Multiple Levels Of Representation Research Articles

OTM-HC: Enhanced Skeleton-Based Action Representation via One-to-Many Hierarchical Contrastive Learning

Human action recognition has become crucial in computer vision, with growing applications in surveillance, human–computer interaction, and healthcare. Traditional approaches often use broad feature representations, which may miss subtle variations in timing and movement within action sequences. Our proposed One-to-Many Hierarchical Contrastive Learning (OTM-HC) framework maps the input into multi-layered feature vectors, creating a hierarchical contrast representation that captures various granularities within a human skeleton sequence temporal and spatial domains. Using sequence-to-sequence (Seq2Seq) transformer encoders and downsampling modules, OTM-HC can distinguish between multiple levels of action representations, such as instance, domain, clip, and part levels. Each level contributes significantly to a comprehensive understanding of action representations. The OTM-HC model design is adaptable, ensuring smooth integration with advanced Seq2Seq encoders. We tested the OTM-HC framework across four datasets, demonstrating improved performance over state-of-the-art models. Specifically, OTM-HC achieved improvements of 0.9% and 0.6% on NTU60, 0.4% and 0.7% on NTU120, and 0.7% and 0.3% on PKU-MMD I and II, respectively, surpassing previous leading approaches across these datasets. These results showcase the robustness and adaptability of our model for various skeleton-based action recognition tasks.

Which classifiers are connected to others? An optimal connection framework for multi-layer ensemble systems

Ensemble learning is a powerful machine learning strategy that combines multiple models e.g. classifiers to improve predictions beyond what any single model can achieve. Until recently, traditional ensemble methods typically use only one layer of models which limits the exploration of different aspects in the classifiers’ predictions. On the other hand, the rise of deep learning has introduced multi-layer architectures that can learn complex functions by transforming data into multiple levels of representation. This characteristic of deep learning suggests that multi-layer ensembles may potentially provide better performance compared to single-layer ensembles. However, a problem which might arise is that in the subsequent layers, not all the inputs to a classifier are desirable, leading to lower performance. In this paper, we introduce a novel multi-layer ensemble of classifiers named COME in which each classifier at a specific layer is connected to multiple classifiers in the previous layer. These connections signify the use of the previous-layer-classifiers’ outputs as inputs for training the current layer's classifier. Each classifier can be connected to different classifiers in the previous layer, which allows inputs in each layer to be optimally selected. We propose a binary encoding scheme to encode the topology of the proposed multi-layer ensemble with defined connections between layers. Differential Evolution, a popular evolutionary computation method, is used as the optimisation algorithm to search for the optimal set of connections. Experimental results on 30 datasets from the UCI Machine Learning Repository and OpenML demonstrate that our proposed ensemble outperforms many state-of-the-art ensemble learning algorithms.

Structural and sequential regularities modulate phrase-rate neural tracking

Electrophysiological brain activity has been shown to synchronize with the quasi-regular repetition of grammatical phrases in connected speech—so-called phrase-rate neural tracking. Current debate centers around whether this phenomenon is best explained in terms of the syntactic properties of phrases or in terms of syntax-external information, such as the sequential repetition of parts of speech. As these two factors were confounded in previous studies, much of the literature is compatible with both accounts. Here, we used electroencephalography (EEG) to determine if and when the brain is sensitive to both types of information. Twenty native speakers of Mandarin Chinese listened to isochronously presented streams of monosyllabic words, which contained either grammatical two-word phrases (e.g., catch fish, sell house) or non-grammatical word combinations (e.g., full lend, bread far). Within the grammatical conditions, we varied two structural factors: the position of the head of each phrase and the type of attachment. Within the non-grammatical conditions, we varied the consistency with which parts of speech were repeated. Tracking was quantified through evoked power and inter-trial phase coherence, both derived from the frequency-domain representation of EEG responses. As expected, neural tracking at the phrase rate was stronger in grammatical sequences than in non-grammatical sequences without syntactic structure. Moreover, it was modulated by both attachment type and head position, revealing the structure-sensitivity of phrase-rate tracking. We additionally found that the brain tracks the repetition of parts of speech in non-grammatical sequences. These data provide an integrative perspective on the current debate about neural tracking effects, revealing that the brain utilizes regularities computed over multiple levels of linguistic representation in guiding rhythmic computation.

Early visual cortices reveal interrelated item and category representations in aging.

