World Academy of Science, Engineering and Technology

Authors: Farah Al-Fityani, Aljohara Alsowail, Shatha Bindawood, Heba Balrbeah

Abstract:

Locket is a popular app that lets users share spontaneous photos with a close circle of friends. The app offers a unique way to stay connected with loved ones by allowing users to see glimpses of their day through photos displayed on a widget on their home screen. This summary outlines the process of developing an app like Locket, highlighting the importance of user privacy and security. It also details the findings of a study on user engagement with the Locket app, revealing positive sentiment towards its features and concept but also identifying areas for improvement. Overall, the summary portrays Locket as a successful app that is changing the way people connect on social media.

Keywords: locket, app, machine learning, connect

Procedia PDF Downloads 14

Authors: Sarah Mohammed, Huda Allagany, Ayah Barakat, Muna Elyas

Abstract:

This paper delves into the history and development of ChatGPT, tracing its evolution from its inception by OpenAI to its current state, and emphasizing its design improvements and strategic partnerships. It also explores the performance and applicability of ChatGPT versions 3.5 and 4 in various contexts, examining its capabilities and limitations in producing accurate and relevant responses. Utilizing a quantitative approach, user satisfaction, speed of response, learning capabilities, and overall utility in academic performance were assessed through surveys and analysis tools. Findings indicate that while ChatGPT generally delivers high accuracy and speed in responses, the need for clarification and more specific user instructions persists. The study highlights the tool's increasing integration across different sectors, showcasing its potential in educational and professional settings.

Keywords: artificial intelligence, chat GPT, analysis, education

Procedia PDF Downloads 24

Authors: Jae Ni Jang, Young Uk Kim

Abstract:

Background: Chat Generative Pre-training Transformer-3 (ChatGPT; San Francisco, California, Open Artificial Intelligence) is an artificial intelligence chatbot based on a large language model designed to generate human-like text. As the usage of ChatGPT is increasing among less knowledgeable patients, medical students, and anesthesia and pain medicine residents or trainees, we aimed to evaluate the accuracy of ChatGPT-3 responses to questions about the American Society of Anesthesiologists (ASA) classification based on patients’ underlying diseases and assess the quality of the generated responses. Methods: A total of 47 questions were submitted to ChatGPT using textual prompts. The questions were designed for ChatGPT-3 to provide answers regarding ASA classification in response to common underlying diseases frequently observed in adult patients. In addition, we created 18 questions regarding the ASA classification for pediatric patients and pregnant women. The accuracy of ChatGPT’s responses was evaluated by cross-referencing with Miller’s Anesthesia, Morgan & Mikhail’s Clinical Anesthesiology, and the American Society of Anesthesiologists’ ASA Physical Status Classification System (2020). Results: Out of the 47 questions pertaining to adults, ChatGPT -3 provided correct answers for only 23, resulting in an accuracy rate of 48.9%. Furthermore, the responses provided by ChatGPT-3 regarding children and pregnant women were mostly inaccurate, as indicated by a 28% accuracy rate (5 out of 18). Conclusions: ChatGPT provided correct responses to questions relevant to the daily clinical routine of anesthesiologists in approximately half of the cases, while the remaining responses contained errors. Therefore, caution is advised when using ChatGPT to retrieve anesthesia-related information. Although ChatGPT may not yet be suitable for clinical settings, we anticipate significant improvements in ChatGPT and other large language models in the near future. Regular assessments of ChatGPT's ASA classification accuracy are essential due to the evolving nature of ChatGPT as an artificial intelligence entity. This is especially important because ChatGPT has a clinically unacceptable rate of error and hallucination, particularly in pediatric patients and pregnant women. The methodology established in this study may be used to continue evaluating ChatGPT.

Keywords: American Society of Anesthesiologists, artificial intelligence, Chat Generative Pre-training Transformer-3, ChatGPT

Procedia PDF Downloads 20

Authors: Arwa Alnowaiser, Hala Shoukri

Abstract:

The ‘FreeAITherapist’ is an artificial intelligence application that uses the power of AI to offer advice and mental health counseling to its users through its chatbot services. The AI therapist is designed to understand users' issues, concerns, and problems and respond appropriately; it provides empathy and guidance and uses evidence-based therapeutic techniques. With its user-friendly platform, it ensures accessibility for individuals in need, regardless of their geographical location. This website was created in direct response to the growing demand for mental health support, aiming to provide a cost-effective and confidential solution. Through promising confidentiality, it considers user privacy and data security. The ‘FreeAITherapist’ strives to bridge the gap in mental health services, offering a reliable resource for individuals seeking guidance and counseling to improve their overall well-being.

