Search results for: convolutional long short-term memory

Authors: Derssie Mebratu

Abstract:

As a large variety of micro services, web services, social graphic applications, and media applications are continuously developed, it is substantially vital to design and build a reliable, efficient, and faster memory tiering system. Despite limited design, implementation, and deployment in the last few years, several techniques are currently developed to improve a memory tiering system in a cloud. Some of these techniques are to develop an optimal scanning frequency; improve and track pages movement; identify pages that recently accessed; store pages across each tiering, and then identify pages as a hot, warm, and cold so that hot pages can store in the first tiering Dynamic Random Access Memory (DRAM) and warm pages store in the second tiering Compute Express Link(CXL) and cold pages store in the third tiering Non-Volatile Memory (NVM). Apart from the current proposal and implementation, we also develop a new technique based on a machine learning algorithm in that the throughput produced 25% improved performance compared to the performance produced by the baseline as well as the latency produced 95% improved performance compared to the performance produced by the baseline.

Keywords: machine learning, bayesian optimization, memory tiering, CXL, DRAM

Procedia PDF Downloads 69

Authors: Harshit Mittal, Neeraj Garg

Abstract:

Hand symbol recognition is a pivotal component in the domain of computer vision, with far-reaching applications spanning sign language interpretation, human-computer interaction, and accessibility. This research paper discusses the approach with the integration of the Canny Edge algorithm and convolutional neural network. The significance of this study lies in its potential to enhance communication and accessibility for individuals with hearing impairments or those engaged in gesture-based interactions with technology. In the experiment mentioned, the data is manually collected by the authors from the webcam using Python codes, to increase the dataset augmentation, is applied to original images, which makes the model more compatible and advanced. Further, the dataset of about 6000 coloured images distributed equally in 5 classes (i.e., 1, 2, 3, 4, 5) are pre-processed first to gray images and then by the Canny Edge algorithm with threshold 1 and 2 as 150 each. After successful data building, this data is trained on the Convolutional Neural Network model, giving accuracy: 0.97834, precision: 0.97841, recall: 0.9783, and F1 score: 0.97832. For user purposes, a block of codes is built in Python to enable a window for hand symbol recognition. This research, at its core, seeks to advance the field of computer vision by providing an advanced perspective on hand sign recognition. By leveraging the capabilities of the Canny Edge algorithm and convolutional neural network, this study contributes to the ongoing efforts to create more accurate, efficient, and accessible solutions for individuals with diverse communication needs.

Keywords: hand symbol recognition, computer vision, Canny edge algorithm, convolutional neural network

Procedia PDF Downloads 33

Authors: Jinny Hong, Jeanne C. Watson

Abstract:

Three types of autobiographical memory recall -specific, episodic, and generic- were examined in relation to the quality of descriptions and in-session levels of emotional arousal. Correlational analyses and general estimating equation were conducted to test the relationships between 1) quality of descriptions and type of memory, 2) type of memory and emotional arousal, and 3) quality of descriptions and emotional arousal. The data was transcripts drawn from an archival randomized-control study comparing cognitive-behavioral therapy and emotion-focused therapy in a 16-week treatment for depression. Autobiographical memory recall segments were identified and sorted into three categories: specific, episodic, and generic. Quality of descriptions of these segments was then operationalized and measured using the Referential Activity Scale, and each memory segment was rated on four dimensions: concreteness, specificity, clarity, and overall imagery. Clients’ level of emotional arousal for each recall was measured using the Client’s Expression Emotion Scale. Contrary to the predictions, generic memories are associated with higher emotional arousal ratings and descriptive language ratings compared to specific memories. However, a positive relationship emerged between the quality of descriptions and expressed emotional arousal, indicating that the quality of descriptions in which memories are described in sessions is more important than the type of memory recalled in predicting clients’ level of emotional arousal. The results from this study provide a clearer understanding of the role of memory recall types and use of language in activating emotional arousal in psychotherapy sessions in a depressed sample.