Neural dedifferentiation, the finding that neural representations tend to be less distinct in older adults compared with younger adults, has been associated with age-related declines in memory performance. Most studies assessing the relation between memory and neural dedifferentiation have evaluated how age impacts the distinctiveness of neural representations for different visual categories (e.g., scenes and objects). However, how age impacts the quality of neural representations at the level of individual items is still an open question. Here, we present data from an age-comparative fMRI study that aimed to understand how the distinctiveness of neural representations for individual stimuli differs between younger and older adults and relates to memory outcomes. Pattern similarity searchlight analyses yielded indicators of neural dedifferentiation at the level of individual items as well as at the category level in posterior occipital cortices. We asked whether age differences in neural distinctiveness at each representational level were associated with inter- and/or intraindividual variability in memory performance. While age-related dedifferentiation at both the item and category level related to between-person differences in memory, neural distinctiveness at the category level also tracked within-person variability in memory performance. Concurrently, neural distinctiveness at the item level was strongly associated with neural distinctiveness at the category level both within and across participants, elucidating a potential representational mechanism linking item- and category-level distinctiveness. In sum, we provide evidence that age-related neural dedifferentiation co-exists across multiple representational levels and is related to memory performance.Significance Statement Age-related memory decline has been associated with neural dedifferentiation, the finding that older adults have less distinctive neural representations than younger adults. This has been mostly shown for category information, while evidence for age differences in the specificity of item representations is meager. We used pattern similarity searchlight analyses to find indicators of neural dedifferentiation at both levels of representation (category and item) and linked distinctiveness to memory performance. Both item- and category-level dedifferentiation in the calcarine cortex were related to interindividual differences in memory performance, while category-level distinctiveness further tracked intraindividual variability. Crucially, neural distinctiveness was strongly tied between the item and category levels, indicating that intersecting representational properties of posterior occipital cortices reflect both individual exemplars and categories.

Neural Representations of Non-native Speech Reflect Proficiency and Interference from Native Language Knowledge.

Learning to process speech in a foreign language involves learning new representations for mapping the auditory signal to linguistic structure. Behavioral experiments suggest that even listeners that are highly proficient in a non-native language experience interference from representations of their native language. However, much of the evidence for such interference comes from tasks that may inadvertently increase the salience of native language competitors. Here we tested for neural evidence of proficiency and native language interference in a naturalistic story listening task. We studied electroencephalography responses of 39 native speakers of Dutch (14 male) to an English short story, spoken by a native speaker of either American English or Dutch. We modeled brain responses with multivariate temporal response functions, using acoustic and language models. We found evidence for activation of Dutch language statistics when listening to English, but only when it was spoken with a Dutch accent. This suggests that a naturalistic, monolingual setting decreases the interference from native language representations, whereas an accent in the listener's own native language may increase native language interference, by increasing the salience of the native language and activating native language phonetic and lexical representations. Brain responses suggest that such interference stems from words from the native language competing with the foreign language in a single word recognition system, rather than being activated in a parallel lexicon. We further found that secondary acoustic representations of speech (after 200 ms latency) decreased with increasing proficiency. This may reflect improved acoustic-phonetic models in more proficient listeners.Significance Statement Behavioral experiments suggest that native language knowledge interferes with foreign language listening, but such effects may be sensitive to task manipulations, as tasks that increase metalinguistic awareness may also increase native language interference. This highlights the need for studying non-native speech processing using naturalistic tasks. We measured neural responses unobtrusively while participants listened for comprehension and characterized the influence of proficiency at multiple levels of representation. We found that salience of the native language, as manipulated through speaker accent, affected activation of native language representations: significant evidence for activation of native language (Dutch) categories was only obtained when the speaker had a Dutch accent, whereas no significant interference was found to a speaker with a native (American) accent.

On the theory of deep learning: A theoretical physics perspective (Part I)

Deep learning machines are computational models composed of multiple processing layers of adaptive weights to learn representations of data with multiple levels of abstraction. Their structures mainly reflect the intuitive plausibility of decomposing a problem into multiple levels of computation and representation since it is believed that higher layers of representation allow a system to learn complex functions. Surprisingly, after decades of research, from learning and design perspectives these models are still deployed in a heuristic manner. In this paper, deep learning machines are modeled as disordered physical systems where its macroscopic behavior is determined in terms of the interactions defined between the basic information-processing constituent of these models, namely, the artificial neuron. They are viewed as the equilibrium states of a theoretical body that is subject to the law of increase of the entropy. The study of the changes in energy of the body when passing from one equilibrium state to another is used to understand the structure and role of the phase space of the system, and the resulting degree of disorder. It is shown that the topology of these models is strongly linked to their resulting level of disorder. Furthermore, the proposed theoretical characterization permit to assess the thermodynamic efficiency with which information can be processed by these models, and to provide a practical methodology to quantitatively estimate and compare their expected learning and generalization capabilities. These theoretical results provides new insights to the theory of deep learning and their implications are shown to be consistent through a set of benchmarks designed to experimentally assess their validity.