Keywords: artificial intelligence, mental health, AI therapist, website, counseling

Procedia PDF Downloads 17

Authors: Elen Gasparyan, Naira Hakobyan

Abstract:

One of the leading factors determining the effectiveness of work in a modern organization is the motivation of its employees. In the scientific psychological literature, this phenomenon is understood mainly as constructive forms of motivation and the search for ways to increase it. At the same time, the motivation of employees can sometimes lead to a decrease in the productivity of the organization, i.e., destructive motivation is usually not considered from the point of view of various motivational theories. This article provides an analysis of various forms of destructive motivation of employees. These forms include formalism in labor behavior, inadequate assessment of the work done, and an imbalance of personal and organizational interests. The destructive motivation of personnel has certain negative consequences both for the employees themselves and for the entire organization - it leads to a decrease in the rate of production and the quality of products or services, increased conflict in the behavior of employees, etc. Currently, there is an increase in scientific interest in the study of destructive motivation. The subject of psychological research is not only modern socio-psychological processes but also the achievements of scientific thought in the field of theories of motivation and management. This article examines the theoretical approaches of J. S. Adams and Porter-Lawler, provides an analysis of theoretical concepts, and emphasizes the main characteristics of the destructiveness of motivation. Destructive work motivation is presented at the macro, meso, and micro levels. These levels express various directions of development of motivation stimuli, such as social, organizational, and personal ones. At the macro level, the most important characteristics of destructive motivation are the high-income gap between employers and employees, а high degree of unemployment, weak social protection of workers, non-compliance by employers with labor legislation, and emergencies. At the organizational level, the main characteristics are decreasing the diversity of work and insufficient work conditions. At the personal level, the main characteristic of destructive motivation is a discrepancy between personal and organizational interests. A comparative analysis of the theoretical and methodological foundations of the study of motivation makes it possible to identify not only the main characteristics of destructive motivation but also to determine the contours of psychological counseling to reduce destructiveness in the behavior of employees.

Keywords: destructive, motivation, organization, behavior

Procedia PDF Downloads 22

Authors: Habtamu Ayenew Asegie

Abstract:

Wealth, as opposed to income or consumption, implies a more stable and permanent status. Due to natural and human-made difficulties, households' economies will be diminished, and their well-being will fall into trouble. Hence, governments and humanitarian agencies offer considerable resources for poverty and malnutrition reduction efforts. One key factor in the effectiveness of such efforts is the accuracy with which low-income or poor populations can be identified. As a result, this study aims to predict a household’s wealth status using ensemble Machine learning (ML) algorithms. In this study, design science research methodology (DSRM) is employed, and four ML algorithms, Random Forest (RF), Adaptive Boosting (AdaBoost), Light Gradient Boosted Machine (LightGBM), and Extreme Gradient Boosting (XGBoost), have been used to train models. The Ethiopian Demographic and Health Survey (EDHS) dataset is accessed for this purpose from the Central Statistical Agency (CSA)'s database. Various data pre-processing techniques were employed, and the model training has been conducted using the scikit learn Python library functions. Model evaluation is executed using various metrics like Accuracy, Precision, Recall, F1-score, area under curve-the receiver operating characteristics (AUC-ROC), and subjective evaluations of domain experts. An optimal subset of hyper-parameters for the algorithms was selected through the grid search function for the best prediction. The RF model has performed better than the rest of the algorithms by achieving an accuracy of 96.06% and is better suited as a solution model for our purpose. Following RF, LightGBM, XGBoost, and AdaBoost algorithms have an accuracy of 91.53%, 88.44%, and 58.55%, respectively. The findings suggest that some of the features like ‘Age of household head’, ‘Total children ever born’ in a family, ‘Main roof material’ of their house, ‘Region’ they lived in, whether a household uses ‘Electricity’ or not, and ‘Type of toilet facility’ of a household are determinant factors to be a focal point for economic policymakers. The determinant risk factors, extracted rules, and designed artifact achieved 82.28% of the domain expert’s evaluation. Overall, the study shows ML techniques are effective in predicting the wealth status of households.

Keywords: ensemble machine learning, households wealth status, predictive model, wealth status prediction

Procedia PDF Downloads 22

Authors: Yara Bajnaid, Malak Zaidan, Eman Dakkak

Abstract:

This research explores the use of Artificial Intelligence in Duolingo, a popular mobile application for language learning. Duolingo's success hinges on its gamified approach and adaptive learning system, both heavily reliant on AI functionalities. The research also analyzes user feedback regarding Duolingo's AI functionalities. While a significant majority (70%) consider Duolingo a reliable tool for language learning, there's room for improvement. Overall, AI plays a vital role in personalizing the learning journey and delivering interactive exercises. However, continuous improvement based on user feedback can further enhance the effectiveness of Duolingo's AI functionalities.

