World Academy of Science, Engineering and Technology

Authors: Ouafa Benaida, Abdelhamid Loukil, Adda Ali Pacha

Abstract:

In recent years, the growing interest of scientists in the field of image processing and analysis of underwater images and videos has been strengthened following the emergence of new underwater exploration techniques, such as the emergence of autonomous underwater vehicles and the use of underwater image sensors facilitating the exploration of underwater mineral resources as well as the search for new species of aquatic life by biologists. Indeed, underwater images and videos have several defects and must be preprocessed before their analysis. Underwater landscapes are usually darkened due to the interaction of light with the marine environment: light is absorbed as it travels through deep waters depending on its wavelength. Additionally, light does not follow a linear direction but is scattered due to its interaction with microparticles in water, resulting in low contrast, low brightness, color distortion, and restricted visibility. The improvement of the underwater image is, therefore, more than necessary in order to facilitate its analysis. The research presented in this paper aims to implement and evaluate a set of classical techniques used in the field of improving the quality of underwater images in several color representation spaces. These methods have the particularity of being simple to implement and do not require prior knowledge of the physical model at the origin of the degradation.

Keywords: underwater image enhancement, histogram normalization, histogram equalization, contrast limited adaptive histogram equalization, single-scale retinex

Procedia PDF Downloads 71

Authors: Aleksandra Jonas, Aleksandra Gronowska, Maciej Ścigacz, Szymon Jadczak

Abstract:

Exact Data is a smart tool which helps with meaningful marketing content creation. It helps marketers achieve this by analyzing the text of an advertisement before and after its publication on social media sites like Facebook or Instagram. In our research we focus on four areas of natural language processing (NLP): grammar correction, sentiment analysis, irony detection and advertisement interpretation. Our research has identified a considerable lack of NLP tools for the Polish language, which specifically aid online marketers. In light of this, our research team has set out to create a robust and versatile NLP tool for the Polish language. The primary objective of our research is to develop a tool that can perform a range of language processing tasks in this language, such as sentiment analysis, text classification, text correction and text interpretation. Our team has been working diligently to create a tool that is accurate, reliable, and adaptable to the specific linguistic features of Polish, and that can provide valuable insights for a wide range of marketers needs. In addition to the Polish language version, we are also developing an English version of the tool, which will enable us to expand the reach and impact of our research to a wider audience. Another area of focus in our research involves tackling the challenge of the limited availability of linguistically diverse corpora for non-English languages, which presents a significant barrier in the development of NLP applications. One approach we have been pursuing is the translation of existing English corpora, which would enable us to use the wealth of linguistic resources available in English for other languages. Furthermore, we are looking into other methods, such as gathering language samples from social media platforms. By analyzing the language used in social media posts, we can collect a wide range of data that reflects the unique linguistic characteristics of specific regions and communities, which can then be used to enhance the accuracy and performance of NLP algorithms for non-English languages. In doing so, we hope to broaden the scope and capabilities of NLP applications. Our research focuses on several key NLP techniques including sentiment analysis, text classification, text interpretation and text correction. To ensure that we can achieve the best possible performance for these techniques, we are evaluating and comparing different approaches and strategies for implementing them. We are exploring a range of different methods, including transformers and convolutional neural networks (CNNs), to determine which ones are most effective for different types of NLP tasks. By analyzing the strengths and weaknesses of each approach, we can identify the most effective techniques for specific use cases, and further enhance the performance of our tool. Our research aims to create a tool, which can provide a comprehensive analysis of advertising effectiveness, allowing marketers to identify areas for improvement and optimize their advertising strategies. The results of this study suggest that a smart tool for advertisement analysis can provide valuable insights for businesses seeking to create effective advertising campaigns.

Keywords: NLP, AI, IT, language, marketing, analysis

Procedia PDF Downloads 68

Authors: Simiao Ren, En Wei

Abstract:

Drowning is a significant safety issue worldwide, and a robust computer vision-based alert system can easily prevent such tragedies in swimming pools. However, due to domain shift caused by the visual gap (potentially due to lighting, indoor scene change, pool floor color etc.) between the training swimming pool and the test swimming pool, the robustness of such algorithms has been questionable. The annotation cost for labeling each new swimming pool is too expensive for mass adoption of such a technique. To address this issue, we propose a domain-aware data augmentation pipeline based on Gaussian Poisson Generative Adversarial Network (GP-GAN). Combined with YOLOv8, we demonstrate that such a domain adaptation technique can significantly improve the model performance (from 0.24 mAP to 0.82 mAP) on new test scenes. As the augmentation method only require background imagery from the new domain (no annotation needed), we believe this is a promising, practical route for preventing swimming pool drowning.