Handling multiple levels in agent-based models of complex socio-environmental systems: A comprehensive review

Agent-based modeling (ABM) has been successfully used, since its emergence in the 1990s, to model and simulate the dynamics at work in complex socio-environmental systems, in many domains and applications where interactions between people and their environments give rise to emergent phenomena that are difficult to study otherwise (urban planning, land-use change, adaptation to environmental changes, biodiversity protection in socio-ecosystems, environmental pollution control, etc.). The inclusion of multiple levels of analysis, abstraction, and representation in these models, however, is much more recent and is still the subject of many proposals and discussions within a relatively informal field, Multilevel Agent-Based Modeling (ML-ABM), which is most often presented as an approach that extends the classical ABM paradigm to include multilevel concepts. Over the past decade, ML-ABM has been increasingly adopted and explored by researchers as an effective paradigm for framing and defining the mechanisms underlying multilevel dynamics. However, due to the youth of the field, no single definition, methodology, or tool unifies studies in this rapidly expanding area. This review will begin with an introduction to socio-environmental systems (SES) and the challenges that modeling approaches face in representing them properly, especially regarding the complexity of human behaviors and organizations. ABM presents opportunities for modeling SESs with respect to these challenges, including the simulation of individual and social behavior and their ability to provide a descriptive and generative representation of the simulated system. However, ABM is limited in its ability to represent levels and scales, as these concepts are absent from the classical ABM metamodel. A complete review of the ML-ABM literature will be carried out, structured around a continuum that emerged during the review: that of the distribution of behaviors (and thus, from a software engineering perspective, of control) across the levels, from approaches that allow only one level to be active at a time, to approaches that rely on simultaneous activity and feedback loops between several levels. Different design choices will, thus, be presented to meet the different needs of multi-level representation, focusing on the interest on modelers and the strengths and limitations of each. In particular, we will highlight a limitation shared by all the reviewed approaches, namely their inability to represent several parallel hierarchies of levels and their interactions, a capability that appears more and more crucial to finely represent social behaviors in SES. A new perspective on the interest that the AGR approach could represent to allow this representation of hierarchies allows us to conclude on the research perspectives are still open.

Recommending Profiles To Social Event Participation In Online Social Network Service Applications Using Deep Learning Techniques

Nowadays, organizing online Social events is growing especially in current pandemic situation due to corona. Thus social network services helps to organize the event oriented online social gathering. The events discussed on social networks can be associated with topics, locations, and time periods. Various literatures have employed clustering mechanism to group the profiles of the user of social networking applications. More research has been carried out in event based online network services as existing models leads to scalability and sparsity problems. Event-based online social networks are used to maintain interest-based groups with high relevancy rate, recommendation quality and predictive accuracy. In order to achieve the above goal, in this paper, we propose a novel framework named as Deep Influence Predict (DIP) which explores the features of Recurrent Neural Network in order identify the target or potential users through different patterns and behaviours of the profile on the social networking service applications. It learns multiple levels of representations and abstractions of the latent data through individual participation record. Further, it extracts the extrinsic and intrinsic properties of the profiles on their social connections and social effects. Specifically, it identifies the distinguishing social groups with different topics and categories as multifaceted interest in iterative process. Finally decision of recommendation for the event is integrated on outcomes of user behaviour model through personnel impact, social relation and equilibrium. Evaluation of the proposed model through various case studies has been implemented using hadoop architecture and validated across various measures such as accuracy on precision, Recall and f measure along scalability and Execution time.

Fast and Interactive Positioning of Proteins within Membranes

(1) Background: We developed an algorithm to perform interactive molecular simulations (IMS) of protein alignment in membranes, allowing on-the-fly monitoring and manipulation of such molecular systems at various scales. (2) Methods: UnityMol, an advanced molecular visualization software; MDDriver, a socket for data communication; and BioSpring, a Spring network simulation engine, were extended to perform IMS. These components are designed to easily communicate with each other, adapt to other molecular simulation software, and provide a development framework for adding new interaction models to simulate biological phenomena such as protein alignment in the membrane at a fast enough rate for real-time experiments. (3) Results: We describe in detail the integration of an implicit membrane model for Integral Membrane Protein And Lipid Association (IMPALA) into our IMS framework. Our implementation can cover multiple levels of representation, and the degrees of freedom can be tuned to optimize the experience. We explain the validation of this model in an interactive and exhaustive search mode. (4) Conclusions: Protein positioning in model membranes can now be performed interactively in real time.

