Search results for: learning networks

Authors: Sarah O. Alhumoud, Mawaheb I. Altuwaijri, Tarfa M. Albuhairi, Wejdan M. Alohaideb

Abstract:

Large-scale data stream analysis has become one of the important business and research priorities lately. Social networks like Twitter and other micro-blogging platforms hold an enormous amount of data that is large in volume, velocity and variety. Extracting valuable information and trends out of these data would aid in a better understanding and decision-making. Multiple analysis techniques are deployed for English content. Moreover, one of the languages that produce a large amount of data over social networks and is least analyzed is the Arabic language. The proposed paper is a survey on the research efforts to analyze the Arabic content in Twitter focusing on the tools and methods used to extract the sentiments for the Arabic content on Twitter.

Keywords: big data, social networks, sentiment analysis, twitter

Procedia PDF Downloads 576

Authors: Sayed-Mahdi Hashemi-Dehkordi, Ian Baker

Abstract:

This paper investigates the benefits of implementing distance learning in training courses for the oil and gas industries to reduce lean. Due to the remote locations of many oil and gas operations, scheduling and organizing in-person training classes for employees in these sectors is challenging. Furthermore, considering that employees often work in periodic shifts such as day, night, and resting periods, arranging in-class training courses requires significant time and transportation. To explore the effectiveness of distance learning compared to in-class learning, a set of questionnaires was administered to employees of a far on-shore refinery unit in Iran, where both in-class and distance classes were conducted. The survey results revealed that over 72% of the participants agreed that distance learning saved them a significant amount of time by rating it 4 to 5 points out of 5 on a Likert scale. Additionally, nearly 67% of the participants acknowledged that distance learning considerably reduced transportation requirements, while approximately 64% agreed that it helped in resolving scheduling issues. Introducing and encouraging the use of distance learning in the training environments of oil and gas industries can lead to notable time and transportation savings for employees, ultimately reducing lean in a positive manner.

Keywords: distance learning, in-class learning, lean, oil and gas, scheduling, time, training programs, transportation

Procedia PDF Downloads 68

Authors: Omer Agail

Abstract:

The purpose of this study was to assess the social skills of students with and without learning disabilities in primary education in Saudi Arabia. A Social Skills Rating Scale for Teachers Form (SSRS-TF) was used to evaluate students' social skills as perceived by teachers. A randomly-selected sample was chosen from students with and without learning disabilities. Descriptive statistics were used to describe the demographic characteristics of participants. Analysis indicated that there were statistically significant differences in SSRS-TF by academic status, i.e. students with learning disabilities exhibit less social skills compared to students without learning disabilities. In addition, analysis indicated that there were no statistically significant differences in SSRS-TF by gender. A conclusion and recommendations are presented.

Keywords: primary education, students with learning disabilities, social skills, social competence

Procedia PDF Downloads 391

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 115

Authors: Apidet Booranawong, Wiklom Teerapabkajorndet

Abstract:

An enhanced ad-hoc on-demand distance vector routing (E-AODV) protocol for control system applications in wireless sensor and actuator networks (WSANs) is proposed. Our routing algorithm is designed by considering both wireless network communication and the control system aspects. Control system error and network delay are the main selection criteria in our routing protocol. The control and communication performance is evaluated on multi-hop IEEE 802.15.4 networks for building-temperature control systems. The Gilbert-Elliott error model is employed to simulate packet loss in wireless networks. The simulation results demonstrate that the E-AODV routing approach can significantly improve the communication performance better than an original AODV routing under various packet loss rates. However, the control performance result by our approach is not much improved compared with the AODV routing solution.