Keywords: AI, Duolingo, language learning, application

Procedia PDF Downloads 25

Authors: Abbas Khosravi

Abstract:

This paper discusses the use of cooperation without communication in a multi-agent, unpredictable, dynamic real-time environment. The architecture of the Persian Gulf agent consists of three layers: fixed rule, low level, and high level layers, allowing for cooperation without direct communication. A scenario is presented to each agent in the form of a file, specifying each player's role and actions in the game. The scenario helps in cases of miscommunication, improving team performance. Cooperation without communication enhances reliability and coordination among agents, leading to better results in challenging situations.

Keywords: multi-agent systems, communication, Robocop, software engineering

Procedia PDF Downloads 16

Authors: Alia El Akhrass, Raheed Al Jifri, Sara Babalghoum, Jana Bushnag

Abstract:

This project delves into exploring the functionalities of Mailchimp, an artificial intelligence application. The objective is to comprehend its operations through the AI tools it offers. To achieve this, a survey was conducted among peers, seeking insights into Mailchimp's functionality, accessibility, efficiency, and overall benefits. The survey aimed to gather valuable feedback for analysis. Subsequently, a thorough analysis of the collected data was performed to identify trends, patterns, and areas of improvement. Visual representations were then crafted to effectively summarize the findings, aiding in conveying the research outcomes clearly. Founded in 2001, Mailchimp initially provided email marketing services but has since expanded into a comprehensive marketing platform. Its focus on simplicity and accessibility has contributed to its success among businesses of all sizes. Alternative platforms such as Constant Contact, AWeber, and GetResponse offer similar services with their own unique strengths. Mailchimp's journey exemplifies the importance of vision and adaptability in the ever-evolving digital marketing landscape. By prioritizing innovation, user-centricity, and customer service, Mailchimp has established itself as a trusted partner in the field of digital marketing, enabling businesses to effectively connect with their customers and achieve their marketing goals.

Keywords: email marketing, ai tool, connect, communicate, generate

Procedia PDF Downloads 23

Authors: Andrew John Zeller, Artjoms Formulevics

Abstract:

Banking and financial services are rapidly transitioning from being monolithic structures focusing merely on their own financial offerings to becoming integrated players in multiple customer journeys and supply chains. Banks themselves are refocusing on being liquidity providers and underwriters in these networks, while the general concept of ‘embeddedness’ builds on the market readily available API (Application Programming Interface) architectures to flexibly deliver services to various requestors, i.e., online retailers who need finance and insurance products to better serve their customers, respectively. With this new flexibility come new requirements for enhanced cybersecurity. API structures are more decentralized and inherently prone to change. Unfortunately, this has not been comprehensively addressed in the literature. This paper tries to fill this gap by looking at security approaches and technologies relevant to API architectures found in embedded finance. After presenting the research methodology applied and introducing the major bodies of knowledge involved, the paper will discuss six dominating technology trends shaping high-level financial services architectures. Subsequently, embedded finance and the respective usage of API strategies will be described. Building on this, security considerations for APIs in financial and insurance services will be elaborated on before concluding with some ideas for possible further research.

Keywords: embedded finance, embedded banking strategy, cybersecurity, API management, data security, cybersecurity, IT management

Procedia PDF Downloads 21

Authors: Liu Yi, Bao Liyong

Abstract:

Aiming at the problem of low efficiency of pipelined scheduling in periodic query-qualified service, this paper proposes a system service resource scheduling strategy with parallel optimized qualified service polling control. The paper constructs the polling queuing system and its mathematical model; firstly, the first-order and second-order characteristic parameter equations are obtained by partial derivation of the probability mother function of the system state variables, and the complete mathematical, analytical expressions of each system parameter are deduced after the joint solution. The simulation experimental results are consistent with the theoretical calculated values. The system performance analysis shows that the average captain and average period of the system have been greatly improved, which can better adapt to the service demand of delay-sensitive data in the dense data environment.

