Search results for: Imbalanced dataset

Authors: Tolulope Aremu

Abstract:

The key process steps to produce liquid detergent products will introduce potential defects, such as formulation, mixing, filling, and packaging, which might compromise product quality, consumer safety, and operational efficiency. Real-time identification and characterization of such defects are of prime importance for maintaining high standards and reducing waste and costs. Usually, defect detection is performed by human inspection or rule-based systems, which is very time-consuming, inconsistent, and error-prone. The present study overcomes these limitations in dealing with optimization in defect characterization within the process for making liquid detergents using Machine Learning algorithms. Performance testing of various machine learning models was carried out: Support Vector Machine, Decision Trees, Random Forest, and Convolutional Neural Network on defect detection and classification of those defects like wrong viscosity, color deviations, improper filling of a bottle, packaging anomalies. These algorithms have significantly benefited from a variety of optimization techniques, including hyperparameter tuning and ensemble learning, in order to greatly improve detection accuracy while minimizing false positives. Equipped with a rich dataset of defect types and production parameters consisting of more than 100,000 samples, our study further includes information from real-time sensor data, imaging technologies, and historic production records. The results are that optimized machine learning models significantly improve defect detection compared to traditional methods. Take, for instance, the CNNs, which run at 98% and 96% accuracy in detecting packaging anomaly detection and bottle filling inconsistency, respectively, by fine-tuning the model with real-time imaging data, through which there was a reduction in false positives of about 30%. The optimized SVM model on detecting formulation defects gave 94% in viscosity variation detection and color variation. These values of performance metrics correspond to a giant leap in defect detection accuracy compared to the usual 80% level achieved up to now by rule-based systems. Moreover, this optimization with models can hasten defect characterization, allowing for detection time to be below 15 seconds from an average of 3 minutes using manual inspections with real-time processing of data. With this, the reduction in time will be combined with a 25% reduction in production downtime because of proactive defect identification, which can save millions annually in recall and rework costs. Integrating real-time machine learning-driven monitoring drives predictive maintenance and corrective measures for a 20% improvement in overall production efficiency. Therefore, the optimization of machine learning algorithms in defect characterization optimum scalability and efficiency for liquid detergent companies gives improved operational performance to higher levels of product quality. In general, this method could be conducted in several industries within the Fast moving consumer Goods industry, which would lead to an improved quality control process.

Keywords: liquid detergent manufacturing, defect detection, machine learning, support vector machines, convolutional neural networks, defect characterization, predictive maintenance, quality control, fast-moving consumer goods

Procedia PDF Downloads 16

Authors: Chandu Rathnayake, Isuri Anuradha

Abstract:

Early detection and accurate diagnosis of lung diseases play a crucial role in improving patient prognosis. However, conventional diagnostic methods heavily rely on subjective symptom assessments and medical imaging, often causing delays in diagnosis and treatment. To overcome this challenge, we propose a novel lung disease prediction system that integrates patient symptoms and X-ray images to provide a comprehensive and reliable diagnosis.In this project, develop a mobile application specifically designed for detecting lung diseases. Our application leverages both patient symptoms and X-ray images to facilitate diagnosis. By combining these two sources of information, our application delivers a more accurate and comprehensive assessment of the patient's condition, minimizing the risk of misdiagnosis. Our primary aim is to create a user-friendly and accessible tool, particularly important given the current circumstances where many patients face limitations in visiting healthcare facilities. To achieve this, we employ several state-of-the-art algorithms. Firstly, the Decision Tree algorithm is utilized for efficient symptom-based classification. It analyzes patient symptoms and creates a tree-like model to predict the presence of specific lung diseases. Secondly, we employ the Random Forest algorithm, which enhances predictive power by aggregating multiple decision trees. This ensemble technique improves the accuracy and robustness of the diagnosis. Furthermore, we incorporate a deep learning model using Convolutional Neural Network (CNN) with the RestNet50 pre-trained model. CNNs are well-suited for image analysis and feature extraction. By training CNN on a large dataset of X-ray images, it learns to identify patterns and features indicative of lung diseases. The RestNet50 architecture, known for its excellent performance in image recognition tasks, enhances the efficiency and accuracy of our deep learning model. By combining the outputs of the decision tree-based algorithms and the deep learning model, our mobile application generates a comprehensive lung disease prediction. The application provides users with an intuitive interface to input their symptoms and upload X-ray images for analysis. The prediction generated by the system offers valuable insights into the likelihood of various lung diseases, enabling individuals to take appropriate actions and seek timely medical attention. Our proposed mobile application has significant potential to address the rising prevalence of lung diseases, particularly among young individuals with smoking addictions. By providing a quick and user-friendly approach to assessing lung health, our application empowers individuals to monitor their well-being conveniently. This solution also offers immense value in the context of limited access to healthcare facilities, enabling timely detection and intervention. In conclusion, our research presents a comprehensive lung disease prediction system that combines patient symptoms and X-ray images using advanced algorithms. By developing a mobile application, we provide an accessible tool for individuals to assess their lung health conveniently. This solution has the potential to make a significant impact on the early detection and management of lung diseases, benefiting both patients and healthcare providers.