Keywords: WSANs, building temperature control, AODV routing protocol, control system error, settling time, delay, delivery ratio

Procedia PDF Downloads 337

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 173

Authors: Gavin J. Baxter, Mark H. Stansfield

Abstract:

This paper reviews the internal use of blogs and their potential effectiveness as organisational learning tools. Prior to and since the emergence of the concept of ‘Enterprise 2.0’ there still remains a lack of empirical evidence associated with how organisations are applying social media tools and whether they are effective towards supporting organisational learning. Surprisingly, blogs, one of the more traditional social media tools, still remains under-researched in the context of ‘Enterprise 2.0’ and organisational learning. The aim of this paper is to identify the theoretical linkage between blogs and organisational learning in addition to reviewing prior research on organisational blogging with a view towards exploring why this area remains under-researched and identifying what needs to be done to try and move the area forward. Through a review of the literature, one of the principal findings of this paper is that organisational blogs, dependent on their use, do have a mutual compatibility with the interpretivist aspect of organisational learning. This paper further advocates that further empirical work in this subject area is required to substantiate this theoretical assumption.

Keywords: Enterprise 2.0, blogs, organisational learning, social media tools

Procedia PDF Downloads 286

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 96

Authors: Jorge Fernandes Teixeira Filho, André Oliveira Alcantara Fontenele, Érick Aragão Ribeiro

Abstract:

The constant emergence of new technologies used in automated processes makes it necessary for teachers and traders to apply new technologies in their classes. This paper presents an application of a new technology that will be employed in a didactic plant, which represents an effluent treatment process located in a laboratory of a federal educational institution. At work were studied in the first place, all components to be placed on automation laboratory in order to determine ways to program, parameterize and organize the plant. New technologies that have been implemented to the process are basically an AS-i network and a Profinet network, a SCADA system, which represented a major innovation in the laboratory. The project makes it possible to carry out in the laboratory various practices of industrial networks and SCADA systems.

Keywords: automation, industrial networks, SCADA systems, lab automation

Procedia PDF Downloads 544

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: earnings management, generalized linear regression, neural networks multi-layer perceptron, Tehran stock exchange

Procedia PDF Downloads 421

Authors: Anika Chebrolu

Abstract:

Mono-targeted drugs can be of limited efficacy against complex diseases. Recently, multi-target drug design has been approached as a promising tool to fight against these challenging diseases. However, the scope of current computational approaches for multi-target drug design is limited. DeepLig presents a de-novo drug discovery platform that uses reinforcement learning to generate and optimize novel, potent, and multitargeted drug candidates against protein targets. DeepLig’s model consists of two networks in interplay: a generative network and a predictive network. The generative network, a Stack- Augmented Recurrent Neural Network, utilizes a stack memory unit to remember and recognize molecular patterns when generating novel ligands from scratch. The generative network passes each newly created ligand to the predictive network, which then uses multiple Graph Attention Networks simultaneously to forecast the average binding affinity of the generated ligand towards multiple target proteins. With each iteration, given feedback from the predictive network, the generative network learns to optimize itself to create molecules with a higher average binding affinity towards multiple proteins. DeepLig was evaluated based on its ability to generate multi-target ligands against two distinct proteins, multi-target ligands against three distinct proteins, and multi-target ligands against two distinct binding pockets on the same protein. With each test case, DeepLig was able to create a library of valid, synthetically accessible, and novel molecules with optimal and equipotent binding energies. We propose that DeepLig provides an effective approach to design multi-targeted drug therapies that can potentially show higher success rates during in-vitro trials.

Keywords: drug design, multitargeticity, de-novo, reinforcement learning

Procedia PDF Downloads 97

Authors: Mohamed Idris S. Abozaed, Suliman Mohamed Elrajoubi

Abstract:

Researches and concerns in power quality gained significant momentum in the field of power electronics systems over the last two decades globally. This sudden increase in the number of concerns over power quality problems is a result of the huge increase in the use of non-linear loads. In this paper, power quality evaluation of some distribution networks at Misurata - Libya has been done using a power quality and energy analyzer (Fluke 437 Series II). The results of this evaluation are used to minimize the problems of power quality. The analysis shows the main power quality problems that exist and the level of awareness of power quality issues with the aim of generating a start point which can be used as guidelines for researchers and end users in the field of power systems.