Keywords: polling, parallel scheduling, mean queue length, average cycle time

Procedia PDF Downloads 20

Authors: Tesfaw Belayneh Abebe

Abstract:

Integrating low-altitude earth orbit (LEO) satellites and unmanned aerial vehicles (UAVs) within a non-terrestrial network (NTN) with the assistance of reconfigurable intelligent surfaces (RIS), we investigate the problem of how to enhance throughput through integrated LEO satellites and UAVs with the assistance of RIS. We propose a method to jointly optimize the associations with the LEO satellite, the 3D trajectory of the UAV, and the phase shifts of the RIS to maximize communication throughput for RIS-assisted integrated LEO satellite and UAV-enabled wireless communications, which is challenging due to the time-varying changes in the position of the LEO satellite, the high mobility of UAVs, an enormous number of possible control actions, and also the large number of RIS elements. Utilizing a multi-agent double deep Q-network (MADDQN), our approach dynamically adjusts LEO satellite association, UAV positioning, and RIS phase shifts. Simulation results demonstrate that our method significantly outperforms baseline strategies in maximizing throughput. Lastly, thanks to the integrated network and the RIS, the proposed scheme achieves up to 65.66x higher peak throughput and 25.09x higher worst-case throughput.

Keywords: integrating low-altitude earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs) within a non-terrestrial network (NTN), reconfigurable intelligent surfaces (RIS), multi-agent double deep Q-network (MADDQN)

Procedia PDF Downloads 19

Authors: Reyhaneh Soltanshah, Hamid R. Zarandi

Abstract:

In order to be more efficient in industries that are related to computer systems, software testing is necessary despite spending time and money. In the embedded system software test, complete knowledge of the embedded system architecture is necessary to avoid significant costs and damages. Software tests increase the price of the final product. The aim of this article is to provide a method to reduce time and cost in tests based on program structure. First, a complete review of eleven white box test methods based on ISO/IEC/IEEE 29119 2015 and 2021 versions has been done. The proposed algorithm is designed using two versions of the 29119 standards, and some white-box testing methods that are expensive or have little coverage have been removed. On each of the functions, white box test methods were applied according to the 29119 standard and then the proposed algorithm was implemented on the functions. To speed up the implementation of the proposed method, the Unity framework has been used with some changes. Unity framework can be used in embedded software testing due to its open source and ability to implement white box test methods. The test items obtained from these two approaches were evaluated using a mathematical ratio, which in various software mining reduced between 50% and 80% of the test cost and reached the desired result with the minimum number of test items.

Keywords: embedded software, reduce costs, software testing, white-box testing

Procedia PDF Downloads 23

Authors: Belayneh Matebie, Michael Melese

Abstract:

The study focuses on addressing the challenges in classifying and ensuring the quality of Eragrostis Teff, a small and round grain that is the smallest cereal grain. Employing a traditional classification method is challenging because of its small size and the similarity of its environmental characteristics. To overcome this, this study employs a machine learning approach to develop a source and quality classification system for Teff cereal. Data is collected from various production areas in the Amhara regions, considering two types of cereal (high and low quality) across eight classes. A total of 5,920 images are collected, with 740 images for each class. Image enhancement techniques, including scaling, data augmentation, histogram equalization, and noise removal, are applied to preprocess the data. Convolutional Neural Network (CNN) is then used to extract relevant features and reduce dimensionality. The dataset is split into 80% for training and 20% for testing. Different classifiers, including FVGG16, FINCV3, QSCTC, EMQSCTC, SVM, and RF, are employed for classification, achieving accuracy rates ranging from 86.91% to 97.72%. The ensemble of FVGG16, FINCV3, and QSCTC using the Max-Voting approach outperforms individual algorithms.

Keywords: Teff, ensemble learning, max-voting, CNN, SVM, RF

Procedia PDF Downloads 27

Authors: Mohammed Abu Shquier

Abstract:

This paper introduces a word segmentation method using the novel BP-LSTM-CRF architecture for processing semantic output training. The objective of web morphological analysis tools is to link a formal morpho-syntactic description to a lemma, along with morpho-syntactic information, a vocalized form, a vocalized analysis with morpho-syntactic information, and a list of paradigms. A key objective is to continuously enhance the proposed system through an inductive learning approach that considers semantic influences. The system is currently under construction and development based on data-driven learning. To evaluate the tool, an experiment on homograph analysis was conducted. The tool also encompasses the assumption of deep binary segmentation hypotheses, the arbitrary choice of trigram or n-gram continuation probabilities, language limitations, and morphology for both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), which provide justification for updating this system. Most Arabic word analysis systems are based on the phonotactic morpho-syntactic analysis of a word transmitted using lexical rules, which are mainly used in MENA language technology tools, without taking into account contextual or semantic morphological implications. Therefore, it is necessary to have an automatic analysis tool taking into account the word sense and not only the morpho-syntactic category. Moreover, they are also based on statistical/stochastic models. These stochastic models, such as HMMs, have shown their effectiveness in different NLP applications: part-of-speech tagging, machine translation, speech recognition, etc. As an extension, we focus on language modeling using Recurrent Neural Network (RNN); given that morphological analysis coverage was very low in dialectal Arabic, it is significantly important to investigate deeply how the dialect data influence the accuracy of these approaches by developing dialectal morphological processing tools to show that dialectal variability can support to improve analysis.

