Advanced Machine Research Articles

Detection of bipolar disorder by means of ensemble machine learning classifier

The accurate diagnosis of bipolar disorder is extremely challenging, due to unpredictable mood swings, behaviors, sleep, judgment, and inability to think, which makes it difficult to make a proper diagnosis. This paper aims to investigate the application of ensemble classifiers in classifying bipolar disorder and to compare their performance with existing methods. Herein, the work involves a thorough analysis of diagnostic precision and performance metrics. According to a study, an existing classifier achieved an accuracy rate of 87% in bipolar disorder classification. In addition, the two most widely used classifiers, which are Random Forest and Decision Tree, achieved accuracy rates of 90% and 86%, respectively. These results highlight the performance baseline against which the proposed ensemble classifier is evaluated. Notably, the proposed ensemble classifier shows excellent results in bipolar disorder classification thereby, achieving an impressive accuracy rate of 98%. This considerable improvement in accuracy marks a significant stride in diagnostic precision, showcasing the potential of ensemble classifiers in enhancing bipolar disorder detection. The results of this study have given substantial implications for the field of mental health diagnosis, offering a promising avenue for a more accurate and reliable classification of bipolar disorder. This research reinforces the significance of advanced machine learning techniques and their potential to revolutionize the approach to diagnose and to manage mental health conditions.

QRxPERT: Automated Medicine Dispensing Machine with QR Code-Enabled Medication Counselling

QRxPERT aims to tackle chronic illnesses and medication non-compliance by integrating smart medication counseling and AI-enabled drug dispensers, with the help of a Smart Health Card. Patients can effortlessly scan QR codes on medication labels, unlocking a wealth of information instantly available at their fingertips. This includes vital details such as dosage instructions, potential side effects, and other pertinent information crucial for informed and effective self-management. QRxPERT’s AI-enabled drug Dispenser uses advanced machine learning and an RFID chip to accurately dispense medication, reducing human error and preventing medication non-compliance. This dispenser is designed to significantly reduce the margin of error in medication administration, ensuring that patients receive the precise dosage required. This not only enhances the efficacy of treatment but also serves as a robust preventative measure against medication non-compliance. The SMART HEALTH CARD also sends Reminder Messages to Mobile Phones, Regarding Tablets/Medication to take according to dose Interval given by DOCTORS. In conclusion, QRxPERT is a revolutionary healthcare innovation that integrates advanced technology to improve medication management and adherence, by offering smart medication counseling and AI-enabled drug dispensers.

Characterizing the spatio-temporal distribution, detection, and prediction of aerosol atmospheric rivers on a global scale

Aerosol Atmospheric Rivers (AARs) are elongated and narrow regions that carry high concentrations of aerosols (tiny particles suspended in the atmosphere) across large distances, exerting effects on both air quality and human health (Chakraborty et al., 2021, 2022). Monitoring and modeling these aerosols present distinct challenges due to their dynamic nature and complex interactions within the atmosphere. In this context, the present study detects and predicts the AARs using MERRA-2 reanalysis datasets with their seasonal climatology of key aerosol species, including Black Carbon (BC), Dust (DU), Organic Carbon (OC), Sea Salt (SS), and Sulphates (SU). The study employs an innovative Integrated Aerosol Transport (IAT) based AAR algorithm from 2015 to 2022. A total count of 44,020 BC AARs, 13,280 DU AARs, 21,599 OC AARs, 17,925 SS AARs, and 31,437 SU AARs were detected globally. The seasonal climatology of BC and OC AARs intensifies in areas such as the Amazon rainforest and Congo during AMJJAS (April–September) due to forest fires. Similarly, DU AARs are more frequent in regions near the Saharan desert, primarily around the equator during AMJJAS. SS AARs tend to predominate over the oceans, while SU AARs are predominantly found in the northern hemisphere, primarily due to higher anthropogenic emissions. Furthermore, convolutional autoencoder-based models were developed for key aerosol species, strengthening predictive accuracy by effectively capturing complex data relationships and delivering precise predictions for the last 5-time frames. During validation, the model evaluation parameters for image prediction such as the Structural Similarity Index ranged from 0.86 to 0.94, Peak Signal-to-Noise Ratio fluctuated between 1.14 and 42.25 dB, Root Mean Square Error varied from 2.39 to 296.4 mg/(m-sec), and Mean Square Error fell within the range of 1.55–17.22 mg/(m-sec). These collectively reflect image closeness, quality, dissimilarity, and accuracy in AAR prediction. This study demonstrates the effectiveness of advanced machine and deep learning models in predicting AARs, offering the potential for advanced forecasting and enhancing resilience in high-aerosol concentration regions.

