Search results for: long short-term memory networks (LSTM)

Authors: Luo Jin China, Jin Fang

Abstract:

Countryside has been generally recognized and regarded as a characteristic symbol which presents in human memory for a long time. As a result of the change of times, because of it’s failure to meet the growing needs of the growing life and mental decline, the vast rural area began to decline. But their history feature image which accumulated by the ancient tradition provides people with the origins of existence on the spiritual level, such as "identity" and "belonging", makes people closer to the others in the spiritual and psychological aspects of a common experience about the past, thus the sense of a lack of culture caused by the losing of memory symbols is weakened. So, in the modernization process, how to repair its vitality and transform and planning it in a sustainable way has become a hot topics in architectural and urban planning. This paper aims to break the constraints of disciplines, from the perspective of interdiscipline, using the research methods of systems science to analyze and discuss the theories and methods of rural form factors, which based on the viewpoint of memory in psychology. So, we can find a right way to transform the Rural to give full play to the role of the countryside in the actual use and the shape of history spirits.

Keywords: rural, sustainable renovation, restoration, psychology, memory

Procedia PDF Downloads 570

Authors: B. Sadek, N. Khan, Shreesh K. Ojha, Adel Sadeq, D. Lazewska, K. Kiec-Kononowicz

Abstract:

The involvement of Histamine H3 receptors (H3Rs) in memory and the potential role of H3R antagonists in pharmacological control of neurodegenerative disorders, e.g., Alzheimer disease (AD) is well established. Therefore, the memory-enhancing effects of the H3R antagonist DL77 on MK801-induced cognitive deficits were evaluated in passive avoidance paradigm (PAP) and novel object recognition (NOR) tasks in adult male rats, applying donepezil (DOZ) as a reference drug. Animals pretreated with acute systemic administration of DL77 (2.5, 5, and 10 mg/kg, i.p.) were significantly ameliorated in regard to MK801-induced memory deficits in PAP. The ameliorative effect of most effective dose of DL77 (5 mg/kg, i.p.) was abrogated when animals were pretreated with a co-injection with the H3R agonist R-(α)-methylhistamine (RAMH, 10 mg/kg, i.p.). Moreover, and in the NOR paradigm, DL77 (5 mg/kg, i.p.) reversed MK801-induced deficits long-term memory (LTM), and the DL77-provided procognitive effect was comparable to that of reference drug DOZ, and was reversed when animals were co-injected with RAMH (10 mg/kg, i.p.). However, DL77(5 mg/kg, i.p.) failed to alter short-term memory (STM) impairment in NOR test. Furthermore, DL77 (5 mg/kg) failed to induce any alterations of anxiety and locomotor behaviors of animals naive to elevated-plus maze (EPM), indicating that the ameliorative effects observed in PAP or NOR tests were not associated to alterations in emotions or in natural locomotion of tested animals. These results reveal the potential contribution of H3Rs in modulating CNS neurotransmission systems associated with neurodegenerative disorders, e.g., AD.

Keywords: histamine H3 receptor, antagonist, learning and memory, Alzheimer's disease, neurodegeneration, passive avoidance paradigm, novel object recognition, behavioral research

Procedia PDF Downloads 151

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations of previous approaches, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with attention mechanism. In a previous work on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: transformers, generative ai, gene expression design, classification

Procedia PDF Downloads 57

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 160

Authors: Marianna Constantinou, Hana Burianova, Ala Yankouskaya

Abstract:

Episodic memory retrieval benefits from arousal, with better performance linked to arousing to-be-remembered information. However, the enduring impact of arousal on subsequent memory processes, particularly for non-arousing stimuli, remains unclear. This functional Magnetic Resonance Imaging (fMRI) study examined the effects of arousal on episodic memory processes in young and old adults, focusing on memory of neutral information following arousal exposure. Neural activity was assessed at three distinct timepoints: during exposure to arousing and non-arousing stimuli, memory consolidation (with or without arousing stimulus exposure), and during memory retrieval (with or without arousing stimulus exposure). Behavioural results show that across both age groups, participants performed worse when retrieving episodic memories about a video preceded by a highly arousing negative image. Our fMRI findings reveal three key findings: i) the extension of the influence of negative arousal beyond encoding; ii) the presence of this influence in both young and old adults; iii) and the differential treatment of positive arousal between these age groups. Our findings emphasise valence-specific effects on memory processes and support the enduring impact of negative arousal. We further propose an age-related alteration in the old adult brain in differentiating between positive and negative arousal.