Keywords: power quality disturbances, power quality evaluation, statistical analysis, electrical distribution networks

Procedia PDF Downloads 533

Authors: Naoki Okamura

Abstract:

From a perspective of moral education, this study has examined the experiences of a group of college students who volunteered in disaster areas after the magnitude 9.0 Earthquake, which struck the Northeastern region of Japan in March, 2011. The research, utilizing the method of grounded theory, has uncovered that most of the students have gone through positive changes in their development of moral and social characters, such as attaining deeper sense of empathy and caring personalities. The study expresses, in identifying the nature of those transformations, that the importance of volunteer work should strongly be recognized by the colleges and universities in Japan, in fulfilling their public responsibility of creating and building learning communities that are responsible and caring.

Keywords: moral development, moral education, service learning, volunteer learning

Procedia PDF Downloads 320

Authors: Naritphol Boonyakiat

Abstract:

This research attempts to investigate the effects of corporate social responsibility and knowledge management factors on students’ learning process of the Silpakorn University. The goal of this study is to fill the literature gap by gaining an understanding of corporate social responsibility and the knowledge management factors that fundamentally relate to students’ learning process within the university context. Thus, this study will focus on the outcomes that derive from a set of quantitative data that were obtained using Silpakorn university’s database of 200 students. The results represent the perceptions of students regarding the impact of corporate social responsibility and knowledge management factors on their learning process within the university. The findings indicate that corporate social responsibility and knowledge management have significant effects on students’ learning process. This study may assist us in gaining a better understanding of the integrated aspects of university and learning environments to discover how to allocate optimally university’s resources and management approaches to gain benefits from corporate social responsibility and knowledge management practices toward students’ learning process within the university bodies. Therefore, there is a sufficient reason to believe that the findings can contribute to research in the area of CSR, KM and students’ learning process as an essential aspect of university’s stakeholder.

Keywords: corporate social responsibility, knowledge management, learning process, university’s students

Procedia PDF Downloads 317

Authors: Sophie Huck, Knut Linke

Abstract:

This study will examine how IT practitioners can be motivated for IT studies and which kind of support they need during their occupational studies. Within this research project, the challenge of supporting students being engaged in business for several years arose. Here, it is especially important to successfully guide them through their studies. The problem of this group is that they finished their school education years ago. In order to gather first experiences, preliminary e-learning courses were introduced and tested with a group of users studying General Management. They had to work with these courses and have been questioned later on about their approach to the different methods. Moreover, a second group of potential students was interviewed with the help of online questionnaires to give information about their expectations regarding extra occupational studies. We also want to present best practices and cases in e-education in the subarea of mathematics and distance learning. Within these cases and practices, we use state of the art systems and technologies in e-education to find a way to increase teaching quality and the success of students. Our research indicated that the first group of enrolled students appreciated the new preliminary e-learning courses. The second group of potential students was convinced of this way of learning as a significant component of extra occupational studies. It can be concluded that this part of the project clarified the acceptance of the e-learning strategy by both groups and led to satisfactory results with the enrolled students.

Keywords: e-learning evaluation, self-learning, virtual classroom, virtual learning environments

Procedia PDF Downloads 322

Authors: Bi̇rsen Tutunis, Zuhal Aydin

Abstract:

Guided digital learning has attracted many researchers as it leads to autonomous learning.The developments in Guided digital learning have led to changes in teaching and learning in English Language Teaching classes (Jeong-Bae, 2014). This study reports on tasks designed under the principles of learner autonomy in an online learning platform ‘’Webquest’’ with the purpose of teaching English to Turkish tertiary level students at a foundation university in Istanbul. Guided digital learning blog project contents were organized according to work-cycles phases (planning and negotiation phase, decision-making phase, project phase and evaluation phase) which are compatible with the principles of autonomous learning (Legenhausen,2003). The aim of the study was to implement the class blog project to find out its impact on students’ behaviours and beliefs towards autonomous learning. The mixed method research approach was taken. 24 tertiary level students participated in the study on voluntary basis. Data analysis was performed with Statistical Package for the Social Sciences. According to the results, students' attitudes towards digital learning did not differ before and after the training application. The learning styles of the students and their knowledge on digital learning scores differed. It has been observed that the students' learning styles and their digital learning scores increased after the training application. Autonomous beliefs, autonomous behaviors, group cohesion and group norms differed before and after the training application. Students' motivation level, strategies for learning English, perceptions of responsibility and out-of-class activity scores differed before and after the training application. It was seen that work-cycles in online classes create student centered learning that fosters autonomy. This paper will display the work cycles in detail and the researchers will give examples of in and beyond class activities and blog projects.