Parkinson's Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms

Parkinson's disease (PD) is a prevalent neurodegenerative disorder known for its impact on motor neurons, causing symptoms like tremors, stiffness, and gait difficulties. This study explores the potential of vocal feature alterations in PD patients as a means of early disease prediction. This research aims to predict the onset of Parkinson's disease. Utilizing a variety of advanced machine-learning algorithms, including XGBoost, LightGBM, Bagging, AdaBoost, and Support Vector Machine, among others, the study evaluates the predictive performance of these models using metrics such as accuracy, area under the curve (AUC), sensitivity, and specificity. The findings of this comprehensive analysis highlight LightGBM as the most effective model, achieving an impressive accuracy rate of 96% alongside a matching AUC of 96%. LightGBM exhibited a remarkable sensitivity of 100% and specificity of 94.43%, surpassing other machine learning algorithms in accuracy and AUC scores. Given the complexities of Parkinson's disease and its challenges in early diagnosis, this study underscores the significance of leveraging vocal biomarkers coupled with advanced machine-learning techniques for precise and timely PD detection.

Maternal Health Risk Detection Using Light Gradient Boosting Machine Approach

Maternal health risk detection is crucial for reducing morbidity and mortality among pregnant women. In this study, we employed the Light Gradient Boosting Machine (LightGBM) model to identify risk levels using data from rural healthcare facilities. The dataset included key health indicators aligned with the United Nations Sustainable Development Goals. The LightGBM model underwent rigorous optimization through hyperparameter tuning and 10-fold cross-validation. Its predictive performance was benchmarked against other algorithms using accuracy, precision, recall, and F1-score, with feature importance assessed to identify critical risk predictors. The LightGBM model demonstrating the highest performance across all metrics. The results underscore the value of advanced machine learning techniques in public health. Future research directions include expanding the demographic scope, incorporating temporal data, and enhancing model transparency. This study highlights the transformative potential of machine learning in maternal healthcare, providing a foundation for improved risk detection and proactive healthcare interventions.

CNN inference acceleration on limited resources FPGA platforms_epilepsy detection case study

<span lang="EN-US">The use of a convolutional neural network (CNN) to analyze and classify electroencephalogram (EEG) signals has recently attracted the interest of researchers to identify epileptic seizures. This success has come with an enormous increase in the computational complexity and memory requirements of CNNs. For the sake of boosting the performance of CNN inference, several hardware accelerators have been proposed. The high performance and flexibility of the field programmable gate array (FPGA) make it an efficient accelerator for CNNs. Nevertheless, for resource-limited platforms, the deployment of CNN models poses significant challenges. For an ease of CNN implementation on such platforms, several tools and frameworks have been made available by the research community along with different optimization techniques. In this paper, we proposed an FPGA implementation for an automatic seizure detection approach using two CNN models, namely VGG-16 and ResNet-50. To reduce the model size and computation cost, we exploited two optimization approaches: pruning and quantization. Furthermore, we presented the results and discussed the advantages and limitations of two implementation alternatives for the inference acceleration of quantized CNNs on Zynq-7000: an advanced RISC machine (ARM) software implementation-based ARM, NN, software development kit (SDK) and a software/hardware implementation-based deep learning processor unit (DPU) accelerator and DNNDK toolkit.</span>

Towards understanding the material removal mechanism on the effect of ultrasonic vibration and anisotropy for unidirectional CFRP by scratching

Rotary Ultrasonic Machining (RUM) is a well-known non-traditional machining method for hole-making and surface grinding of Carbon Fiber Reinforced Plastics (CFRP). However, the complicated material removal behavior of CFRP is difficult to understand due to its heterogeneity and anisotropy resulting from components and the nature of laminated structures. In this concern, we conducted ultrasonic vibration-assisted scratching (UVAS) to understand the material removal mechanisms with the effect of ultrasonic vibration and fiber anisotropy. Based on scratching morphology, the removal behavior of unidirectional CFRP (UD-CFRP) varied in different scratching directions. Meanwhile, the addition of ultrasonic vibration could suppress machining damage generated by the scratching process. The motion trajectory analysis and experimental results show that the ultrasonic vibration-assisted scratching load is smaller under the same machining parameters. Discussions on the material removal mechanism of UD-CFRP during the effect of ultrasonic vibration and fiber anisotropy were also provided. This research will contribute towards an in-depth understanding of the material removal mechanism for fiber reinforced plastics composites in RUM, which will be useful in optimizing the application of ultrasonic vibration assisted processes for advanced composites machining.

