Representation Scheme Research Articles

Local but not global graph theoretic measures of semantic networks generalize across tasks.

"Dogs" are connected to "cats" in our minds, and "backyard" to "outdoors." Does the structure of this semantic knowledge differ across people? Network-based approaches are a popular representational scheme for thinking about how relations between different concepts are organized. Recent research uses graph theoretic analyses to examine individual differences in semantic networks for simple concepts and how they relate to other higher-level cognitive processes, such as creativity. However, it remains ambiguous whether individual differences captured via network analyses reflect true differences in measures of the structure of semantic knowledge, or differences in how people strategically approach semantic relatedness tasks. To test this, we examine the reliability of local and global metrics of semantic networks for simple concepts across different semantic relatedness tasks. In four experiments, we find that both weighted and unweighted graph theoretic representations reliably capture individual differences in local measures of semantic networks (e.g., how related pot is to pan versus lion). In contrast, we find that metrics of global structural properties of semantic networks, such as the average clustering coefficient and shortest path length, are less robust across tasks and may not provide reliable individual difference measures of how people represent simple concepts. We discuss the implications of these results and offer recommendations for researchers who seek to apply graph theoretic analyses in the study of individual differences in semantic memory.

Depression, anxiety, and burnout in academia: topic modeling of PubMed abstracts

The problem of mental health in academia is increasingly discussed in literature, and to extract meaningful insights from the growing amount of scientific publications, text mining approaches are used. In this study, BERTopic, an advanced method of topic modeling, was applied to abstracts of 2,846 PubMed articles on depression, anxiety, and burnout in academia published in years 1975–2023. BERTopic is a modular technique comprising a text embedding method, a dimensionality reduction procedure, a clustering algorithm, and a weighing scheme for topic representation. A model was selected based on the proportion of outliers, the topic interpretability considerations, topic coherence and topic diversity metrics, and the inevitable subjectivity of the criteria was discussed. The selected model with 27 topics was explored and visualized. The topics evolved differently with time: research papers on students' pandemic-related anxiety and medical residents' burnout peaked in recent years, while publications on psychometric research or internet-related problems are yet to be presented more amply. The study demonstrates the use of BERTopic for analyzing literature on mental health in academia and sheds light on areas in the field to be addressed by further research.

Rethinking Extractivism and Masculinity: Aesthetics of the Environment in There Will Be Blood (2007) and First Cow (2019)

As today we face the urgency of thinking film history through the implications of the ecological emergency, the aesthetics of oil extraction in cinema can be linked to representations of petro-masculinity and to discourses of capitalist exploitation of nature. Considering the ecocritical trend in film studies, this paper analyzes the subgenre of the oil film, which is inextricably related to the genre of the western historical tradition and its revisions, and presents There Will Be Blood (Paul Thomas Anderson, 2007) as a key case. The comparative analysis discovers that the critical and aesthetic representational strategies of landscape and character of the US founding myth in First Cow (Kelly Reichardt, 2019) manifest a proposal that deconstructs the genre with the intention of filming the relationships between the human and more-than-human from a viewpoint that approaches environmental consciousness.
 Keywords: 
 oil, masculinity, western, Paul Thomas Anderson, Kelly Reichard, nature aesthetic, ecological emergency, film history

Human-Robot Shared Assembly Taxonomy: A step toward seamless human-robot knowledge transfer

Future manufacturing will witness a shift in human-robot relationships toward collaboration, compassion, and coevolution. This will require seamless human-robot knowledge transfer. Differences in language and knowledge representation hinder the transfer of knowledge between humans and robots. Thus, a unified knowledge representation system that can be shared by humans and robots is essential. Driven by this need in a product assembly scenario, we propose the Human-Robot Shared Assembly Taxonomy (HR-SAT). With HR-SAT, any comprehensive assembly task can be represented as a knowledge graph that both humans and robots can understand. To ensure consistency in task decomposition and representation, we define the key elements of HR-SAT. HR-SAT incorporates rich assembly information and provides necessary information for diverse applications, e.g., process planning, quality checking, and human-robot collaboration. The usage and practicality of HR-SAT are demonstrated through two case studies. As a unified assembly process representation schema, HR-SAT constitutes a critical step toward seamless human-robot knowledge transfer. The specifications of HR-SAT and the two case studies are available at: https://iai-hrc.github.io/hr-sat.

Altered neural encoding of vowels in noise does not affect behavioral vowel discrimination in gerbils with age-related hearing loss.

