Search results for: precision seeding

Authors: Diana Gomez-Cano, J. C. Ochoa-Botero, Roberto Bernal Correa, Yhan Paul Arias

Abstract:

To obtain high mechanical performance, the fresh conditions of a mortar are decisive. Measuring the absorption of aggregates used in mortar mixes is a fundamental requirement for proper design of the mixes prior to their placement in construction sites. In this sense, absorption is a determining factor in the design of a mix because it conditions the amount of water, which in turn affects the water/cement ratio and the final porosity of the mortar. Thus, this work focuses on the mechanical behavior of recycled mortars manufactured from moisture correction using the Thermogravimetric Balancing Halogen Light (TBHL) technique in comparison with the traditional ASTM C 128 International Standard method. The advantages of using the TBHL technique are favorable in terms of reduced consumption of resources such as materials, energy, and time. The results show that in contrast to the ASTM C 128 method, the TBHL alternative technique allows obtaining a higher precision in the absorption values of recycled aggregates, which is reflected not only in a more efficient process in terms of sustainability in the characterization of construction materials but also in an effect on the mechanical performance of recycled mortars.

Keywords: alternative raw materials, halogen light, recycled mortar, resources optimization, water absorption

Procedia PDF Downloads 110

Authors: Candra Irawan, David Yudianto, Ahsanu Nadiyya, Dewi Anna Br Sitepu, Hanafi, Erna Styani

Abstract:

Jelly drink was produced from a combination of both natural and synthetic materials, such as acesulfame potassium (acesulfame-K) as synthetic sweetener material. Acesulfame-K content in jelly drink could be determined by High-Performance Liquid Chromatography (HPLC), but this method needed validation due to having a change on the reagent addition step which skips the carrez addition and comparison of mix mobile phase (potassium dihydrogen phosphate and acetonitrile) with ratio from 75:25 to 90:10 to be more efficient and cheap. This study was conducted to evaluate the performance of determination method for acesulfame-K content in the jelly drink by HPLC. The method referred to Deutsches Institut fur Normung European Standard International Organization for Standardization (DIN EN ISO):12856 (1999) about Foodstuffs, Determination of acesulfame-K, aspartame and saccharin. The result of the correlation coefficient value (r) on the linearity test was 0.9987 at concentration range 5-100 mg/L. Detection limit value was 0.9153 ppm, while the quantitation limit value was 1.1932 ppm. The recovery (%) value on accuracy test for sample concentration by spiking 100 mg/L was 102-105%. Relative Standard Deviation (RSD) value for precision and homogenization tests were 2.815% and 4.978%, respectively. Meanwhile, the comparative and stability tests were tstat (0.136) < ttable (2.101) and |µ1-µ2| (1.502) ≤ 0.3×CV Horwitz. Obstinacy test value was tstat < ttable. It can be concluded that the HPLC  method for the determination of acesulfame-K in jelly drink product by HPLC has been valid and can be used for analysis with good performance.

Keywords: acesulfame-K, jelly drink, HPLC, validation

Procedia PDF Downloads 125

Authors: Ghulam Haider Haidaree, Nsenda Lukumwena

Abstract:

Today the world of research enjoys abundant data, available in virtually any field, technology, science, and business, politics, etc. This is commonly referred to as big data. This offers a great deal of precision and accuracy, supportive of an in-depth look at any decision-making process. When and if well used, Big Data affords its users with the opportunity to produce substantially well supported and good results. This paper leans extensively on big data to investigate possible smart solutions to urban mobility and related issues, namely road traffic accidents, its casualties, and fatalities based on multiple factors, including age, gender, location occurrences of accidents, etc. Multiple technologies were used in combination to produce an Information Communication Technology (ICT) based solution with embedded technology. Those technologies include principally Geographic Information System (GIS), Orange Data Mining Software, Bayesian Statistics, to name a few. The study uses the Leeds accident 2016 to illustrate the thinking process and extracts thereof a model that can be tested, evaluated, and replicated. The authors optimistically believe that the proposed model will significantly and smartly help to flatten the curve of road traffic accidents in the fast-growing population densities, which increases considerably motor-based mobility.

