World Academy of Science, Engineering and Technology

Authors: Qingqing Gai, Junxing Shen, Yu Luo

Abstract:

Due to the hardware architecture characteristics, some operators tend to acquire better performance if the input/output tensor dimensions are aligned to a certain minimum granularity, such as convolution and deconvolution commonly used in deep learning. Furthermore, if the requirements are not met, the general strategy is to pad with 0 to satisfy the requirements, potentially leading to the under-utilization of the hardware resources. Therefore, for the convolution and deconvolution whose input and output channels do not meet the minimum granularity alignment, we propose to transfer the W-dimensional data to the C-dimension for computation (W2C) to enable the C-dimension to meet the hardware requirements. This scheme also reduces the number of computations in the W-dimension. Although this scheme substantially increases computation, the operator’s speed can improve significantly. It achieves remarkable speedups on multiple hardware accelerators, including Nvidia Tensor cores, Qualcomm digital signal processors (DSPs), and Huawei neural processing units (NPUs). All you need to do is modify the network structure and rearrange the operator weights offline without retraining. At the same time, for some operators, such as the Reducemax, we observe that transferring the Cdimensional data to the W-dimension(C2W) and replacing the Reducemax with the Maxpool can accomplish acceleration under certain circumstances.

Keywords: convolution, deconvolution, W2C, C2W, alignment, hardware accelerator

Procedia PDF Downloads 104

Authors: Antonio Horta, Renato Marinho, Raimir Holanda

Abstract:

Considered as an evolution of the Blockchain, the Ethereum platform, besides allowing transactions of its cryptocurrency named Ether, it allows the programming of decentralised applications (DApps) and smart contracts. However, this functionality into blockchains has raised other types of threats, and the exploitation of smart contracts vulnerabilities has taken companies to experience big losses. This research intends to figure out the number of contracts that are under risk of being drained. Through a deep investigation, more than two hundred thousand smart contracts currently available in the Ethereum platform were scanned and estimated how much money is at risk. The experiment was based in a query run on Google Big Query in July 2022 and returned 50,707,133 contracts published on the Ethereum platform. After applying the filtering criteria, the experimentgot 430,584 smart contracts to download and analyse. The filtering criteria consisted of filtering out: ERC20 and ERC721 contracts, contracts without transactions, and contracts without balance. From this amount of 430,584 smart contracts selected, only 268,103 had source codes published on Etherscan, however, we discovered, using a hashing process, that there were contracts duplication. Removing the duplicated contracts, the process ended up with 20,417 source codes, which were analysed using the open source SAST tool smartbugswith oyente and securify algorithms. In the end, there was nearly $100,000 at risk of being drained from the potentially vulnerable smart contracts. It is important to note that the tools used in this study may generate false positives, which may interfere with the number of vulnerable contracts. To address this point, our next step in this research is to develop an application to test the contract in a parallel environment to verify the vulnerability. Finally, this study aims to alert users and companies about the risk on not properly creating and analysing their smart contracts before publishing them into the platform. As any other application, smart contracts are at risk of having vulnerabilities which, in this case, may result in direct financial losses.

Keywords: blockchain, reentrancy, static application security testing, smart contracts

Procedia PDF Downloads 88

Authors: Regan Harper, Song Yang, Douglas Adams

Abstract:

During the historically unprecedent time of Covid-19 pandemic, we survey college students with social issue generators to measure their core discussion groups. For the total 191 students, we elicit 847 conversation partners (alters) with our five social issue generators such as school closing, facemasks, collegiate sports, race and policing, and social inequality, producing an average of 4.43 alters per respondent. The core discussion groups of our sample are very gender balanced, with female alters slightly outnumbering male alters. However, the core discussion groups are racially homogenous, consisting of mostly white students (around or above 80 percent). Explanatory analyses reveal that gender and race of respondents significantly impact the size, gender composition, and racial composition of their core discussion networks. We discuss those major findings and implications of future studies in our conclusion section.

Keywords: core discussion groups, social issue generators, ego-centric network, Covid-19 pandemic

Procedia PDF Downloads 91

Authors: Sultan Samah A. Alenezi

Abstract:

Many EFL teachers are eager to look into the best way to suit the needs of their students in EFL writing courses. Numerous studies suggest that online blogging may present a social interaction opportunity for EFL writing students. Additionally, it can foster peer collaboration and social support in the form of scaffolding, which, when viewed from the perspective of socio-cultural theory, can boost social support and foster the development of students' writing abilities. This idea is based on Vygotsky's theories, which emphasize how collaboration and social interaction facilitate effective learning. In Saudi Arabia, students are taught to write using conventional methods that are totally under the teacher's control. Without any peer contact or cooperation, students are spoon-fed in a passive environment. This study included the cognitive processes of the genre-process approach into the EFL writing classroom to facilitate the use of internet blogging in EFL writing education. Thirty second-year undergraduate students from the Department of Languages and Translation at a Saudi college participated in this study. This study employed an action research project that blended qualitative and quantitative methodologies to comprehend Saudi students' perceptions and experiences with internet blogging in an EFL process-genre writing classroom. It also looked at the advantages and challenges people faced when blogging. They included a poll, interviews, and blog postings made by students. The intervention's outcomes showed that merging genre-process procedures with blogging was a successful tactic, and the Saudi students' perceptions of this method of online blogging for EFL writing were quite positive. The socio-cultural theory constructs that Vygotsky advocates, such as scaffolding, collaboration, and social interaction, were also improved by blogging. These elements demonstrated the improvement in the students' written, reading, social, and collaborative thinking skills, as well as their positive attitudes toward English-language writing. But the students encountered a variety of problems that made blogging difficult for them. These problems ranged from technological ones, such sluggish internet connections, to learner inadequacies, like a lack of computer know-how and ineffective time management.

Keywords: blogging, process-gnere approach, saudi learenrs, writing quality

Procedia PDF Downloads 121

Authors: Tarek Aboueldahab, Hanan Farag

Abstract:

Cost minimization of Multiple Vehicle Routing Problem becomes a critical issue in the field of transportation because it is NP-hard optimization problem and the search space is complex. Many researches use the hybridization of artificial intelligence (AI) models to solve this problem; however, it can not guarantee to reach the best solution due to the difficulty of searching the whole search space. To overcome this problem, we introduce the hybrid model of Discrete Particle Swarm Optimization (DPSO) with a passive congregation which enable searching the whole search space to compromise between both local and global search. The practical experiment shows that our model obviously outperforms other hybrid models in cost minimization.

Keywords: cost minimization, multi-vehicle routing problem, passive congregation, discrete swarm, passive congregation

Procedia PDF Downloads 98

Authors: Shuo Liu, Dan Liu

Abstract:

In the field of named entity recognition, most of the research has been conducted around simple entities. However, for nested named entities, which still contain entities within entities, it has been difficult to identify them accurately due to their boundary ambiguity. In this paper, a hierarchical recognition model is constructed based on the grammatical structure and semantic features of Chinese text for boundary calculation based on lexical features. The analysis is carried out at different levels in terms of granularity, semantics, and lexicality, respectively, avoiding repetitive work to reduce computational effort and using the semantic features of words to calculate the boundaries of entities to improve the accuracy of the recognition work. The results of the experiments carried out on web-based microblogging data show that the model achieves an accuracy of 86.33% and an F1 value of 89.27% in recognizing nested named entities, making up for the shortcomings of some previous recognition models and improving the efficiency of recognition of nested named entities.

Keywords: coarse-grained, nested named entity, Chinese natural language processing, word embedding, T-SNE dimensionality reduction algorithm

Procedia PDF Downloads 128

Authors: Zhang Shuqi, Liu Dan

Abstract:

For the problems in intelligent network anomaly traffic detection models, such as low detection accuracy caused by the lack of training samples, poor effect with small sample attack detection, a classification model enhancement method, F-ACGAN(Flow Auxiliary Classifier Generative Adversarial Network) which introduces generative adversarial network and adversarial training, is proposed to solve these problems. Generating adversarial data with category labels could enhance the training effect and improve classification accuracy and model robustness. FACGAN consists of three steps: feature preprocess, which includes data type conversion, dimensionality reduction and normalization, etc.; A generative adversarial network model with feature learning ability is designed, and the sample generation effect of the model is improved through adversarial iterations between generator and discriminator. The adversarial disturbance factor of the gradient direction of the classification model is added to improve the diversity and antagonism of generated data and to promote the model to learn from adversarial classification features. The experiment of constructing a classification model with the UNSW-NB15 dataset shows that with the enhancement of FACGAN on the basic model, the classification accuracy has improved by 8.09%, and the score of F1 has improved by 6.94%.

Keywords: data imbalance, GAN, ACGAN, anomaly detection, adversarial training, data augmentation

Procedia PDF Downloads 105

Authors: Dinmukhamed T., Vassiliy S.

Abstract:

This article suggests the idea of fitting clothes and accessories based on augmented reality. A logical data model has been developed, taking into account the decision-making module (colors, style, type, material, popularity, etc.) based on personal data (age, gender, weight, height, leg size, hoist length, geolocation, photogrammetry, number of purchases of certain types of clothing, etc.) and statistical data of the purchase history (number of items, price, size, color, style, etc.). Also, in order to provide information to the user, it is planned to develop an augmented reality system using a QR code. This system of selection and fitting of clothing and accessories based on augmented reality will be used in stores to reduce the time for the buyer to make a decision on the choice of clothes.