Investigations on Deep Learning Techniques for Analysing Mammograms

Mammograms have been acknowledged as one of the most reliable screening tools as well as a key diagnostic mechanism for early breast cancer detection. Though mammography is a valuable screening tool for detecting malignant growth in breasts, its competence as a diagnostic tool is heavily reliant on the radiologists’ understanding. Automated systems are now widely used for detection of breast cancer. Image processing techniques were widely used in automated systems for classifying mammograms. Of late with the advent of deep learning (DL) where images can be processed directly for classification, the DL is widely researched for medical image classification. Basically, DL techniques are representation-learning methods which aid in understanding data like sounds, images as well as texts. DL algorithms have the ability to learn multiple levels of representation as well as abstraction. Residual network (ResNet) is given due consideration as a kind of highly advanced Convolutional Neural Networks (CNNs). This work has offered a potential application of Visual Geometry Group (VGG), Residual network (ResNet) and Inception based CNN model for differentiating the mammograms into the abnormal class and the normal class. Experimental results demonstrated that the deep learners are effective for classifying mammograms and Inception deep learner achieved the best accuracy of 91.49%.

Age-related neural dedifferentiation for individual stimuli: an across-participant pattern similarity analysis

ABSTRACT Age-related neural dedifferentiation – reductions in the regional specificity and precision of neural representations – is proposed to compromise the ability of older adults to form sufficiently distinct neural representations to support episodic memory encoding. The computational model that spurred investigations of age-related neural dedifferentiation initially characterized this phenomenon as a reduction in the specificity of neural patterns for individual items or stimuli. Most investigations have focused on reductions in neural differentiation for patterns of neural activity associated with category-level information, such as reduced neural selectivity between categories of visual stimuli (e.g., scenes, objects, and faces). Here, I report a novel across-participant pattern similarity analysis method to measure neural distinctiveness for individual stimuli that were presented to participants on a single occasion. Measures of item-level pattern similarity during encoding showed a graded positive subsequent memory effect in younger, with no significant subsequent memory effect in older adults. These results suggest that age-related reductions in the distinctiveness of neural patterns for individual stimuli during age differences in memory encoding. Moreover, a measure of category-level similarity demonstrated a significant subsequent memory effect associated with item recognition (regardless of an object source memory detail), whereas the effect in older was associated with source memory. These results converge with predictions of computational models of dedifferentiation showing age-related reductions in the distinctiveness of neural patterns across multiple levels of representation.

Age-related differences in encoding-retrieval similarity and their relationship to false memory

Typical aging is associated with increases in false memory rates among older adults. Such errors are frequently associated with differential neural activity during encoding and retrieval in older compared to younger adults within visual cortices and the hippocampus. It remains unknown how pattern similarity reductions relate to false memories in healthy aging. Using encoding-retrieval similarity (ERS) analyses in a sample of younger and older adults, we examined how the similarity of neural patterns between memory phases associated with target and lure objects was impacted by age and contributed to false memory rates. Single-item ERS for targets and lures was reduced by age throughout much of the ventral visual stream and the posterior hippocampus. Furthermore, ERS associated with perceptual lures within the visual stream maintained differential relationships with false memory. Finally, a global ERS metric accounted for age deficits in single-item ERS, but did not contribute to false memory rates. These findings highlight the contribution of age-related reductions in ERS across multiple representational levels to false memories in healthy aging.

Predictive pre-activation of orthographic and lexical-semantic representations facilitates visual word recognition.