Keywords: accident factors, geographic information system, information communication technology, mobility

Procedia PDF Downloads 204

Authors: Mohamed Mahmoud Hasan, Hoda M. O. Mokhtar

Abstract:

With the gigantic increment in portable applications use and the spread of positioning and location-aware technologies that we are seeing today, new procedures and methodologies for location-based strategies are required. Location recommendation is one of the highly demanded location-aware applications uniquely with the wide accessibility of social network applications that are location-aware including Facebook check-ins, Foursquare, and others. In this paper, we aim to present a new methodology for location recommendation. The proposed approach coordinates customary spatial traits alongside other essential components including shortest distance, and user interests. We also present another idea namely, "activity trajectory" that represents trajectory that fulfills the set of activities that the user is intrigued to do. The approach dispatched acquaints the related distance value to select trajectory(ies) with minimum cost value (distance) and spatial-area to prune unneeded directions. The proposed calculation utilizes the idea of movement direction to prescribe most comparable N-trajectory(ies) that matches the client's required action design with least voyaging separation. To upgrade the execution of the proposed approach, parallel handling is applied through the employment of a MapReduce based approach. Experiments taking into account genuine information sets were built up and tested for assessing the proposed approach. The exhibited tests indicate how the proposed approach beets different strategies giving better precision and run time.

Keywords: location based recommendation, map-reduce, recommendation system, trajectory search

Procedia PDF Downloads 219

Authors: Alok S Chauhan, Sridhar S., Pradyumna R.

Abstract:

In the process of precision investment casting of turbine hollow blade/vane components, a part of the dimensional deviations observed in the castings can be attributed to the wax pattern. In the process of injection moulding of wax to produce patterns, heated wax shrinks in size during cooling in the die, leading to a reduction in the dimensions of the pattern. Also, flow and thermal induced residual stresses result in shrinkage & warpage of the component after removal from the die, further adding to the deviations. Injection moulding parameters such as wax temperature, flow rate, packing pressure, etc. affect the flow and thermal behavior of the component and hence are directly responsible for the dimensional deviations. There is a need to precisely determine and control these deviations in order to achieve stringent dimensional accuracies imposed on these castings by aerospace standards. Simulation based approaches provide a platform to predict these dimensional deviations without resorting to elaborate experimentation. In the present paper, Moldex3D simulation package has been utilized to analyze the effect of variations in injection temperature, packing pressure and cooling time on the shrinkage behavior of a stepped pattern. Two types of waxes with different rheological properties have been included in the study to gauge the effect of change in wax on the dimensional deviations. A full factorial design of experiments has been configured with these parameters and results of analysis of variance have been presented.

Keywords: wax patterns, investment casting, pattern die/mould, wax injection, Moldex3D simulation

Procedia PDF Downloads 366

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 137

Authors: Eva Tolmeijer, Emmanuelle Peters, Veena Kumari, Liam Mason

Abstract:

Cognitive behavioral therapy for psychosis (CBTp) is effective in many but not all patients, making it important to better understand the factors that determine treatment outcomes. To date, no studies have examined whether neuroimaging can make clinically useful predictions about who will respond to CBTp. To this end, we used machine learning methods that make predictions about symptom improvement at the individual patient level. Prior to receiving CBTp, 22 patients with a diagnosis of schizophrenia completed a social-affective processing task during functional MRI. Multivariate pattern analysis assessed whether treatment response could be predicted by brain activation responses to facial affect that was either socially threatening or prosocial. The resulting models did significantly predict symptom improvement, with distinct multivariate signatures predicting psychotic (r=0.54, p=0.01) and affective (r=0.32, p=0.05) symptoms. Psychotic symptom improvement was accurately predicted from relatively focal threat-related activation across hippocampal, occipital, and temporal regions; affective symptom improvement was predicted by a more dispersed profile of responses to prosocial affect. These findings enrich our understanding of the neurobiological underpinning of treatment response. This study provides a foundation that will hopefully lead to greater precision and tailoring of the interventions offered to patients.

