Search results for: predictive accuracy

Authors: Angela U. Makolo

Abstract:

Protein-coding and Non-coding regions determine the biology of a sequenced transcriptome. Research advances have shown that Non-coding regions are important in disease progression and clinical diagnosis. Existing bioinformatics tools have been targeted towards Protein-coding regions alone. Therefore, there are challenges associated with gaining biological insights from transcriptome sequence data. These tools are also limited to computationally intensive sequence alignment, which is inadequate and less accurate to identify both Protein-coding and Non-coding regions. Alignment-free techniques can overcome the limitation of identifying both regions. Therefore, this study was designed to develop an efficient sequence alignment-free model for identifying both Protein-coding and Non-coding regions in sequenced transcriptomes. Feature grouping and randomization procedures were applied to the input transcriptomes (37,503 data points). Successive iterations were carried out to compute the gradient vector that converged the developed Protein-coding and Non-coding Region Identifier (PNRI) model to the approximate coefficient vector. The logistic regression algorithm was used with a sigmoid activation function. A parameter vector was estimated for every sample in 37,503 data points in a bid to reduce the generalization error and cost. Maximum Likelihood Estimation (MLE) was used for parameter estimation by taking the log-likelihood of six features and combining them into a summation function. Dynamic thresholding was used to classify the Protein-coding and Non-coding regions, and the Receiver Operating Characteristic (ROC) curve was determined. The generalization performance of PNRI was determined in terms of F1 score, accuracy, sensitivity, and specificity. The average generalization performance of PNRI was determined using a benchmark of multi-species organisms. The generalization error for identifying Protein-coding and Non-coding regions decreased from 0.514 to 0.508 and to 0.378, respectively, after three iterations. The cost (difference between the predicted and the actual outcome) also decreased from 1.446 to 0.842 and to 0.718, respectively, for the first, second and third iterations. The iterations terminated at the 390th epoch, having an error of 0.036 and a cost of 0.316. The computed elements of the parameter vector that maximized the objective function were 0.043, 0.519, 0.715, 0.878, 1.157, and 2.575. The PNRI gave an ROC of 0.97, indicating an improved predictive ability. The PNRI identified both Protein-coding and Non-coding regions with an F1 score of 0.970, accuracy (0.969), sensitivity (0.966), and specificity of 0.973. Using 13 non-human multi-species model organisms, the average generalization performance of the traditional method was 74.4%, while that of the developed model was 85.2%, thereby making the developed model better in the identification of Protein-coding and Non-coding regions in transcriptomes. The developed Protein-coding and Non-coding region identifier model efficiently identified the Protein-coding and Non-coding transcriptomic regions. It could be used in genome annotation and in the analysis of transcriptomes.

Keywords: sequence alignment-free model, dynamic thresholding classification, input randomization, genome annotation

Procedia PDF Downloads 68

Authors: Salah Ghamari

Abstract:

In this study, the ability of self organizing map artificial (SOM) neural networks in clustering the wheat seeds varieties according to morphological properties of them was considered. The SOM is one type of unsupervised competitive learning. Experimentally, five morphological features of 300 seeds (including three varieties: gaskozhen, Md and sardari) were obtained using image processing technique. The results show that the artificial neural network has a good performance (90.33% accuracy) in classification of the wheat varieties despite of high similarity in them. The highest classification accuracy (100%) was achieved for sardari.

Keywords: artificial neural networks, clustering, self organizing map, wheat variety

Procedia PDF Downloads 656

Authors: Güzi̇n Ti̇rkeş, Özge Teki̇n, Kerem Kurtuluş, Y. Yekta Yurtseven, Murat Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: convolutional neural networks, deep learning, image classification, scanning electron microscope

Procedia PDF Downloads 125

Authors: Xu Jiaqiao

Abstract:

Text sentiment analysis is an important branch of natural language processing. This technology is widely used in public opinion analysis and web surfing recommendations. At present, the mainstream sentiment analysis methods include three parts: sentiment analysis based on a sentiment dictionary, based on traditional machine learning, and based on deep learning. This paper mainly analyzes and compares the advantages and disadvantages of the SVM method of traditional machine learning and the Long Short-term Memory (LSTM) method of deep learning in the field of Chinese sentiment analysis, using Chinese comments on Sina Microblog as the data set. Firstly, this paper classifies and adds labels to the original comment dataset obtained by the web crawler, and then uses Jieba word segmentation to classify the original dataset and remove stop words. After that, this paper extracts text feature vectors and builds document word vectors to facilitate the training of the model. Finally, SVM and LSTM models are trained respectively. After accuracy calculation, it can be obtained that the accuracy of the LSTM model is 85.80%, while the accuracy of SVM is 91.07%. But at the same time, LSTM operation only needs 2.57 seconds, SVM model needs 6.06 seconds. Therefore, this paper concludes that: compared with the SVM model, the LSTM model is worse in accuracy but faster in processing speed.