Keywords: guided digital learning, work cycles, english language teaching, autonomous learning

Procedia PDF Downloads 78

Authors: Kriuk Boris, Kriuk Fedor

Abstract:

This paper presents a comparative study of fundamental similarity functions for Siamese networks in semantic textual similarity (STS) tasks. We evaluate various similarity functions using the STS Benchmark dataset, analyzing their performance and stability. Additionally, we introduce a multi-objective approach for optimal threshold selection. Our findings provide insights into the effectiveness of different similarity functions and offer a straightforward method for threshold selection optimization, contributing to the advancement of Siamese network architectures in STS applications.

Keywords: siamese networks, semantic textual similarity, similarity functions, STS benchmark dataset, threshold selection

Procedia PDF Downloads 37

Authors: Somtop Keawchuer

Abstract:

This research aims to study (1) the relationship between competency-based learning and learning efficiency of new media communication students at Suan Sunandha University (2) the demographic factor effect on learning efficiency of students at Suan Sunandha University. This research method will use quantitative research; data was collected by questionnaires distributed to students from new media communication in management science faculty of Suan Sunandha Rajabhat University for 1340 sample by purposive sampling method. Data was analyzed by descriptive statistic including percentage, mean, standard deviation and inferential statistic including T-test, ANOVA and Pearson correlation for hypothesis testing. The results showed that the competency-based learning in term of ability to communicate, ability to think and solve the problem, life skills and ability to use technology has a significant relationship with learning efficiency in term of the cognitive domain, psychomotor domain and affective domain at the 0.05 level and which is in harmony with the research hypotheses.

Keywords: competency-based learning, learning efficiency, new media communication students, Suan Sunandha Rajabhat University

Procedia PDF Downloads 243

Authors: Cristina Galván-Fernández, Elena Barberà, Jingjing Zhang

Abstract:

In recent years, MOOCs have been in the spotlight for its high drop-out rates, which potentially impact on the quality of the learning experience. This study attempts to explore how learning support can be used to keep student retention, and in turn to improve the quality of learning in MOOCs. In this study, the patterns of learning support were identified from a total of 4202592 units of video sessions, clickstream data of 25600 students, and 382 threads generated in 10 forums (optional and mandatory) in five different types of MOOCs (e.g. conventional MOOCs, professional MOOCs, and informal MOOCs). The results of this study have shown a clear correlation between the types of MOOCs, the design framework of the MOOCs, and the learning support. The patterns of tutor-peer interaction are identified, and are found to be highly correlated with student retention in all five types of MOOCs. In addition, different patterns of ‘good’ students were identified, which could potentially inform the instruction design of MOOCs.

Keywords: higher education, learning support, MOOC, retention

Procedia PDF Downloads 335

Authors: Bahloul Amel

Abstract:

This study is an attempt to raise the awareness of the stakeholders and the authorities on the sensitivity of Algerian secondary school teachers of English as a Foreign Language about the students’ loss of English language skills learned during formal schooling with effort and at expense and the supposed measures to arrest that loss. Data was collected from secondary school teachers of EFL and analyzed quantitatively using a questionnaire containing open-ended and close-ended questions. The results advocate a consensus about the need for actions to be adopted to make assessment techniques outcome-oriented. Most of the participants were in favor of including curricular activities involving contextualized learning, problem-solving learning critical self-awareness, self and peer-assisted learning, use of computers and internet so as to make learners autonomous.