Keywords: cognitive behavioral therapy, machine learning, psychosis, schizophrenia

Procedia PDF Downloads 273

Authors: Chia-Jung Li, Li-Te Lin, Kuan-Hao Tsui

Abstract:

The study identifies SPP1 as a potential gene associated with ovarian aging, revealing a significant decline in its expression in aged ovaries. SPP1, also known as osteopontin (OPN), is a multifunctional glycoprotein involved with regulatory proteins and pro-inflammatory immune chemokines. However, its genetic links to ovarian aging have not been extensively explored. Spatial transcriptomic analyses were conducted on ovaries from young and aged female mice, along with a sample from a 73-year-old individual. Additionally, single-cell RNA sequencing analysis was performed to identify associations between SPP1 and key genes. The study focused on crucial genes, including ITGAV, ITGB1, CD44, MMP3, and FN1, with a particular emphasis on the correlation between SPP1 and ITGB1. The findings indicate a significant decline in SPP1 expression in aged ovaries, which was consistent in the 73-year-old sample. Single-cell RNA sequencing unveiled associations between SPP1 and key genes, emphasizing a strong co-expression correlation between SPP1 and ITGB1. While the study provides valuable insights, further research is necessary to understand the broader implications and potential applications of SPP1 in ovarian aging. Translating these findings to clinical settings requires careful consideration. The identification of SPP1 as a gene implicated in ovarian aging opens new avenues for advancing precision medicine and refining treatment strategies for conditions related to ovarian aging.

Keywords: SPP1, ovarian aging, spatial transcriptomic, single-cell RNA sequencing

Procedia PDF Downloads 29

Authors: Nazli Uren, Ayse Okur

Abstract:

Tactile comfort of a textile product is an essential property and a major concern when it comes to customer perceptions and preferences. The subjective nature of comfort and the difficulties regarding the simulation of human hand sensory feelings make it hard to establish a well-accepted link between tactile comfort and objective evaluations. On the other hand, shear behavior of a fabric is a mechanical parameter which can be measured by various objective test methods. The principal aim of this study is to determine the tactile comfort of commercially available denim fabrics by subjective measurements, create a tactile score database for denim fabrics and investigate the relations between tactile comfort and shear behavior. In-plane shear behaviors of 17 different commercially available denim fabrics with a variety of raw material and weave structure were measured by a custom design shear frame and conventional bias extension method in two corresponding diagonal directions. Tactile comfort of denim fabrics was determined via subjective customer evaluations as well. Aforesaid relations were statistically investigated and introduced as regression equations. The analyses regarding the relations between tactile comfort and shear behavior showed that there are considerably high correlation coefficients. The suggested regression equations were likewise found out to be statistically significant. Accordingly, it was concluded that the tactile comfort of denim fabrics can be estimated with a high precision, based on the results of in-plane shear behavior measurements.

Keywords: denim fabrics, in-plane shear behavior, linear regression estimation, tactile comfort

Procedia PDF Downloads 296

Authors: Lingling Shui, Shuting Xie

Abstract:

As alternatives to electronic devices, optically active structures from responsive nanomaterials offer great opportunity buildup smart functional sensors. Hereby, we report on droplet microfluidics enabled construction and application of photonic microcapsules (PMCs) for colorimetric temperature microsensors, enabling miniaturization for injectable local micro-area sensing and integration for large-area sensing. Monodispersed PMCs are produced by in-situ photopolymerization of hydrogel shells of cholesteric liquid crystal (CLC)-in-water-in-oil double emulsion droplets prepared using microfluidic devices, with controllable physical structures and chemical compositions. Constructed PMCs exhibit thermal responsive structural color according to the selective Bragg reflection of CLC’s periodical helical structures within the microdroplet’s spherical confinement. Constructed PMCs with tunable size and composition have been successfully applied for monitoring the living cell extracellular temperature via co-incubation with cell suspension, and for detecting human body temperature via a flexible device from assembled PMCs. These PMCs could be flexibly applied in either micro-environment or large-area surface, enabling wide applications for precision temperature monitoring biological activities (e.g. cells or organs), optoelectronic devices working conditions (e.g. temperature indicators under extreme conditions), and etc.

Keywords: droplet, microfluidics, assembly, soft materials, microsensor

Procedia PDF Downloads 77

Authors: Mohammad Tayefeh Norooz, Amirhossein Kargarzadeh

Abstract:

Overweight and obesity as an abnormality are health threatening factors. Body mass index (BMI) above 25 is referred to as overweight and above 30 as obese. Apollo Endosurgery, Inc., a pioneering company in endoscopy surgeries, is poised to revolutionize patient care with its minimally invasive treatment options. Some product solutions are designed to improve patient outcomes and redefine the future of healthcare. Weight gain post-weight-loss surgery may stem from an enlarged stomach opening, reducing fullness and increasing food intake. Apollo Endosurgery's OverStitch system, a minimally invasive approach, addresses this by using sutures to reduce stomach opening size. This reflects Apollo's commitment to transformative improvements in healing endoscopy, emphasizing a shift towards minimally invasive options. The system's versatility and precision in full-thickness suturing offer treatment alternatives, exemplified in applications like Endoscopic Sleeve Gastroplasty for reshaping obesity management. Apollo’s dedication to pioneering advancements suggests ongoing breakthroughs in minimally invasive surgery, positioning the OverStitch systems as a testament to innovation in patient care.