Keywords: sentiment analysis, support vector machine, long short-term memory, Chinese microblog comments

Procedia PDF Downloads 94

Authors: Omer Burak Iskender, Keck Voon Ling, Vincent Dubanchet, Luca Simonini

Abstract:

This paper presents Guidance and Control (G&C) strategy to approach and synchronize with potentially rotating targets. The proposed strategy generates and tracks a safe trajectory for space servicing missions, including tasks like approaching, inspecting, and capturing. The main objective of this paper is to validate the G&C laws using a Hardware-In-the-Loop (HIL) setup with realistic rendezvous and docking equipment. Throughout this work, the assumption of full relative state feedback is relaxed by onboard sensors that bring realistic errors and delays and, while the proposed closed loop approach demonstrates the robustness to the above mentioned challenge. Moreover, G&C blocks are unified via the Model Predictive Control (MPC) paradigm, and the coupling between translational motion and rotational motion is addressed via dual quaternion based kinematic description. In this work, G&C is formulated as a convex optimization problem where constraints such as thruster limits and the output constraints are explicitly handled. Furthermore, the Monte-Carlo method is used to evaluate the robustness of the proposed method to the initial condition errors, the uncertainty of the target's motion and attitude, and actuator errors. A capture scenario is tested with the robotic test bench that has onboard sensors which estimate the position and orientation of a drifting satellite through camera imagery. Finally, the approach is compared with currently used robust H-infinity controllers and guidance profile provided by the industrial partner. The HIL experiments demonstrate that the proposed strategy is a potential candidate for future space servicing missions because 1) the algorithm is real-time implementable as convex programming offers deterministic convergence properties and guarantee finite time solution, 2) critical physical and output constraints are respected, 3) robustness to sensor errors and uncertainties in the system is proven, 4) couples translational motion with rotational motion.

Keywords: dual quaternion, model predictive control, real-time experimental test, rendezvous and docking, spacecraft autonomy, space servicing

Procedia PDF Downloads 146

Authors: Feng Guolin, Gong Zhiqiang

Abstract:

In order to study the spatial structure and dynamical mechanism of extreme precipitation in East Asia, a corresponding climate network is constructed by employing the method of event synchronization. It is found that the area of East Asian summer extreme precipitation can be separated into two regions: one with high area weighted connectivity receiving heavy precipitation mostly during the active phase of the East Asian Summer Monsoon (EASM), and another one with low area weighted connectivity receiving heavy precipitation during both the active and the retreat phase of the EASM. Besides，a way for the prediction of extreme precipitation is also developed by constructing a directed climate networks. The simulation accuracy in East Asia is 58% with a 0-day lead, and the prediction accuracy is 21% and average 12% with a 1-day and an n-day (2≤n≤10) lead, respectively. Compare to the normal EASM year, the prediction accuracy is lower in a weak year and higher in a strong year, which is relevant to the differences in correlations and extreme precipitation rates in different EASM situations. Recognizing and identifying these effects is good for understanding and predicting extreme precipitation in East Asia.

Keywords: synchronization, climate network, prediction, rainfall

Procedia PDF Downloads 442

Authors: Nahashon Mwirigi

Abstract:

The management of HIV/AIDS is a global challenge, demanding precise tools to predict disease progression and guide tailored treatment. CD4 cell count dynamics, a crucial immune function indicator, play an essential role in understanding HIV/AIDS progression and enhancing patient care through effective modeling. While several models assess disease progression, existing methods often fall short in capturing the complex, non-linear nature of HIV/AIDS, especially across diverse demographics. A need exists for models that balance predictive accuracy with clinical applicability, enabling individualized care strategies based on patient-specific progression rates. This study utilizes patient data from Kenyatta National Hospital (2003–2014) to model HIV/AIDS progression across six CD4-defined states. The Exponential, 2-Parameter Weibull, and 3-Parameter Weibull models are employed to analyze failure rates and explore progression patterns by age and gender. Model selection is based on Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) to identify models best representing disease progression variability across demographic groups. The 3-Parameter Weibull model emerges as the most effective, accurately capturing HIV/AIDS progression dynamics, particularly by incorporating delayed progression effects. This model reflects age and gender-specific variations, offering refined insights into patient trajectories and facilitating targeted interventions. One key finding is that older patients progress more slowly through CD4-defined stages, with a delayed onset of advanced stages. This suggests that older patients may benefit from extended monitoring intervals, allowing providers to optimize resources while maintaining consistent care. Recognizing slower progression in this demographic helps clinicians reduce unnecessary interventions, prioritizing care for faster-progressing groups. Gender-based analysis reveals that female patients exhibit more consistent progression, while male patients show greater variability. This highlights the need for gender-specific treatment approaches, as men may require more frequent assessments and adaptive treatment plans to address their variable progression. Tailoring treatment by gender can improve outcomes by addressing distinct risk patterns in each group. The model’s ability to account for both accelerated and delayed progression equips clinicians with a robust tool for estimating the duration of each disease stage. This supports individualized treatment planning, allowing clinicians to optimize antiretroviral therapy (ART) regimens based on demographic factors and expected disease trajectories. Aligning ART timing with specific progression patterns can enhance treatment efficacy and adherence. The model also has significant implications for healthcare systems, as its predictive accuracy enables proactive patient management, reducing the frequency of advanced-stage complications. For resource limited providers, this capability facilitates strategic intervention timing, ensuring that high-risk patients receive timely care while resources are allocated efficiently. Anticipating progression stages enhances both patient care and resource management, reinforcing the model’s value in supporting sustainable HIV/AIDS healthcare strategies. This study underscores the importance of models that capture the complexities of HIV/AIDS progression, offering insights to guide personalized, data-informed care. The 3-Parameter Weibull model’s ability to accurately reflect delayed progression and demographic risk variations presents a valuable tool for clinicians, supporting the development of targeted interventions and resource optimization in HIV/AIDS management.