Keywords: computer vision, deep learning, YOLOv8, detection, swimming pool, drowning, domain adaptation, generative adversarial network, GAN, GP-GAN

Procedia PDF Downloads 73

Authors: Lifar M. S., Tereshchenko A. A., Bulgakov A. N., Guda S. A., Guda A. A., Soldatov A. V.

Abstract:

Metal nanoparticles are widely used as heterogeneous catalysts to activate adsorbed molecules and reduce the energy barrier of the reaction. Reaction product yield depends on the interplay between elementary processes - adsorption, activation, reaction, and desorption. These processes, in turn, depend on the inlet feed concentrations, temperature, and pressure. At stationary conditions, the active surface sites may be poisoned by reaction byproducts or blocked by thermodynamically adsorbed gaseous reagents. Thus, the yield of reaction products can significantly drop. On the contrary, the dynamic control accounts for the changes in the surface properties and adjusts reaction parameters accordingly. Therefore dynamic control may be more efficient than stationary control. In this work, a reinforcement learning algorithm has been applied to control the simulation of CO oxidation on a catalyst. The policy gradient algorithm is learned to maximize the CO₂ production rate based on the CO and O₂ flows at a given time step. Nonstationary solutions were found for the regime with surface deactivation. The maximal product yield was achieved for periodic variations of the gas flows, ensuring a balance between available adsorption sites and the concentration of activated intermediates. This methodology opens a perspective for the optimization of catalytic reactions under nonstationary conditions.

Keywords: artificial intelligence, catalyst, co oxidation, reinforcement learning, dynamic control

Procedia PDF Downloads 105

Authors: Issam Jebreen, Eman Al-Qbelat

Abstract:

Outsourcing software development projects can be challenging, and there are several common challenges that organizations face. A study was conducted with a sample of 46 papers on outsourcing challenges, and the results show that there are several common challenges faced by organizations when outsourcing software development projects. Poor outsourcing relationship was identified as the most significant challenge, with 35% of the papers referencing it. Lack of quality was the second most significant challenge, with 33% of the papers referencing it. Language and cultural differences were the third most significant challenge, with 24% of the papers referencing it. Non-competitive price was another challenge faced by organizations, with 21% of the papers referencing it. Poor coordination and communication were also identified as a challenge, with 21% of the papers referencing it. Opportunistic behavior, lack of contract negotiation, inadequate user involvement, and constraints due to time zone were also challenges faced by organizations. Other challenges faced by organizations included poor project management, lack of technical capabilities, vendor employee high turnover, poor requirement specification, IPR issues, poor management of budget, schedule, and delay, geopolitical and country instability, the difference in development methodologies, failure to manage end-user expectations, and poor monitoring and control. In conclusion, outsourcing software development projects can be challenging, but organizations can mitigate these challenges by selecting the right outsourcing partner, having a well-defined contract and clear communication, having a clear understanding of the requirements, and implementing effective project management practices.

Keywords: software outsourcing, vendor, outsourcing challenges, quality model, continent, country, global outsourcing, IT workforce outsourcing.

Procedia PDF Downloads 72

Authors: Degale Desta, Cheng Jian

Abstract:

The most important factor in identifying a person is their face. Even identical twins have their own distinct faces. As a result, identification and face recognition are needed to tell one person from another. A face recognition system is a verification tool used to establish a person's identity using biometrics. Nowadays, face recognition is a common technique used in a variety of applications, including home security systems, criminal identification, and phone unlock systems. This system is more secure because it only requires a facial image instead of other dependencies like a key or card. Face detection and face identification are the two phases that typically make up a human recognition system.The idea behind designing and creating a face recognition system using deep learning with Azure ML Python's OpenCV is explained in this paper. Face recognition is a task that can be accomplished using deep learning, and given the accuracy of this method, it appears to be a suitable approach. To show how accurate the suggested face recognition system is, experimental results are given in 98.46% accuracy using Fast-RCNN Performance of algorithms under different training conditions.