Keywords: NLP, DL, ML, analyser, MSA, RNN, CNN

Procedia PDF Downloads 20

Authors: Armel Asongu Nkembi, Ahmad Fawad

Abstract:

In this paper, we design a smart car parking system using the Node-Red interface, which enables the user to find the nearest parking area from his current location and gives the availability of parking slots in that respective parking area. The closest parking area is determined by sending an HTTP request to an API, and the shortest distance is computed using some mathematical formulations based on the coordinates retrieved. There is also the use of IR sensors to signal the availability or lack of available parking lots within any parking area. The aim is to reduce the time and effort needed to find empty parking lots and also avoid unnecessary traveling through filled parking lots in a parking area. Thus, it reduces fuel consumption, which in turn reduces carbon footprints in the atmosphere and, overall, makes the city much smarter.

Keywords: node-red, smart parking system, API, http request, IR sensors, Internet of Things, smart city, parking lots.

Procedia PDF Downloads 18

Authors: Getaneh Berie Tarekegn, Li-Chia Tai

Abstract:

With the rapid advancement of artificial intelligence, low-power built-in sensors on Internet of Things devices, and communication technologies, location-aware services have become increasingly popular and have permeated every aspect of people’s lives. Global navigation satellite systems (GNSSs) are the default method of providing continuous positioning services for ground and aerial vehicles, as well as consumer devices (smartphones, watches, notepads, etc.). However, the environment affects satellite positioning systems, particularly indoors, in dense urban and suburban cities enclosed by skyscrapers, or when deep shadows obscure satellite signals. This is because (1) indoor environments are more complicated due to the presence of many objects surrounding them; (2) reflection within the building is highly dependent on the surrounding environment, including the positions of objects and human activity; and (3) satellite signals cannot be reached in an indoor environment, and GNSS doesn't have enough power to penetrate building walls. GPS is also highly power-hungry, which poses a severe challenge for battery-powered IoT devices. Due to these challenges, IoT applications are limited. Consequently, precise, seamless, and ubiquitous Positioning, Navigation and Timing (PNT) systems are crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

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

Procedia PDF Downloads 21

Authors: Aishatu Ibrahim Birma, Aminu Tukur, Abdulkarim Abbass Gora

Abstract:

Machine translation plays a vital role in the Field of Natural Language Processing (NLP), breaking down language barriers and enabling communication across diverse communities. In the context of Hausa, a widely spoken language in West Africa, mainly in Nigeria, effective translation systems are essential for enabling seamless communication and promoting cultural exchange. However, due to the unique linguistic characteristics of Hausa, accurate translation remains a challenging task. The research proposes an approach to improving the machine learning translation of Hausa by integrating Named Entity Recognition (NER) techniques. Named entities, such as person names, locations, organizations, and dates, are critical components of a language's structure and meaning. Incorporating NER into the translation process can enhance the quality and accuracy of translations by preserving the integrity of named entities and also maintaining consistency in translating entities (e.g., proper names), and addressing the cultural references specific to Hausa. The NER will be incorporated into Neural Machine Translation (NMT) for the Hausa to English Translation.

Keywords: machine translation, natural language processing (NLP), named entity recognition (NER), neural machine translation (NMT)

Procedia PDF Downloads 19

Authors: Getaneh Berie Tarekegn, Li-Chia Tai

Abstract:

With the rapid advancement of artificial intelligence, low-power built-in sensors on Internet of Things devices, and communication technologies, location-aware services have become increasingly popular and have permeated every aspect of people’s lives. Global navigation satellite systems (GNSSs) are the default method of providing continuous positioning services for ground and aerial vehicles, as well as consumer devices (smartphones, watches, notepads, etc.). However, the environment affects satellite positioning systems, particularly indoors, in dense urban and suburban cities enclosed by skyscrapers, or when deep shadows obscure satellite signals. This is because (1) indoor environments are more complicated due to the presence of many objects surrounding them; (2) reflection within the building is highly dependent on the surrounding environment, including the positions of objects and human activity; and (3) satellite signals cannot be reached in an indoor environment, and GNSS doesn't have enough power to penetrate building walls. GPS is also highly power-hungry, which poses a severe challenge for battery-powered IoT devices. Due to these challenges, IoT applications are limited. Consequently, precise, seamless, and ubiquitous Positioning, Navigation and Timing (PNT) systems are crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarms, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