Understanding speech in a noisy environment, as opposed to speech in quiet, becomes increasingly more difficult with increasing age. Using the quiet-aged gerbil, we studied the effects of aging on speech-in-noise processing. Specifically, behavioral vowel discrimination and the encoding of these vowels by single auditory-nerve fibers were compared, to elucidate some of the underlying mechanisms of age-related speech-in-noise perception deficits. Young-adult and quiet-aged Mongolian gerbils, of either sex, were trained to discriminate a deviant naturally-spoken vowel in a sequence of vowel standards against a speech-like background noise. In addition, we recorded responses from single auditory-nerve fibers of young-adult and quiet-aged gerbils while presenting the same speech stimuli. Behavioral vowel discrimination was not significantly affected by aging. For both young-adult and quiet-aged gerbils, the behavioral discrimination between /eː/ and /iː/ was more difficult to make than /eː/ vs. /aː/ or /iː/ vs. /aː/, as evidenced by longer response times and lower d' values. In young-adults, spike timing-based vowel discrimination agreed with the behavioral vowel discrimination, while in quiet-aged gerbils it did not. Paradoxically, discrimination between vowels based on temporal responses was enhanced in aged gerbils for all vowel comparisons. Representation schemes, based on the spectrum of the inter-spike interval histogram, revealed stronger encoding of both the fundamental and the lower formant frequencies in fibers of quiet-aged gerbils, but no qualitative changes in vowel encoding. Elevated thresholds in combination with a fixed stimulus level, i.e., lower sensation levels of the stimuli for old individuals, can explain the enhanced temporal coding of the vowels in noise. These results suggest that the altered auditory-nerve discrimination metrics in old gerbils may mask age-related deterioration in the central (auditory) system to the extent that behavioral vowel discrimination matches that of the young adults.

Multi-level knowledge-driven feature representation and triplet loss optimization network for image–text retrieval

Image–text retrieval plays a considerable role in associating vision and language. Existing mainstream approaches focus on fine-grained alignment while ignoring the influence of prior knowledge on model performance and the limitation of using a fixed margin in the triplet loss. In this paper, we propose a Multi-level Knowledge-driven feature representation and Triplet Loss Optimization Network (MKTLON) that exploits prior knowledge to enhance visual and textual feature representations and utilizes an adaptive margin of the triplet loss to optimize network training. Specifically, we first present an Enhanced feature Representation scheme based on the Self-Attention (ERSA) module, which incorporates the prior knowledge randomly initialized by uniform distribution into the matrices K and V in the self-attention mechanism. Subsequently, we adopt cascaded ERSA modules to encode images and texts to obtain multi-level visual and textual features with prior knowledge. Furthermore, we develop an adaptive margin optimization strategy that models the relevance scores of positive and negative samples as two independent Gaussian distributions, and obtain the optimized margin by minimizing the intersection of these two distributions. Extensive experiments on two benchmarks, Flickr30K (155,000 image–text pairs) and MSCOCO (616,435 image–text pairs), show the proposed MKTLON achieves 5.7% and 4.3% improvements on rSum, respectively, compared to the state-of-the-art method. The source code will be released at https://github.com/FlyCuteBird/MKTLON.

Variation in Mathematics Content Coverage, Instructional Grouping, and Representational Strategies

Variation in Mathematics Content Coverage, Instructional Grouping, and Representational Strategies

Exploring visual representations of computer mouse movements for bot detection using deep learning approaches

Nowadays, bots can be seen everywhere on the Internet and are responsible for a large percentage of website traffic. The problem of bot detection has increasingly gained attention since more and more bots have been abused from click fraud in online advertisements to launching credential stuffing attacks for harvesting user accounts at a large scale. In this work, we present an end-to-end deep framework for bot detection based on computer mouse movements. Specifically, we propose a novel visual representation scheme that can simultaneously encode spatial and kinematic information in mouse movements into an image which can then be used as the input to Convolutional Neural Networks (CNN). Various strategies to encode kinematic features into images are investigated to obtain a better scheme of visual representation. Experimental results show that the proposed representation scheme in combination with CNN outperforms several baseline models with a TPR of 99.34% in detecting known bots and can be generalized to unknown bots with a highest accuracy of 99.20%. We also demonstrate that the proposed approach can reach acceptable performance levels even for models trained with a small number of training samples. This makes the deployment of our approach easier in real-world scenarios.