Preface

The International Conference on Power Electronics and Electrical Technology (ICPEET) has confirmed once again this year the enthusiasm and determination of students and young researchers to play a major role in the scientific progress. Since 2022, we have regularly gathered to discuss the most recent developments and achievement on power electronics and electrical technology, and we firmly convince that sharing our expertise and experience is the foundation of research activity.The 2023 2nd International Conference on Power Electronics and Electrical Technology (ICPEET 2023) took place on July 7th to 9th, 2023 in Chongqing, China (virtual event), attracting about 80 leading delegates around the world. The format we chose is a formal meeting primarily aimed at graduate students and leading researchers, who were encouraged to present their work through oral or poster presentations that provide genuine engagement of the audience and cross-pollination of ideas. One of the main purposes of the Conference was to create an international network of researchers, both experimentalists and theorists, and fruitful collaborations across different branches of power electronics and electrical technology.After previous meeting that strengthened it, the International Conference on Power Electronics and Electrical Technology was held for the second time. It was a three-day Conference, where there was an extremely rich and interactive keynote speech, oral and poster session that covered several areas of power electronics and electrical technology.With the intent of broadening the contents and stimuli adopting academic communication, the keynote speech part was held. This choice reflected the growing importance of the activity performed by scientists and researchers, especially at the earliest stages of their career, as a way of increasing their expertise and developing soft skills. Prof. Jiashen Teh (Universiti Sains Malaysia, Malaysia) addressed a speech on Flexible Thermal Line Rating for Reliable Power Systems, Prof. Zhenbin Zhang (Shandong University, China) on Bias-Free Fast Start-Up Strategy and High-Performance Predictive Control Method for DC Energy, and Prof. Ali Arefi (Murdoch University, Australia) on Reliability of Renewable-Rich Microgrids: Evaluation and Planning.In this volume, we collected part of the contributions that have been presented at the Conference. They cover topics on Cogeneration and Distributed Generation, High Voltage Technology, Wireless Power Transmission, Electromagnetic Compatibility, Advanced and Sensorless Machine Control, etc. Given the recent experimental achievements in power electronics and electrical technology, several contributions were focused on the latest results obtained in these fields, presenting the impact of experiments to the community of young researchers and forecasting the future goals in these areas of research.The organizers of ICPEET 2023 would like to thank all the keynote speakers, authors, peer reviewers, and everyone who contributed to the Conference. We owe gratitude to all the Committee members for providing necessary help and support throughout the meeting. The publication of the Proceedings of this Conference is supported by Journal of Physics: Conference Series.The Committee of ICPEET 2023List of Committee Member is available in this Pdf

Analysis of the evolution of advanced transformer-based language models: experiments on opinion mining

<p>Opinion mining, also known as sentiment analysis, is a subfield of natural language processing (NLP) that focuses on identifying and extracting subjective information in textual material. This can include determining the overall sentiment of a piece of text (e.g., positive or negative), as well as identifying specific emotions or opinions expressed in the text, that involves the use of advanced machine and deep learning techniques. Recently, transformer-based language models make this task of human emotion analysis intuitive, thanks to the attention mechanism and parallel computation. These advantages make such models very powerful on linguistic tasks, unlike recurrent neural networks that spend a lot of time on sequential processing, making them prone to fail when it comes to processing long text. The scope of our paper aims to study the behaviour of the cutting-edge Transformer-based language models on opinion mining and provide a high-level comparison between them to highlight their key particularities. Additionally, our comparative study shows leads and paves the way for production engineers regarding the approach to focus on and is useful for researchers as it provides guidelines for future research subjects.</p>

Landslide Susceptibility Assessment in Western External Rif Chain using Machine Learning Methods