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

Procedia PDF Downloads 17

Authors: Gangmin Li, Fan Yang

Abstract:

Personalized recommendation is crucial for any recommendation system. One of the techniques for personalized recommendation is to identify the intention. Traditional user intention identification uses the user’s selection when facing multiple items. This modeling relies primarily on historical behaviour data resulting in challenges such as the cold start, unintended choice, and failure to capture intention when items are new. Motivated by recent advancements in Large Language Models (LLMs) like ChatGPT, we present an approach for user intention identification by embracing LLMs with Chain-of-Thought (CoT) prompting. We use the initial user profile as input to LLMs and design a collection of prompts to align the LLM's response through various recommendation tasks encompassing rating prediction, search and browse history, user clarification, etc. Our tests on real-world datasets demonstrate the improvements in recommendation by explicit user intention identification and, with that intention, merged into a user model.

Keywords: personalized recommendation, generative user modelling, user intention identification, large language models, chain-of-thought prompting

Procedia PDF Downloads 23

Authors: Jinan Fiaidhi, Sabah Mohammed

Abstract:

Cross-domain learning in the medical field is a research challenge as many conditions, like in oncology imaging, use different imaging modalities. Moreover, in most of the medical learning applications, the sample training size is relatively small. Although few-shot learning (FSL) through the use of a Siamese neural network was able to be trained on a small sample with remarkable accuracy, FSL fails to be effective for use in multiple domains as their convolution weights are set for task-specific applications. In this paper, we are addressing this problem by enabling FSL to possess the ability to shift across domains by designing a two-layer FSL network that can learn individually from each domain and produce a shared features map with extra modulation to be used at the second layer that can recognize important targets from mix domains. Our initial experimentations based on mixed medical datasets like the Medical-MNIST reveal promising results. We aim to continue this research to perform full-scale analytics for testing our cross-domain FSL learning.

Keywords: Siamese neural network, few-shot learning, meta-learning, metric-based learning, thick data transformation and analytics

Procedia PDF Downloads 33

Authors: Jinan Fiaidhi, Hashmath Shaik

Abstract:

Breaking the barrier for practicing evidence-based medicine relies on effective methods for rapidly identifying relevant evidence from the body of biomedical literature. An important challenge confronted by medical practitioners is the long time needed to browse, filter, summarize and compile information from different medical resources. Deep learning can help in solving this based on automatic question answering (Q&A) and transformers. However, Q&A and transformer technologies are not trained to answer clinical queries that can be used for evidence-based practice, nor can they respond to structured clinical questioning protocols like PICO (Patient/Problem, Intervention, Comparison and Outcome). This article describes the use of deep learning techniques for Q&A that are based on transformer models like BERT and GPT to answer PICO clinical questions that can be used for evidence-based practice extracted from sound medical research resources like PubMed. We are reporting acceptable clinical answers that are supported by findings from PubMed. Our transformer methods are reaching an acceptable state-of-the-art performance based on two staged bootstrapping processes involving filtering relevant articles followed by identifying articles that support the requested outcome expressed by the PICO question. Moreover, we are also reporting experimentations to empower our bootstrapping techniques with patch attention to the most important keywords in the clinical case and the PICO questions. Our bootstrapped patched with attention is showing relevancy of the evidence collected based on entropy metrics.

Keywords: automatic question answering, PICO questions, evidence-based medicine, generative models, LLM transformers

Procedia PDF Downloads 18

Authors: Yoganathan Karthik, Guhanathan Poravi

Abstract:

Colorizing near-infrared (NIR) images poses unique challenges due to the absence of color information and the nuances in light absorption. In this paper, we present an approach to NIR image colorization utilizing a synthetic dataset generated from visible light images. Our method addresses two major challenges encountered in NIR image colorization: accurately colorizing objects with color variations and avoiding over/under saturation in dimly lit scenes. To tackle these challenges, we propose a Generative Adversarial Network (GAN)-based framework that learns to map NIR images to their corresponding colorized versions. The synthetic dataset ensures diverse color representations, enabling the model to effectively handle objects with varying hues and shades. Furthermore, the GAN architecture facilitates the generation of realistic colorizations while preserving the integrity of dimly lit scenes, thus mitigating issues related to over/under saturation. Experimental results on benchmark NIR image datasets demonstrate the efficacy of our approach in producing high-quality colorizations with improved color accuracy and naturalness. Quantitative evaluations and comparative studies validate the superiority of our method over existing techniques, showcasing its robustness and generalization capability across diverse NIR image scenarios. Our research not only contributes to advancing NIR image colorization but also underscores the importance of synthetic datasets and GANs in addressing domain-specific challenges in image processing tasks. The proposed framework holds promise for various applications in remote sensing, medical imaging, and surveillance where accurate color representation of NIR imagery is crucial for analysis and interpretation.