#EndSARS Protests and the Search for Social Justice in Nigeria: Examining Activist Discourses on Police Brutality, Politics and Human Security

Abstract On October 3, 2020, members of the Special Anti-Robbery Squad (sars) of the Nigerian Police Force arrested a young man at Wetland Hotel, Ughelli in Delta State, and later shot and killed him, and threw him out of a moving police van. In addition to eye witnesses of what happened, the video of this incident was also trending on social media. Again, on October 5, another video went viral of sars officers’ killing a young musician popularly known as “Sleek,” in unjustifiable circumstances. This was the last straw that broke the camel’s back. What initially began as spontaneous peaceful protests soon turned bloody and by October 8, the protests had spread to almost all Nigerian cities demanding the disbandment of sars. This empirical study examines the operational structure of sars, the formation of the EndSARS movement and its first main protests in 2020 in the search for social justice. Methods in qualitative discourse analysis and multimodality, are used to analyze representational strategies in the protest discourse of the #EndSARS protesters. Other issues bordering on police brutality, injustice, corruption and state failure, which form the main narratives of the protests are analyzed.

Deep Temporal State Perception Toward Artificial Cyber–Physical Systems

Cyber-Physical systems, as the cornerstone of smart city, has been attracting great interest from academia and industry. It aims to monitor/ control physical components via communication and computation, while ensuring effectiveness, intelligence, and security. The related research has pointed that the state perception on physical device is the prerequisite for boosting overall CPS performance. Towards this end, we present an effective deep temporal perception networks to achieve classification based state detection. Namely, we first design a multi-feature encoding network for multi-view time series representation. Concretely, on the one hand, we utilize two piecewise aggregate representation strategies to obtain the key temporal trends; on the other hand, we adopt a temporal symbolic representation strategy to capture the necessary contextual semantic correlations. Thereafter, we develop a comprehensive representation enhancement module to improve feature comprehension capability, and thus boosting the overall performance and interpretability. Corresponding comparison experiments, ablation studies, and data visualization analyses on benchmark datasets have verified the effectiveness of our model.

Transferable Adaptive Differential Evolution for Many-Task Optimization.

The evolutionary multitask optimization (EMTO) algorithm is a promising approach to solve many-task optimization problems (MaTOPs), in which similarity measurement and knowledge transfer (KT) are two key issues. Many existing EMTO algorithms estimate the similarity of population distribution to select a set of similar tasks and then perform KT by simply mixing individuals among the selected tasks. However, these methods may be less effective when the global optima of the tasks greatly differ from each other. Therefore, this article proposes to consider a new kind of similarity, namely, shift invariance, between tasks. The shift invariance is defined that the two tasks are similar after linear shift transformation on both the search space and the objective space. To identify and utilize the shift invariance between tasks, a two-stage transferable adaptive differential evolution (TRADE) algorithm is proposed. In the first evolution stage, a task representation strategy is proposed to represent each task by a vector that embeds the evolution information. Then, a task grouping strategy is proposed to group the similar (i.e., shift invariant) tasks into the same group while the dissimilar tasks into different groups. In the second evolution stage, a novel successful evolution experience transfer method is proposed to adaptively utilize the suitable parameters by transferring successful parameters among similar tasks within the same group. Comprehensive experiments are carried out on two representative MaTOP benchmarks with a total of 16 instances and a real-world application. The comparative results show that the proposed TRADE is superior to some state-of-the-art EMTO algorithms and single-task optimization algorithms.

Probabilistic finite element-based reliability of corroded pipelines with interacting corrosion cluster defects

The random distribution of pitting corrosion defects in pipelines normally leads to interacting cluster defects that behave noticeably different from single metal loss defects. Generally, the probabilistic approaches employ explicit burst pressure limit states for corroded pipelines subjected to only internal pressure. However, a significant level of conservatism is typically associated with the probabilistic assessments of corroded pipelines using the closed-form explicit limit state functions, which presents considerable challenges in maintenance planning and risk management. Therefore, this paper proposes a pathway for developing efficient performance functions for the assessment of interacting pipeline corrosion clustering defects using probabilistic finite element-based reliability method. This seven-stage framework combines multiple uncertainty representation schemes to evaluate the probability of failure. The impact of the critical design variables such as the elastic and plastic material properties, corrosion features, and interacting cluster defect characterisations are identified to guide the burst pressure design, operations and maintenance optimisation. The employed surrogate-based active learning reliability approach yielded an efficient probability estimate at a lesser computational cost than the simulation-based reliability methods. The proposed framework reduces the conservatism and computational cost related with explicit burst pressure limit state functions for corroded pipelines and offers informed decision-making on risk and maintenance management.