Landslides are a major natural hazard in the mountainous Rif region of Northern Morocco. This study aims to create and compare landslide susceptibility maps in the Western External Rif Chain context using three advanced machine learning models: Random Forest (RF), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbors (KNN). The landslide database, created by satellite imagery and field research, contains an inventory of 3528 cases of slope movements. A database of 12 conditioning factors was prepared, including elevation, slope, aspect, curvature, lithology, rainfall, topographic wetness index (TWI), stream power index (SPI), distance to streams, distance to faults, distance to roads, and land cover. The database was randomly divided into training and validation sets at a ratio of 70/30. The predictive capabilities of the models were evaluated using overall accuracy (Acc), area under the receiver operating characteristic curve (AUC), kappa index, and F score measures. The results indicated that RF was the most suitable model for this study area, demonstrating the highest predictive capability (AUC= 0.86) compared to the other models. This aligns with previous landslide studies, which found that ensemble methods like RF and XGBoost offer superior accuracy. The most important causal factors of landslides in the study area were identified as slope, rainfall, and elevation, while the influence rate of TWI and SPI was the minimum. By analyzing a larger inventory of landslides on a more extensive scale, this study aims to improve the accuracy and reliability of landslide predictions in a west Mediterranean morphoclimatic context that encompasses a wide variety of lithologies. The resulting maps can serve as a crucial resource for land use planning and disaster management planning. Doi: 10.28991/CEJ-2023-09-12-018 Full Text: PDF

AI Content Generation Technology based on Open AI Language Model

The Open AI language model is a powerful tool for generating AI content. A Large amount of text data is trained through the language model, which can generate new text that is similar in style and tone to the training data. This language model can assist writers in generating high-quality content by offering suggestions and insights for improving language usage, sentence structure, and overall readability. This study represents the development of a content generation tool based on the open AI language model by utilising GPT 3 in the backend as an API to generate the necessary information for the model. With the help of this tool, businesses and individuals can produce high-quality, engaging content more efficiently than ever before. This content generation tool uses a recurrent neural network (RNN) architecture, which enables it to make more accurate predictions than rule-based chatbots. All the features, like Facebook ads, LinkedIn posts, Amazon product descriptions, blogs, company bios, chat bots, and so on, will be presented in the dashboard. This tool is powered by advanced machine learning algorithms that can analyse and understand natural language, allowing them to produce content that is grammatically correct, free of errors, and tailored to specific audiences. They can also help optimize content for search engines, ensuring that it reaches a wider audience and generates more traffic with fine-tuning templates.

Markerless motion capture technology to quantify functional performance in dementias: a systematic review

AbstractBackgroundQuantifying functional performance objectively and unobtrusively could offer vital insights for clinical decision making on the level of support required by people living with dementia and other neurodegenerative conditions. Markerless motion capture (MMC) is more suitable for deployment in clinical and real‐world settings because single sensor MMC systems are less expensive and less complex compared to marker‐based systems. The aim of this study was to complete a systematic review of published literature on the use of MMC with full‐body tracking in people with dementias.MethodWe systematically searched for relevant articles using the search terms motion capture, motion analysis and movement analysis combined with dementia, mild cognitive impairment (MCI) and Parkinson’s disease (PD) which yielded a total of 1103 results. Inclusion criteria were MMC and full‐body tracking. Studies evaluating marker‐based motion capture, body‐worn sensors or Inertial Measurement Units, virtual reality, kinetics and interventions like DBS or exercises were excluded. 134 studies were included for full article screening out of which 17 eligible studies that met the selection criteria were included in the review.ResultMMC devices used in the reviewed studies included Microsoft Kinect (n = 15) and unspecified 2D motion camera (n = 2). Patient groups included in the studies were PD (n = 12), dementia (n = 4) and MCI (n = 1). Functional performance components evaluated were gait (n = 16), sit to stand (n = 2), turning (n = 1) and stepping in place (n = 1). About half the studies used advanced machine learning methods whereas the other half used descriptive statistical methods. The lack of standardisation in the measures used prevented us from comparing and synthesizing study results.ConclusionAlthough MMC has the potential to be used for quantifying functional performance in people with dementia, MCI and PD, there appears to be significant variation in the methods used in its evaluation. Although features of mobility were measured, none of the reviewed studies analysed activities of daily living tasks, a key component of functional performance. Standardising the process for extracting features and assessing accuracy would enable more effective validation of real‐world impact. Further research is required in people with neurodegenerative conditions for MMC to be routinely used in clinical and real‐world applications.