Keywords: computer vision, near-infrared images, automatic image colorization, generative adversarial networks, synthetic data

Procedia PDF Downloads 21

Authors: Diogo José Morgado Rebelo, Francisco António Carneiro Pacheco de Andrade, Paulo Jorge Freitas de Oliveira Novais

Abstract:

Not everything in AI-power consumer credit scoring turns out to be a wonder. When using AI in Creditworthiness Assessment (CWA), opacity and unfairness ‘sins’ must be considered to the task be deemed Responsible. AI software is not always 100% accurate, which can lead to misclassification. Discrimination of some groups can be exponentiated. A hetero personalized identity can be imposed on the individual(s) affected. Also, autonomous CWA sometimes lacks transparency when using black box models. However, for this intended purpose, human analysts ‘on-the-loop’ might not be the best remedy consumers are looking for in credit. This study seeks to explore the legality of implementing a Multi-Agent System (MAS) framework in consumer CWA to ensure compliance with the regulation outlined in Article 14(4) of the Proposal for an Artificial Intelligence Act (AIA), dated 21 April 2021 (as per the last corrigendum by the European Parliament on 19 April 2024), Especially with the adoption of Art. 18(8)(9) of the EU Directive 2023/2225, of 18 October, which will go into effect on 20 November 2026, there should be more emphasis on the need for hybrid oversight in AI-driven scoring to ensure fairness and transparency. In fact, the range of EU regulations on AI-based consumer credit will soon impact the AI lending industry locally and globally, as shown by the broad territorial scope of AIA’s Art. 2. Consequently, engineering the law of consumer’s CWA is imperative. Generally, the proposed MAS framework consists of several layers arranged in a specific sequence, as follows: firstly, the Data Layer gathers legitimate predictor sets from traditional sources; then, the Decision Support System Layer, whose Neural Network model is trained using k-fold Cross Validation, provides recommendations based on the feeder data; the eXplainability (XAI) multi-structure comprises Three-Step-Agents; and, lastly, the Oversight Layer has a 'Bottom Stop' for analysts to intervene in a timely manner. From the analysis, one can assure a vital component of this software is the XAY layer. It appears as a transparent curtain covering the AI’s decision-making process, enabling comprehension, reflection, and further feasible oversight. Local Interpretable Model-agnostic Explanations (LIME) might act as a pillar by offering counterfactual insights. SHapley Additive exPlanation (SHAP), another agent in the XAI layer, could address potential discrimination issues, identifying the contribution of each feature to the prediction. Alternatively, for thin or no file consumers, the Suggestion Agent can promote financial inclusion. It uses lawful alternative sources such as the share of wallet, among others, to search for more advantageous solutions to incomplete evaluation appraisals based on genetic programming. Overall, this research aspires to bring the concept of Machine-Centered Anthropocentrism to the table of EU policymaking. It acknowledges that, when put into service, credit analysts no longer exert full control over the data-driven entities programmers have given ‘birth’ to. With similar explanatory agents under supervision, AI itself can become self-accountable, prioritizing human concerns and values. AI decisions should not be vilified inherently. The issue lies in how they are integrated into decision-making and whether they align with non-discrimination principles and transparency rules.

Keywords: creditworthiness assessment, hybrid oversight, machine-centered anthropocentrism, EU policymaking

Procedia PDF Downloads 19

Authors: Raya Al Khayari, Rasha Al Jassim, Muna Al Balushi, Fatma Al Moqbali, Said El Hajjar

Abstract:

This study utilizes linear regression analysis to investigate the correlation between user account passwords and the probability of civil ID exposure, offering statistical insights into civil ID security. The study employs multiple linear regression (MLR) analysis to further investigate the elements that influence consumers’ views of civil ID security. This aims to increase awareness and improve preventive measures. The results obtained from the MLR analysis provide a thorough comprehension and can guide specific educational and awareness campaigns aimed at promoting improved security procedures. In summary, the study’s results offer significant insights for improving existing security measures and developing more efficient tactics to reduce risks related to civil ID security in Oman. By identifying key factors that impact consumers’ perceptions, organizations can tailor their strategies to address vulnerabilities effectively. Additionally, the findings can inform policymakers on potential regulatory changes to enhance civil ID security in the country.