Keywords: HIV/AIDS progression, 3-parameter Weibull model, CD4 cell count stages, antiretroviral therapy, demographic-specific modeling

Procedia PDF Downloads 8

Authors: Ching-Ting Hsu, Wei-Hua Ho, Yi-Chun Chang

Abstract:

Video object tracking is one of the popular research topics in computer graphics area. The trajectory can be applied in security, traffic control, even the sports training. The trajectory for sports training can be utilized to analyze the athlete’s performance without traditional sensors. There are many relevant works which utilize mean shift algorithm with background subtraction. This kind of the schemes should select a kernel function which may affect the accuracy and performance. In this paper, we consider the motion information in the pre-coded bitstream. The proposed algorithm extracts the trajectory by composing the motion vectors from the pre-coded bitstream. We gather the motion vectors from the overlap area of the object and calculate mean of the overlapped motion vectors. We implement and simulate our proposed algorithm in H.264 video codec. The performance is better than relevant works and keeps the accuracy of the object trajectory. The experimental results show that the proposed trajectory extraction can extract trajectory form the pre-coded bitstream in high accuracy and achieve higher performance other relevant works.

Keywords: H.264, video bitstream, video object tracking, sports training

Procedia PDF Downloads 428

Authors: Mohsen Farhadloo, Majid Farhadloo

Abstract:

Aspect-level opinion mining that aims at discovering aspects (aspect identification) and their corresponding ratings (sentiment identification) from customer reviews have increasingly attracted attention of researchers and practitioners as it provides valuable insights about products/services from customer's points of view. Instead of addressing aspect identification and sentiment identification in two separate steps, it is possible to simultaneously identify both aspects and sentiments. In recent years many graphical models based on Latent Dirichlet Allocation (LDA) have been proposed to solve both aspect and sentiment identifications in a single step. Although LDA models have been effective tools for the statistical analysis of document collections, they also have shortcomings in addressing some unique characteristics of opinion mining. Our goal in this paper is to address one of the limitations of topic models to date; that is, they fail to directly model the associations among topics. Indeed in many text corpora, it is natural to expect that subsets of the latent topics have higher probabilities. We propose a probabilistic graphical model called focus-LDA, to better capture the associations among topics when applied to aspect-level opinion mining. Our experiments on real-life data sets demonstrate the improved effectiveness of the focus-LDA model in terms of the accuracy of the predictive distributions over held out documents. Furthermore, we demonstrate qualitatively that the focus-LDA topic model provides a natural way of visualizing and exploring unstructured collection of textual data.

Keywords: aspect-level opinion mining, document modeling, Latent Dirichlet Allocation, LDA, sentiment analysis

Procedia PDF Downloads 94

Authors: K. Khaerunnisa, D. Ryangga, S. A. Pawiro

Abstract:

Over the past few decades, film dosimetry has become a tool which is used in various radiotherapy modalities, either for clinical quality assurance (QA) or dose verification. The response of the film to irradiation is usually expressed in optical density (OD) or net optical density (netOD). While the film's response to radiation is not linear, then the use of film as a dosimeter must go through a calibration process. This study aimed to compare the function of the calibration curve of various measurement methods with various densitometer, using a flat bad scanner, point densitometer and spectrophotometer. For every response function, a radichromic film calibration curve is generated from each method by performing accuracy, precision and sensitivity analysis. netOD is obtained by measuring changes in the optical density (OD) of the film before irradiation and after irradiation when using a film scanner if it uses ImageJ to extract the pixel value of the film on the red channel of three channels (RGB), calculate the change in OD before and after irradiation when using a point densitometer, and calculate changes in absorbance before and after irradiation when using a spectrophotometer. the results showed that the three calibration methods gave readings with a netOD precision of doses below 3% for the uncertainty value of 1σ (one sigma). while the sensitivity of all three methods has the same trend in responding to film readings against radiation, it has a different magnitude of sensitivity. while the accuracy of the three methods provides readings below 3% for doses above 100 cGy and 200 cGy, but for doses below 100 cGy found above 3% when using point densitometers and spectrophotometers. when all three methods are used for clinical implementation, the results of the study show accuracy and precision below 2% for the use of scanners and spectrophotometers and above 3% for precision and accuracy when using point densitometers.