Keywords: CNN, random forest, decision tree, machine learning, deep learning

Procedia PDF Downloads 72

Authors: Ankur Chaudhuri, Sibani Sen Chakraborty

Abstract:

In human, glutaminyl cyclase activity is highly abundant in neuronal and secretory tissues and is preferentially restricted to hypothalamus and pituitary. The N-terminal modification of β-amyloids (Aβs) peptides by the generation of a pyro-glutamyl (pGlu) modified Aβs (pE-Aβs) is an important process in the initiation of the formation of neurotoxic plaques in Alzheimer’s disease (AD). This process is catalyzed by glutaminyl cyclase (QC). The expression of QC is characteristically up-regulated in the early stage of AD, and the hallmark of the inhibition of QC is the prevention of the formation of pE-Aβs and plaques. A computer-aided drug design (CADD) process was employed to give an idea for the designing of potentially active compounds to understand the inhibitory potency against human glutaminyl cyclase (QC). This work elaborates the ligand-based and structure-based pharmacophore exploration of glutaminyl cyclase (QC) by using the known inhibitors. Three dimensional (3D) quantitative structure-activity relationship (QSAR) methods were applied to 154 compounds with known IC50 values. All the inhibitors were divided into two sets, training-set, and test-sets. Generally, training-set was used to build the quantitative pharmacophore model based on the principle of structural diversity, whereas the test-set was employed to evaluate the predictive ability of the pharmacophore hypotheses. A chemical feature-based pharmacophore model was generated from the known 92 training-set compounds by HypoGen module implemented in Discovery Studio 2017 R2 software package. The best hypothesis was selected (Hypo1) based upon the highest correlation coefficient (0.8906), lowest total cost (463.72), and the lowest root mean square deviation (2.24Å) values. The highest correlation coefficient value indicates greater predictive activity of the hypothesis, whereas the lower root mean square deviation signifies a small deviation of experimental activity from the predicted one. The best pharmacophore model (Hypo1) of the candidate inhibitors predicted comprised four features: two hydrogen bond acceptor, one hydrogen bond donor, and one hydrophobic feature. The Hypo1 was validated by several parameters such as test set activity prediction, cost analysis, Fischer's randomization test, leave-one-out method, and heat map of ligand profiler. The predicted features were then used for virtual screening of potential compounds from NCI, ASINEX, Maybridge and Chembridge databases. More than seven million compounds were used for this purpose. The hit compounds were filtered by drug-likeness and pharmacokinetics properties. The selective hits were docked to the high-resolution three-dimensional structure of the target protein glutaminyl cyclase (PDB ID: 2AFU/2AFW) to filter these hits further. To validate the molecular docking results, the most active compound from the dataset was selected as a reference molecule. From the density functional theory (DFT) study, ten molecules were selected based on their highest HOMO (highest occupied molecular orbitals) energy and the lowest bandgap values. Molecular dynamics simulations with explicit solvation systems of the final ten hit compounds revealed that a large number of non-covalent interactions were formed with the binding site of the human glutaminyl cyclase. It was suggested that the hit compounds reported in this study could help in future designing of potent inhibitors as leads against human glutaminyl cyclase.