Keywords: lifelong learning, EFL, contextualized learning, Algeria

Procedia PDF Downloads 348

Authors: Zheng Zhihao

Abstract:

Recently, Knowledge Graph Framework Network (KGCN) has developed powerful capabilities in knowledge representation and reasoning tasks. However, traditional KGCN often uses a fixed weight mechanism when aggregating information, failing to make full use of rich structural information, resulting in a certain expression ability of node representation, and easily causing over-smoothing problems. In order to solve these challenges, the paper proposes an new graph neural network model called KGCN-STAR (Knowledge Graph Convolutional Network with Structural Adaptive Receptive Fields). This model dynamically adjusts the perception of each node by introducing a structural adaptive receptive field. wild range, and a subgraph aggregator is designed to capture local structural information more effectively. Experimental results show that KGCN-STAR shows significant performance improvement on multiple knowledge graph data sets, especially showing considerable capabilities in the task of representation learning of complex structures.

Keywords: knowledge graph, graph neural networks, structural adaptive receptive fields, information aggregation

Procedia PDF Downloads 33

Authors: Soheila Sadeghi

Abstract:

Accurate forecasting of project performance metrics is crucial for successfully managing and delivering urban road reconstruction projects. Traditional methods often rely on static baseline plans and fail to consider the dynamic nature of project progress and external factors. This research proposes a machine learning-based approach to forecast project performance metrics, such as cost variance and earned value, for each Work Breakdown Structure (WBS) category in an urban road reconstruction project. The proposed model utilizes time series forecasting techniques, including Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) networks, to predict future performance based on historical data and project progress. The model also incorporates external factors, such as weather patterns and resource availability, as features to enhance the accuracy of forecasts. By applying the predictive power of machine learning, the performance forecasting model enables proactive identification of potential deviations from the baseline plan, which allows project managers to take timely corrective actions. The research aims to validate the effectiveness of the proposed approach using a case study of an urban road reconstruction project, comparing the model's forecasts with actual project performance data. The findings of this research contribute to the advancement of project management practices in the construction industry, offering a data-driven solution for improving project performance monitoring and control.

Keywords: project performance forecasting, machine learning, time series forecasting, cost variance, earned value management

Procedia PDF Downloads 49

Authors: Chuanphit Chumkhong

Abstract:

This research aimed 1) to study the effects of the management of Active Learning among 3rd year students enrolled in teacher’s profession courses and 2) to assess the satisfaction of the students with courses using the Active Learning approach. The population for the study consisted of 442 3rd year undergraduate students enrolled in two teacher education courses in 2015: Curriculum Development and Learning Process Management. They were 442 from 11 education programs. Respondents for evaluation of satisfaction with Active Learning management comprised 432 students. The instruments used in research included a detailed course description and rating scale questionnaire on Active Learning. The data were analyzed using arithmetic mean and standard deviation. The results of the study reveal the following: 1. Overall, students gain a better understanding of the Active Learning due to their actual practice on the activity of course. Students have the opportunity to exchange learning knowledge and skills. The AL teaching activities make students interested in the contents and they seek to search for knowledge on their own. 2. Overall, 3rd year students are satisfied with the Active Learning management at a ‘high’ level with a mean score (μ) of 4.12 and standard deviation (σ) of. 51. By individual items, students are satisfied with the 10 elements in the two courses at a ‘high’ level with the mean score (μ) between 3.79 to 4.41 and a standard deviation (σ) between to 68. 79.

Keywords: active learning teaching model, teacher’s professional courses, professional courses, curriculum and instruction teacher's

Procedia PDF Downloads 248

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 127

Authors: Atabak Faramarzpour, Mohsen Mohammadian

Abstract:

In this article, we introduce the stability of power system voltage and state DG power plants placement and its effect on improving voltage security margin in radial distribution networks. For this purpose, first, important definitions in voltage stability area such as small and big voltage disturbances, instability, and voltage collapse, and voltage security definitions are stated. Then, according to voltage collapse time, voltage stability is classified and each one's characteristics are stated.