PREDICTION OF CHRONIC KIDNEY DISEASE

Chronic Kidney Disease is a prevalent and weakening medical condition with a substantial impact on public health. Early detection and prediction reduces its adverse effects and improve patient outcomes. In this project, wepropose a comprehensive predictive analysis framework utilizing advanced machine learning algorithms to forecast the onset and progression of the disease. The dataset comprises a diverse range of clinical, population, and laboratory features collected from a group of chronic kidney disease patients over a defined period. Preprocessing techniques are employed to handle missing values and normalize data. Subsequently, various machine learning algorithms, including Random Forest, Support Vector Machine, and Gradient Boosting , are trained on the processed dataset to learn complex patterns and relationships within the data. Additionally, feature importance analysis is undertaken to identify the most influential variables contributing to prediction accuracy. The machine learning algorithms can effectively aid clinicians in predicting chronic kidney diseases, enabling timely interventions and personalized treatment plans. This research contributes to the growing knowledge on the application of machine learning in healthcare, particularly in chronic disease prediction.

Improving the machined surface in electrochemical mill-grinding by particle tracking fluid simulation and experimental research

The hybrid machining method called electrochemical mill-grinding is an advanced machining technology, which can achieve high-quality processing of various difficult-to-cut materials. However, achieving rapid transportation and removal of processed products within a small machining gap is a key challenge, which directly affects the final machined surface quality. In this paper, the product transport under different flushing modes was studied through numerical simulation of the flow field. By using the particle tracking method, the time required for the removal of machining products from the machining gap was dynamically simulated. The analysis results indicated that the removal speed of machining products could be significantly improved when the flushing pressure was 0.8 MPa and the electrolyte jet angle was 30°. In addition, machining experiments were conducted. The machining experiment results showed that the machined surface had a metallic luster with clear edge contours. The grinding marks on the machined surface indicated the grinding effect. The continuous machining of complex patterns demonstrated the reliability of this hybrid machining process.

AI Based Asthma Recognition System Using Respiratory Sound

Abstract: Asthma is a chronic respiratory condition that affects millions of people worldwide, leading to significant healthcare costs and a reduced quality of life for affected individuals. Timely and accurate detection of asthma exacerbations is crucial for effective management and intervention. Traditional methods of asthma diagnosis rely heavily on clinical assessments, which may not always provide real-time, objective data for prompt action. The aim of this project is to develop an AI-based asthma detection system that leverages the analysis of respiratory sound patterns. Current diagnostic tools often lack the ability to capture subtle changes in respiratory sounds that could indicate the onset or worsening of asthma symptoms. By employing advanced machine learning algorithms, this system aims to identify distinctive patterns and anomalies in respiratory sounds associated with asthma, enabling early detection and intervention.

Intelligent warehouse space optimization using convolutional neural networks

In the era of rapid digital transformation, global commerce and its intricately woven supply chains face unprecedented demands and challenges. As businesses strive to meet the ever-expanding consumer expectations, the spotlight is increasingly on warehouses - the vital nodes of these supply chains. Warehousing, once considered a mere storage facility, is now at the epicenter of a logistical revolution, with the quest for optimized space and streamlined operations becoming paramount. Amidst this evolving paradigm, the present research delves deep into the capabilities of Convolutional Neural Networks (CNNs), an advanced machine learning construct, examining its potential to redefine warehousing strategies. Delving into the intricate architecture of CNNs, we explore their robustness in analyzing and interpreting spatial relationships, a skillset inherently suited for space optimization tasks. This paper aims not just to present the technological prowess of CNNs, but to showcase how their integration could mark a paradigm shift in the warehousing domain, paving the way for smarter, more efficient storage solutions in an increasingly digital world.

Efficient Classification of Marine Debris using SVM with Noise Removal and Feature Extraction Techniques with Improved Performances

Marine debris is a significant environmental issue, necessitating the development of precise and efficient technologies for classifying and reducing its impact. This research tries to address the issues of image noise in ocean trash classification using four alternative filters the Gaussian, Bilateral, Mean, and Alpha-Trimmed Mean (ATM) filters for noise reduction and SVM for classification. The accuracy of categorization algorithms can be considerably impacted by the presence of noise in photos of maritime debris. In this study, we suggest a two-pronged strategy: To effectively decrease noise and improve the quality of the input photos, we first apply filters. These filters were chosen with care to protect significant details while eliminating extraneous noise. Second, we classify the debris into various categories based on its visual attributes using SVM, a powerful ML technique. The ATM filter significantly reduces noise and improves the clarity of photographs of ocean trash, according to the results of our experiments. This work proposes a novel approach for classifying marine debris using advanced machine learning algorithms. For improved classification accuracy, we suggest combining Support Vector Machines (SVM) with Adaptive Thresholding Mean (ATM) filtering and Histogram of Oriented Gradients (HOG) feature extraction. According to this research, the ATM filter is a promising option for noise reduction in ocean trash imaging, potentially increasing the precision of subsequent classification algorithms and assisting in efficient environmental monitoring and marine ecosystem conservation efforts. The language used for execution is Python.

