a novel feature descriptor called elliptical local binary co-occurrence pattern (ELBCoP) for face image retrieval. This descriptor employs a combination of sparse elliptical local binary pattern (ELBP) and grey level co-occurrence matrix (GLCM). Unlike previous approaches, the sparse ELBP consider only 4 horizontal and 4 vertical neighbors from the elliptic shaped neighborhood, and uses 4 simple diagonal neighbors. Then the co-occurrence of pixel pairs, in the three local pattern maps obtained using sparse ELBP, are calculated using GLCM in two selected directions. These two directions of GLCM are selected according to the shape of the elliptic neighborhood. Through GLCM, the proposed ELBCoP extracts the frequency details and also the spatial relationship between the local pattern pairs very effectively. It is also shown that a properly selected subset of ELBCoP can still provide a robust and efficient description of face images, with significant reduction in feature vector dimensions. Experimental results on two benchmark face image databases show superior retrieval performance of ELBCoP and also subset of ELBCoP, when compared to various state of the art methods including a few very recent ones.

Genetics of co-developing conduct and emotional problems during childhood and adolescence.

Common genetic influences offer a partial explanation for comorbidity between different psychiatric disorders1-3. However, the genetics underlying co-development-the cross-domain co-occurrence of patterns of change over time-of psychiatric symptoms during childhood and adolescence has not been well explored. Here, we show genetic influence on joint symptom trajectories of parent-reported conduct and emotional problems (overall N = 15,082) across development (4-16 years) using both twin- and genome-wide polygenic score analyses (genotyped N = 2,610). Specifically, we found seven joint symptom trajectories, including two characterized by jointly stable and jointly increasing symptoms of conduct and emotional problems, respectively (7.3% of the sample, collectively). Twin modelling analyses revealed substantial genetic influence on trajectories (heritability estimates range of 0.41-0.78). Furthermore, individuals' risk of being classified in the most symptomatic trajectory classes was significantly predicted by polygenic scores for years-of-education-associated alleles and depressive symptoms-associated alleles. Complementary analyses of child self-reported symptoms across late childhood and early adolescence yielded broadly similar results. Taken together, our results indicate that genetic factors are involved in the co-development of conduct and emotional problems across childhood and adolescence, and that individuals with co-developing symptoms across multiple domains may represent a clinical subgroup characterized by increased levels of genetic risk.

Physical and Behavioral Characterization of Human Groups Classified Using Symbolic Pattern Analysis

In daily life we perform various activities, such as walking and running. Even if we take an movement for a purpose, behaviors in the movement may differ according to physical/mental condition, background culture of the persons or other factors. If a device, such as a smart phone and a wearable device, can know the condition by observing behaviors, it may be able to use such information for appropriate service. In a previous research we proposed an algorithm which groups humans based on co-occurrence and exclusiveness of patterns between behaviors in Radio Gymnastic Exercises, which is a convenient benchmark for our purpose. In this work we focus on relation between human groups and physical/behavioral property of humans. After we revise the algorithm by introducing similarity among patterns, we characterize groups derived by the modified algorithm using various information by questionnaire and video data of the exercises. In our analysis we confirmed that the groups were characterized better by physical conditions than observed behaviors.

Latent tree models for hierarchical topic detection

We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at the bottom level of an HLTM are observed binary variables that represent the presence/absence of words in a document. The variables at other levels are binary latent variables that represent word co-occurrence patterns or co-occurrences of such patterns. Each latent variable gives a soft partition of the documents, and document clusters in the partitions are interpreted as topics. Latent variables at high levels of the hierarchy capture long-range word co-occurrence patterns and hence give thematically more general topics, while those at low levels of the hierarchy capture short-range word co-occurrence patterns and give thematically more specific topics. In comparison with LDA-based methods, a key advantage of the new method is that it represents co-occurrence patterns explicitly using model structures. Extensive empirical results show that the new method significantly outperforms the LDA-based methods in term of model quality and meaningfulness of topics and topic hierarchies.

Free-ranging livestock influence species richness, occupancy, and daily behaviour of wild mammalian species in Baluran National Park, Indonesia

In some developing countries, human activities in protected areas threaten wildlife populations and their habitats. This study was conducted to understand the influences of free-range livestock on the wild mammalian population in Baluran National Park, Indonesia. There were 3852 and 1156 cows and goats, respectively, and livestock occupied an area of approximately 55.96km2. The species richness and probability of occupancy in areas with and without livestock were assessed, and the spatial co-occurrence and overlap of daily activity patterns among mammalian species and livestock were measured. A total of 39 camera traps were installed from August 2015 to January 2016, collecting 23,021 independent photographs. In areas with livestock, the number of mammal species (eight) was lower than in areas without livestock (11 species). The most affected species were the large herbivores Bubalus bubalis and Bos javanicus, and a large carnivore Panthera pardus, all of which were absent in areas with livestock. Regardless of the feeding guild, the probability of occupancy of almost all species declined in areas with livestock, except the medium herbivores Paradoxurus hermaphroditus and Hystrix javanica that showed a higher probability of occupancy. The species whose probability of occupancy declined were the carnivores Cuon alpinus and Prionailurus bengalensis; the herbivores Rusa timorensis, Tracypithecus auratus and Muntiacus muntjak; and the omnivore Sus scrofa. In the presence of livestock, R. timorensis and S. scrofa changed their activities from diurnal to nocturnal. Livestock affected most wild mammals in several ways, including by reducing the species richness, lessening the probability of occupancy and changing the daily activity patterns of many animals. This research recommends a significant reduction in the size of the range area for domestic livestock.