Keywords: deep learning, face recognition, identification, fast-RCNN

Procedia PDF Downloads 120

Authors: Grace Omowunmi Soyebi

Abstract:

A computerized medical record system is a collection of medical information about a person that is stored on a computer. One principal problem of most hospitals in rural areas is using the file management system for keeping records. A lot of time is wasted when a patient visits the hospital, probably in an emergency, and the nurse or attendant has to search through voluminous files before the patient's file can be retrieved; this may cause an unexpected to happen to the patient. This data mining application is to be designed using a structured system analysis and design method which will help in a well-articulated analysis of the existing file management system, feasibility study, and proper documentation of the design and implementation of a computerized medical record system. This computerized system will replace the file management system and help to quickly retrieve a patient's record with increased data security, access clinical records for decision-making, and reduce the time range at which a patient gets attended to.

Keywords: programming, data, software development, innovation

Procedia PDF Downloads 70

Authors: Grace Omowunmi Soyebi

Abstract:

A computerized medical record system is a collection of medical information about a person that is stored on a computer. One principal problem of most hospitals in rural areas is using the file management system for keeping records. A lot of time is wasted when a patient visits the hospital, probably in an emergency, and the nurse or attendant has to search through voluminous files before the patient's file can be retrieved, this may cause an unexpected to happen to the patient. This Data Mining application is to be designed using a Structured System Analysis and design method which will help in a well-articulated analysis of the existing file management system, feasibility study, and proper documentation of the Design and Implementation of a Computerized medical record system. This Computerized system will replace the file management system and help to quickly retrieve a patient's record with increased data security, access clinical records for decision-making, and reduce the time range at which a patient gets attended to.

Keywords: programming, computing, data, innovation

Procedia PDF Downloads 106

Authors: Divvela Vishnu Sai Kumar, Deepak Arora, Sheenu Rizvi

Abstract:

Forecasting a cyclone through satellite images consists of the estimation of the intensity of the cyclone and predicting it before a cyclone comes. This research work can help people to take safety measures before the cyclone comes. The prediction of the intensity of a cyclone is very important to save lives and minimize the damage caused by cyclones. These cyclones are very costliest natural disasters that cause a lot of damage globally due to a lot of hazards. Authors have proposed five different CNN (Convolutional Neural Network) models that estimate the intensity of cyclones through INSAT-3D IR images. There are a lot of techniques that are used to estimate the intensity; the best model proposed by authors estimates intensity with a root mean squared error (RMSE) of 10.02 kts.

Keywords: estimating cyclone intensity, deep learning, convolution neural network, prediction models

Procedia PDF Downloads 100

Authors: M. Kamel, A. Hoayek, M. Batton-Hubert

Abstract:

With the increase of network virtualization and the disparity of vendors, the continuous monitoring and detection of anomalies cannot rely on static rules. An advanced analytical methodology is needed to discriminate between ordinary events and unusual anomalies. In this paper, we focus on log data (textual data), which is a crucial source of information for network performance. Then, we introduce an algorithm used as a pipeline to help with the pretreatment of such data, group it into patterns, and dynamically label each pattern as an anomaly or not. Such tools will provide users and experts with continuous real-time logs monitoring capability to detect anomalies and failures in the underlying system that can affect performance. An application of real-world data illustrates the algorithm.

Keywords: logs, anomaly detection, ML, scoring, NLP

Procedia PDF Downloads 76

Authors: Chhavi Rana

Abstract:

The aim of the paper is to highlight the existing development in the field of big data analytics. Applications like bioinformatics, smart infrastructure projects, Healthcare, and business intelligence contain voluminous and incremental data, which is hard to organise and analyse and can be dealt with using the framework and model in this field of study. An organization's decision-making strategy can be enhanced using big data analytics and applying different machine learning techniques and statistical tools on such complex data sets that will consequently make better things for society. This paper reviews the current state of the art in this field of study as well as different application domains of big data analytics. It also elaborates on various frameworks in the process of Analysis using different machine-learning techniques. Finally, the paper concludes by stating different challenges and issues raised in existing research.