Keywords: Callibration Methods, Film Dosimetry EBT3, Flat Bad Scanner, Densitomete, Spectrophotometer

Procedia PDF Downloads 135

Authors: Paria Soleimani, Arezoo Neshati

Abstract:

Myocardial infarction is one of the leading causes of ‎death in the world. Some of these deaths occur even before the patient ‎reaches the hospital. Myocardial infarction occurs as a result of ‎impaired blood supply. Because the most of these deaths are due to ‎coronary artery disease, hence the awareness of the warning signs of a ‎heart attack is essential. Some heart attacks are sudden and intense, but ‎most of them start slowly, with mild pain or discomfort, then early ‎detection and successful treatment of these symptoms is vital to save ‎them. Therefore, importance and usefulness of a system designing to ‎assist physicians in the early diagnosis of the acute heart attacks is ‎obvious.‎ The purpose of this study is to determine how well a predictive ‎model would perform based on the only patient-reportable clinical ‎history factors, without using diagnostic tests or physical exams. This ‎type of the prediction model might have application outside of the ‎hospital setting to give accurate advice to patients to influence them to ‎seek care in appropriate situations. For this purpose, the data were ‎collected on 711 heart patients in Iran hospitals. 28 attributes of clinical ‎factors can be reported by patients; were studied. Three logistic ‎regression models were made on the basis of the 28 features to predict ‎the risk of heart attacks. The best logistic regression model in terms of ‎performance had a C-index of 0.955 and with an accuracy of 94.9%. ‎The variables, severe chest pain, back pain, cold sweats, shortness of ‎breath, nausea, and vomiting were selected as the main features.‎

Keywords: Coronary heart disease, Acute heart attacks, Prediction, Logistic ‎regression‎

Procedia PDF Downloads 449

Authors: Frantisek Odvarka

Abstract:

Based on the data from the Moravian Karst, the influence of the calcite speleothem growth by selected meteorological factors was evaluated. External temperature was determined as one of the main factors influencing speleothem growth in Moravian Karst. This factor significantly influences the CO₂ concentration in soil/epikarst, and cave atmosphere in the Moravian Karst and significantly contributes to the changes in the CO₂ partial pressure differences between soil/epikarst and cave atmosphere in Moravian Karst, which determines the drip water supersaturation with respect to the calcite and quantity of precipitated calcite in the Moravian Karst cave environment. External air temperatures and cave air temperatures were measured using a COMET S3120 data logger, which can measure temperatures in the range from -30 to +80 °C with an accuracy of ± 0.4 °C. CO₂ concentrations in the cave and soils were measured with a FT A600 CO₂H Ahlborn probe (value range 0 ppmv to 10,000 ppmv, accuracy 1 ppmv), which was connected to the data logger ALMEMO 2290-4, V5 Ahlborn. The soil temperature was measured with a FHA646E1 Ahlborn probe (temperature range -20 to 70 °C, accuracy ± 0.4 °C) connected to an ALMEMO 2290-4 V5 Ahlborn data logger. The airflow velocities into and out of the cave were monitored by a FVA395 TH4 Thermo anemometer (speed range from 0.05 to 2 m s⁻¹, accuracy ± 0.04 m s⁻¹), which was connected to the ALMEMO 2590-4 V5 Ahlborn data logger for recording. The flow was measured in the lower and upper entrance of the Imperial Cave. The data were analyzed in MS Office Excel 2019 and PHREEQC.

Keywords: speleothem growth, carbon dioxide partial pressure, Moravian Karst, external temperature

Procedia PDF Downloads 144

Authors: Chung-Ming Lo, Kevin Li-Chun Hsieh

Abstract:

The central nervous system in the World Health Organization defines grade 2, 3, 4 gliomas according to the aggressiveness. For brain tumors, using image examination would have a lower risk than biopsy. Besides, it is a challenge to extract relevant tissues from biopsy operation. Observing the whole tumor structure and composition can provide a more objective assessment. This study further proposed a computer-aided diagnosis (CAD) system based on a convolutional neural network to quantitatively evaluate a tumor's malignancy from brain magnetic resonance imaging. A total of 30 grade 2, 43 grade 3, and 57 grade 4 gliomas were collected in the experiment. Transferred parameters from AlexNet were fine-tuned to classify the target brain tumors and achieved an accuracy of 98% and an area under the receiver operating characteristics curve (Az) of 0.99. Without pre-trained features, only 61% of accuracy was obtained. The proposed convolutional neural network can accurately and efficiently classify grade 2, 3, and 4 gliomas. The promising accuracy can provide diagnostic suggestions to radiologists in the clinic.