Keywords: augmented reality, online store, decision-making module, like QR code, clothing store, queue

Procedia PDF Downloads 157

Authors: Marie Oldfield

Abstract:

Anthropomorphism is a technique used by humans to make sense of their surroundings. Anthropomorphism is a widely used technique used to influence consumers to purchase goods or services. These techniques can entice consumers into buying something to fulfill a gap or desire in their life, ranging from loneliness to the desire to be exclusive. By manipulating belief systems, consumer behaviour can be exploited. This paper examines a series of studies to show how anthropomorphism can be used as a basis for exploitation. The first set of studies in this paper examines how anthropomorphism is used in marketing and the effects on humans engaging with this technique. The second set of studies examines how humans can be potentially exploited by artificial agents. We then discuss the consequences of this type of activity within the context of dehumanisation. This research has found potential serious consequences for society and humanity, which indicate an urgent need for further research in this area.

Keywords: anthropomorphism, ethics, human-computer interaction, AI

Procedia PDF Downloads 89

Authors: Amara Rafik, Mostefa Belhadj Aissa

Abstract:

Radar data is one of the many data sources used by ATM Air Traffic Management systems. These data come from air navigation radar antennas. These radars intercept signals emitted by the various aircraft crossing the controlled airspace and calculate the position of these aircraft and retransmit their positions to the Air Traffic Management System. For greater reliability, these radars are positioned in such a way as to allow their coverage areas to overlap. An aircraft will therefore be detected by at least one of these radars. However, the position coordinates of the same aircraft and sent by these different radars are not necessarily identical. Therefore, the ATM system must calculate a single position (radar track) which will ultimately be sent to the control position and displayed on the air traffic controller's monitor. There are several techniques for calculating the radar track. Furthermore, the geographical nature of the problem requires the use of a Geographic Information System (GIS), i.e. a geographical database on the one hand and geographical processing. The objective of this work is to propose a GIS for traffic simulation which reconstructs the evolution over time of aircraft positions from a multi-source radar data set and by applying these different techniques.

Keywords: ATM, GIS, radar data, simulation

Procedia PDF Downloads 118

Authors: Yang Yang, Dan Liu

Abstract:

Anomaly detection models for network flow based on machine learning have poor detection performance under extremely unbalanced training data conditions and also have slow detection speed and large resource consumption when deploying on network edge devices. Embedding multi-teacher knowledge distillation (mKD) in anomaly detection can transfer knowledge from multiple teacher models to a single model. Inspired by this, we proposed a state-of-the-art model, mKDNAD, to improve detection performance. mKDNAD mine and integrate the knowledge of one-dimensional sequence and two-dimensional image implicit in network flow to improve the detection accuracy of small sample classes. The multi-teacher knowledge distillation method guides the train of the student model, thus speeding up the model's detection speed and reducing the number of model parameters. Experiments in the CICIDS2017 dataset verify the improvements of our method in the detection speed and the detection accuracy in dealing with the small sample classes.

Keywords: network flow anomaly detection (NAD), multi-teacher knowledge distillation, machine learning, deep learning

Procedia PDF Downloads 122

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 199

Authors: Garry Gorman, Nigel McKelvey, James Connolly

Abstract:

This study will evaluate a growth mindset intervention with Junior Cycle Coding and Senior Cycle Computer Science students in Ireland, where gamification will be used to incentivise growth mindset behaviour. An artificial intelligence (AI) driven personalised learning system will be developed to present computer programming learning tasks in a manner that is best suited to the individuals’ own learning preferences while incentivising and rewarding growth mindset behaviour of persistence, mastery response to challenge, and challenge seeking. This research endeavours to measure mindset with before and after surveys (conducted nationally) and by recording growth mindset behaviour whilst playing a digital game. This study will harness the capabilities of AI and aims to determine how a personalised learning (PL) experience can impact the mindset of a broad range of students. The focus of this study will be to determine how personalising the learning experience influences female and disadvantaged students' sense of belonging in the computer science classroom when tasks are presented in a manner that is best suited to the individual. Whole Brain Learning will underpin this research and will be used as a framework to guide the research in identifying key areas such as thinking and learning styles, cognitive potential, motivators and fears, and emotional intelligence. This research will be conducted in multiple school types over one academic year. Digital games will be played multiple times over this period, and the data gathered will be used to inform the AI algorithm. The three data sets are described as follows: (i) Before and after survey data to determine the grit scores and mindsets of the participants, (ii) The Growth Mind-Set data from the game, which will measure multiple growth mindset behaviours, such as persistence, response to challenge and use of strategy, (iii) The AI data to guide PL. This study will highlight the effectiveness of an AI-driven personalised learning experience. The data will position AI within the Irish educational landscape, with a specific focus on the teaching of CS. These findings will benefit coding and computer science teachers by providing a clear pedagogy for the effective delivery of personalised learning strategies for computer science education. This pedagogy will help prevent students from developing a fixed mindset while helping pupils to exhibit persistence of effort, use of strategy, and a mastery response to challenges.