Keywords: apollo endosurgery, endoscopic sleeve gastroplasty, weight loss system, overstitch endoscopic suturing system, therapeutic, perforations, fistula

Procedia PDF Downloads 55

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 51

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: consensus, curse of correlation, imbalance classification, rank-based chain-mode ensemble

Procedia PDF Downloads 133

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 175

Authors: S. Aswath, Chinmaya Krishna Tilak, Amal Suresh, Ganesh Udupa

Abstract:

There are technologies to control a humanoid robot in many ways. But the use of Electromyogram (EMG) electrodes has its own importance in setting up the control system. The EMG based control system helps to control robotic devices with more fidelity and precision. In this paper, development of an electromyogram based interface for human gesture recognition for the control of a humanoid robot is presented. To recognize control signs in the gestures, a single channel EMG sensor is positioned on the muscles of the human body. Instead of using a remote control unit, the humanoid robot is controlled by various gestures performed by the human. The EMG electrodes attached to the muscles generates an analog signal due to the effect of nerve impulses generated on moving muscles of the human being. The analog signals taken up from the muscles are supplied to a differential muscle sensor that processes the given signal to generate a signal suitable for the microcontroller to get the control over a humanoid robot. The signal from the differential muscle sensor is converted to a digital form using the ADC of the microcontroller and outputs its decision to the CM-530 humanoid robot controller through a Zigbee wireless interface. The output decision of the CM-530 processor is sent to a motor driver in order to control the servo motors in required direction for human like actions. This method for gaining control of a humanoid robot could be used for performing actions with more accuracy and ease. In addition, a study has been conducted to investigate the controllability and ease of use of the interface and the employed gestures.

Keywords: electromyogram, gesture, muscle sensor, humanoid robot, microcontroller, Zigbee

Procedia PDF Downloads 403

Authors: Saad M. Darwish, Mohamed A. El-Iskandarani, Guitar M. Shawkat

Abstract:

Nowadays, the amount of available multimedia data is continuously on the rise. The need to find a required image for an ordinary user is a challenging task. Content based image retrieval (CBIR) computes relevance based on the visual similarity of low-level image features such as color, textures, etc. However, there is a gap between low-level visual features and semantic meanings required by applications. The typical method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, a multi-label image annotation system guided by Firefly and Bayesian method is proposed. Firstly, images are segmented using the maximum variance intra cluster and Firefly algorithm, which is a swarm-based approach with high convergence speed, less computation rate and search for the optimal multiple threshold. Feature extraction techniques based on color features and region properties are applied to obtain the representative features. After that, the images are annotated using translation model based on the Net Bayes system, which is efficient for multi-label learning with high precision and less complexity. Experiments are performed using Corel Database. The results show that the proposed system is better than traditional ones for automatic image annotation and retrieval.

Keywords: feature extraction, feature selection, image annotation, classification

Procedia PDF Downloads 582

Authors: S. Visetpotjanakit, N. Nakkaew

Abstract:

Determination of ⁹⁰Sr in environmental samples has been widely developed with several radioanlytical methods and radiation measurement techniques since ⁹⁰Sr is one of the most hazardous radionuclides produced from nuclear reactors. Liquid extraction technique using di-(2-ethylhexyl) phosphoric acid (HDEHP) to separate and purify ⁹⁰Y and Cherenkov counting using liquid scintillation counter to determine ⁹⁰Y in secular equilibrium to ⁹⁰Sr was developed and performed at our institute, the Office of Atoms for Peace. The approach is inexpensive, non-laborious, and fast to analyse ⁹⁰Sr in environmental samples. To validate our analytical performance for the accurate and precise criteria, determination of ⁹⁰Sr using the IAEA-TEL-2016-04 ALMERA proficiency test samples were performed for statistical evaluation. The experiment used two spiked tap water samples and one naturally contaminated spruce needles sample from Austria collected shortly after the Chernobyl accident. Results showed that all three analyses were successfully passed in terms of both accuracy and precision criteria, obtaining “Accepted” statuses. The two water samples obtained the measured results of 15.54 Bq/kg and 19.76 Bq/kg, which had relative bias 5.68% and -3.63% for the Maximum Acceptable Relative Bias (MARB) 15% and 20%, respectively. And the spruce needles sample obtained the measured results of 21.04 Bq/kg, which had relative bias 23.78% for the MARB 30%. These results confirm our analytical performance of ⁹⁰Sr determination in water and spruce needles samples using the same developed method.