SEBP_HNHC: Stacking Ensemble-based Bi-level Predictor for Human Non-Histone Crotonylation combining with iterative feature representation strategy

Accurate identification of crotonylation on human non-histone sites plays a crucial role in human biological research. Compared with traditional experimental methods that are labor-intensive and time-consuming, computational methods are more and more popular in recent years. Most of previous research methods are only for the prediction of crotonylation sites of histones, and there is a lack of targeted prediction tools for the identification of crotonylation sites of human non-histone proteins. In this study, we propose a stacking ensemble-based bi-level predictor for human non-histone crotonylation combining with iterative feature representation strategy, named SEBP_HNHC. To take full advantage of all the training information and solve the extreme imbalance between positive samples and negative samples, we propose a two-layer training data structure including preliminary training dataset and balanced training dataset. Preliminary training dataset is firstly divided into twelve subset using a special data division method. Then, multi-view feature encoding schemes are integrated to comprehensively represent the attribution of samples in each training subset. Next, Gini index combined with sequential forward search is employed for feature optimization for each preliminary training subset. Then, 84 preliminary models are built based on seven kinds of classifiers for twelve preliminary training subset that are now more commonly used and efficient. And then, a balanced training dataset is utilized to synthesize the capabilities of 84 preliminary models by generating 84 probability values as 84-D features for stacking ensemble. Finally, deep ensemble features are mined through iterative feature representation strategy. The experiment results show that the SEBP_HNHC method achieves robust performance in crotonylation sites prediction. Therefore, SEBP_HNHC is an effective tool for identification of crotonylation on lysine sites in human non-histone proteins.

An Artificial Intelligence-Based Model for Knowledge Evaluation and Integration in Public Organizations

In the construction of knowledge bases, it is very important to evaluate the quality of the knowledge entered into them. This is exacerbated in public administrations, where knowledge should be oriented towards public services. In this study, an artificial intelligence-based method for the evaluation of knowledge is described. This method takes advantage of the structure and contents of the knowledge representation schemas (representing the knowledge of the corresponding experts) to carry out knowledge evaluation. More precisely, the method allows the various comparisons between the schemas to be integrated and the overall schema to evaluate the contribution of each schema.

Structure-Driven Representation Learning for Deep Clustering

As an important branch of unsupervised learning methods, clustering makes a wide contribution in the area of data mining. It is well known that capturing the group-discriminative properties of each sample for clustering is crucial. Among them, deep clustering delivers promising results due to the strong representational power of neural networks. However, most of them adopt sample-level learning strategies, and the standalone data point barely captures its holistic cluster’s context and may undergo sub-optimal cluster assignment. To tackle this issue, we propose a Structure-driven Representation Learning (SRL) method by introducing latent structure information into the representation learning process at both the local and global levels. Specifically, a local-structure-driven sample representation strategy is proposed to approximate the estimation of data distribution, which models the neighborhood distribution of samples with potential structure information and exploits statistical dependencies between them to improve cluster consistency. A global-structure-driven cluster representation strategy is designed, where the context of each cluster is sufficiently encoded according to its samples (exemplar-theory) and corresponding prototype (prototype-theory). In this case, each cluster can only be related to its most similar samples, and different clusters are separated as much as possible. These two models are seamlessly combined into a joint optimization problem, which can be efficiently solved. Experiments on six widely-used datasets demonstrate the superiority of SRL over state-of-the-art clustering methods.

A Multi-perspective Model for Protein-Ligand-Binding Affinity Prediction.

Gathering information from multi-perspective graphs is an essential issue for many applications especially for protein-ligand-binding affinity prediction. Most of traditional approaches obtained such information individually with low interpretability. In this paper, we harness the rich information from multi-perspective graphs with a general model, which abstractly represents protein-ligand complexes with better interpretability while achieving excellent predictive performance. In addition, we specially analyze the protein-ligand-binding affinity problem, taking into account the heterogeneity of proteins and ligands. Experimental evaluations demonstrate the effectiveness of our data representation strategy on public datasets by fusing information from different perspectives. All codes are available in the https://github.com/Jthy-af/HaPPy .

Multiple-input streams attention (MISA) network for skeleton-based construction workers' action recognition using body-segment representation strategies

With the rapid growth of deep learning algorithms, graph convolutional networks (GCNs) have become a common choice for skeleton-based human action recognition, boasting impressive performance. However, existing GCN-based models often rely on physical human body connections, which may not suit complex construction tasks involving various body parts and hand movements. To address this concern, the human body is modeled in this paper through topological graphs at varying levels, designed based on body-segment strategies. A multiple-input streams attention (MISA) network is introduced, incorporating GCN and temporal convolutional network (TCN) components to enhance the body-structure topology graph of GCNs with more comprehensive input graphs. Additionally, two-modality motion data and three attention blocks are integrated to capture more discerning features. Finally, experimental results using the Construction Motion Library (CML) dataset demonstrated the superiority of the developed method, reaching approximately 84.94% recognition accuracy.