Speech Processing on Detection of Respiratory Disease

Abstract: Speech processing applied to the detection of respiratory diseases has emerged as an innovative and groundbreaking field in the medical domain. By analyzing audio signals, specifically cough and respiratory sounds, this cutting-edge approach offers a non-invasive and costefficient method for early diagnosis and continuous monitoring of various respiratory conditions. Herein we report a review on the process entailing extraction of crucial features like Mel-Frequency Cepstral Coefficients (MFCCs) and cochlegram image characteristics, inputting the subsequent ones advanced machine learning techniques like Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) for accurate classification. Despite encouraging outcomes, certain challenges, including limited data availability and variability in cough sounds, pose obstacles to further advancements. Nevertheless, dedicated researchers are actively working on expanding datasets, bolstering the robustness of algorithms, and integrating multimodal data to surmount these hurdles. The potential benefits of speech processing in respiratory disease detection are vast, encompassing prompt identification, remote assessment capabilities, and personalized medical interventions. Continued collaboration between engineers, healthcare professionals, and patients is essential to fully harness the potential of this technology in revolutionizing respiratory disease diagnosis and improving patient care.

Brain-Storming to Detect Brain Disorders

Abstract: Brain disorders represent a significant and growing global health challenge, encompassing a spectrum of conditions ranging from neurodegenerative diseases, like Alzheimer's and Parkinson's, to various neuropsychiatric disorders. Timely and accurate detection of brain disorders is crucial for enabling prompt interventions, tailoring appropriate treatments, and improving the overall quality of life for affected individuals. This research paper explores an innovative and interdisciplinary approach to enhance the process of brain disorder detection through the integration of brainstorming techniques and advanced machine learning algorithms. The research delves into the adaptability and effectiveness of brainstorming techniques for brain disorder detection, leveraging diverse data sources such as clinical records, genetic information, and patient histories. The study presents various brainstorming techniques that are utilised to analyse, identify and arrive at the best possible methodology that can be used for the detection of brain disorders.

Retail Optimization

Abstract: In an era characterized by the overwhelming influx of digital information and the pervasive influence of social media platforms like Instagram, the act of exploring local venues such as restaurants, concerts, and travel destinations remains a daunting task for urban dwellers. This article aims to address these challenges by introducing a novel program leveraging augmented reality (AR) and virtual reality (VR) technologies to enrich the experience of local exploration. At its core, this program employs advanced machine learning algorithms to provide tailored recommendations, taking into account diverse parameters such as cuisine preferences, geographical location, and seating preferences. The iterative nature of the system ensures continuous improvement based on user feedback. The interactive fusion of VR and AR offers users an immersive and dynamic experience, enabling them to virtually "immerse" themselves in local attractions before embarking on physical visits. This not only enhances the anticipation of exploration but also aids in informed decision-making. The objectives of this update encompass: Surveying the Challenge: Central to this endeavor is the recognition of the formidable challenge posed by the modern-day struggle to explore one's local environment. This difficulty is amplified by the deluge of messages and information inundating social media platforms, further complicating the decision-making process. Content, Methodology, and Technological Innovation: The project is founded on a multidimensional approach that harnesses the potential of AR/VR technology in synergy with machine learning. By tailoring and enhancing the perceptual experience of city dwellers, we aim to revolutionize local exploration. Statement of Insights and Values: While the abstract is inherently devoid of specific research findings, this article will comprehensively review the strategies deployed to identify challenges and evaluate user acceptance and satisfaction. Our findings will serve as valuable guidance for future research initiatives seeking to refine and expand the realm of urban discovery. In summary, this article seeks to bridge the widening gap between digital information overload and meaningful local exploration. By harnessing cutting- edge technologies and user-centric machine learning, we endeavor to provide individuals with a personalized, immersive, and informed means of rediscovering the treasures hidden within their own cities