Keywords: ALMERA proficiency test, Cerenkov counting, determination of 90Sr, environmental samples

Procedia PDF Downloads 227

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 112

Authors: Dionisio Andujar, Juan lópez-Correa, Hugo Moreno, Angela Ri

Abstract:

The increased number of weeds in tomato crops highly lower yields. Weed identification with the aim of machine learning is important to carry out site-specific control. The last advances in computer vision are a powerful tool to face the problem. The analysis of RGB (Red, Green, Blue) images through Artificial Neural Networks had been rapidly developed in the past few years, providing new methods for weed classification. The development of the algorithms for crop and weed species classification looks for a real-time classification system using Object Detection algorithms based on Convolutional Neural Networks. The site study was located in commercial corn fields. The classification system has been tested. The procedure can detect and classify weed seedlings in tomato fields. The input to the Neural Network was a set of 10,000 RGB images with a natural infestation of Cyperus rotundus l., Echinochloa crus galli L., Setaria italica L., Portulaca oeracea L., and Solanum nigrum L. The validation process was done with a random selection of RGB images containing the aforementioned species. The mean average precision (mAP) was established as the metric for object detection. The results showed agreements higher than 95 %. The system will provide the input for an online spraying system. Thus, this work plays an important role in Site Specific Weed Management by reducing herbicide use in a single step.

Keywords: deep learning, object detection, cnn, tomato, weeds

Procedia PDF Downloads 97

Authors: Zoran Šverko, Saša Vlahinić, Nino Stojković, Ivan Markovinović

Abstract:

In this article, the classification of target letters is performed using data from the EEG P300 Speller paradigm. Neural networks trained with the results of dynamic connectivity analysis between different brain regions are used for classification. Dynamic connectivity analysis is based on the adaptive window size and the imaginary part of the complex Pearson correlation coefficient. Brain dynamics are analysed using the relative intersection of confidence intervals for the imaginary component of the complex Pearson correlation coefficient method (RICI-imCPCC). The RICI-imCPCC method overcomes the shortcomings of currently used dynamical connectivity analysis methods, such as the low reliability and low temporal precision for short connectivity intervals encountered in constant sliding window analysis with wide window size and the high susceptibility to noise encountered in constant sliding window analysis with narrow window size. This method overcomes these shortcomings by dynamically adjusting the window size using the RICI rule. This method extracts information about brain connections for each time sample. Seventy percent of the extracted brain connectivity information is used for training and thirty percent for validation. Classification of the target word is also done and based on the same analysis method. As far as we know, through this research, we have shown for the first time that dynamic connectivity can be used as a parameter for classifying EEG signals.

Keywords: dynamic connectivity analysis, EEG, neural networks, Pearson correlation coefficients

Procedia PDF Downloads 207

Authors: Roberto Machado

Abstract:

We conducted a systematic review using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses methodology, analyzing 2,996 studies and synthesizing 41 of them to explore the evolution of data science and its integration into geography. By employing optimization algorithms, we accelerated the review process, significantly enhancing the efficiency and precision of literature selection. Our findings indicate that data science has developed over five decades, facing challenges such as the diversified integration of data and the need for advanced statistical and computational skills. In geography, the integration of data science underscores the importance of interdisciplinary collaboration and methodological innovation. Techniques like large-scale spatial data analysis and predictive algorithms show promise in natural disaster management and transportation route optimization, enabling faster and more effective responses. These advancements highlight the transformative potential of data science in geography, providing tools and methodologies to address complex spatial problems. The relevance of this study lies in the use of optimization algorithms in systematic reviews and the demonstrated need for deeper integration of data science into geography. Key contributions include identifying specific challenges in combining diverse spatial data and the necessity for advanced computational skills. Examples of connections between these two fields encompass significant improvements in natural disaster management and transportation efficiency, promoting more effective and sustainable environmental solutions with a positive societal impact.