Keywords: autobiographical memory recall, emotional arousal, psychotherapy for depression, quality of descriptions, referential activity

Procedia PDF Downloads 139

Authors: Aragorn Joaquin Pineda Dela Cruz

Abstract:

Road traffic congestion is continually deteriorating in Hong Kong. The largest contributing factor is the increase in vehicle fleet size, resulting in higher competition over the utilisation of road space. This study proposes a project that can process closed-circuit television images and videos to provide real-time traffic detection and prediction capabilities. Specifically, a deep-learning model involving computer vision techniques for video and image-based vehicle counting, then a separate model to detect and predict traffic congestion levels based on said data. State-of-the-art object detection models such as You Only Look Once and Faster Region-based Convolutional Neural Networks are tested and compared on closed-circuit television data from various major roads in Hong Kong. It is then used for training in long short-term memory networks to be able to predict traffic conditions in the near future, in an effort to provide more precise and quicker overviews of current and future traffic conditions relative to current solutions such as navigation apps.

Keywords: intelligent transportation system, vehicle detection, traffic analysis, deep learning, machine learning, computer vision, traffic prediction

Procedia PDF Downloads 70

Authors: Vaishnavi Shivde, Shrishti Sinha, Trapti Mishra

Abstract:

Traffic light detection from a moving vehicle is an important technology both for driver safety assistance functions as well as for autonomous driving in the city. This paper proposed a deep-learning-based traffic light recognition method that consists of a pixel-wise image segmentation technique and a fully convolutional network i.e., UNET architecture. This paper has used a method for detecting the position and recognizing the state of the traffic lights in video sequences is presented and evaluated using Traffic Light Dataset which contains masked traffic light image data. The first stage is the detection, which is accomplished through image processing (image segmentation) techniques such as image cropping, color transformation, segmentation of possible traffic lights. The second stage is the recognition, which means identifying the color of the traffic light or knowing the state of traffic light which is achieved by using a Convolutional Neural Network (UNET architecture).

Keywords: traffic light detection, image segmentation, machine learning, classification, convolutional neural networks

Procedia PDF Downloads 135

Authors: Mary Dorothy Roxas, Jeian Mae Dungca, Reginald Agor, Beatriz Figueroa, Lennon Andre Patricio, Honey Joy Cabahug

Abstract:

Parentification occurs when children are expected to provide instrumental or emotional caregiving within the family. It was found that parentification has the latter effect on adolescents’ cognitive and emotional vulnerability. Attachment theory helps clarify the process of parentification as it involves the relationship between the child and the parent. Carandang theory of “taga-salo” helps explain parentification in the Philippines setting. The present study examined the potential risk of parentification on adolescent’s memory retention by hypothesizing that there is a correlation between the two. The research was conducted with 249 female adolescents ages 12-24, residing in Valenzuela City. Results indicated that there is a significant inverse correlation between parentification and memory retention.

Keywords: memory retention, neurocognitive, parentification, stress

Procedia PDF Downloads 560

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 41

Authors: Motonobu Hattori

Abstract:

In neural networks, when new patters are learned by a network, they radically interfere with previously stored patterns. This drawback is called catastrophic forgetting. We have already proposed a biologically inspired dual-network memory model which can much reduce this forgetting for static patterns. In this model, information is first stored in the hippocampal network, and thereafter, it is transferred to the neocortical network using pseudo patterns. Because, temporal sequence learning is more important than static pattern learning in the real world, in this study, we improve our conventional dual-network memory model so that it can deal with temporal sequences without catastrophic forgetting. The computer simulation results show the effectiveness of the proposed dual-network memory model.

Keywords: catastrophic forgetting, dual-network, temporal sequences, hippocampal

Procedia PDF Downloads 239

Authors: Li Yu, Chenlu Jiao, Hongrun Xin, Yan Wang, Kaiyang Wang

Abstract:

In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.

Keywords: deep learning, convolutional neural network, LSTM, housing prediction

Procedia PDF Downloads 275

Authors: Shourav Chowdhury, Subrata Barua, K. M. Naimuddin, Imam Hassan Sajib, Md. Hasan, Shudipta Banik, Muna Das

Abstract:

Traffic accidents stand as a leading cause of fatalities worldwide, significantly impacting global mortality rates. Accurate classification of road accidents through advanced technological solutions presents a crucial opportunity to revolutionize accident prevention and emergency response strategies. This paper presents an advanced deep-learning methodology customized for the classification of road accidents using CCTV surveillance footage. This real-time dataset, comprising approximately 18,000 frames, has been amassed, which is pivotal for enabling comprehensive research in this field. This substantial dataset is the foundation for these investigative efforts, providing a rich and diverse source for conducting an in-depth analysis of the features. It has achieved a remarkable accuracy of 97% on this dataset through the strategic utilization of transfer learning in conjunction with LSTM (Long short-term memory) techniques. This accomplishment underscores the efficacy of our approach, combining the strengths of transfer learning and LSTM models, resulting in a highly accurate classification system for road accident events.