Keywords: DG power plants, evaluation, voltage security, radial distribution networks

Procedia PDF Downloads 670

Authors: Alexander Vandesompele, Joni Dambre

Abstract:

The diversity in dendritic arborization, as first illustrated by Santiago Ramon y Cajal, has always suggested a role for dendrites in the functionality of neurons. In the past decades, thanks to new recording techniques and optical stimulation methods, it has become clear that dendrites are not merely passive electrical components. They are observed to integrate inputs in a non-linear fashion and actively participate in computations. Regardless, in simulations of neural networks dendritic structure and functionality are often overlooked. Especially in a machine learning context, when designing artificial neural networks, point neuron models such as the leaky-integrate-and-fire (LIF) model are dominant. These models mimic the integration of inputs at the neuron soma, and ignore the existence of dendrites. In this work, the LIF point neuron model is extended with a simple form of dendritic computation. This gives the LIF neuron increased capacity to discriminate spatiotemporal input sequences, a dendritic functionality as observed in another study. Simulations of the spiking neurons are performed using the Bindsnet framework. In the common LIF model, incoming synapses are independent. Here, we introduce a dependency between incoming synapses such that the post-synaptic impact of a spike is not only determined by the weight of the synapse, but also by the activity of other synapses. This is a form of short term plasticity where synapses are potentiated or depressed by the preceding activity of neighbouring synapses. This is a straightforward way to prevent inputs from simply summing linearly at the soma. To implement this, each pair of synapses on a neuron is assigned a variable,representing the synaptic relation. This variable determines the magnitude ofthe short term plasticity. These variables can be chosen randomly or, more interestingly, can be learned using a form of Hebbian learning. We use Spike-Time-Dependent-Plasticity (STDP), commonly used to learn synaptic strength magnitudes. If all neurons in a layer receive the same input, they tend to learn the same through STDP. Adding inhibitory connections between the neurons creates a winner-take-all (WTA) network. This causes the different neurons to learn different input sequences. To illustrate the impact of the proposed dendritic mechanism, even without learning, we attach five input neurons to two output neurons. One output neuron isa regular LIF neuron, the other output neuron is a LIF neuron with dendritic relationships. Then, the five input neurons are allowed to fire in a particular order. The membrane potentials are reset and subsequently the five input neurons are fired in the reversed order. As the regular LIF neuron linearly integrates its inputs at the soma, the membrane potential response to both sequences is similar in magnitude. In the other output neuron, due to the dendritic mechanism, the membrane potential response is different for both sequences. Hence, the dendritic mechanism improves the neuron’s capacity for discriminating spa-tiotemporal sequences. Dendritic computations improve LIF neurons even if the relationships between synapses are established randomly. Ideally however, a learning rule is used to improve the dendritic relationships based on input data. It is possible to learn synaptic strength with STDP, to make a neuron more sensitive to its input. Similarly, it is possible to learn dendritic relationships with STDP, to make the neuron more sensitive to spatiotemporal input sequences. Feeding structured data to a WTA network with dendritic computation leads to a significantly higher number of discriminated input patterns. Without the dendritic computation, output neurons are less specific and may, for instance, be activated by a sequence in reverse order.

Keywords: dendritic computation, spiking neural networks, point neuron model

Procedia PDF Downloads 133

Authors: Ryota Sugino, Satoshi Mizoguchi, Koji Kimita, Keiichi Muramatsu, Tatsunori Matsui, Yoshiki Shimomura

Abstract:

Improving added value and productivity of services entails improving both value-in-exchange and value-in-use. Value-in-use is realized by value co-creation, where providers and receivers create value together. In higher education services, value-in-use comes from learners achieving learning outcomes (e.g., knowledge and skills) that are consistent with their learning goals. To enhance the learning outcomes of a learner, it is necessary to enhance and utilize the abilities of the teacher along with the abilities of the learner. To do this, however, the learner and the teacher need to build a consensus about their respective roles. Teachers need to provide effective learning content; learners need to choose the appropriate learning strategies by using the learning content through consensus building. This makes consensus building an important factor in value co-creation. However, methods to build a consensus about their respective roles may not be clearly established, making such consensus difficult. In this paper, we propose some strategies for consensus building between a teacher and a learner in value co-creation. We focus on a teacher and learner co-design and propose an analysis method to clarify a collaborative design process to realize value co-creation. We then analyze some counseling data obtained from a university class. This counseling aimed to build a consensus for value-in-use, learning outcomes, and learning strategies between the teacher and the learner.