Adaptive Deep Feature Fusion for Continuous Authentication With Data Augmentation

Mobile devices are becoming increasingly popular and are playing significant roles in our daily lives. Insufficient security and weak protection mechanisms, however, cause serious privacy leakage of the unattended devices. To fully protect mobile device privacy, we propose ADFFDA, a novel mobile continuous authentication system using an Adaptive Deep Feature Fusion scheme for effective feature representation, and a transformer-based GAN for Data Augmentation, by leveraging smartphone built-in sensors of the accelerometer, gyroscope and magnetometer. Given the normalized sensor data, ADFFDA utilizes the transformer-based GAN consisting of a transformer-based generator and a CNN-based discriminator to augment the training data for CNN training. With the augmented data and the especially designed CNN based on the ghost module and ghost bottleneck, ADFFDA extracts deep features from the three sensors by the trained CNN, and exploits an adaptive-weighted concatenation method to adaptively fuse the CNN-extracted features. Based on the fused features, ADFFDA authenticates users by using the one-class SVM (OC-SVM) classifier. We evaluate the authentication performance of ADFFDA in terms of the efficiency of the transformer-based GAN, GAN-based data augmentation, CNN architecture, adaptive-weighted feature fusion, and OC-SVM classifier. The experimental results show that ADFFDA obtains the best authentication performance w.r.t representative approaches, by achieving a mean equal error rate of 0.01%.

Surrogate-Assisted Cooperative Co-evolutionary Reservoir Architecture Search for Liquid State Machines

Liquid state machines (LSMs) are biologically more plausible than feedforward spiking neural networks for brain-inspired computing and neuromorphic engineering. However, optimizing and training complex recurrent network architectures in the reservoir of LSMs remains challenging. Most existing algorithms aim to adjust the synaptic strength only, without fundamentally modifying the reservoir architecture of LSMs. Recently, it has become popular to simultaneously optimize the architecture and parameters of the reservoir in LSMs. However, most existing architecture representation schemes are too restricted to discover more powerful architectures of LSMs. To address the above issue, this paper proposes a generative liquid state machine, whose reservoir architecture is evolved using a cooperative co-evolutionary algorithm whose weights are tuned by synaptic plasticity rules. To reduce the computation time for evolving the reservoir, random forest is adopted to assist the cooperative co-evolutionary algorithm, together with a data parallelism strategy. The proposed algorithm is assessed on three sequence classification benchmarks and our experimental results show that the proposed algorithm outperforms the state-of-the-art on the benchmark problems. Meanwhile, our analysis shows that the data parallelism strategy is effective in speeding up the evaluation process.

Babur, Akbar, and the Transformation of Gwalior's Rock-Hewn Tirthankaras

During his 1528 sojourn in Gwalior, the first Mughal emperor, Babur (r. 1526–1530), encountered numerous colossal Digambara Jain Tirthankaras fashioned from outcrops in the Urvai valley. He recounts in his memoirs how he ordered the naked “idols” destroyed. While this famed episode of iconoclasm in the Bāburnāma is well known to scholars, three paintings portraying Babur's trip to Gwalior that survive from the multiple illustrated manuscripts commissioned by Babur's grandson Akbar (r. 1556–1605) have eluded close examination. This article probes the divergent representational strategies employed by the artists of those folios tasked with depicting the same scene. I demonstrate how one artist pictorially transformed Gwalior's rock-hewn Tirthankaras into animate idols, another alluded to yet elided their portrayal, and a third bypassed entirely the thorny issue of their representation. I argue that those illustrations constitute a visual emendation to Babur's memoirs that effectively exonerated Babur from any charge of desecrating inert Jain icons—an act by then incongruous with Akbar's policy of ṣulḥ-i kull and the strong Mughal-Jain relations at his court. This proposition is further supported by an original translation of an excerpt from Siddhicandra's (d. ca. 1666) Bhānucandragaṇicarita, a Sanskrit text composed by a Jain monk at the Mughal court. Ultimately, this study contributes to critical discourses on iconoclasm, artistic agency, Mughal-Jain relations, and historical memory by exploring the theoretical issues concerning the depiction of rock carvings and idols in the pictorial afterlife of Babur's encounter with Gwalior's rock-hewn Tirthankaras.