Keywords: episodic memory, ageing, fmri, arousal, valence

Procedia PDF Downloads 58

Authors: Eid Abo Hamza, Ahmed Helal

Abstract:

Purpose: The objective is to measure the capacity of the working memory, ie. the maximum number of elements that can be retrieved and processed, by measuring the basic functions of working memory (inhibition/transfer/update), and also to investigate its relationship to life stress and depressive thoughts. Methods: The study sample consisted of 50 students from Egypt. A cognitive task was designed to measure the working memory capacity based on the determinants found in previous research, which showed that cognitive tasks are the best measurements of the functions and capacity of working memory. Results: The results indicated that there were statistically significant differences in the level of life stress events (high/low) on the task of measuring the working memory capacity. The results also showed that there were no statistically significant differences between males and females or between academic major on the task of measuring the working memory capacity. Furthermore, the results reported that there was no statistically significant effect of the interaction of the level of life stress (high/low) and gender (male/female) on the task of measuring working memory capacity. Finally, the results showed that there were significant differences in the level of depressive thoughts (high/low) on the task of measuring working memory. Conclusions: The current research concludes that neither the interaction of stressful life events, gender, and academic major, nor the interaction of depressive thoughts, gender, and academic major, influence on working memory capacity.

Keywords: working memory, depression, stress, life event

Procedia PDF Downloads 156

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 127

Authors: K. Julia Rose Mary, Victor Arokia Doss

Abstract:

Electrical and chemical stimulations up-regulate phosphorylaion of CREB, a transcriptional factor that induces its target gene production for memory consolidation and Late Long-Term Potentiation (L-LTP) in CA1 region of the hippocampus. L-LTP requires complex interactions among second-messenger signaling cascade molecules such as cAMP, CAMKII, CAMKIV, MAPK, RSK, PKA, all of which converge to phosphorylate CREB which along with CBP induces the transcription of target genes involved in memory consolidation. A differential equation based model for L-LTP representing stimulus-mediated activation of downstream mediators which confirms the steep, supralinear stimulus-response effects of activation and inhibition was used. The same was extended to accommodate the inhibitory effect of the Inducible cAMP Early Repressor (ICER). ICER is the natural inducible CREB antagonist represses CRE-Mediated gene transcription involved in long-term plasticity for learning and memory. After verifying the sensitivity and robustness of the model, we had simulated it with various empirical levels of repressor concentration to analyse their effect on the gene induction. The model appears to predict the regulatory dynamics of repression on the L-LTP and agrees with the experimental values. The flux data obtained in the simulations demonstrate various aspects of equilibrium between the gene induction and repression.

Keywords: CREB, L-LTP, mathematical modeling, simulation

Procedia PDF Downloads 290

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of the flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on the spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts, as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with an attention mechanism. In previous works on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work, with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on the presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: machine learning, classification and regression, gene circuit design, bidirectional transformers

Procedia PDF Downloads 58

Authors: Rahimah Akbar, Abdullah Al-Hashemi, Hanan Taqi, Taiba Sadeq

Abstract:

As technology continues to develop, teaching curriculums in both schools and universities have begun adopting a more computer/digital based approach to the transmission of knowledge and information, as opposed to the more old-fashioned use of textbooks. This gives rise to the question: Are there any differences in learning from a digital source over learning from a printed source, as in from a textbook? More specifically, which medium of information results in better long-term retention? A review of the confounding factors implicated in understanding the relationship between learning from the two different mediums was done. Alongside this, a 4-week cohort study involving 76 1st year English Language female students was performed, whereby the participants were divided into 2 groups. Group A studied material from a paper source (referred to as the Print Medium), and Group B studied material from a digital source (Digital Medium). The dependent variables were grading of memory recall indexed by a 4 point grading system, and total frequency of item repetition. The study was facilitated by advanced computer software called Super Memo. Results showed that, contrary to prevailing evidence, the Digital Medium group showed no statistically significant differences in terms of the shift from Remember (Episodic) to Know (Semantic) when all confounding factors were accounted for. The shift from Random Guess and Familiar to Remember occurred faster in the Digital Medium than it did in the Print Medium.

Keywords: digital medium, print medium, long-term memory recall, episodic memory, semantic memory, super memo, forgetting index, frequency of repetitions, total time spent

Procedia PDF Downloads 288

Authors: Nagi Mekhiel

Abstract:

Many applications use vector operations by applying single instruction to multiple data that map to different locations in conventional memory. Transferring data from memory is limited by access latency and bandwidth affecting the performance gain of vector processing. We present a memory system that makes all of its content available to processors in time so that processors need not to access the memory, we force each location to be available to all processors at a specific time. The data move in different orbits to become available to other processors in higher orbits at different time. We use this memory to apply parallel vector operations to data streams at first orbit level. Data processed in the first level move to upper orbit one data element at a time, allowing a processor in that orbit to apply another vector operation to deal with serial code limitations inherited in all parallel applications and interleaved it with lower level vector operations.

Keywords: Memory Organization, Parallel Processors, Serial Code, Vector Processing

Procedia PDF Downloads 266

Authors: Grienggrai Rajchakit

Abstract:

As we all know that coronavirus is announced as a pandemic in the world by WHO. It is speeded all over the world with few days of time. To control this spreading, every citizen maintains social distance and self-preventive measures are the best strategies. As of now, many researchers and scientists are continuing their research in finding out the exact vaccine. The machine learning model finds that the coronavirus disease behaves in an exponential manner. To abolish the consequence of this pandemic, an efficient step should be taken to analyze this disease. In this paper, a recurrent neural network model is chosen to predict the number of active cases in a particular state. To make this prediction of active cases, we need a database. The database of COVID-19 is downloaded from the KAGGLE website and is analyzed by applying a recurrent LSTM neural network with univariant features to predict the number of active cases of patients suffering from the corona virus. The downloaded database is divided into training and testing the chosen neural network model. The model is trained with the training data set and tested with a testing dataset to predict the number of active cases in a particular state; here, we have concentrated on Andhra Pradesh state.

Keywords: COVID-19, coronavirus, KAGGLE, LSTM neural network, machine learning

Procedia PDF Downloads 154

Authors: Ayse Cobanoglu

Abstract:

Working memory can be defined as a workspace that holds and regulates active information in mind. This study investigates individual changes in children's working memory from kindergarten to first grade. The main purpose of the study is whether parental discipline methods and child impulsive/overactive behaviors affect children's working memory initial status and growth rate, controlling for gender, minority status, and socioeconomic status (SES). A linear growth curve model with the first four waves of the Early Childhood Longitudinal Study-Kindergarten Cohort of 2011 (ECLS-K:2011) is performed to analyze the individual growth of children's working memory longitudinally (N=3915). Results revealed that there is a significant variation among students' initial status in the kindergarten fall semester as well as the growth rate during the first two years of schooling. While minority status, SES, and children's overactive/impulsive behaviors influenced children's initial status, only SES and minority status were significantly associated with the growth rate of working memory. For parental discipline methods, such as giving a warning and ignoring the child's negative behavior, are also negatively associated with initial working memory scores. Following that, students' working memory growth rate is examined, and students with lower SES as well as minorities showed a faster growth pattern during the first two years of schooling. However, the findings of parental disciplinary methods on working memory growth rates were mixed. It can be concluded that schooling helps low-SES minority students to develop their working memory.