Keywords: accident, CCTV, footage, long short-term memory, surveillance

Procedia PDF Downloads 23

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 301

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 38

Authors: Sharun Akter Khushbu

Abstract:

‘SOS’ addresses text summary such as feasibility study and allows more comprehensive methods on text of language resources. Resources language has been exploited by the importance of text documental procedure. Throughout this key idea will come out a machine interpreter called an SOS that has built an argumentative as an employed model is LSTM-CNN(long short-term memory- recurrent neural network). Summarization of Bengali text formulated by the information of latent structure instead of brief input string counting as text. Text summarization is the proper utilization of optimal solutions being time reduction, and easy interpretation whenever human-generated summary and machine targeted summary remain similar and without degrading the semantic summarization quality. According to the problem affirmation key idea has advanced an algorithm with the method of encoder and decoder describing a sequential structure that is rigorously connected with actual predicted and meaningful output. Regarding the seq2seq approach aimed in the future with high semantic summarization similarity on behalf of the large data samples that are also enlisted by the method. Thus, the SOS method assigns a discriminator over Bengali text documents where encoded input sequences such as summary and decoded the targeted summary of gist will be an error-free machine.

Keywords: LSTM-CNN, NN, SOS, text summarization

Procedia PDF Downloads 41

Authors: Hope Amba Neji

Abstract:

The study adopted a quasi-experimental design. Two schools were used for the experimental study, while one school was used for the control. The experimental groups were subjected to treatment for four weeks with chemistry museum artifacts and a visit as made to the museum so that learners would have real-life learning experiences with museum resources, while the control group was taught with the conventional method. The instrument for the study was a 20-item Chemistry Memory Test (CMT) and a 10-item Chemistry Interest Questionnaire (CIQ). The reliability was ascertained using (KR-20) and alpha reliability coefficient, which yielded a reliability coefficient of .83 and .81, respectively. Data obtained was analyzed using Analysis of Covariance (ANCOVA) and Analysis of variance (ANOVA) at 0.05 level of significance. Findings revealed that museum artifacts have a significant effect on students’ memory enhancement and interest in chemistry. It was recommended chemistry learning should be enhanced, motivating and real with museum artifacts, which significantly aid memory enhancement and interest in chemistry.

Keywords: museum artifacts, memory, chemistry, atitude

Procedia PDF Downloads 35

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 166

Authors: Chhavi Saxena

Abstract:

FinFETs can be a replacement for bulk-CMOS transistors in many different designs. Its low leakage/standby power property makes FinFETs a desirable option for memory sub-systems. Memory modules are widely used in most digital and computer systems. Leakage power is very important in memory cells since most memory applications access only one or very few memory rows at a given time. As technology scales down, the importance of leakage current and power analysis for memory design is increasing. In this paper, we discover an option for low power interconnect synthesis at the 32nm node and beyond, using Fin-type Field-Effect Transistors (FinFETs) which are a promising substitute for bulk CMOS at the considered gate lengths. We consider a mechanism for improving FinFETs efficiency, called variable supply voltage schemes. In this paper, we’ve illustrated the design and implementation of FinFET based 4x4 SRAM cell array by means of one bit 7T SRAM. FinFET based 7T SRAM has been designed and analysis have been carried out for leakage current, dynamic power and delay. For the validation of our design approach, the output of FinFET SRAM array have been compared with standard CMOS SRAM and significant improvements are obtained in proposed model.

Keywords: FinFET, 7T SRAM cell, leakage current, delay

Procedia PDF Downloads 427

Authors: Ivana Hrebickova, Maria Sevcikova, Romana Slamberova

Abstract:

The present study was aimed at evaluation of cognitive changes following scheduled neonatal methamphetamine exposure in combination with long-term exposure in adulthood of female Wistar rats. Pregnant mothers were divided into two groups: group with indirect exposure (methamphetamine in dose 5 mg/ml/kg, saline in dose 1 ml/kg) during early lactation period (postnatal day 1–11) - progeny of these mothers were exposed to the effects of methamphetamine or saline indirectly via the breast milk; and the second group with direct exposure – all mothers were left intact for the entire lactation period, while progeny was treated with methamphetamine (5 mg/ml/kg) by injection or the control group, which was received needle pick (shame, not saline) at the same time each day of period of application (postnatal day 1–11). Learning ability and memory consolidation were tested in the Morris Water Maze, which consisted of three types of tests: ‘Place Navigation Test ‘; ‘Probe Test ‘; and ‘Memory Recall Test ‘. Adult female progeny were injected daily, after completion last trial with saline or methamphetamine (1 mg/ml/kg). We compared the effects of indirect/direct neonatal methamphetamine exposure and adult methamphetamine treatment on cognitive function of female rats. Statistical analyses showed that neonatal methamphetamine exposure worsened spatial learning and ability to remember the position of the platform. The present study demonstrated that direct methamphetamine exposure has more significant impact on process of learning and memory than indirect exposure. Analyses of search strategies (thigmotaxis, scanning) used by females during the Place Navigation Test and Memory Recall Test confirm all these results.

Keywords: methamphetamine, Morris water maze, neonatal exposure, strategies, Wistar rats

Procedia PDF Downloads 236

Authors: Mingaile Jurkute, Vilnius University

Abstract:

The memory of the Lithuanian partisan war (1944-1953) underwent extremely dramatic transformations. During this war, the image of the resistance and a partisan was one of the key elements of Lithuanian identity. Its importance is evidenced by the extremely large legacy of songs about partisans, no other topic has collected so much folklore in Lithuania. In the Soviet years, this resistance was practically forced to be forgotten. Terror and Soviet laws have forced people to stop talking about the events, even in the family circle. In addition, the Soviets created their own propaganda story, reinterpreting the Lithuanian partisan war, presenting partisans as bandits who brutally tortured and murdered locals. But even in the Soviet years, the memory could neither be completely suppressed, nor completely transformed into wishful shape. The analysis of fiction and cinema shows that the traumatic memory of real events rushed to the surface, thus transforming the very propagandistic narrative. After the restoration of the Republic of Lithuania in 1990, the Lithuanian partisan war was gradually returned to the central place of Lithuanian history. After 2014 the nationalist heroic narrative about Lithuanian partisans became the central narrative of modern Lithuanian history. Nevertheless, interviews I conducted in Lithuanian villages reveal that the memory of local communities and families preserves quite different experiences that do not fit into neither the Soviet narrative nor the heroic one. Such experiences include, for example, partisan violence against local families. This paper is about the efforts of two political ideologies (the Soviet and the Lithuanian patriotic) to use the history of the Lithuanian partisans for their own needs, and the attempts of small communities (mostly families) to resist these efforts. The research reveals that family memory, even when opposed to aggressive state memory policies, can preserve counter-narratives by exploiting unexpected objects beyond the control of the state, such as nature and wildlife. Basically, the paper analyses the limits of the instrumentalization of memory, even by extremely aggressive political regimes.

Keywords: collective memory, post-memory, violence, military conflict, family memory

Procedia PDF Downloads 70

Authors: Lana Burmistrova

Abstract:

Introduction: The influence of visual impairments on several cognitive processes used in the music learning process is an increasingly important area in special education and cognitive musicology. Many children have several visual impairments due to the refractive errors and irreversible inhibitors. However, based on the compensatory neuroplasticity and functional reorganization, congenitally blind (CB) and early blind (EB) individuals use several areas of the occipital lobe to perceive and process auditory and tactile information. CB individuals have greater memory capacity, memory reliability, and less false memory mechanisms are used while executing several tasks, they have better working memory (WM) and short-term memory (STM). Blind individuals use several strategies while executing tactile and working memory n-back tasks: verbalization strategy (mental recall), tactile strategy (tactile recall) and combined strategies. Methods and design: The aim of the pilot study was to substantiate similar tendencies while executing attention, memory and combined auditory tasks in blind and sighted individuals constructed for this study, and to investigate attention, memory and combined mechanisms used in the music learning process. For this study eight (n=8) blind and eight (n=8) sighted individuals aged 13-20 were chosen. All respondents had more than five years music performance and music learning experience. In the attention task, all respondents had to identify pitch changes in tonal and randomized melodic pairs. The memory task was based on the mismatch negativity (MMN) proportion theory: 80 percent standard (not changed) and 20 percent deviant (changed) stimuli (sequences). Every sequence was named (na-na, ra-ra, za-za) and several items (pencil, spoon, tealight) were assigned for each sequence. Respondents had to recall the sequences, to associate them with the item and to detect possible changes. While executing the combined task, all respondents had to focus attention on the pitch changes and had to detect and describe these during the recall. Results and conclusion: The results support specific features in CB and EB, and similarities between late blind (LB) and sighted individuals. While executing attention and memory tasks, it was possible to observe the tendency in CB and EB by using more precise execution tactics and usage of more advanced periodic memory, while focusing on auditory and tactile stimuli. While executing memory and combined tasks, CB and EB individuals used passive working memory to recall standard sequences, active working memory to recall deviant sequences and combined strategies. Based on the observation results, assessment of blind respondents and recording specifics, following attention and memory correlations were identified: reflective attention and STM, reflective attention and periodic memory, auditory attention and WM, tactile attention and WM, auditory tactile attention and STM. The results and the summary of findings highlight the attention and memory features used in the music learning process in the context of blindness, and the tendency of the several attention and memory types correlated based on the task, strategy and individual features.