Keywords: glutaminyl cyclase, hit lead, pharmacophore model, simulation

Procedia PDF Downloads 130

Authors: Daniele Lerede, Gianvito Colucci, Matteo Nicoli, Laura Savoldi

Abstract:

The European Green Deal is the first internationally agreed set of measures to contrast climate change and environmental degradation. Besides the main target of reducing emissions by at least 55% by 2030, it sets the target of accompanying European countries through an energy transition to make the European Union into a modern, resource-efficient, and competitive net-zero emissions economy by 2050, decoupling growth from the use of resources and ensuring a fair adaptation of all social categories to the transformation process. While the general purpose to allow the realization of the purposes of the Green Deal already dates back to 2019, strategies and policies keep being developed coping with recent circumstances and achievements. However, general long-term measures like the Circular Economy Action Plan, the proposals to shift from fossil natural gas to renewable and low-carbon gases, in particular biomethane and hydrogen, and to end the sale of gasoline and diesel cars by 2035, will all have significant effects on energy supply and demand evolution across the next decades. The interactions between energy supply and demand over long-term time frames are usually assessed via energy system models to derive useful insights for policymaking and to address technological choices and research and development. TEMOA-Europe is a newly developed energy system optimization model instance based on the minimization of the total cost of the system under analysis, adopting a technologically integrated, detailed, and explicit formulation and considering the evolution of the system in partial equilibrium in competitive markets with perfect foresight. TEMOA-Europe is developed on the TEMOA platform, an open-source modeling framework totally implemented in Python, therefore ensuring third-party verification even on large and complex models. TEMOA-Europe is based on a single-region representation of the European Union and EFTA countries on a time scale between 2005 and 2100, relying on a set of assumptions for socio-economic developments based on projections by the International Energy Outlook and a large technological dataset including 7 sectors: the upstream and power sectors for the production of all energy commodities and the end-use sectors, including industry, transport, residential, commercial and agriculture. TEMOA-Europe also includes an updated hydrogen module considering its production, storage, transportation, and utilization. Besides, it can rely on a wide set of innovative technologies, ranging from nuclear fusion and electricity plants equipped with CCS in the power sector to electrolysis-based steel production processes and steel in the industrial sector – with a techno-economic characterization based on public literature – to produce insightful energy scenarios and especially to cope with the very long analyzed time scale. The aim of this work is to examine in detail the scheme of measures and policies for the realization of the purposes of the Green Deal and to transform them into a set of constraints and new socio-economic development pathways. Based on them, TEMOA-Europe will be used to produce and comparatively analyze scenarios to assess the consequences of Green Deal-related measures on the future evolution of the energy mix over the whole energy system in an economic optimization environment.

Keywords: European Green Deal, energy system optimization modeling, scenario analysis, TEMOA-Europe

Procedia PDF Downloads 104

Authors: Anjalika Fernando, Banuka Athuraliya

Abstract:

This paper presents a comprehensive approach for converting Sinhala Sign Language (SSL) into grammatically correct sentences using Natural Language Processing (NLP) techniques in real-time. While previous studies have explored various aspects of SSL translation, the research gap lies in the absence of grammar checking for SSL. This work aims to bridge this gap by proposing a two-stage methodology that leverages deep learning models to detect signs and translate them into coherent sentences, ensuring grammatical accuracy. The first stage of the approach involves the utilization of a Long Short-Term Memory (LSTM) deep learning model to recognize and interpret SSL signs. By training the LSTM model on a dataset of SSL gestures, it learns to accurately classify and translate these signs into textual representations. The LSTM model achieves a commendable accuracy rate of 94%, demonstrating its effectiveness in accurately recognizing and translating SSL gestures. Building upon the successful recognition and translation of SSL signs, the second stage of the methodology focuses on improving the grammatical correctness of the translated sentences. The project employs a Neural Machine Translation (NMT) architecture, consisting of an encoder and decoder with LSTM components, to enhance the syntactical structure of the generated sentences. By training the NMT model on a parallel corpus of Sinhala wrong sentences and their corresponding grammatically correct translations, it learns to generate coherent and grammatically accurate sentences. The NMT model achieves an impressive accuracy rate of 98%, affirming its capability to produce linguistically sound translations. The proposed approach offers significant contributions to the field of SSL translation and grammar correction. Addressing the critical issue of grammar checking, it enhances the usability and reliability of SSL translation systems, facilitating effective communication between hearing-impaired and non-sign language users. Furthermore, the integration of deep learning techniques, such as LSTM and NMT, ensures the accuracy and robustness of the translation process. This research holds great potential for practical applications, including educational platforms, accessibility tools, and communication aids for the hearing-impaired. Furthermore, it lays the foundation for future advancements in SSL translation systems, fostering inclusive and equal opportunities for the deaf community. Future work includes expanding the existing datasets to further improve the accuracy and generalization of the SSL translation system. Additionally, the development of a dedicated mobile application would enhance the accessibility and convenience of SSL translation on handheld devices. Furthermore, efforts will be made to enhance the current application for educational purposes, enabling individuals to learn and practice SSL more effectively. Another area of future exploration involves enabling two-way communication, allowing seamless interaction between sign-language users and non-sign-language users.In conclusion, this paper presents a novel approach for converting Sinhala Sign Language gestures into grammatically correct sentences using NLP techniques in real time. The two-stage methodology, comprising an LSTM model for sign detection and translation and an NMT model for grammar correction, achieves high accuracy rates of 94% and 98%, respectively. By addressing the lack of grammar checking in existing SSL translation research, this work contributes significantly to the development of more accurate and reliable SSL translation systems, thereby fostering effective communication and inclusivity for the hearing-impaired community