Keywords: growth curve modeling, impulsive/overactive behaviors, parenting, working memory

Procedia PDF Downloads 128

Authors: Amirmozafar Benshams, Khatere Kashmari, Farzad Hatami, Mesbah Saybani

Abstract:

Shape memory alloys with high capability of energy dissipation and large deformation bearing with return ability to their original shape without too much hysteresis strain have opened their place among the other damping systems as smart materials. Ninitol which is the most well-known and most used alloy material from the shape memory alloys family, has high resistance and fatigue and is coverage for large deformations. Shape memory effect and super-elasticity by shape alloys like Nitinol, are the reasons of the high power of these materials in energy depreciation. Thus, these materials are suitable for use in reciprocating dynamic loading conditions. The experiments results showed that Nitinol wires with small diameter have greater energy dissipation capability and by increase of diameter and thickness the damping capability and energy dissipation increase.

Keywords: shape memory alloys, shape memory effect, super elastic effect, nitinol, energy dissipation

Procedia PDF Downloads 507

Authors: Abbas Nesayan

Abstract:

Background: In recent years, autism has been under consideration in public and research area. Autistic children have dysfunction in communication, socialization, repetitive and stereotyped behaviors. In addition, they clinically suffer from difficulty in attention, challenge with familiar behaviors and sensory processing problems. Several variables are linked to sensory processing problems in autism, one of these variables is working memory. Working memory is part of the executive function which provides the necessary ability to completing multiple stages tasks. Method: This study has categorized in correlational research methods. After determining of entry criteria, according to purposive sampling method, 50 children were selected. Dunn’s sensory profile school companion was used for assessment of sensory processing patterns; behavioral rating inventory of executive functions was used (BRIEF) for assessment of working memory. Pearson correlation coefficient and linear regression were used for data analyzing. Results: The results showed the significant relationship between sensory processing patterns (low registration, sensory seeking, sensory sensitivity and sensory avoiding) with working memory in autistic children. Conclusion: According to the findings, there is the significant relationship between the patterns of sensory processing and working memory. So, in order to improve the working memory could be used some interventions based on the sensory processing.

Keywords: sensory processing patterns, working memory, autism, autistic children

Procedia PDF Downloads 215

Authors: Q. Raza

Abstract:

Getting old is inevitable, tasks which were once simple are now a daily struggle. This paper is a study of how older users interact with web application based upon a series of experiments. The experiments conducted involved 12 participants and the experiments were split into two parts. The first set gives the users a feel of current social networks and the second set take into considerations from the participants and the results of the two are compared. This paper goes in detail on the psychological aspects such as social exclusion, Metacognition memory and Therapeutic memories and how this relates to users becoming isolated from society, social networking can be the roof on a foundation of successful computer interaction. The purpose of this paper is to carry out a study and to propose new ideas to help users to be able to use social networking sites easily and efficiently.

Keywords: cognitive psychology, special memory, social networking and human computer interaction

Procedia PDF Downloads 441

Authors: Victor Breux, Jérôme Boutet, Alain Goret, Viviane Cattin

Abstract:

Early detection of anomalies in data centers is important to reduce downtimes and the costs of periodic maintenance. However, there is little research on this topic and even fewer on the fusion of sensor data for the detection of abnormal events. The goal of this paper is to propose a method for anomaly detection in data centers by combining sensor data (temperature, humidity, power) and deep learning models. The model described in the paper uses one autoencoder per sensor to reconstruct the inputs. The auto-encoders contain Long-Short Term Memory (LSTM) layers and are trained using the normal samples of the relevant sensors selected by correlation analysis. The difference signal between the input and its reconstruction is then used to classify the samples using feature extraction and a random forest classifier. The data measured by the sensors of a data center between January 2019 and May 2020 are used to train the model, while the data between June 2020 and May 2021 are used to assess it. Performances of the model are assessed a posteriori through F1-score by comparing detected anomalies with the data center’s history. The proposed model outperforms the state-of-the-art reconstruction method, which uses only one autoencoder taking multivariate sequences and detects an anomaly with a threshold on the reconstruction error, with an F1-score of 83.60% compared to 24.16%.