Keywords: computer science education, artificial intelligence, growth mindset, pedagogy

Procedia PDF Downloads 88

Authors: Veysel Seker

Abstract:

Graphic designing and virtual reality have been affected by digital development and technological development for the last decades. This study aims to compare and evaluate digitalization and virtual reality evaluation in traditional and classical methods of the graphic designing sector in Turkey. The qualitative and quantitative studies and research were discussed and identified according to the evaluated results of the literature surveys. Moreover, the study showed that the competency gap between graphic design schools and the field should be determined and well-studied. The competencies of traditional graphic designers will have a big challenge for the purpose of the transition into the developed and evaluated digital graphic design world.

Keywords: digitalization, evaluation, graphic designing, virtual reality

Procedia PDF Downloads 144

Authors: Naoum Abderrahmane, Boumehed Meriem, Alshaqaqi Belal

Abstract:

Background subtraction algorithm is a larger used technique for detecting moving objects in video surveillance to extract the foreground objects from a reference background image. There are many challenges to test a good background subtraction algorithm, like changes in illumination, dynamic background such as swinging leaves, rain, snow, and the changes in the background, for example, moving and stopping of vehicles. In this paper, we propose an efficient and accurate background subtraction method for moving object detection in video surveillance. The main idea is to use a developed fast-independent component analysis (ICA) algorithm to separate background, noise, and foreground masks from an image sequence in practical environments. The fast-ICA algorithm is adapted and adjusted with a matrix calculation and searching for an optimum non-quadratic function to be faster and more robust. Moreover, in order to estimate the de-mixing matrix and the denoising de-mixing matrix parameters, we propose to convert all images to YCrCb color space, where the luma component Y (brightness of the color) gives suitable results. The proposed technique has been verified on the publicly available datasets CD net 2012 and CD net 2014, and experimental results show that our algorithm can detect competently and accurately moving objects in challenging conditions compared to other methods in the literature in terms of quantitative and qualitative evaluations with real-time frame rate.

Keywords: background subtraction, moving object detection, fast-ICA, de-mixing matrix

Procedia PDF Downloads 96

Authors: Shao-Di Feng, Von-Wun Soo

Abstract:

To generate symbolic music with specific emotions is a challenging task due to symbolic music datasets that have emotion labels are scarce and incomplete. This research aims to generate more refined emotions based on the training datasets that are only labeled with four quadrants in Russel’s 2D emotion model. We focus on the theory of Music Fadernet and map arousal and valence to the low-level attributes, and build a symbolic music generation model by combining transformer and GM-VAE. We adopt an in-attention mechanism for the model and improve it by allowing modulation by conditional information. And we show the music generation model could control the generation of music according to the emotions specified by users in terms of high-level linguistic expression and by manipulating their corresponding low-level musical attributes. Finally, we evaluate the model performance using a pre-trained emotion classifier against a pop piano midi dataset called EMOPIA, and by subjective listening evaluation, we demonstrate that the model could generate music with more refined emotions correctly.

Keywords: music generation, music emotion controlling, deep learning, semi-supervised learning

Procedia PDF Downloads 90

Authors: Nasser Salah Eldin Mohammed Salih Shebka

Abstract:

Current problematic issues in AI fields are mainly due to those of knowledge representation conceptual theories, which in turn reflected on the entire scope of cognitive sciences. Knowledge representation methods and tools are driven from theoretical concepts regarding human scientific perception of the conception, nature, and process of knowledge acquisition, knowledge engineering and knowledge generation. And although, these theoretical conceptions were themselves driven from the study of the human knowledge representation process and related theories; some essential factors were overlooked or underestimated, thus causing critical methodological deficiencies in the conceptual theories of human knowledge and knowledge representation conceptions. The evaluation criteria of human cumulative knowledge from the perspectives of nature and theoretical aspects of knowledge representation conceptions are affected greatly by the very materialistic nature of cognitive sciences. This nature caused what we define as methodological deficiencies in the nature of theoretical aspects of knowledge representation concepts in AI. These methodological deficiencies are not confined to applications of knowledge representation theories throughout AI fields, but also exceeds to cover the scientific nature of cognitive sciences. The methodological deficiencies we investigated in our work are: - The Segregation between cognitive abilities in knowledge driven models.- Insufficiency of the two-value logic used to represent knowledge particularly on machine language level in relation to the problematic issues of semantics and meaning theories. - Deficient consideration of the parameters of (existence) and (time) in the structure of knowledge. The latter requires that we present a more detailed introduction of the manner in which the meanings of Existence and Time are to be considered in the structure of knowledge. This doesn’t imply that it’s easy to apply in structures of knowledge representation systems, but outlining a deficiency caused by the absence of such essential parameters, can be considered as an attempt to redefine knowledge representation conceptual approaches, or if proven impossible; constructs a perspective on the possibility of simulating human cognition on machines. Furthermore, a redirection of the aforementioned expressions is required in order to formulate the exact meaning under discussion. This redirection of meaning alters the role of Existence and time factors to the Frame Work Environment of knowledge structure; and therefore; knowledge representation conceptual theories. Findings of our work indicate the necessity to differentiate between two comparative concepts when addressing the relation between existence and time parameters, and between that of the structure of human knowledge. The topics presented throughout the paper can also be viewed as an evaluation criterion to determine AI’s capability to achieve its ultimate objectives. Ultimately, we argue some of the implications of our findings that suggests that; although scientific progress may have not reached its peak, or that human scientific evolution has reached a point where it’s not possible to discover evolutionary facts about the human Brain and detailed descriptions of how it represents knowledge, but it simply implies that; unless these methodological deficiencies are properly addressed; the future of AI’s qualitative progress remains questionable.

Keywords: cognitive sciences, knowledge representation, ontological reasoning, temporal logic

Procedia PDF Downloads 113

Authors: Qisheng Hu, Jianglei Han, Yue Yang, My Hoa Ha

Abstract:

When a company is considering purchasing software for commercial use, contract risk assessment is critical to identify risks to mitigate the potential adverse business impact, e.g., security, financial and regulatory risks. Contract risk assessment requires reviewers with specialized knowledge and time to evaluate the legal documents manually. Specifically, validating contracts for a software vendor requires the following steps: manual screening, interpreting legal documents, and extracting risk-prone segments. To automate the process, we proposed a framework to assist legal contract document risk identification, leveraging pre-trained deep learning models and natural language processing techniques. Given a set of pre-defined risk evaluation problems, our framework utilizes the pre-trained transformer-based models for question-answering to identify risk-prone sections in a contract. Furthermore, the question-answering model encodes the concatenated question-contract text and predicts the start and end position for clause extraction. Due to the limited labelled dataset for training, we leveraged transfer learning by fine-tuning the models with the CUAD dataset to enhance the model. On a dataset comprising 287 contract documents and 2000 labelled samples, our best model achieved an F1 score of 0.687.

Keywords: contract risk assessment, NLP, transfer learning, question answering

Procedia PDF Downloads 129

Authors: Shih-Chieh Liao, Cheng-Yan Shuai

Abstract:

The feature of a side-scrolling shooting game is facing the surrounding enemy and barraging in entire screen. The player will be in trouble when they are trying to do complicated operations because of the physical and system limitations of the joystick in the games. This study designed the prototype of a new type of arcade stick by focus group and assessed by the expert. By filtering the most representative, and build up the control system for the arcade stick, and testing time and bullets consumed in two experiments, try to prove it works in the game. Finally, the prototype of L-1 solves the dilemma of scroll shooting games when the player uses the arcade stick and improves the function of the arcade stick.

Keywords: arcade stick, joystick, user interface, 2D STG

Procedia PDF Downloads 80

Authors: Anna Fowler

Abstract:

When considering assets that may need protection, the mind begins to contemplate homes, cars, and investment funds. In most cases, the protection of those assets can be covered through security systems and insurance. Data is not the first thought that comes to mind that would need protection, even though data is at the core of most supply chain operations. It includes trade secrets, management of personal identifiable information (PII), and consumer data that can be used to enhance the overall experience. Data is considered a critical element of success for supply chains and should be one of the most critical areas to protect. In the supply chain industry, there are two major misconceptions about protecting data: (i) We do not manage or store confidential/personally identifiable information (PII). (ii) Reliance on Third-Party vendor security. These misconceptions can significantly derail organizational efforts to adequately protect data across environments. These statistics can be exciting yet overwhelming at the same time. The first misconception, “We do not manage or store confidential/personally identifiable information (PII)” is dangerous as it implies the organization does not have proper data literacy. Enterprise employees will zero in on the aspect of PII while neglecting trade secret theft and the complete breakdown of information sharing. To circumvent the first bullet point, the second bullet point forges an ideology that “Reliance on Third-Party vendor security” will absolve the company from security risk. Instead, third-party risk has grown over the last two years and is one of the major causes of data security breaches. It is important to understand that a holistic approach should be considered when protecting data which should not involve purchasing a Data Loss Prevention (DLP) tool. A tool is not a solution. To protect supply chain data, start by providing data literacy training to all employees and negotiating the security component of contracts with vendors to highlight data literacy training for individuals/teams that may access company data. It is also important to understand the origin of the data and its movement to include risk identification. Ensure processes effectively incorporate data security principles. Evaluate and select DLP solutions to address specific concerns/use cases in conjunction with data visibility. These approaches are part of a broader solutions framework called Data Security Assurance (DSA). The DSA Framework looks at all of the processes across the supply chain, including their corresponding architecture and workflows, employee data literacy, governance and controls, integration between third and fourth-party vendors, DLP as a solution concept, and policies related to data residency. Within cloud environments, this framework is crucial for the supply chain industry to avoid regulatory implications and third/fourth party risk.