Keywords: attention, blindness, memory, music learning, strategy

Procedia PDF Downloads 156

Authors: Leila Maleki, Ezatollah Ahmadi

Abstract:

The aim of this study was to investigate the effectiveness of memory training exercise on cognitive flexibility. The method of this study was experimental. The statistical population selected 40 students 14 years old, samples were chosen by available sampling method and then they were replaced in experimental (training program) group and control group randomly and answered to Wisconsin Card Sorting Test; covariance test results indicated that there were a significant in post-test scores of experimental group (p<0.005).

Keywords: cognitive flexibility, working memory exercises, problem solving, reaction time

Procedia PDF Downloads 384

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: convolutional neural network, discrete wavelet transform, deep learning, heart sound classification

Procedia PDF Downloads 318

Authors: Rui Xing, Baolin Ye, Nan Zhou, Guohong Wang

Abstract:

Drawing upon a perspective of cognitive interaction, this study explores the relationship between team cognitive heterogeneity and team strategic decision-making flexibility, treating the transactive memory system as a mediator and task complexity as a moderator. The hypotheses were tested in linear regression models by using data gathered from 67 strategic decision-making teams in the new-energy vehicle industry. It is found that team cognitive heterogeneity has a positive impact on strategic decision-making flexibility through the mediation of specialization and coordination of the transactive memory system, which is positively moderated by task complexity.

Keywords: strategic decision-making flexibility, team cognitive heterogeneity, transactive memory system, task complexity

Procedia PDF Downloads 43

Authors: Yuri Kitahara

Abstract:

Background: Cognitive reappraisal refers to an emotion regulation strategy in which one changes the interpretation of emotion-eliciting events. Numerous studies show that cognitive reappraisal is associated with mental health and better social functioning. However the examination of the predictive factors of adaptive emotion regulation remains as an issue. The present study examined the factors contributing to the habitual use of cognitive reappraisal, with a focus on emotional awareness and working memory. Methods: Data was collected from 30 junior high school students, using a Japanese version of the Emotion Regulation Questionnaire (ERQ), the Levels of Emotional Awareness Scale for Children (LEAS-C), and N-back task. Results: A positive correlation between emotional awareness and cognitive reappraisal was observed in the high-working-memory group (r = .54, p < .05), whereas no significant relationship was found in the low-working-memory group. In addition, the results of the analysis of variance (ANOVA) showed a significant interaction between emotional awareness and working memory capacity (F(1, 26) = 7.74, p < .05). Subsequent analysis of simple main effects confirmed that high working memory capacity significantly increases the use of cognitive reappraisal for high-emotional-awareness subjects, and significantly decreases the use of cognitive reappraisal for low-emotional-awareness subjects. Discussion: These results indicate that under the condition when one has an adequate ability for simultaneous processing of information, explicit understanding of emotion would contribute to adaptive cognitive emotion regulation. The findings are discussed along with neuroscientific claims.