Keywords: big data, big data analytics, machine learning, review

Procedia PDF Downloads 64

Authors: John Paul Q. Tomas, Mark Wilson L. de los Reyes, Kirsten Joyce P. Vasquez

Abstract:

The most frequent type of fracture is a wrist fracture, which often makes it difficult for medical professionals to find and locate. In this study, fractures in wrist x-ray pictures were located and identified using deep learning and computer vision. The researchers used image filtering, masking, morphological operations, and data augmentation for the image preprocessing and trained the RetinaNet and Faster R-CNN models with ResNet50 backbones and Adam optimizers separately for each image filtering technique and projection. The RetinaNet model with Anisotropic Diffusion Smoothing filter trained with 50 epochs has obtained the greatest accuracy of 99.14%, precision of 100%, sensitivity/recall of 98.41%, specificity of 100%, and an IoU score of 56.44% for the Posteroanterior projection utilizing augmented data. For the Lateral projection using augmented data, the RetinaNet model with an Anisotropic Diffusion filter trained with 50 epochs has produced the highest accuracy of 98.40%, precision of 98.36%, sensitivity/recall of 98.36%, specificity of 98.43%, and an IoU score of 58.69%. When comparing the test results of the different individual projections, models, and image filtering techniques, the Anisotropic Diffusion filter trained with 50 epochs has produced the best classification and regression scores for both projections.

Keywords: Artificial Intelligence, Computer Vision, Wrist Fracture, Deep Learning

Procedia PDF Downloads 60

Authors: Spanova Yerkezhan, Amantay Ayan, Alimzhanova Laura

Abstract:

This article discusses the concept of rebranding and its relationship to cybersecurity. Rebranding is the process of changing the appearance and image of a company or organization in order to appeal to new customers or change the perception of a company. It can be a powerful tool for businesses looking to renew their reputation or expand into new markets. In today's digital age, companies increasingly rely on technology and the internet to conduct business; rebranding can also present significant cybersecurity risks. This is because a rebranding effort can create new vulnerabilities for companies, particularly in terms of their online presence. This article explores the potential hazards associated with rebranding and provides recommendations for mitigating those risks. It also highlights the importance of considering cybersecurity in the rebranding process and how it can be integrated into the overall strategy for a successful and secure rebranding.

Keywords: rebranding, cybersecurity, cyberattack, logo, vulnerability

Procedia PDF Downloads 147

Authors: Jihen Bennaceur, Wissem Zouaghi, Ali Mabrouk

Abstract:

The major aim of cyber threat intelligence (CTI) is to provide sophisticated knowledge about cybersecurity threats to ensure internal and external safeguards against modern cyberattacks. Inaccurate, incomplete, outdated, and invaluable threat intelligence is the main problem. Therefore, data analysis based on AI algorithms is one of the emergent solutions to overcome the threat of information-sharing issues. In this paper, we propose a supervised machine learning-based algorithm to improve threat information sharing by providing a sophisticated classification of cyber threats and data. Extensive simulations investigate the accuracy, precision, recall, f1-score, and support overall to validate the designed algorithm and to compare it with several supervised machine learning algorithms.

Keywords: threat information sharing, supervised learning, data classification, performance evaluation

Procedia PDF Downloads 133

Authors: A. Kavya Sri, K. Sai Vineela, R. Vanitha, S. Rohith

Abstract:

Large pieces of ice that break from the glaciers are known as icebergs. The threat that icebergs pose to navigation, production of offshore oil and gas services, and underwater pipelines makes their detection crucial. In this project, an automated iceberg tracking method using deep learning techniques and satellite images of icebergs is to be developed. With a temporal resolution of 12 days and a spatial resolution of 20 m, Sentinel-1 (SAR) images can be used to track iceberg drift over the Southern Ocean. In contrast to multispectral images, SAR images are used for analysis in meteorological conditions. This project develops a web-based graphical user interface to detect and track icebergs using sentinel-1 images. To track the movement of the icebergs by using temporal images based on their latitude and longitude values and by comparing the center and area of all detected icebergs. Testing the accuracy is done by precision and recall measures.

Keywords: synthetic aperture radar (SAR), icebergs, deep learning, spatial resolution, temporal resolution

Procedia PDF Downloads 75

Authors: Olivia A. Kjorlien, Maryam Asghari, Farshid Alizadeh-Shabdiz

Abstract:

The goal of this paper is to investigate the impact of mosaic augmentation on the performance of object detection solutions. To carry out the study, YOLOv4 and YOLOv4-Tiny models have been selected, which are popular, advanced object detection models. These models are also representatives of two classes of complex and simple models. The study also has been carried out on two categories of objects, simple and complex. For this study, YOLOv4 and YOLOv4 Tiny are trained with and without mosaic augmentation for two sets of objects. While mosaic augmentation improves the performance of simple object detection, it deteriorates the performance of complex object detection, specifically having the largest negative impact on the false positive rate in a complex object detection case.