Keywords: Sinhala sign language, sign Language, NLP, LSTM, NMT

Procedia PDF Downloads 103

Authors: Asma Omri, Iheb Sifaoui, Sofiane Sayahi, Hichem Besbes

Abstract:

Future vehicle systems demand advanced capabilities, notably in-cabin life detection and driver monitoring systems, with a particular emphasis on drowsiness detection. To meet these requirements, several techniques employ artificial intelligence methods based on real-time vital sign measurements. In parallel, Frequency-Modulated Continuous-Wave (FMCW) radar technology has garnered considerable attention in the domains of healthcare and biomedical engineering for non-invasive vital sign monitoring. FMCW radar offers a multitude of advantages, including its non-intrusive nature, continuous monitoring capacity, and its ability to penetrate through clothing. In this paper, we propose a system utilizing the AWR6843AOP radar from Texas Instruments (TI) to extract precise vital sign information. The radar allows us to estimate Ballistocardiogram (BCG) signals, which capture the mechanical movements of the body, particularly the ballistic forces generated by heartbeats and respiration. These signals are rich sources of information about the cardiac cycle, rendering them suitable for heart rate estimation. The process begins with real-time subject positioning, followed by clutter removal, computation of Doppler phase differences, and the use of various filtering methods to accurately capture subtle physiological movements. To address the challenges associated with FMCW radar-based vital sign monitoring, including motion artifacts due to subjects' movement or radar micro-vibrations, Long Short-Term Memory (LSTM) networks are implemented. LSTM's adaptability to different heart rate patterns and ability to handle real-time data make it suitable for continuous monitoring applications. Several crucial steps were taken, including feature extraction (involving amplitude, time intervals, and signal morphology), sequence modeling, heart rate estimation through the analysis of detected cardiac cycles and their temporal relationships, and performance evaluation using metrics such as Root Mean Square Error (RMSE) and correlation with reference heart rate measurements. For dataset construction and LSTM training, a comprehensive data collection system was established, integrating the AWR6843AOP radar, a Heart Rate Belt, and a smart watch for ground truth measurements. Rigorous synchronization of these devices ensured data accuracy. Twenty participants engaged in various scenarios, encompassing indoor and real-world conditions within a moving vehicle equipped with the radar system. Static and dynamic subject’s conditions were considered. The heart rate estimation through LSTM outperforms traditional signal processing techniques that rely on filtering, Fast Fourier Transform (FFT), and thresholding. It delivers an average accuracy of approximately 91% with an RMSE of 1.01 beat per minute (bpm). In conclusion, this paper underscores the promising potential of FMCW radar technology integrated with artificial intelligence algorithms in the context of automotive applications. This innovation not only enhances road safety but also paves the way for its integration into the automotive ecosystem to improve driver well-being and overall vehicular safety.