Keywords: cognitive reappraisal, emotional awareness, emotion regulation, working memory

Procedia PDF Downloads 196

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 122

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 161

Authors: Mathew Wakefield, Matthew Mitchell, Lisa Wise, Christopher McCarthy

Abstract:

The properties of memory representations in artificial neural networks have cognitive implications. Distributed representations that encode instances as a pattern of activity across layers of nodes afford memory compression and enforce the selection of a single point in instance space. These encoding schemes also appear to distort the representational space, as well as trading off the ability to validate that input information is within the bounds of past experience. In contrast, a localist representation which encodes some meaningful information into individual nodes in a network layer affords less memory compression while retaining the integrity of the representational space. This allows the validity of an input to be determined. The validity (or familiarity) of input along with the capacity of localist representation for multiple instance selections affords a memory sampling approach that dynamically balances the bias-variance trade-off. When the input is familiar, bias may be high by referring only to the most similar instances in memory. When the input is less familiar, variance can be increased by referring to more instances that capture a broader range of features. Using this approach in a localist instance memory network, an experiment demonstrates a relationship between representational conflict, generalization performance, and memorization demand. Relatively small sampling ranges produce the best performance on a classic machine learning dataset of visual objects. Combining memory validity with conflict detection produces a reliable confidence judgement that can separate responses with high and low error rates. Confidence can also be used to signal the need for supervisory input. Using this judgement, the need for supervised learning as well as memory encoding can be substantially reduced with only a trivial detriment to classification performance.

Keywords: artificial neural networks, representation, memory, conflict monitoring, confidence

Procedia PDF Downloads 99

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 118

Authors: Kemka Ihemelandu, Chukwuemeka Ihemelandu

Abstract:

Melanoma remains a public health crisis, with incidence rates increasing rapidly in the past decades. Improving diagnostic accuracy to decrease misdiagnosis using Artificial intelligence (AI) continues to be documented. Unfortunately, unintended racially biased outcomes, a product of lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone, have increasingly been recognized as a problem.Resulting in noted limitations of the accuracy of the Convolutional neural network (CNN)models. CNN models are prone to biased output due to biases in the dataset used to train them. Our aim in this study was the optimization of convolutional neural network algorithms to mitigate bias in the automated diagnosis of melanoma. We hypothesized that our proposed training algorithms based on a data augmentation method to optimize the diagnostic accuracy of a CNN classifier by generating new training samples from the original ones will reduce bias in the automated diagnosis of melanoma. We applied geometric transformation, including; rotations, translations, scale change, flipping, and shearing. Resulting in a CNN model that provided a modifiedinput data making for a model that could learn subtle racial features. Optimal selection of the momentum and batch hyperparameter increased our model accuracy. We show that our augmented model reduces bias while maintaining accuracy in the automated diagnosis of melanoma.

Keywords: bias, augmentation, melanoma, convolutional neural network

Procedia PDF Downloads 175

Authors: Jun Seung Woo, Shin Dong Ho

Abstract:

The Image Captioning models with Attention technology have developed significantly compared to previous models, but it is still unsatisfactory in recognizing images. We perform an extensive search over seven interesting Convolutional Neural Networks(CNN) architectures to analyze the behavior of different models for image captioning. We compared seven different CNN Architectures, according to batch size, using on public benchmarks: MS-COCO datasets. In our experimental results, DenseNet and InceptionV3 got about 14% loss and about 160sec training time per epoch. It was the most satisfactory result among the seven CNN architectures after training 50 epochs on GPU.

Keywords: deep learning, image captioning, CNN architectures, densenet, inceptionV3

Procedia PDF Downloads 98

Authors: Khon Natalya, Kim Alla, Mukhitdinova Tansulu

Abstract:

The aim of the research was to reveal the link between mental variables, such as spatial abilities, memory, intellect and professional experience of drivers. Participants were allocated within 4 groups: no experience, inexperienced, skilled and professionals (total 85 participants). Level of ability for spatial navigation and indicator of nonverbal memory grow along the process of accumulation of driving experience. At high levels of driving experience this tendency is especially noticeable. The professionals having personal achievements in driving (racing) differ from skilled drivers in better feeling of direction which is specific for them not just in a short-term situation of an experimental task, but in life-size perspective. The level of ability of mental rotation does not grow with growth of driving experience which confirms the multiple intelligence theory according to which spatial abilities represent specific, other than logical intelligence type of intellect. The link between spatial abilities, memory, intellect, and professional experience of drivers seems to be different relating spatial navigation or mental rotation as different kinds of spatial abilities.

Keywords: memory, spatial ability, intellect, drivers

Procedia PDF Downloads 585