Keywords: accuracy, false positives, mosaic augmentation, object detection, YOLOV4, YOLOV4-Tiny

Procedia PDF Downloads 113

Authors: Nassima Noufail, Sara Bouhali

Abstract:

In this work, we develop a semi-supervised solution for the purpose of action detection in videos and propose an efficient algorithm for video segmentation. The approach is divided into video segmentation, feature extraction, and classification. In the first part, a video is segmented into clips, and we used the K-means algorithm for this segmentation; our goal is to find groups based on similarity in the video. The application of k-means clustering into all the frames is time-consuming; therefore, we started by the identification of transition frames where the scene in the video changes significantly, and then we applied K-means clustering into these transition frames. We used two image filters, the gaussian filter and the Laplacian of Gaussian. Each filter extracts a set of features from the frames. The Gaussian filter blurs the image and omits the higher frequencies, and the Laplacian of gaussian detects regions of rapid intensity changes; we then used this vector of filter responses as an input to our k-means algorithm. The output is a set of cluster centers. Each video frame pixel is then mapped to the nearest cluster center and painted with a corresponding color to form a visual map. The resulting visual map had similar pixels grouped. We then computed a cluster score indicating how clusters are near each other and plotted a signal representing frame number vs. clustering score. Our hypothesis was that the evolution of the signal would not change if semantically related events were happening in the scene. We marked the breakpoints at which the root mean square level of the signal changes significantly, and each breakpoint is an indication of the beginning of a new video segment. In the second part, for each segment from part 1, we randomly selected a 16-frame clip, then we extracted spatiotemporal features using convolutional 3D network C3D for every 16 frames using a pre-trained model. The C3D final output is a 512-feature vector dimension; hence we used principal component analysis (PCA) for dimensionality reduction. The final part is the classification. The C3D feature vectors are used as input to a multi-class linear support vector machine (SVM) for the training model, and we used a multi-classifier to detect the action. We evaluated our experiment on the UCF101 dataset, which consists of 101 human action categories, and we achieved an accuracy that outperforms the state of art by 1.2%.

Keywords: video segmentation, action detection, classification, Kmeans, C3D

Procedia PDF Downloads 59

Authors: Lyamine Guezouli, Kamel Barka, Zineb Seghir

Abstract:

Wireless sensor and actor networks (WSANs) present a research challenge for different practice areas. Researchers are trying to optimize the use of such networks through their research work. This optimization is done on certain criteria, such as improving energy efficiency, exploiting node heterogeneity, self-adaptability and self-configuration. In this article, we present our proposal for BIFSA (Biologically-Inspired Framework for Wireless Sensor and Actor networks). Indeed, BIFSA is a middleware that addresses the key issues of wireless sensor and actor networks. BIFSA consists of two types of agents: sensor agents (SA) that operate at the sensor level to collect and transport data to actors and actor agents (AA) that operate at the actor level to transport data to base stations. Once the sensor agent arrives at the actor, it becomes an actor agent, which can exploit the resources of the actors and vice versa. BIFSA allows agents to evolve their genetic structures and adapt to the current network conditions. The simulation results show that BIFSA allows the agents to make better use of all the resources available in each type of node, which improves the performance of the network.

Keywords: wireless sensor and actor networks, self-management, genetic algorithm, agent.

Procedia PDF Downloads 69

Authors: Kamel Barka, Lyamine Guezouli, Assem Rezki

Abstract:

In this article, we propose a protocol called DataGA-DRF (a protocol for Data collection using a Genetic Algorithm through Dynamic Reference Points) that collects data from Heterogeneous wireless sensor networks. This protocol is based on DGA (Destination selection according to Genetic Algorithm) to control the movement of the UAV (Unmanned aerial vehicle) between dynamic reference points that virtually represent the sensor node deployment. The dynamics of these points ensure an even distribution of energy consumption among the sensors and also improve network performance. To determine the best points, DataGA-DRF uses a classification algorithm such as K-Means.