Keywords: ballistocardiogram, FMCW Radar, vital sign monitoring, LSTM

Procedia PDF Downloads 72

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 70

Authors: Subhash Nerella, Ziyuan Guan, Azra Bihorac, Parisa Rashidi

Abstract:

Intensive care units (ICUs) provide care to critically ill patients in severe and life-threatening conditions. However, patient monitoring in the ICU is limited by the time and resource constraints imposed on healthcare providers. Many critical care indices such as mobility are still manually assessed, which can be subjective, prone to human errors, and lack granularity. Other important aspects, such as environmental factors, are not monitored at all. For example, critically ill patients often experience circadian disruptions due to the absence of effective environmental “timekeepers” such as the light/dark cycle and the systemic effect of acute illness on chronobiologic markers. Although the occurrence of delirium is associated with circadian disruption risk factors, these factors are not routinely monitored in the ICU. Hence, there is a critical unmet need to develop systems for precise and real-time assessment through novel enabling technologies. We have developed the mobility and circadian disruption quantification system (Mobi-DiQ) by augmenting biomarker and clinical data with pervasive sensing data to generate mobility and circadian cues related to mobility, nightly disruptions, and light and noise exposure. We hypothesize that Mobi-DiQ can provide accurate mobility and circadian cues that correlate with bedside clinical mobility assessments and circadian biomarkers, ultimately important for delirium risk assessment and prevention. The collected multimodal dataset consists of depth images, Electromyography (EMG) data, patient extremity movement captured by accelerometers, ambient light levels, Sound Pressure Level (SPL), and indoor air quality measured by volatile organic compounds, and the equivalent CO₂ concentration. For delirium risk assessment, the system recognizes mobility cues (axial body movement features and body key points) and circadian cues, including nightly disruptions, ambient SPL, and light intensity, as well as other environmental factors such as indoor air quality. The Mobi-DiQ system consists of three major components: the pervasive sensing system, a data storage and analysis server, and a data annotation system. For data collection, six local pervasive sensing systems were deployed, including a local computer and sensors. A video recording tool with graphical user interface (GUI) developed in python was used to capture depth image frames for analyzing patient mobility. All sensor data is encrypted, then automatically uploaded to the Mobi-DiQ server through a secured VPN connection. Several data pipelines are developed to automate the data transfer, curation, and data preparation for annotation and model training. The data curation and post-processing are performed on the server. A custom secure annotation tool with GUI was developed to annotate depth activity data. The annotation tool is linked to the MongoDB database to record the data annotation and to provide summarization. Docker containers are also utilized to manage services and pipelines running on the server in an isolated manner. The processed clinical data and annotations are used to train and develop real-time pervasive sensing systems to augment clinical decision-making and promote targeted interventions. In the future, we intend to evaluate our system as a clinical implementation trial, as well as to refine and validate it by using other data sources, including neurological data obtained through continuous electroencephalography (EEG).

Keywords: deep learning, delirium, healthcare, pervasive sensing

Procedia PDF Downloads 91

Authors: Philipp Sommer, Amgad Agoub

Abstract:

The construction sector significantly impacts global CO₂ emissions, particularly through the energy usage of residential buildings. To address this, various governments, including Germany's, are focusing on reducing emissions via sustainable refurbishment initiatives. This study examines the application of machine learning (ML) to estimate energy demands dynamically in residential buildings and enhance the potential for large-scale sustainable refurbishment. A major challenge in Germany is the lack of extensive publicly labeled datasets for energy performance, as energy performance certificates, which provide critical data on building-specific energy requirements and consumption, are not available for all buildings or require on-site inspections. Conversely, England and other countries in the European Union (EU) have rich public datasets, providing a viable alternative for analysis. This research adapts insights from these English datasets to the German context by developing a comprehensive data schema and calibration dataset capable of predicting building energy demand effectively. The study proposes a minimal feature set, determined through feature importance analysis, to optimize the ML model. Findings indicate that ML significantly improves the scalability and accuracy of energy demand forecasts, supporting more effective emissions reduction strategies in the construction industry. Integrating energy performance certificates into municipal heat planning in Germany highlights the transformative impact of data-driven approaches on environmental sustainability. The goal is to identify and utilize key features from open data sources that significantly influence energy demand, creating an efficient forecasting model. Using Extreme Gradient Boosting (XGB) and data from energy performance certificates, effective features such as building type, year of construction, living space, insulation level, and building materials were incorporated. These were supplemented by data derived from descriptions of roofs, walls, windows, and floors, integrated into three datasets. The emphasis was on features accessible via remote sensing, which, along with other correlated characteristics, greatly improved the model's accuracy. The model was further validated using SHapley Additive exPlanations (SHAP) values and aggregated feature importance, which quantified the effects of individual features on the predictions. The refined model using remote sensing data showed a coefficient of determination (R²) of 0.64 and a mean absolute error (MAE) of 4.12, indicating predictions based on efficiency class 1-100 (G-A) may deviate by 4.12 points. This R² increased to 0.84 with the inclusion of more samples, with wall type emerging as the most predictive feature. After optimizing and incorporating related features like estimated primary energy consumption, the R² score for the training and test set reached 0.94, demonstrating good generalization. The study concludes that ML models significantly improve prediction accuracy over traditional methods, illustrating the potential of ML in enhancing energy efficiency analysis and planning. This supports better decision-making for energy optimization and highlights the benefits of developing and refining data schemas using open data to bolster sustainability in the building sector. The study underscores the importance of supporting open data initiatives to collect similar features and support the creation of comparable models in Germany, enhancing the outlook for environmental sustainability.