Keywords: security by design, data security architecture, cybersecurity framework, data security assurance

Procedia PDF Downloads 89

Authors: N. Liu, N. Tuah, D. Ying

Abstract:

This research aims to identify and test whether serious games can help children learn and pick up healthy eating habits. The practical component takes the form of digitalizing an already existing educational board game called “All you can eat” (AYCE), designed with the nutritious subject matter in mind. This time with the added features of online playability, which will widen its availability and accessibility to reach more players compared to the physical iteration. The game will be deployed alongside the conducting of theoretical research, which also involves teachers leading children to play said digital version. The research methodology utilizes two experiments, such as handing out surveys to gather feedback from both the partners and students. The research was carried out in several countries, namely Brunei, Malaysia, and Taiwan. The results are to be used for validating the concept of “serious games,” particularly when tied to the health aspect of the players, which in this case were children. As for the research outcomes, they can be applied to a variety of serious games that are related to health topics more broadly and not simply limited to healthy eating habits alone, adopting a balanced combination of practical and theoretical considerations. The study will also help other researchers in the correlated fields of serious game development and pediatrics to better comprehend the needs of children. On the theoretical side, these findings can enable further technological advancements to be made possible, a case in point being more serious games, to provide the appropriate social support precisely on the matter of health-related issues. Not just individuals but rather communities could benefit from improved health and well-being as a result of the project, which, when done right, will potentially improve their quality of life and have fun while doing it. AYCE will be demonstrated to support a wide range of health issues as a result of this research case.

Keywords: culture heritage, digital games, digitalization, traditional religious culture

Procedia PDF Downloads 76

Authors: Sumaya Iqbal, Aijaz Ahmad Reshi

Abstract:

The advances in sensor and embedded technologies have led to rapid developments in Wireless Sensor Networks (WSNs). Presently researchers focus on the integration of WSNs to Internet for their pervasive availability to access these network resources as the interoperable subsystems. The recent computing technologies like cloud computing has made the resource sharing as a converged infrastructure with required service interfaces for the shared resources over the Internet. This paper presents application architecture for wireless Sensor and Actuator Networks (WSANS) following web of things, which allows easy integration of each node to the Internet in order to provide them web accessibility. The architecture enables the sensors and actuator nodes accessed and controlled using cloud interface on WWW. The application architecture was implemented using existing web and its emerging technologies. In particular Representational State Transfer protocol (REST) was extended for the specific requirements of the application. Cloud computing environment has been used as a development platform for the application to assess the possibility of integrating the WSAN nodes to Cloud services. The mushroom farm environment monitoring and control using WSANs has been taken as a research use case.

Keywords: WSAN, REST, web of things, ZigBee, cloud interface, PaaS, sensor gateway

Procedia PDF Downloads 122

Authors: Vaishali D. Khairnar

Abstract:

The main aim is to provide lower-latency and highly reliable communication facilities for vehicles in the automobile industry; vehicle-to-everything (V2X) communication basically intends to increase expressway road security and its effectiveness. The Ultra-Reliable Low-Latency Communications (URLLC) algorithm and cellular networks are applied in combination with Mobile Broadband (MBB). This is particularly used in express way safety-based driving applications. Expressway vehicle drivers (humans) will communicate in V2X systems using the sixth-generation (6G) communication systems which have very high-speed mobility features. As a result, we need to determine how to ensure reliable and consistent wireless communication links and improve the quality to increase channel gain, which is becoming a challenge that needs to be addressed. To overcome this challenge, we proposed a unique multi-user scheduling algorithm for ultra-massive multiple-input multiple-output (MIMO) systems using 6G. In wideband wireless network access in case of high traffic and also in medium traffic conditions, moreover offering quality-of-service (QoS) to distinct service groups with synchronized contemporaneous traffic on the highway like the Mumbai-Pune expressway becomes a critical problem. Opportunist MAC (OMAC) is a way of proposing communication across a wireless communication link that can change in space and time and might overcome the above-mentioned challenge. Therefore, a multi-user scheduling algorithm is proposed for MIMO systems using a cross-layered MAC protocol to achieve URLLC and high reliability in V2X communication.