Keywords: civil-id disclosure, awareness, linear regression, multiple regression

Procedia PDF Downloads 34

Authors: Augustine Ndudi Egere, Shehu Adamu, Esther Ishaya Solomon

Abstract:

As internet accessibility and smartphones continue to increase in Nigeria, Africa’s most populous country, social media platforms have become ubiquitous, causing students of 18-25 age brackets to spend more time on social media. The research investigated the impact of prolonged social media use on the physical health of students, with a specific focus on computer vision syndrome, hand pain, headaches and mental status. The study adopted a mixed-methods approach combining quantitative surveys to gather statistical data on usage patterns and symptoms, along with qualitative interviews into the experiences and perceptions of medical practitioners concerning cases under study within the geopolitical region. The result was analyzed using Regression analysis. It was observed that there is a significant correlation between social media usage by the students in the study age bracket concerning computer vision syndrome, hand pain, headache and general mental status. The research concluded by providing valuable insights into potential interventions and strategies to mitigate the adverse effects of excessive social media use on student well-being and recommends, among others, that educational institutions, parents, and students themselves collaborate to implement strategies aimed at promoting responsible and balanced use of social media.

Keywords: social media, student health, computer vision syndrome, hand pain, headaches, mental staus

Procedia PDF Downloads 25

Authors: Sayor Ajfar Aaron, Sajjat Hossain Abir, Ashif Newaz, Mushfiqur Rahman

Abstract:

Investigating the convergence of blockchain technology and artificial intelligence, this paper examines their synergistic effects on data integrity and decision-making within smart contracts. By implementing AI-driven analytics on blockchain-based platforms, the research identifies improvements in automated contract enforcement and decision accuracy. The paper presents a framework that leverages AI to enhance transparency and trust while blockchain ensures immutable record-keeping, culminating in significantly optimized operational efficiencies in various industries.

Keywords: artificial intelligence, blockchain, data integrity, smart contracts

Procedia PDF Downloads 19

Authors: Sayor Ajfar Aaron, Ashif Newaz, Sajjat Hossain Abir, Mushfiqur Rahman

Abstract:

This paper examines the transformative potential of quantum computing in the field of cybersecurity, with a focus on advanced penetration testing and forensics. It explores how quantum technologies can be leveraged to identify and exploit vulnerabilities more efficiently than traditional methods and how they can enhance the forensic analysis of cyber-attacks. Through theoretical analysis and practical simulations, this study highlights the enhanced capabilities of quantum algorithms in detecting and responding to sophisticated cyber threats, providing a pathway for developing more resilient cybersecurity infrastructures.

Keywords: cybersecurity, cyber forensics, penetration testing, quantum computing

Procedia PDF Downloads 22

Authors: Laila Khaled Almawaldi, Hiew Khai Hang, Sugumaran A. l. Nallusamy

Abstract:

Legacy systems are crucial for organizations, but their intricacy and lack of documentation pose challenges for maintenance and enhancement. Redocumentation of legacy systems is vital for automatically or semi-automatically creating documentation for software lacking sufficient records. It aims to enhance system understandability, maintainability, and knowledge transfer. However, existing redocumentation methods need improvement in data processing performance and document generation efficiency. This stems from the necessity to efficiently handle the extensive and complex code of legacy systems. This paper proposes a method for semi-automatic legacy system re-documentation using semantic parallel processing and ontology. Leveraging parallel processing and ontology addresses current challenges by distributing the workload and creating documentation with logically interconnected data. The paper outlines challenges in legacy system redocumentation and suggests a method of redocumentation using parallel processing and ontology for improved efficiency and effectiveness.

Keywords: legacy systems, redocumentation, big data analysis, parallel processing

Procedia PDF Downloads 20

Authors: Sayor Ajfar Aaron, Mushfiqur Rahman, Sajjat Hossain Abir, Ashif Newaz

Abstract:

This study delves into the development of an artificial intelligence application designed for real-time emotion recognition from human vocal patterns. Utilizing advanced machine learning algorithms, including deep learning and neural networks, the paper highlights both the technical challenges and potential opportunities in accurately interpreting emotional cues from speech. Key findings demonstrate the critical role of diverse training datasets and the impact of ambient noise on recognition accuracy, offering insights into future directions for improving robustness and applicability in real-world scenarios.

Keywords: artificial intelligence, convolutional neural network, emotion recognition, vocal patterns

Procedia PDF Downloads 20