Keywords: convolutional neural network, computer-aided diagnosis, glioblastoma, magnetic resonance imaging

Procedia PDF Downloads 147

Authors: Cheng-Yu Tsai, Wen-Te Liu, Shin-Mei Hsu, Yin-Tzu Lin, Chi Wu

Abstract:

Background: Obstructive Sleep apnea syndrome (OSAS) is a common respiratory disorder during sleep. In addition, Body parameters were identified high predictive importance for OSAS severity. However, the effects of body parameters on OSAS severity remain unclear. Objective: In this study, the objective is to establish a prediction model for OSAS by using body parameters and investigate the effects of body parameters in OSAS. Methodologies: Severity was quantified as the polysomnography and the mean hourly number of greater than 3% dips in oxygen saturation during examination in a hospital in New Taipei City (Taiwan). Four levels of OSAS severity were classified by the apnea and hypopnea index (AHI) with American Academy of Sleep Medicine (AASM) guideline. Body parameters, including neck circumference, waist size, and body mass index (BMI) were obtained from questionnaire. Next, dividing the collecting subjects into two groups: training and testing groups. The training group was used to establish the random forest (RF) to predicting, and test group was used to evaluated the accuracy of classification. Results: There were 3330 subjects recruited in this study, whom had been done polysomnography for evaluating severity for OSAS. A RF of 1000 trees achieved correctly classified 79.94 % of test cases. When further evaluated on the test cohort, RF showed the waist and BMI as the high import factors in OSAS. Conclusion It is possible to provide patient with prescreening by body parameters which can pre-evaluate the health risks.

Keywords: apnea and hypopnea index, Body parameters, obstructive sleep apnea syndrome, Random Forest

Procedia PDF Downloads 153

Authors: Joseph Salim

Abstract:

This paper proposes the development of a supervised machine learning system to predict the consequences of untreated bruxism (teeth grinding) on gingival (gum) recession and jaw pain (most often bilateral jaw pain with possible headaches and limited ability to open the mouth). As a general dentist in a multi-specialty practice, the author has encountered many patients suffering from these issues due to uncontrolled bruxism (teeth grinding) at night. The most effective treatment for managing this problem involves wearing a nightguard during sleep and receiving therapeutic Botox injections to relax the muscles (the masseter muscle) responsible for grinding. However, some patients choose to postpone these treatments, leading to potentially irreversible and costlier consequences in the future. The proposed machine learning model aims to track patients who forgo the recommended treatments and assess the percentage of individuals who will experience worsening jaw pain, gingival (gum) recession, or both within a 3-to-5-year timeframe. By accurately predicting these outcomes, the model seeks to motivate patients to address the root cause proactively, ultimately saving time and pain while improving quality of life and avoiding much costlier treatments such as full-mouth rehabilitation to help recover the loss of vertical dimension of occlusion due to shortened clinical crowns because of bruxism, gingival grafts, etc.

Keywords: artificial intelligence, machine learning, predictive insights, bruxism, teeth grinding, therapeutic botox, nightguard, gingival recession, gum recession, jaw pain

Procedia PDF Downloads 93

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 7

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 139

Authors: Jie Xu, Zengshan Tian, Ze Li

Abstract:

Previous indoor ranging or localization systems achieving high accuracy time of flight (ToF) estimation relied on two key points. One is to do strict time and frequency synchronization between the transmitter and receiver to eliminate equipment asynchronous errors such as carrier frequency offset (CFO), but this is difficult to achieve in a practical communication system. The other one is to extend the total bandwidth of the communication because the accuracy of ToF estimation is proportional to the bandwidth, and the larger the total bandwidth, the higher the accuracy of ToF estimation obtained. For example, ultra-wideband (UWB) technology is implemented based on this theory, but high precision ToF estimation is difficult to achieve in common WiFi or Bluetooth systems with lower bandwidth compared to UWB. Therefore, it is meaningful to study how to achieve high-precision ranging with lower bandwidth when the transmitter and receiver are asynchronous. To tackle the above problems, we propose a two-way channel error elimination theory and a frequency hopping-based carrier phase ranging algorithm to achieve high accuracy ranging under asynchronous conditions. The two-way channel error elimination theory uses the symmetry property of the two-way channel to solve the asynchronous phase error caused by the asynchronous transmitter and receiver, and we also study the effect of the two-way channel generation time difference on the phase according to the characteristics of different hardware devices. The frequency hopping-based carrier phase ranging algorithm uses frequency hopping to extend the equivalent bandwidth and incorporates a carrier phase ranging algorithm with multipath resolution to achieve a ranging accuracy comparable to that of UWB at 400 MHz bandwidth in the typical 80 MHz bandwidth of commercial WiFi. Finally, to verify the validity of the algorithm, we implement this theory using a software radio platform, and the actual experimental results show that the method proposed in this paper has a median ranging error of 5.4 cm in the 5 m range, 7 cm in the 10 m range, and 10.8 cm in the 20 m range for a total bandwidth of 80 MHz.