Keywords: heterogeneous wireless networks, unmanned aerial vehicles, reference point, collect data, genetic algorithm

Procedia PDF Downloads 66

Authors: Rochelle Elva

Abstract:

Faculty in Higher Education today are faced with the challenge of convincing their students of the importance of learning and mastery of skills. This is because most students often have a single motivation -to get high grades. If it appears that this goal will not be met, they lose their motivation, and their academic efforts wane. This is true even for students in the competitive fields of STEM, including Computer Science majors. As educators, we have to understand our students and leverage what motivates them to achieve our learning outcomes. This paper presents a case study that utilizes cognitive psychology’s Expectancy Value Theory and Motivation Theory to investigate the effect of sustained expectancy for success on students’ learning outcomes. In our case study, we explore how students’ motivation and persistence in their academic efforts are impacted by providing them with an unexpected possible path to success that continues to the end of the semester. The approach was tested in an undergraduate computer science course with n = 56. The results of the study indicate that when presented with the real possibility of success, despite existing low grades, both low and high-scoring students persisted in their efforts to improve their performance. Their final grades were, on average, one place higher on the +/-letter grade scale, with some students scoring as high as three places above their predicted grade.

Keywords: expectancy for success and persistence, motivation and performance, computer science education, motivation and performance in computer science

Procedia PDF Downloads 64

Authors: Rita Chattopadhyay, Vivek Anand Thoutam

Abstract:

Speech is the most acceptable means of communication where we can quickly exchange our feelings and thoughts. Quite often, people can communicate orally but cannot interact or work with computers or devices. It’s easy and quick to give speech commands than typing commands to computers. In the same way, it’s easy listening to audio played from a device than extract output from computers or devices. Especially with Robotics being an emerging market with applications in warehouses, the hospitality industry, consumer electronics, assistive technology, etc., speech-based human-machine interaction is emerging as a lucrative feature for robot manufacturers. Considering this factor, the objective of this paper is to design the “Audio-Visual Co-Data Processing Pipeline.” This pipeline is an integrated version of Automatic speech recognition, a Natural language model for text understanding, object detection, and text-to-speech modules. There are many Deep Learning models for each type of the modules mentioned above, but OpenVINO Model Zoo models are used because the OpenVINO toolkit covers both computer vision and non-computer vision workloads across Intel hardware and maximizes performance, and accelerates application development. A speech command is given as input that has information about target objects to be detected and start and end times to extract the required interval from the video. Speech is converted to text using the Automatic speech recognition QuartzNet model. The summary is extracted from text using a natural language model Generative Pre-Trained Transformer-3 (GPT-3). Based on the summary, essential frames from the video are extracted, and the You Only Look Once (YOLO) object detection model detects You Only Look Once (YOLO) objects on these extracted frames. Frame numbers that have target objects (specified objects in the speech command) are saved as text. Finally, this text (frame numbers) is converted to speech using text to speech model and will be played from the device. This project is developed for 80 You Only Look Once (YOLO) labels, and the user can extract frames based on only one or two target labels. This pipeline can be extended for more than two target labels easily by making appropriate changes in the object detection module. This project is developed for four different speech command formats by including sample examples in the prompt used by Generative Pre-Trained Transformer-3 (GPT-3) model. Based on user preference, one can come up with a new speech command format by including some examples of the respective format in the prompt used by the Generative Pre-Trained Transformer-3 (GPT-3) model. This pipeline can be used in many projects like human-machine interface, human-robot interaction, and surveillance through speech commands. All object detection projects can be upgraded using this pipeline so that one can give speech commands and output is played from the device.

Keywords: OpenVINO, automatic speech recognition, natural language processing, object detection, text to speech

Procedia PDF Downloads 63

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 70

Authors: Robin Singh, Jing-Chiou Liou

Abstract:

The Internet of Things (IoT) devices are being used heavily as part of our everyday routines. Through improved communication and automated procedures, its popularity has assisted users in raising the quality of work. These devices are used in healthcare in order to better collect the patient’s data for their treatment. They are generally considered safe and secure. However, there is some possibility that some loopholes do exist which manufacturers do need to identify before some hacker takes advantage of them. For this study, we focused on two medical IoT devices which are pacemakers and hearing aids. The aim of this paper is to identify if there is any likelihood of these medical devices being hijacked and used as a botnet in Distributed Denial-Of Service attacks. Moreover, some mitigation strategies are being proposed to better secure

Keywords: cybersecurity, DDoS, IoT, medical devices

Procedia PDF Downloads 68

Authors: Marcelino Caetano Noronha, Vosco Pereira, Jose Soares Pinto, Ferdinando Da C. Saores