Keywords: consensus building, value co-creation, higher education, learning service

Procedia PDF Downloads 301

Authors: Haiyan Wu, Ying Liu, Shaoyun Shi

Abstract:

Authorship attribution is to extract features to identify authors of anonymous documents. Many previous works on authorship attribution focus on statistical style features (e.g., sentence/word length), content features (e.g., frequent words, n-grams). Modeling these features by regression or some transparent machine learning methods gives a portrait of the authors' writing style. But these methods do not capture the syntactic (e.g., dependency relationship) or semantic (e.g., topics) information. In recent years, some researchers model syntactic trees or latent semantic information by neural networks. However, few works take them together. Besides, predictions by neural networks are difficult to explain, which is vital in authorship attribution tasks. In this paper, we not only utilize the statistical style and content features but also take advantage of both syntactic and semantic features. Different from an end-to-end neural model, feature selection and prediction are two steps in our method. An attentive n-gram network is utilized to select useful features, and logistic regression is applied to give prediction and understandable representation of writing style. Experiments show that our extracted features can improve the state-of-the-art methods on three benchmark datasets.

Keywords: authorship attribution, attention mechanism, syntactic feature, feature extraction

Procedia PDF Downloads 136

Authors: Jainendra Singh, Zaheeruddin

Abstract:

A typical wireless sensor networks (WSNs) consists of several tiny and low-power sensors which use radio frequency to perform distributed sensing tasks. The longevity of wireless sensor networks (WSNs) is a major issue that impacts the application of such networks. While routing protocols are striving to save energy by acting on sensor nodes, recent studies show that network lifetime can be enhanced by further involving sink mobility. A common approach for energy efficiency is partitioning the network into clusters with correlated data, where the representative nodes simply transmit or average measurements inside the cluster. In this paper, we propose an energy- efficient homogenous clustering (EHC) technique. In this technique, the decision of each sensor is based on their residual energy and an estimate of how many of its neighboring cluster heads (CHs) will benefit from it being a CH. We, also explore the routing algorithm in clustered WSNs. We show that the proposed schemes significantly outperform current approaches in terms of packet delay, hop count and energy consumption of WSNs.

Keywords: wireless sensor network, energy efficiency, clustering, routing

Procedia PDF Downloads 264

Authors: Lijuan Zhou, Mengqi Wu, Changyong Niu

Abstract:

Attributed graph clustering can utilize the graph topology and node attributes to uncover hidden community structures and patterns in complex networks, aiding in the understanding and analysis of complex systems. Utilizing contrastive learning for attributed graph clustering can effectively exploit meaningful implicit relationships between data. However, existing attributed graph clustering methods based on contrastive learning suffer from the following drawbacks: 1) Complex data augmentation increases computational cost, and inappropriate data augmentation may lead to semantic drift. 2) The selection of positive and negative samples neglects the intrinsic cluster structure learned from graph topology and node attributes. Therefore, this paper proposes a method called self-supervised Attributed Graph Clustering with Dual Contrastive Loss constraints (AGC-DCL). Firstly, Siamese Multilayer Perceptron (MLP) encoders are employed to generate two views separately to avoid complex data augmentation. Secondly, the neighborhood contrastive loss is introduced to constrain node representation using local topological structure while effectively embedding attribute information through attribute reconstruction. Additionally, clustering-oriented contrastive loss is applied to fully utilize clustering information in global semantics for discriminative node representations, regarding the cluster centers from two views as negative samples to fully leverage effective clustering information from different views. Comparative clustering results with existing attributed graph clustering algorithms on six datasets demonstrate the superiority of the proposed method.

Keywords: attributed graph clustering, contrastive learning, clustering-oriented, self-supervised learning

Procedia PDF Downloads 53