Keywords: machine learning, remote sensing, residential building, energy performance certificates, data-driven, heat planning

Procedia PDF Downloads 55

Authors: Savvas Rogotis, Nikolaos Kalatzis, Stergios Dimou-Sakellariou, Nikolaos Marianos

Abstract:

As precision holds the key for the introduction of distinct benefits in agriculture (e.g., energy savings, reduced labor costs, optimal application of inputs, improved products, and yields), it steadily becomes evident that new initiatives should focus on rendering Precision Agriculture (PA) more accessible to the average farmer. PA leverages on technologies such as the Internet of Things (IoT), earth observation, robotics and positioning systems (e.g., the Global Navigation Satellite System – GNSS - as well as individual positioning systems like GPS, Glonass, Galileo) that allow: from simple data georeferencing to optimal navigation of agricultural machinery to even more complex tasks like Variable Rate Applications. An identified customer pain point is that, from one hand, typical triangulation-based positioning systems are not accurate enough (with errors up to several meters), while on the other hand, high precision positioning systems reaching centimeter-level accuracy, are very costly (up to thousands of euros). Within this paper, a Ground-Based Augmentation System (GBAS) is introduced, that can be adapted to any existing IoT field-sensing station infrastructure. The latter should cover a minimum set of requirements, and in particular, each station should operate as a fixed, obstruction-free towards the sky, energy supplying unit. Station augmentation will allow them to function in pairs with GNSS rovers following the differential GNSS base-rover paradigm. This constitutes a key innovation element for the proposed solution that encompasses differential GNSS capabilities into an IoT field-sensing infrastructure. Integrating this kind of information supports the provision of several additional PA beneficial services such as spatial mapping, route planning, and automatic field navigation of unmanned vehicles (UVs). Right at the heart of the designed system, there is a high-end GNSS toolkit with base-rover variants and Real-Time Kinematic (RTK) capabilities. The GNSS toolkit had to tackle all availability, performance, interfacing, and energy-related challenges that are faced for a real-time, low-power, and reliable in the field operation. Specifically, in terms of performance, preliminary findings exhibit a high rover positioning precision that can even reach less than 10-centimeters. As this precision is propagated to the full dataset collection, it enables tractors, UVs, Android-powered devices, and measuring units to deal with challenging real-world scenarios. The system is validated with the help of Gaiatrons, a mature network of agro-climatic telemetry stations with presence all over Greece and beyond ( > 60.000ha of agricultural land covered) that constitutes part of “gaiasense” (www.gaiasense.gr) smart farming (SF) solution. Gaiatrons constantly monitor atmospheric and soil parameters, thus, providing exact fit to operational requirements asked from modern SF infrastructures. Gaiatrons are ultra-low-cost, compact, and energy-autonomous stations with a modular design that enables the integration of advanced GNSS base station capabilities on top of them. A set of demanding pilot demonstrations has been initiated in Stimagka, Greece, an area with a diverse geomorphological landscape where grape cultivation is particularly popular. Pilot demonstrations are in the course of validating the preliminary system findings in its intended environment, tackle all technical challenges, and effectively highlight the added-value offered by the system in action.