Abstract:

One particularly popular social media platform is Youtube. It’s a video-sharing platform where users can submit videos, and other users can like, dislike or comment on the videos. In this study, we conduct a binary classification task on YouTube’s video comments and review from the users regarding the accession process of Timor Leste to become the eleventh member of the Association of South East Asian Nations (ASEAN). We scrape the data directly from the public YouTube video and apply several pre-processing and weighting techniques. Before conducting the classification, we categorized the data into two classes, namely positive and negative. In the classification part, we apply Support Vector Machine (SVM) algorithm. By comparing with Naïve Bayes Algorithm, the experiment showed SVM achieved 84.1% of Accuracy, 94.5% of Precision, and Recall 73.8% simultaneously.

Keywords: classification, YouTube, sentiment analysis, support sector machine

Procedia PDF Downloads 89

Authors: Hongbo Zhang, Xinlu Tang, Jiangwei Li, Chi Yan

Abstract:

Home zone parking pilot (HPP) is a fast-growing segment in low-speed autonomous driving applications. It requires the car automatically cruise around a parking lot and park itself in a range of up to 100 meters inside a recurrent home/office parking lot, which requires precise parking lot mapping and localization solution. Although Lidar is ideal for SLAM, the car OEMs favor a low-cost fish-eye camera based visual SLAM approach. Recent approaches have employed segmentation models to extract semantic features and improve mapping accuracy, but these AI models are memory unfriendly and computationally expensive, making deploying on embedded ADAS systems difficult. To address this issue, we proposed a new method that utilizes object detection models to extract robust and accurate parking lot features. The proposed method could reduce computational costs while maintaining high accuracy. Once combined with vehicles’ wheel-pulse information, the system could construct maps and locate the vehicle in real-time. This article will discuss in detail (1) the fish-eye based Around View Monitoring (AVM) with transparent chassis images as the inputs, (2) an Object Detection (OD) based feature point extraction algorithm to generate point cloud, (3) a low computational parking lot mapping algorithm and (4) the real-time localization algorithm. At last, we will demonstrate the experiment results with an embedded ADAS system installed on a real car in the underground parking lot.

Keywords: ADAS, home zone parking pilot, object detection, visual SLAM

Procedia PDF Downloads 56

Authors: Baoliang Xu

Abstract:

The future of education should focus on creating meaningful learning for learners. Play is a basic form and an important means of carrying out kindergarten educational activities, which promotes the creation and development of meaningful learning and is of great importance in the harmonious physical and mental development of young children. Through literature research and case studies, this paper finds that: meaningful learning has the characteristics of contextuality, interaction and constructiveness; teachers should pay great attention to the guidance of children's games, fully respect children's autonomy and create a prepared game environment; children's meaningful learning exists in games and hidden in things that interest them, and "the generation of questions The "generation of questions" fuels the depth of children's meaningful learning, and teachers' professional support helps children's meaningful learning to develop continuously. In short, teachers' guidance of young children's play should be emphasized to effectively provide scaffolding instruction to promote meaningful learning in a holistic manner.

Keywords: meaningful learning, young childhood, game, case study

Procedia PDF Downloads 52

Authors: Ken Zakreski

Abstract:

Regulating Canadian Facebook Groups, of a size and type, when they reach a threshold of audio video content. Consider the evolution of the Streaming Act, Parl GC Bill C-11 (44-1) and the regulations that will certainly follow. The Canadian Heritage Minister's office stipulates, "the Broadcasting Act only applies to audio and audiovisual content, not written journalism.” Governance— After 10 years, a community radio station for Gabriola Island, BC – Canadian Radio-television and Telecommunications Commission (“CRTC”) was approved but never started – became a Facebook Group “Community Bulletin Board - Life on Gabriola“ referred to as CBBlog. After CBBlog started and began to gather real traction, a member of the Group cloned the membership and ran their competing Facebook group under the banner of "free speech”. Here we see an inflection point [change of cultural stewardship] with two different mathematical results [engagement and membership growth]. Canada's telecommunication history of “portability” and “interoperability” made that Facebook Group CBBlog the better option, over broadcast FM radio for a community pandemic information sharing service for Gabriola Island, BC. A culture of ignorance flourishes in social media. Often people do not understand their own experience, or the experience of others because they do not have the concepts needed for understanding. It is thus important they are not denied concepts required for their full understanding. For example, Legislators need to know something about gay culture before they can make any decisions about it. Community Media policies and CRTC regulations are known and regulators can use that history to forge forward with regulations for internet platforms of a size and content type that reach a threshold of audio / video content. Mostly volunteer run media services, provide order of magnitude lower costs over commercial media. (Treating) Facebook Groups as new media.? Cathy Edwards, executive director of the Canadian Association of Community Television Users and Stations (“CACTUS”), calls it new media in that the distribution platform is not the issue. What does make community groups community media? Cathy responded, "... it's bylaws, articles of incorporation that state they are community media, they have accessibility, commitments to skills training, any member of the community can be a member, and there is accountability to a board of directors". Eligibility for funding through CACTUS requires these same commitments. It is risky for a community to invest into a platform as ownership has not been litigated. Is a FaceBook Group an asset of a not for profit society? The memo, from law student, Jared Hubbard summarizes, “Rights and interests in a Facebook group could, in theory, be transferred as property... This theory is currently unconfirmed by Canadian courts. “