To a crucial extent, the efficiency of reading results from the fact that visual word recognition is faster in predictive contexts. Predictive coding models suggest that this facilitation results from pre-activation of predictable stimulus features across multiple representational levels before stimulus onset. Still, it is not sufficiently understood which aspects of the rich set of linguistic representations that are activated during reading-visual, orthographic, phonological, and/or lexical-semantic-contribute to context-dependent facilitation. To investigate in detail which linguistic representations are pre-activated in a predictive context and how they affect subsequent stimulus processing, we combined a well-controlled repetition priming paradigm, including words and pseudowords (i.e., pronounceable nonwords), with behavioral and magnetoencephalography measurements. For statistical analysis, we used linear mixed modeling, which we found had a higher statistical power compared to conventional multivariate pattern decoding analysis. Behavioral data from 49 participants indicate that word predictability (i.e., context present vs. absent) facilitated orthographic and lexical-semantic, but not visual or phonological processes. Magnetoencephalography data from 38 participants show sustained activation of orthographic and lexical-semantic representations in the interval before processing the predicted stimulus, suggesting selective pre-activation at multiple levels of linguistic representation as proposed by predictive coding. However, we found more robust lexical-semantic representations when processing predictable in contrast to unpredictable letter strings, and pre-activation effects mainly resembled brain responses elicited when processing the expected letter string. This finding suggests that pre-activation did not result in "explaining away" predictable stimulus features, but rather in a "sharpening" of brain responses involved in word processing.

The form of reference frames in vision: The case of intermediate shape-centered representations

Although a great deal is known about the early sensory and the later, perceptual, stages of visual processing, far less is known about the nature of intermediate representational units and reference frames. Progress in understanding intermediate levels of representations in vision is hindered by the complexity of interactions among multiple levels of representation in the visual system, making it difficult to isolate and study the nature of each particular level. Nature occasionally provides the opportunity to peer inside complex systems by isolating components of a system through accidental damage or genetic modification of neural components. We have recently reported the case of a young woman who perceives 2D bounded regions of space as if they were plane-rotated by 90, 180 or 270° around their center, mirrored across their own axes, or both. This suggested that an intermediate stage of processing consists in representing mutually exclusive 2D bounded regions extracted from the retinal image in their own “shape-centered” perceptual frame. We proposed to refer to this level of representation as “intermediate shape-centered representation” (ISCR). Here, we used Davida's pattern of errors across 9 experiments as a tool for specifying in greater detail the geometrical properties of the reference frame in which elongated and/or symmetrical shapes are represented at the level of the ISCR. The nature of Davida's errors in these experiments suggests that ISCRs are represented in reference frames composed of orthogonal axes aligned with and centered on the most elongated segment of elongated shapes and, for symmetrical shapes deprived of a straight segment, aligned with their axis of symmetry, and centered on their centroid.

The effects of divided attention at encoding on specific and gist-based associative episodic memory.

Effects of divided attention (DA) during encoding on later memory performance are widely documented. However, the precise nature of these effects on underlying memory representations and subsequent retrieval processes has not been thoroughly investigated. Here, we examined whether DA at encoding would disrupt young adults’ ability to remember associations in episodic memory at highly specific levels of representation (i.e., verbatim memory), or whether the effects of DA extend also to gist memory for associations. Two groups of participants (one under full attention, one under DA) studied face–scene pairs. The DA group simultaneously completed an auditory choice reaction-time task during encoding. Following either a short or long delay, participants were tested on their ability to discriminate intact face–scene pairs from recombined pairs that were either highly similar, less similar, or completely unrelated to originally studied pairs. The DA group performed more poorly than the full attention participants at correctly classifying most types of test pairs at both delays, and results from a multinomial-processing-tree model demonstrated that participants who encoded associations under DA experienced deficits in both specific and gist memory retrieval. We also compared the DA group to full attention older adults who were tested with the same paradigm (Greene & Naveh-Benjamin, Psychological Science, 31[3], 316–331, 2020). The DA group had lower estimates of gist retrieval than the older adults but similar estimates of verbatim memory. These results suggest that DA at encoding disrupts episodic memories at multiple levels of representation, in contrast to age-related effects, which are restricted only to the highest levels of specificity.Supplementary InformationThe online version contains supplementary material available at 10.3758/s13421-021-01196-9.

Attentional Modulation of Hierarchical Speech Representations in a Multitalker Environment.

Humans are remarkably adept in listening to a desired speaker in a crowded environment, while filtering out nontarget speakers in the background. Attention is key to solving this difficult cocktail-party task, yet a detailed characterization of attentional effects on speech representations is lacking. It remains unclear across what levels of speech features and how much attentional modulation occurs in each brain area during the cocktail-party task. To address these questions, we recorded whole-brain blood-oxygen-level-dependent (BOLD) responses while subjects either passively listened to single-speaker stories, or selectively attended to a male or a female speaker in temporally overlaid stories in separate experiments. Spectral, articulatory, and semantic models of the natural stories were constructed. Intrinsic selectivity profiles were identified via voxelwise models fit to passive listening responses. Attentional modulations were then quantified based on model predictions for attended and unattended stories in the cocktail-party task. We find that attention causes broad modulations at multiple levels of speech representations while growing stronger toward later stages of processing, and that unattended speech is represented up to the semantic level in parabelt auditory cortex. These results provide insights on attentional mechanisms that underlie the ability to selectively listen to a desired speaker in noisy multispeaker environments.