Keywords: frequency hopping, phase error elimination, carrier phase, ranging

Procedia PDF Downloads 122

Authors: J. Carlos Kuri, Varun Vij, Raymond J. Turner, Orly Yadid-Pecht

Abstract:

Celiac disease (CD) is an immune system disorder that is triggered by ingesting gluten. As a gluten-free (GF) diet has become a concern of many people for health reasons, a gold standard had to be nominated. Enzyme-linked immunosorbent assay (ELISA) has taken the seat of this role. However, multiple limitations were discovered, and with that, the desire for an alternative method now exists. Nucleic acid-based aptamers have become of great interest due to their selectivity, specificity, simplicity, and rapid-testing advantages. However, fluorescence-based aptasensors have been tagged as unstable, but lifespan details are rarely stated. In this work, the lifespan stability of a fluorescence-based aptasensor is shown over an 8-week-long study displaying the accuracy of the sensor and false negatives. This study follows 22 different samples, including GF and gluten-rich (GR) and soy sauce products, off-the-shelf products, and reference material from laboratories, giving a total of 836 tests. The analysis shows an accuracy of correctly classifying GF and GR products of 96.30% and 100%, respectively when the protocol is augmented with molecular sieves. The overall accuracy remains around 94% within the first four weeks and then decays to 63%.

Keywords: aptasensor, PEG, rGO, FAM, RM, ELISA

Procedia PDF Downloads 124

Authors: Luis N. Pereira, Marco P. Carrasco

Abstract:

Dynamic pricing is a revenue management strategy in which hotel suppliers define, over time, flexible and different prices for their services for different potential customers, considering the profile of e-consumers and the demand and market supply. This means that the fundamentals of dynamic pricing are based on economic theory (price elasticity of demand) and market segmentation. This study aims to define a dynamic pricing strategy and a contextualized offer to the e-consumers profile in order to improve the number of reservations of an online distribution channel. Segmentation methods (hierarchical and non-hierarchical) were used to identify and validate an optimal number of market segments. A profile of the market segments was studied, considering the characteristics of the e-consumers and the probability of reservation a room. In addition, the price elasticity of demand was estimated for each segment using econometric models. Finally, predictive models were used to define rules for classifying new e-consumers into pre-defined segments. The empirical study illustrates how it is possible to improve the intelligence of an online distribution channel system through an optimal dynamic pricing strategy and a contextualized offer to the profile of each new e-consumer. A database of 11 million e-consumers of an online distribution channel was used in this study. The results suggest that an appropriate policy of market segmentation in using of online reservation systems is benefit for the service suppliers because it brings high probability of reservation and generates more profit than fixed pricing.

Keywords: dynamic pricing, e-consumers segmentation, online reservation systems, predictive analytics

Procedia PDF Downloads 234

Authors: Gehad S. Kaseb, Mona F. Ahmed

Abstract:

Arabic Sentiment Analysis (SA) is one of the most common research fields with many open areas. Few studies apply SA to Arabic dialects. This paper proposes different pre-processing steps and a modified methodology to improve the accuracy using normal Support Vector Machine (SVM) classification. The paper works on two datasets, Arabic Sentiment Tweets Dataset (ASTD) and Extended Arabic Tweets Sentiment Dataset (Extended-AATSD), which are publicly available for academic use. The results show that the classification accuracy approaches 86%.

Keywords: Arabic, classification, sentiment analysis, tweets

Procedia PDF Downloads 149

Authors: Raúl Pereda García, Julio Manuel de Luis Ruiz, Elena Castillo López, Rubén Pérez Álvarez, Felipe Piña García

Abstract:

New technologies for the capture of point clouds have experienced a great advance in recent years. In this way, its use has been extended in geomatics, providing measurement solutions that have been popularized without there being, many times, a detailed study of its accuracy. This research focuses on the study of the viability of topographic works with drones incorporating different sensors sensitive to the visible spectrum. The fundamentals have been applied to a road, located in Cantabria (Spain), where a platform extension and the reform of a riprap were being constructed. A total of six flights were made during two months, all of them with GPS as part of the photogrammetric process, and the results were contrasted with those measured with total station. The obtained results show that the choice of the camera and the planning of the flight have an important impact on the accuracy. In fact, the representations with a level of detail corresponding to 1/1000 scale are admissible, depending on the existing vegetation, and obtaining better results in the area of the riprap. This set of techniques is, therefore, suitable for the control of earthworks in road works but with certain limitations which are exposed in this paper.

Keywords: drone, earth movement control, global position system, surveying technology.

Procedia PDF Downloads 184

Authors: Syed Basit Ali Shah Bukhari, Yan Qiang, Saad Abdul Rauf, Syed Saqlaina Bukhari

Abstract:

Text Classification is the methodology to classify any given text into the respective category from a given set of categories. It is highly important and vital to use proper set of pre-processing , feature selection and classification techniques to achieve this purpose. In this paper we have used different ensemble techniques along with variance in feature selection parameters to see the change in overall accuracy of the result and also on some other individual class based features which include precision value of each individual category of the text. After subjecting our data through pre-processing and feature selection techniques , different individual classifiers were tested first and after that classifiers were combined to form ensembles to increase their accuracy. Later we also studied the impact of decreasing the classification categories on over all accuracy of data. Text classification is highly used in sentiment analysis on social media sites such as twitter for realizing people’s opinions about any cause or it is also used to analyze customer’s reviews about certain products or services. Opinion mining is a vital task in data mining and text categorization is a back-bone to opinion mining.