Keywords: GNSS, GBAS, precision agriculture, RTK, smart farming

Procedia PDF Downloads 112

Authors: Mara Getachew Zenebe, Luuk Fleskens, Abdu Obieda Ahmed

Abstract:

This paper seeks to advance our scientific understanding of optimizing flood utilization in regions impacted by climate change, with a focus on enhancing agricultural productivity through effective irrigation management. The study was conducted as part of a three-year (2021 to 2023) USAID-supported initiative aimed at promoting Economic Growth and Peace in the Gash Agricultural Scheme (GAS), situated in Sudan's water-stressed Eastern region. GAS is the country's largest flood-irrigated scheme, covering 100,800 hectares of cultivable land, with a potential to provide the food security needs of over a quarter of a million agro-pastoral community members. GAS relies on the Gash River, which sources its water from high-intensity rainfall events in the highlands of Ethiopia and Eritrea. However, climate change and variations in these highlands have led to increased variability in the Gash River's flow. The study conducted water balance analyses based on a ten-year dataset of the annual Gash River flow, irrigated area; as well as the evapotranspiration demand of the major sorghum crop. Data collection methods included field measurements, surveys, remote sensing, and CropWat modelling. The water balance assessment revealed that the existing three-year rotation-based irrigation system management, capping cultivated land at 33,000 hectares annually, is excessively risk-averse. While this system reduced conflicts among the agro-pastoral communities by consistently delivering on the land promised to be annually cultivated, it also increased GAS's vulnerability to flood damage due to several reasons. The irrigation efficiency over the past decade was approximately 30%, leaving significant unharnessed floodwater that caused damage to infrastructure and agricultural land. The three-year rotation resulted in inadequate infrastructural maintenance, given the destructive nature of floods. Additionally, it led to infrequent land tillage, allowing the encroachment of mesquite trees hindering major sorghum crop growth. Remote sensing data confirmed that mesquite trees have overtaken 70,000 hectares in the past two decades, rendering them unavailable for agriculture. The water balance analyses suggest shifting to a two-year rotation, covering approximately 50,000 hectares annually while maintaining risk aversion. This shift could boost GAS's annual sorghum production by two-thirds, exceeding 850,000 tons. The scheme's efficiency can be further enhanced through low-cost on-farm interventions. Currently, large irrigation plots that range from 420 to 756 hectares are irrigated with limited water distribution guidance, leading to uneven irrigation. As demonstrated through field trials, implementing internal longitudinal bunds and horizontal deflector bunds can increase adequately irrigated parts of the irrigation plots from 50% to 80% and thus nearly double the sorghum yield to 2 tons per hectare while reducing the irrigation duration from 30 days to a maximum of 17 days. Flow measurements in 2021 and 2022 confirmed that these changes sufficiently meet the sorghum crop's water requirements, even with a conservative 60% field application efficiency assumption. These insights and lessons from the GAS on enhancing agricultural resilience and sustainability in the face of climate change are relevant to flood-based livelihood systems globally.

Keywords: climate change, irrigation management and productivity, variable flood flows, water balance analysis

Procedia PDF Downloads 72

Authors: Faruk Ozdemir, Roy Kalawsky, Peter Hubbard

Abstract:

Accurate estimation of RUL provides a basis for effective predictive maintenance, reducing unexpected downtime for industrial equipment. However, while models such as the Random Forest have effective predictive capabilities, they are the so-called ‘black box’ models, where interpretability is at a threshold to make critical diagnostic decisions involved in industries related to aviation. The purpose of this work is to present a prognostic framework that embeds Explainable Artificial Intelligence (XAI) techniques in order to provide essential transparency in Machine Learning methods' decision-making mechanisms based on sensor data, with the objective of procuring actionable insights for the aviation industry. Sensor readings have been gathered from critical equipment such as turbofan jet engine and landing gear, and the prediction of the RUL is done by a Random Forest model. It involves steps such as data gathering, feature engineering, model training, and evaluation. These critical components’ datasets are independently trained and evaluated by the models. While suitable predictions are served, their performance metrics are reasonably good; such complex models, however obscure reasoning for the predictions made by them and may even undermine the confidence of the decision-maker or the maintenance teams. This is followed by global explanations using SHAP and local explanations using LIME in the second phase to bridge the gap in reliability within industrial contexts. These tools analyze model decisions, highlighting feature importance and explaining how each input variable affects the output. This dual approach offers a general comprehension of the overall model behavior and detailed insight into specific predictions. The proposed framework, in its third component, incorporates the techniques of causal analysis in the form of Granger causality tests in order to move beyond correlation toward causation. This will not only allow the model to predict failures but also present reasons, from the key sensor features linked to possible failure mechanisms to relevant personnel. The causality between sensor behaviors and equipment failures creates much value for maintenance teams due to better root cause identification and effective preventive measures. This step contributes to the system being more explainable. Surrogate Several simple models, including Decision Trees and Linear Models, can be used in yet another stage to approximately represent the complex Random Forest model. These simpler models act as backups, replicating important jobs of the original model's behavior. If the feature explanations obtained from the surrogate model are cross-validated with the primary model, the insights derived would be more reliable and provide an intuitive sense of how the input variables affect the predictions. We then create an iterative explainable feedback loop, where the knowledge learned from the explainability methods feeds back into the training of the models. This feeds into a cycle of continuous improvement both in model accuracy and interpretability over time. By systematically integrating new findings, the model is expected to adapt to changed conditions and further develop its prognosis capability. These components are then presented to the decision-makers through the development of a fully transparent condition monitoring and alert system. The system provides a holistic tool for maintenance operations by leveraging RUL predictions, feature importance scores, persistent sensor threshold values, and autonomous alert mechanisms. Since the system will provide explanations for the predictions given, along with active alerts, the maintenance personnel can make informed decisions on their end regarding correct interventions to extend the life of the critical machinery.