Keywords: anomaly detection, autoencoder, data centers, deep learning

Procedia PDF Downloads 188

Authors: S. Rozhkova, O. Rozhkova, A. Harlova, V. Lasukov

Abstract:

For optimal unbiased filter as mean-square and in the case of functioning anomalous noises in the observation memory channel, we have proved insensitivity of filter to inaccurate knowledge of the anomalous noise intensity matrix and its equivalence to truncated filter plotted only by non anomalous components of an observation vector.

Keywords: mathematical expectation, filtration, anomalous noise, memory

Procedia PDF Downloads 358

Authors: Svetlana Yefimenko

Abstract:

Situated within the fields of Russian literature, Russian history, and classics, this paper investigates the early writing of Leo Tolstoy in terms of his reception and appropriation of Homeric epic for the purposes of reconstructing early 19th-century Russian history. The epic mode, specifically its Homeric variation, was deployed in Tolstoy’s writing on his military experience in the Crimean War to legitimize a version of historical events which positioned Russian soldiers as the inheritors of ancient Greek heroism. With reference to Tolstoy’s oft-neglected Sevastopol’ Sketches, and the short stories The Raid, The Wood-Felling, and Two Hussars, this paper examines how such narratives pass from communicative memory into collective memory both in the Homeric epics and in Tolstoy’s reworking of them, particularly on the literary effects produced when the distance between communicative and collective memory collapses. Within a song culture, epic song functions as memory, and this paper shows how, by modeling his early work on epic, Tolstoy produced texts which act as memory itself, thereby becoming the authoritative version of Russia’s past in the Crimea, often contradicting historical facts.

Keywords: classical reception, collective memory, Russian history, Russian literature

Procedia PDF Downloads 126

Authors: Shreyansh Singh, Afroz Ahmed

Abstract:

Sentiment Analysis intends to naturally reveal the hidden mentality that we hold towards an entity. The total of this assumption over a populace addresses sentiment surveying and has various applications. Current text-based sentiment analysis depends on the development of word embeddings and Machine Learning models that take in conclusion from enormous text corpora. Sentiment Analysis from text is presently generally utilized for consumer loyalty appraisal and brand insight investigation. With the expansion of online media, multimodal assessment investigation is set to carry new freedoms with the appearance of integral information streams for improving and going past text-based feeling examination using the new transforms methods. Since supposition can be distinguished through compelling follows it leaves, like facial and vocal presentations, multimodal opinion investigation offers good roads for examining facial and vocal articulations notwithstanding the record or printed content. These methodologies use the Recurrent Neural Networks (RNNs) with the LSTM modes to increase their performance. In this study, we characterize feeling and the issue of multimodal assessment investigation and audit ongoing advancements in multimodal notion examination in various spaces, including spoken surveys, pictures, video websites, human-machine, and human-human connections. Difficulties and chances of this arising field are additionally examined, promoting our theory that multimodal feeling investigation holds critical undiscovered potential.

Keywords: sentiment analysis, RNN, LSTM, word embeddings

Procedia PDF Downloads 113

Authors: Mamouni Mohammed Dhiya Eddine

Abstract:

This work aims at studying the exploitation of high-speed networks of clusters for distributed storage. Parallel applications running on clusters require both high-performance communications between nodes and efficient access to the storage system. Many studies on network technologies led to the design of dedicated architectures for clusters with very fast communications between computing nodes. Efficient distributed storage in clusters has been essentially developed by adding parallelization mechanisms so that the server(s) may sustain an increased workload. In this work, we propose to improve the performance of distributed storage systems in clusters by efficiently using the underlying high-performance network to access distant storage systems. The main question we are addressing is: do high-speed networks of clusters fit the requirements of a transparent, efficient and high-performance access to remote storage? We show that storage requirements are very different from those of parallel computation. High-speed networks of clusters were designed to optimize communications between different nodes of a parallel application. We study their utilization in a very different context, storage in clusters, where client-server models are generally used to access remote storage (for instance NFS, PVFS or LUSTRE). Our experimental study based on the usage of the GM programming interface of MYRINET high-speed networks for distributed storage raised several interesting problems. Firstly, the specific memory utilization in the storage access system layers does not easily fit the traditional memory model of high-speed networks. Secondly, client-server models that are used for distributed storage have specific requirements on message control and event processing, which are not handled by existing interfaces. We propose different solutions to solve communication control problems at the filesystem level. We show that a modification of the network programming interface is required. Data transfer issues need an adaptation of the operating system. We detail several propositions for network programming interfaces which make their utilization easier in the context of distributed storage. The integration of a flexible processing of data transfer in the new programming interface MYRINET/MX is finally presented. Performance evaluations show that its usage in the context of both storage and other types of applications is easy and efficient.

Keywords: distributed storage, remote file access, cluster, high-speed network, MYRINET, zero-copy, memory registration, communication control, event notification, application programming interface

Procedia PDF Downloads 214

Authors: Samhani Ismail, Tahamina Begum, Faruque Reza, Zamzuri Idris, Hafizan Juahir, Jafri Malin Abdullah

Abstract:

Holy Quran, a rhymed prosed scripture has a complete literary structure that exemplifies the peak of literary beauty. Memorizing of its verses could enhance one’s memory capacity and cognition while those who are listening to its recitation it is also believed that the Holy Quran alter brainwave producing neuronal excitation engaging with cognitive processes. 28 normal healthy subjects (male =14 & female = 14) were recruited and EEG recording was done using 128-electrode sensor net (Electrical Geosics, Inc.) with the impedance of ≤ 50kΩ. They listened to Sura Fatiha recited by Sheikh Qari Abdul Basit bin Abdus Samad. Arabic news and no sound were chosen as positive and negative control, respectively. The waveform was analysed by Fast Fourier Transform (FFT) to get the power in frequency bands. Bilateral frontal (F7, F8) and temporal region (T7, T8) showed decreased power significantly in alpha wave band in respondent stimulated by Sura Fatihah recitation reflects acoustic attention processing. However, decreased in alpha power in selective attention to memorized, and in familial but not memorized language, reveals the memorial processing in long-term memory. As a conclusion, Quranic recitation relates both cognitive element of memory and language in its listeners and memorizers.

Keywords: auditory stimulation, cognition, EEG, linguistic, memory, Quranic recitation

Procedia PDF Downloads 337

Authors: Sachin Deshmukh

Abstract:

Mind and body synchronization occurs through memory and sensation production. Sensations are the guiding language of subconscious mind for conscious mind to take a proper action. Mind-mechanism is based upon memories collected so far since intrauterine life. There are three universal triggers for memory creation; they are persons, situations and objects. Memory is created as sensations experienced by special senses. Based upon experiencing comfort or discomfort, the triggers are categorized as safe or unsafe triggers. A memory comprises of ‘safe or unsafe feeling for triggers, and actions taken for that feeling’. Memories for triggers are created slowly, thoughtfully and consciously by the conscious mind, and archived in the subconscious mind for future references. Later on, similar triggers can come in contact with the individual. Subconscious mind uses these stored feelings to decide whether these triggers are safe or unsafe. It produces comfort or discomfort sensations as emotions accordingly and reacts in the same way as has been recorded in memory. Speed of sensing and processing the triggers, and reacting by subconscious mind is that of the speed of bioelectricity. Hence, formula for human emotions has been designed in this paper as follows: Emotion (Stress or Peace) = Trigger (Person or Situation or object) x Mass of feelings (stressful or peaceful) associated with the Trigger x Speed of Light². We also establish modern medical scientific facts about relationship between reflex activity and memory. This research further develops the ‘Rational Memory Therapy’ focusing on therapeutic feelings conversion techniques, for stress prevention and management.