Keywords: Natural Language Processing, Ensemble Classifier, Bagging Classifier, AdaBoost

Procedia PDF Downloads 232

Authors: Srinivas Peri, Siva Abhishek Sirivella, Tejaswini Kallakuri, Uzair Ahmad

Abstract:

Smart cities and intelligent transportation systems rely heavily on effective traffic management and infrastructure planning. This research tackles the data scarcity challenge by generating realistically synthetic traffic data from the PeMS-Bay dataset, enhancing predictive modeling accuracy and reliability. Advanced techniques like TimeGAN and GaussianCopula are utilized to create synthetic data that mimics the statistical and structural characteristics of real-world traffic. The future integration of Spatial-Temporal Generative Adversarial Networks (ST-GAN) is anticipated to capture both spatial and temporal correlations, further improving data quality and realism. Each synthetic data generation model's performance is evaluated against real-world data to identify the most effective models for accurately replicating traffic patterns. Long Short-Term Memory (LSTM) networks are employed to model and predict complex temporal dependencies within traffic patterns. This holistic approach aims to identify areas with low vehicle counts, reveal underlying traffic issues, and guide targeted infrastructure interventions. By combining GAN-based synthetic data generation with LSTM-based traffic modeling, this study facilitates data-driven decision-making that improves urban mobility, safety, and the overall efficiency of city planning initiatives.

Keywords: GAN, long short-term memory (LSTM), synthetic data generation, traffic management

Procedia PDF Downloads 14

Authors: Najmeh Mohsenifar, Narjes Mohsenifar, Abbas Kargar

Abstract:

In this paper, has been presented a stable method for predicting the ECG signals through the RBF neural networks, by the PSO algorithm. In spite of quasi-periodic ECG signal from a healthy person, there are distortions in electro cardiographic data for a patient. Therefore, there is no precise mathematical model for prediction. Here, we have exploited neural networks that are capable of complicated nonlinear mapping. Although the architecture and spread of RBF networks are usually selected through trial and error, the PSO algorithm has been used for choosing the best neural network. In this way, 2 second of a recorded ECG signal is employed to predict duration of 20 second in advance. Our simulations show that PSO algorithm can find the RBF neural network with minimum MSE and the accuracy of the predicted ECG signal is 97 %.

Keywords: electrocardiogram, RBF artificial neural network, PSO algorithm, predict, accuracy

Procedia PDF Downloads 627

Authors: Parshanth Maroju, Ramandeep Behl, Sandile S. Motsa

Abstract:

In this study, we proposed a simple and interesting family of fourth-order multi-point methods without memory for obtaining simple roots. This family requires only three functional evaluations (viz. two of functions f(xn), f(yn) and third one of its first-order derivative f'(xn)) per iteration. Moreover, the accuracy and validity of new schemes is tested by a number of numerical examples are also proposed to illustrate their accuracy by comparing them with the new existing optimal fourth-order methods available in the literature. It is found that they are very useful in high precision computations. Further, the dynamic study of these methods also supports the theoretical aspect.

Keywords: basins of attraction, nonlinear equations, simple roots, Newton's method

Procedia PDF Downloads 312

Authors: Bongs Lainjo

Abstract:

The evolution and escalation of bike-sharing programs (BSP) continue unabated. Since the sixties, many countries have introduced different models and strategies of BSP. These include variations ranging from dockless models to electronic real-time monitoring systems. Reasons for using this BSP include recreation, errands, work, etc. And there is all indication that complex, and more innovative rider-friendly systems are yet to be introduced. The objective of this paper is to analyze current variables established by different operators and streamline them identifying the most compelling ones using analytics. Given the contents of available databases, there is a lack of uniformity and common standard on what is required and what is not. Two factors appear to be common: user type (registered and unregistered, and duration of each trip). This article uses historical data provided by one operator based in the greater Washington, District of Columbia, USA area. Several variables including categorical and continuous data types were screened. Eight out of 18 were considered acceptable and significantly contribute to determining a useful and reliable predictive model. Bike-sharing systems have become popular in recent years all around the world. Although this trend has resulted in many studies on public cycling systems, there have been few previous studies on the factors influencing public bicycle travel behavior. A bike-sharing system is a computer-controlled system in which individuals can borrow bikes for a fee or free for a limited period. This study has identified unprecedented useful, and pragmatic parameters required in improving BSP ridership dynamics.