Keywords: predictive maintenance, explainable artificial intelligence, prognostic, RUL, machine learning, turbofan engines, C-MAPSS dataset

Procedia PDF Downloads 4

Authors: Ali Kazemi

Abstract:

Those within the volatile and interconnected international economic markets, appropriately predicting market trends, hold substantial fees for traders and financial establishments. Traditional device mastering strategies have made full-size strides in forecasting marketplace movements; however, monetary data's complicated and networked nature calls for extra sophisticated processes. This observation offers a groundbreaking method for monetary marketplace prediction that leverages the synergistic capability of Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks. Our suggested algorithm is meticulously designed to forecast the traits of inventory market indices and cryptocurrency costs, utilizing a comprehensive dataset spanning from January 1, 2015, to December 31, 2023. This era, marked by sizable volatility and transformation in financial markets, affords a solid basis for schooling and checking out our predictive version. Our algorithm integrates diverse facts to construct a dynamic economic graph that correctly reflects market intricacies. We meticulously collect opening, closing, and high and low costs daily for key inventory marketplace indices (e.g., S&P 500, NASDAQ) and widespread cryptocurrencies (e.g., Bitcoin, Ethereum), ensuring a holistic view of marketplace traits. Daily trading volumes are also incorporated to seize marketplace pastime and liquidity, providing critical insights into the market's shopping for and selling dynamics. Furthermore, recognizing the profound influence of the monetary surroundings on financial markets, we integrate critical macroeconomic signs with hobby fees, inflation rates, GDP increase, and unemployment costs into our model. Our GCN algorithm is adept at learning the relational patterns amongst specific financial devices represented as nodes in a comprehensive market graph. Edges in this graph encapsulate the relationships based totally on co-movement styles and sentiment correlations, enabling our version to grasp the complicated community of influences governing marketplace moves. Complementing this, our LSTM algorithm is trained on sequences of the spatial-temporal illustration discovered through the GCN, enriched with historic fee and extent records. This lets the LSTM seize and expect temporal marketplace developments accurately. Inside the complete assessment of our GCN-LSTM algorithm across the inventory marketplace and cryptocurrency datasets, the version confirmed advanced predictive accuracy and profitability compared to conventional and opportunity machine learning to know benchmarks. Specifically, the model performed a Mean Absolute Error (MAE) of 0.85%, indicating high precision in predicting day-by-day charge movements. The RMSE was recorded at 1.2%, underscoring the model's effectiveness in minimizing tremendous prediction mistakes, which is vital in volatile markets. Furthermore, when assessing the model's predictive performance on directional market movements, it achieved an accuracy rate of 78%, significantly outperforming the benchmark models, averaging an accuracy of 65%. This high degree of accuracy is instrumental for techniques that predict the course of price moves. This study showcases the efficacy of mixing graph-based totally and sequential deep learning knowledge in economic marketplace prediction and highlights the fee of a comprehensive, records-pushed evaluation framework. Our findings promise to revolutionize investment techniques and hazard management practices, offering investors and economic analysts a powerful device to navigate the complexities of cutting-edge economic markets.

Keywords: financial market prediction, graph convolutional networks (GCNs), long short-term memory (LSTM), cryptocurrency forecasting

Procedia PDF Downloads 63