Keywords: memory, sensations, feelings, emotions, rational memory therapy

Procedia PDF Downloads 251

Authors: Niklas Panten, Eberhard Abele

Abstract:

This paper presents a novel approach for real-time and near-optimal control of industrial smart grids by deep reinforcement learning (DRL). To achieve highly energy-efficient factory systems, the energetic linkage of machines, technical building equipment and the building itself is desirable. However, the increased complexity of the interacting sub-systems, multiple time-variant target values and stochastic influences by the production environment, weather and energy markets make it difficult to efficiently control the energy production, storage and consumption in the hybrid industrial smart grids. The studied deep reinforcement learning approach allows to explore the solution space for proper control policies which minimize a cost function. The deep neural network of the DRL agent is based on a multilayer perceptron (MLP), Long Short-Term Memory (LSTM) and convolutional layers. The agent is trained within multiple Modelica-based factory simulation environments by the Advantage Actor Critic algorithm (A2C). The DRL controller is evaluated by means of the simulation and then compared to a conventional, rule-based approach. Finally, the results indicate that the DRL approach is able to improve the control performance and significantly reduce energy respectively operating costs of industrial smart grids.

Keywords: industrial smart grids, energy efficiency, deep reinforcement learning, optimal control

Procedia PDF Downloads 188

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 125

Authors: Anca Radulescu, Danae Evans

Abstract:

The relationship between a network’s hardwiring and its emergent dynamics are central to neuroscience. We study the principles of this correspondence in a canonical setup (in which network nodes exhibit well-studied complex quadratic dynamics), then test their universality in biological networks. By extending methods from discrete dynamics, we study the effects of network connectivity on temporal patterns, encapsulating long-term behavior into the rich topology of network Mandelbrot sets. Then elements of fractal geometry can be used to predict and classify network behavior.

Keywords: canonical model, complex dynamics, dynamic networks, fractals, Mandelbrot set, network connectivity

Procedia PDF Downloads 304

Authors: Gabrielle Veloso, Welison Ty

Abstract:

Trait anxiety is a pervasive tendency to attend to and experience fears and worries to a disproportionate degree, across various situations. This study sought to determine if participants who undergo emotional working memory training will have significantly lower scores on the trait anxiety scales post-intervention. The study also sought to determine if emotional regulation mediated the relationship between working memory training and trait anxiety. Forty-nine participants underwent 20 days of computerized emotional working memory training called Emotional Dual n-back, which involves viewing a continuous stream of emotional content on a grid, and then remembering the location and color of items presented on the grid. Participants of the treatment group had significantly lower trait anxiety compared to controls post-intervention. Mediation analysis determined that working memory training had no significant relationship to anxiety as measured by the Beck’s Anxiety Inventory-Trait (BAIT), but was significantly related to anxiety as measured by form Y2 of the Spielberger State-Trait Anxiety Inventory (STAI-Y2). Emotion regulation, as measured by the Emotional Regulation Questionnaire (ERQ), was found not to mediate between working memory training and trait anxiety reduction. Results suggest that working memory training may be useful in reducing psychoemotional symptoms rather than somatic symptoms of trait anxiety. Moreover, it proposes for future research to further look into the mediating role of emotion regulation via neuroimaging and the development of more comprehensive measures of emotion regulation.

Keywords: anxiety, emotion regulation, working-memory, working-memory training

Procedia PDF Downloads 145

Authors: Pyung Soo Kim, Eung Hyuk Lee, Mun Suck Jang

Abstract:

In the current paper, a residual generation filter with finite memory structure is proposed for fault detection. The proposed finite memory residual generation filter provides the residual by real-time filtering of fault vector using only the most recent finite observations and inputs on the window. It is shown that the residual given by the proposed residual generation filter provides the exact fault for noise-free systems. Finally, to illustrate the capability of the proposed residual generation filter, numerical examples are performed for the discretized DC motor system having the multiple sensor faults.