ProteoVision: web server for advanced visualization of ribosomal proteins.

ProteoVision is a web server designed to explore protein structure and evolution through simultaneous visualization of multiple sequence alignments, topology diagrams and 3D structures. Starting with a multiple sequence alignment, ProteoVision computes conservation scores and a variety of physicochemical properties and simultaneously maps and visualizes alignments and other data on multiple levels of representation. The web server calculates and displays frequencies of amino acids. ProteoVision is optimized for ribosomal proteins but is applicable to analysis of any protein. ProteoVision handles internally generated and user uploaded alignments and connects them with a selected structure, found in the PDB or uploaded by the user. It can generate de novo topology diagrams from three-dimensional structures. All displayed data is interactive and can be saved in various formats as publication quality images or external datasets or PyMol Scripts. ProteoVision enables detailed study of protein fragments defined by Evolutionary Classification of protein Domains (ECOD) classification. ProteoVision is available at http://proteovision.chemistry.gatech.edu/.

Dissociable electrophysiological measures of natural language processing reveal differences in speech comprehension strategy in healthy ageing

Healthy ageing leads to changes in the brain that impact upon sensory and cognitive processing. It is not fully clear how these changes affect the processing of everyday spoken language. Prediction is thought to play an important role in language comprehension, where information about upcoming words is pre-activated across multiple representational levels. However, evidence from electrophysiology suggests differences in how older and younger adults use context-based predictions, particularly at the level of semantic representation. We investigate these differences during natural speech comprehension by presenting older and younger subjects with continuous, narrative speech while recording their electroencephalogram. We use time-lagged linear regression to test how distinct computational measures of (1) semantic dissimilarity and (2) lexical surprisal are processed in the brains of both groups. Our results reveal dissociable neural correlates of these two measures that suggest differences in how younger and older adults successfully comprehend speech. Specifically, our results suggest that, while younger and older subjects both employ context-based lexical predictions, older subjects are significantly less likely to pre-activate the semantic features relating to upcoming words. Furthermore, across our group of older adults, we show that the weaker the neural signature of this semantic pre-activation mechanism, the lower a subject’s semantic verbal fluency score. We interpret these findings as prediction playing a generally reduced role at a semantic level in the brains of older listeners during speech comprehension and that these changes may be part of an overall strategy to successfully comprehend speech with reduced cognitive resources.

The origin of misconceptions in inorganic chemistry and their correction by computer modelling

The paper goal was to analyse the typical mistakes in the learning of the university course of inorganic chemistry, determine the origin of misconceptions and estimate the effectiveness of the use of computer simulations to correct false chemical concepts. Ten problems that are the most typical for students were revealed. One of the leading causes of their occurrence is the failure of many students to form mental relationships between different levels of representation of chemical knowledge - microscopic, macroscopic and symbolic. Other reasons include an insufficient understanding of the material, the incompleteness of the knowledge of the microscopic basis of processes, and inability to work with different models, including misunderstanding of their purpose and constraints. NetLogo programming environment was used for students’ self-administering tests to study gas laws. Scope for the usage of NetLogo models was estimated in correcting of incorrectly formed conceptions of the chemical knowledge. Independent work with NetLogo models facilitates the formation of stable relationships between multiple levels of representation of chemical information. It improves an understanding of the studied topic fundamentally, and this holds for all students practically independently of their grounding level in chemistry. The introduction of computer simulation into the practice of teaching chemical subjects shows promise. Still, it requires the solution of several scientific, methodological, logistical and organisational issues.

Hadoop Deep Neural Network for offending drivers

Deep learning is recently regarded as the closest artificial intelligence model to human brain. It is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text. Based on MapReduce framework and Hadoop distributed file system, this paper proposes a distributed approach for detect offending drivers and training the Deep Neural Network models such as Convolutional Neural Network (CNN) and Long Short Term Memory network (LSTM). Its implementation and performance are evaluated on Big Data platform Hadoop. The intelligence growing process of human brain requires learning from Big Data. The main contribution of this paper is that it is implemented to analyze traffic big data and to detect offending drivers in Hadoop by CNN with Support Vector Machine (SVM) and LSTM. The efficiency of the proposed method is computed by using experimental and theoretical analysis.