Keywords: social media, governance, community media, Canadian radio

Procedia PDF Downloads 52

Authors: Sadiq Nasir

Abstract:

The need for strong cybersecurity measures has been brought to light by society's growing reliance on technology. Cybersecurity breaches continue, with the human aspect playing a crucial role, despite the availability of technology remedies. By analyzing the most recent findings in this area of research on awareness, attitudes, and behaviour, this literature review seeks to comprehend the human element in cybersecurity. A thorough overview of the most recent studies and gaps in the body of knowledge will be determined through a systematic examination of the literature. The paper indicates that in order to address the human component in cybersecurity, a socio-technical strategy is required, and it advocates for additional study in order to fully comprehend the consequences of various interventions. The findings of this study will increase our understanding of cybersecurity and have useful ramifications for companies wanting to strengthen their cybersecurity posture.

Keywords: cybersecurity, cybersecurity awareness, human factor in security, human security

Procedia PDF Downloads 72

Authors: Aikaterini Kentroti, Theodore H. Kaskalis

Abstract:

Today, web servers are expected to serve thousands of client requests concurrently within stringent response time limits. In this paper, we evaluate experimentally and compare the performance as well as the resource utilization of popular web servers, which differ in their approach to handle concurrency. More specifically, Central Processing Unit (CPU)- and I/O intensive tests were conducted against the thread-based Apache and Go as well as the event-based Nginx and Node.js under increasing concurrent load. The tests involved concurrent users requesting a term of the Fibonacci sequence (the 10th, 20th, 30th) and the content of a table from the database. The results show that Go achieved the best performance in all benchmark tests. For example, Go reached two times higher throughput than Node.js and five times higher than Apache and Nginx in the 20th Fibonacci term test. In addition, Go had the smallest memory footprint and demonstrated the most efficient resource utilization, in terms of CPU usage. Instead, Node.js had by far the largest memory footprint, consuming up to 90% more memory than Nginx and Apache. Regarding the performance of Apache and Nginx, our findings indicate that Hypertext Preprocessor (PHP) becomes a bottleneck when the servers are requested to respond by performing CPU-intensive tasks under increasing concurrent load.

Keywords: apache, Go, Nginx, node.js, web server benchmarking

Procedia PDF Downloads 77

Authors: Uma Maheshwari V., Rajanikanth Aluvalu, Kumar Gautam

Abstract:

The COVID-19 disease is a highly contagious viral infection with major worldwide health implications. The global economy suffers as a result of COVID. The spread of this pandemic disease can be slowed if positive patients are found early. COVID-19 disease prediction is beneficial for identifying patients' health problems that are at risk for COVID. Deep learning and machine learning algorithms for COVID prediction using X-rays have the potential to be extremely useful in solving the scarcity of doctors and clinicians in remote places. In this paper, a convolutional neural network (CNN) with deep layers is presented for recognizing COVID-19 patients using real-world datasets. We gathered around 6000 X-ray scan images from various sources and split them into two categories: normal and COVID-impacted. Our model examines chest X-ray images to recognize such patients. Because X-rays are commonly available and affordable, our findings show that X-ray analysis is effective in COVID diagnosis. The predictions performed well, with an average accuracy of 99% on training photographs and 88% on X-ray test images.

Keywords: deep CNN, COVID–19 analysis, feature extraction, feature map, accuracy

Procedia PDF Downloads 62