Keywords: sharing program, historical data, parameters, ridership dynamics, trip duration

Procedia PDF Downloads 138

Authors: Ewa M. Laskowska, Jorn Vatn

Abstract:

Industry 4.0 focuses on digital optimization of industrial processes. The idea is to use extracted data in order to build a decision support model enabling use of those data for real time decision making. In terms of predictive maintenance, the desired decision support tool would be a model enabling prognostics of system's health based on the current condition of considered equipment. Within area of system prognostics and health management, a commonly used health indicator is Remaining Useful Lifetime (RUL) of a system. Because the RUL is a random variable, it has to be estimated based on available health indicators. Health indicators can be of different types and come from different sources. They can be process variables, equipment performance variables, data related to number of experienced failures, etc. The aim of this study is the analysis of performance variables of emergency shutdown valves (ESV) used in oil and gas industry. ESV is inspected periodically, and at each inspection torque and time of valve operation are registered. The data will be analyzed by means of machine learning or statistical analysis. The purpose is to investigate whether the available data could be used as a health indicator for a prognostic purpose. The second objective is to examine what is the most efficient way to incorporate the data into predictive model. The idea is to check whether the data can be applied in form of explanatory variables in Markov process or whether other stochastic processes would be a more convenient to build an RUL model based on the information coming from registered data.

Keywords: emergency shutdown valves, health indicator, prognostics, remaining useful lifetime, RUL

Procedia PDF Downloads 91

Authors: Morten Brøgger, Kim Wittchen

Abstract:

Focus on reducing energy consumption in existing buildings at large scale, e.g. in cities or countries, has been increasing in recent years. In order to reduce energy consumption in existing buildings, political incentive schemes are put in place and large scale investments are made by utility companies. Prioritising these investments requires a comprehensive overview of the energy consumption in the existing building stock, as well as potential energy-savings. However, a building stock comprises thousands of buildings with different characteristics making it difficult to model energy consumption accurately. Moreover, the complexity of the building stock makes it difficult to convey model results to policymakers and other stakeholders. In order to manage the complexity of the building stock, building archetypes are often employed in building stock energy models (BSEMs). Building archetypes are formed by segmenting the building stock according to specific characteristics. Segmenting the building stock according to building type and building age is common, among other things because this information is often easily available. This segmentation makes it easy to convey results to non-experts. However, using a single archetypical building to represent all buildings in a segment of the building stock is associated with loss of detail. Thermal characteristics are aggregated while other characteristics, which could affect the energy efficiency of a building, are disregarded. Thus, using a simplified representation of the building stock could come at the expense of the accuracy of the model. The present study evaluates the accuracy of a conventional archetype-based BSEM that segments the building stock according to building type- and age. The accuracy is evaluated in terms of the archetypes’ ability to accurately emulate the average energy demands of the corresponding buildings they were meant to represent. This is done for the buildings’ energy demands as a whole as well as for relevant sub-demands. Both are evaluated in relation to the type- and the age of the building. This should provide researchers, who use archetypes in BSEMs, with an indication of the expected accuracy of the conventional archetype model, as well as the accuracy lost in specific parts of the calculation, due to use of the archetype method.

Keywords: building stock energy modelling, energy-savings, archetype

Procedia PDF Downloads 154

Authors: Vandna Raghuvanshi, Vikrant Thakur, Anupam Jhobta

Abstract:

Objective: To design HRCT criterion to forecast the threat of pulmonary tuberculosis. Material and methods: This was a prospective study of 69 patients with clinical suspicion of pulmonary tuberculosis. We studied their medical characteristics, numerous separate HRCT-results, and a combination of HRCT findings to foresee the danger for PTB by utilizing univariate and multivariate investigation. Temporary HRCT diagnostic criteria were planned in view of these outcomes to find out the risk of PTB and tested these criteria on our patients. Results: The results of HRCT chest were analyzed, and Rank was given from 1 to 4 according to the HRCT chest findings. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated. Rank 1: Highly suspected PTB. Rank 2: Probable PTB Rank 3: Nonspecific or difficult to differentiate from other diseases Rank 4: Other suspected diseases • Rank 1 (Highly suspected TB) was present in 22 (31.9%) patients, all of them finally diagnosed to have pulmonary tuberculosis. The sensitivity, specificity, and negative likelihood ratio for RANK 1 on HRCT chest was 53.6%, 100%, and 0.43, respectively. • Rank 2 (Probable TB) was present in 13 patients, out of which 12 were tubercular, and 1 was non-tubercular. • The sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of the combination of Rank 1 and Rank 2 was 82.9%, 96.4%, 23.22, and 0.18, respectively. • Rank 3 (Non-specific TB) was present in 25 patients, and out of these, 7 were tubercular, and 18 were non-tubercular. • When all these 3 ranks were considered together, the sensitivity approached 100% however, the specificity reduced to 35.7%. The positive likelihood ratio and negative likelihood ratio were 1.56 and 0, respectively. • Rank 4 (Other specific findings) was given to 9 patients, and all of these were non-tubercular. Conclusion: HRCT is useful in selecting individuals with greater chances of pulmonary tuberculosis.

Keywords: pulmonary, tuberculosis, multivariate, HRCT

Procedia PDF Downloads 172