Keywords: residual generation filter, finite memory structure, kalman filter, fast detection

Procedia PDF Downloads 694

Authors: Farzaneh Badinlou, Reza Kormi-Nouri, Monika Knopf, Kamal Kharazi

Abstract:

Research into long-term memory has demonstrated that the richness of the knowledge base cues in memory tasks improves retrieval process, which in turn influences learning and memory performance. The present research investigated the idea that adding cues connected to knowledge can affect memory performance in the context of action memory in children. In action memory studies, participants are instructed to learn a series of verb–object phrases as verbal learning and experience-based learning (learning by doing and learning by observation). It is well established that executing action phrases is a more memorable way to learn than verbally repeating the phrases, a finding called enactment effect. In the present study, a total of 410 students from four grade groups—2nd, 4th, 6th, and 8th—participated in this study. During the study, participants listened to verbal action phrases (VTs), performed the phrases (SPTs: subject-performed tasks), and observed the experimenter perform the phrases (EPTs: experimenter-performed tasks). During the test phase, cued recall test was administered. Semantic relational cues (i.e., well-integrated vs. poorly integrated items) were manipulated in the present study. In that, the participants were presented two lists of action phrases with high semantic integration between verb and noun, e.g., “write with the pen” and with low semantic integration between verb and noun, e.g., “pick up the glass”. Results revealed that experience-based learning had a better results than verbal learning for both well-integrated and poorly integrated items, though manipulations of semantic relational cues can moderate the enactment effect. In addition, children of different grade groups outperformed for well- than poorly integrated items, in flavour of older children. The results were discussed in relation to the effect of knowledge-based information in facilitating retrieval process in children.

Keywords: action memory, enactment effect, knowledge-based cues, school-aged children, semantic relational cues

Procedia PDF Downloads 273

Authors: Kostas Kouvaris, Anastasia Eleftheriou, Georgios A. Sarantitis, Apostolos Chondronasios

Abstract:

To achieve the objective of almost zero carbon energy solutions by 2050, the EU needs to accelerate the development of integrated, highly efficient and environmentally friendly solutions. In this direction, district heating and cooling (DHC) emerges as a viable and more efficient alternative to conventional, decentralized heating and cooling systems, enabling a combination of more efficient renewable and competitive energy supplies. In this paper, we develop a forecasting tool for near real-time local weather and thermal energy demand predictions for an entire DHC network. In this fashion, we are able to extend the functionality and to improve the energy efficiency of the DHC network by predicting and adjusting the heat load that is distributed from the heat generation plant to the connected buildings by the heat pipe network. Two case-studies are considered; one for Vransko, Slovenia and one for Montpellier, France. The data consists of i) local weather data, such as humidity, temperature, and precipitation, ii) weather forecast data, such as the outdoor temperature and iii) DHC operational parameters, such as the mass flow rate, supply and return temperature. The external temperature is found to be the most important energy-related variable for space conditioning, and thus it is used as an external parameter for the energy demand models. For the development of the forecasting tool, we use state-of-the-art deep neural networks and more specifically, recurrent networks with long-short-term memory cells, which are able to capture complex non-linear relations among temporal variables. Firstly, we develop models to forecast outdoor temperatures for the next 24 hours using local weather data for each case-study. Subsequently, we develop models to forecast thermal demand for the same period, taking under consideration past energy demand values as well as the predicted temperature values from the weather forecasting models. The contributions to the scientific and industrial community are three-fold, and the empirical results are highly encouraging. First, we are able to predict future thermal demand levels for the two locations under consideration with minimal errors. Second, we examine the impact of the outdoor temperature on the predictive ability of the models and how the accuracy of the energy demand forecasts decreases with the forecast horizon. Third, we extend the relevant literature with a new dataset of thermal demand and examine the performance and applicability of machine learning techniques to solve real-world problems. Overall, the solution proposed in this paper is in accordance with EU targets, providing an automated smart energy management system, decreasing human errors and reducing excessive energy production.

Keywords: machine learning, LSTMs, district heating and cooling system, thermal demand

Procedia PDF Downloads 137