Keywords: ultra-reliable low latency communications, vehicle-to-everything communication, multiple-input multiple-output systems, multi-user scheduling algorithm

Procedia PDF Downloads 88

Authors: Samane Sharifi Monfared, Lavdie Rada

Abstract:

Nowadays, autonomous vehicles are developing rapidly toward facilitating human car driving. One of the main issues is road lane detection for a suitable guidance direction and car accident prevention. This paper aims to improve and optimize road line detection based on a combination of camera calibration, the Hough transform, and Canny edge detection. The video processing is implemented using the Open CV library with the novelty of having a scale able region masking. The aim of the study is to introduce automatic road lane detection techniques with the user’s minimum manual intervention.

Keywords: hough transform, canny edge detection, optimisation, scaleable masking, camera calibration, improving the quality of image, image processing, video processing

Procedia PDF Downloads 96

Authors: Yuhong Zhang, Dan Lu, Chenyang Bu, Peipei Li, Kui Yu, Xindong Wu

Abstract:

The Cross-Lingual Entity Alignment (CLEA) task aims to find the aligned entities that refer to the same identity from two knowledge graphs (KGs) in different languages. It is an effective way to enhance the performance of data mining for KGs with scarce resources. In real-world applications, the neighborhood structures of the same entities in different KGs tend to be non-isomorphic, which makes the representation of entities contain diverse semantic information and then poses a great challenge for CLEA. In this paper, we try to address this challenge from two perspectives. On the one hand, the cross-KG relation completion rules are designed with the alignment constraint of entities and relations to improve the topology isomorphism of two KGs. On the other hand, a representation method combining isomorphic weights is designed to include more isomorphic semantics for counterpart entities, which will benefit the CLEA. Experiments show that our model can improve the isomorphism of two KGs and the alignment performance, especially for two non-isomorphic KGs.

Keywords: knowledge graphs, cross-lingual entity alignment, non-isomorphic, relation completion

Procedia PDF Downloads 124

Authors: Xiuzhan Guo, Arthur Berrill, Ajinkya Kulkarni, Kostya Belezko, Min Luo

Abstract:

Ontology operations, e.g., aligning and merging, were studied and implemented extensively in different settings, such as categorical operations, relation algebras, and typed graph grammars, with different concerns. However, aligning and merging operations in the settings share some generic properties, e.g., idempotence, commutativity, associativity, and representativity, labeled by (I), (C), (A), and (R), respectively, which are defined on an ontology merging system (D~M), where D is a non-empty set of the ontologies concerned, ~ is a binary relation on D modeling ontology aligning and M is a partial binary operation on D modeling ontology merging. Given an ontology repository, a finite set O ⊆ D, its merging closure Ô is the smallest set of ontologies, which contains the repository and is closed with respect to merging. If (I), (C), (A), and (R) are satisfied, then both D and Ô are partially ordered naturally by merging, Ô is finite and can be computed, compared, and sorted efficiently, including sorting, selecting, and querying some specific elements, e.g., maximal ontologies and minimal ontologies. We also show that the ontology merging system, given by ontology V -alignment pairs and pushouts, satisfies the properties: (I), (C), (A), and (R) so that the merging system is partially ordered and the merging closure of a given repository with respect to pushouts can be computed efficiently.

Keywords: ontology aligning, ontology merging, merging system, poset, merging closure, ontology V-alignment pair, ontology homomorphism, ontology V-alignment pair homomorphism, pushout

Procedia PDF Downloads 893

Authors: Supria Sarkar, Vasit Sagan, Sourav Bhadra, Meghnath Pokharel, Felix B.Fritschi

Abstract:

Soybean and their derivatives are very important agricultural commodities around the world because of their wide applicability in human food, animal feed, biofuel, and industries. However, the significance of soybean production depends on the quality of the soybean seeds rather than the yield alone. Seed composition is widely dependent on plant physiological properties, aerobic and anaerobic environmental conditions, nutrient content, and plant phenological characteristics, which can be captured by high temporal resolution remote sensing datasets. Planet scope (PS) satellite images have high potential in sequential information of crop growth due to their frequent revisit throughout the world. In this study, we estimate soybean seed composition while the plants are in the field by utilizing PlanetScope (PS) satellite images and different machine learning algorithms. Several experimental fields were established with varying genotypes and different seed compositions were measured from the samples as ground truth data. The PS images were processed to extract 462 hand-crafted vegetative and textural features. Four machine learning algorithms, i.e., partial least squares (PLSR), random forest (RFR), gradient boosting machine (GBM), support vector machine (SVM), and two recurrent neural network architectures, i.e., long short-term memory (LSTM) and gated recurrent unit (GRU) were used in this study to predict oil, protein, sucrose, ash, starch, and fiber of soybean seed samples. The GRU and LSTM architectures had two separate branches, one for vegetative features and the other for textures features, which were later concatenated together to predict seed composition. The results show that sucrose, ash, protein, and oil yielded comparable prediction results. Machine learning algorithms that best predicted the six seed composition traits differed. GRU worked well for oil (R-Squared: of 0.53) and protein (R-Squared: 0.36), whereas SVR and PLSR showed the best result for sucrose (R-Squared: 0.74) and ash (R-Squared: 0.60), respectively. Although, the RFR and GBM provided comparable performance, the models tended to extremely overfit. Among the features, vegetative features were found as the most important variables compared to texture features. It is suggested to utilize many vegetation indices for machine learning training and select the best ones by using feature selection methods. Overall, the study reveals the feasibility and efficiency of PS images and machine learning for plot-level seed composition estimation. However, special care should be given while designing the plot size in the experiments to avoid mixed pixel issues.

Keywords: agriculture, computer vision, data science, geospatial technology

Procedia PDF Downloads 137

Authors: Sidi Ahmed Maouloud, Cheikh Ba

Abstract:

Much of West Africa’s cultural heritage is written in the Al-Soudani Arabic script, which was widely used in West Africa before the time of European colonization. This Al-Soudani Arabic script is an African version of the Maghrebi script, in particular, the Al-Mebssout script. However, the local African qualities were incorporated into the Al-Soudani script in a way that gave it a unique African diversity and character. Despite the existence of several Arabic datasets in Oriental script, allowing for the analysis, layout, and recognition of texts written in these calligraphies, many Arabic scripts and written traditions remain understudied. In this paper, we present a dataset of words from Al-Soudani calligraphy scripts. This dataset consists of 100 images selected from three different manuscripts written in Al-Soudani Arabic script by different copyists. The primary source for this database was the libraries of Boston University and Cambridge University. This dataset highlights the unique characteristics of the Al-Soudani Arabic script as well as the new challenges it presents in terms of automatic word recognition of Arabic manuscripts. An HTR system based on a hybrid ANN (CRNN-CTC) is also proposed to test this dataset. SAMRA is a dataset of annotated Arabic manuscript words in the Al-Soudani script that can help researchers automatically recognize and analyze manuscript words written in this script.

Keywords: dataset, CRNN-CTC, handwritten words recognition, Al-Soudani Arabic script, HTR, manuscripts

Procedia PDF Downloads 130

Authors: Yasaswi Palagummi, Sareh Rowlands

Abstract:

Generalised Zero-Shot Learning, often known as GZSL, is an advanced variant of zero-shot learning in which the samples in the unseen category may be either seen or unseen. GZSL methods typically have a bias towards the seen classes because they learn a model to perform recognition for both the seen and unseen classes using data samples from the seen classes. This frequently leads to the misclassification of data from the unseen classes into the seen classes, making the task of GZSL more challenging. In this work of ours, to solve the GZSL problem, we propose an approach leveraging the Shifted Window based Self-Attention in the Swin Transformer (Swin-GZSL) to work in the inductive GSZL problem setting. We run experiments on three popular benchmark datasets: CUB, SUN, and AWA2, which are specifically used for ZSL and its other variants. The results show that our model based on Swin Transformer has achieved state-of-the-art harmonic mean for two datasets -AWA2 and SUN and near-state-of-the-art for the other dataset - CUB. More importantly, this technique has a linear computational complexity, which reduces training time significantly. We have also observed less bias than most of the existing GZSL models.

Keywords: generalised, zero-shot learning, inductive learning, shifted-window attention, Swin transformer, vision transformer

Procedia PDF Downloads 71

Authors: Alden Boby, Dane Brown, James Connan

Abstract:

Character recognition is a well-researched topic across disciplines. Regardless, creating a solution that can cater to multiple situations is still challenging. Vehicle licence plates lack an international standard, meaning that different countries and regions have their own licence plate format. A problem that arises from this is that the typefaces and designs from different regions make it difficult to create a solution that can cater to a wide range of licence plates. The main issue concerning detection is the character recognition stage. This paper aims to create an object detection-based character recognition model trained on a custom dataset that consists of typefaces of licence plates from various regions. Given that characters have featured consistently maintained across an array of fonts, YOLO can be trained to recognise characters based on these features, which may provide better performance than OCR methods such as Tesseract OCR.

Keywords: computer vision, character recognition, licence plate recognition, object detection

Procedia PDF Downloads 121