Keywords: data science, geography, systematic review, optimization algorithms, supervised learning

Procedia PDF Downloads 17

Authors: Shaila Bahl, S. P. Lochab, Pratik Kumar

Abstract:

Nanotechnology and nanomaterials have attracted researchers from different fields, especially from the field of luminescence. Recent studies on various luminescent nanomaterials have shown their relevance in dosimetry of ionizing radiations for the measurements of high doses using the Thermoluminescence (TL) technique, where the conventional microcrystalline phosphors saturate. Ion beams have been used for diagnostic and therapeutic purposes due to their favorable profile of dose deposition at the end of the range known as the Bragg peak. While dealing with human beings, doses from these beams need to be measured with great precision and accuracy. Henceforth detailed investigations of suitable thermoluminescent dosimeters (TLD) for dose verification in ion beam irradiation are required. This paper investigates the TL response of nanocrystalline BaSO4 doped with Eu to 85 MeV carbon beam. The synthesis was done using Co-precipitation technique by mixing Barium chloride and ammonium sulphate solutions. To investigate the crystallinity and particle size, analytical techniques such as X-ray diffraction (XRD) and Transmission electron microscopy (TEM) were used which revealed the average particle sizes to 45 nm with orthorhombic structure. Samples in pellet form were irradiated by 85 MeV carbon beam in the fluence range of 1X1010-5X1013. TL glow curves of the irradiated samples show two prominent glow peaks at around 460 K and 495 K. The TL response is linear up to 1X1013 fluence after which saturation was observed. The wider linear TL response of nanocrystalline BaSO4: Eu and low fading make it a superior candidate as a dosimeter to be used for detecting the doses of carbon beam.

Keywords: radiation, dosimetry, carbon ions, thermoluminescence

Procedia PDF Downloads 285

Authors: Sean W. T. Bayly, Daniel Glover, Don Horrell, Simon Horrocks, Barnes Callum, Stuart Gibson, Mac Misuira

Abstract:

We assess suitability of recent, ∼7B parameter, instruction-tuned Language Models Mistral-v0.3, Llama-3, and Phi-3, for Generative Named Entity Recognition (GNER). Our proposed Multi-Level Information Retrieval method achieves notable improvements over finetuned entity-level and sentence-level methods. We consider recent developments at the cross roads of prompt engineering and Retrieval Augmented Generation (RAG), such as EmotionPrompt. We conclude that language models directed toward this task are highly capable when distinguishing between positive classes (precision). However, smaller models seem to struggle to find all entities (recall). Poorly defined classes such as ”Miscellaneous” exhibit substantial declines in performance, likely due to the ambiguity it introduces to the prompt. This is partially resolved through a self verification method using engineered prompts containing knowledge of the stricter class definitions, particularly in areas where their boundaries are in danger of overlapping, such as the conflation between the location ”Britain” and the nationality ”British”. Finally, we explore correlations between model performance on the GNER task with performance on relevant academic benchmarks.

Keywords: generative named entity recognition, information retrieval, lightweight artificial intelligence, prompt engineering, personal information identification, retrieval augmented generation, self verification

Procedia PDF Downloads 18

Authors: Jianghao Hu, Hongyu Wang

Abstract:

The effective and efficient human pose estimation algorithm is an important task for real-time human pose estimation on mobile devices. This paper proposes a light-weight human key points detection algorithm, Light-Weight Network for Real-Time Pose Estimation (LWPE). LWPE uses light-weight backbone network and depthwise separable convolutions to reduce parameters and lower latency. LWPE uses the feature pyramid network (FPN) to fuse the high-resolution, semantically weak features with the low-resolution, semantically strong features. In the meantime, with multi-scale prediction, the predicted result by the low-resolution feature map is stacked to the adjacent higher-resolution feature map to intermediately monitor the network and continuously refine the results. At the last step, the key point coordinates predicted in the highest-resolution are used as the final output of the network. For the key-points that are difficult to predict, LWPE adopts the online hard key points mining strategy to focus on the key points that hard predicting. The proposed algorithm achieves excellent performance in the single-person dataset selected in the AI (artificial intelligence) challenge dataset. The algorithm maintains high-precision performance even though the model only contains 3.9M parameters, and it can run at 225 frames per second (FPS) on the generic graphics processing unit (GPU).

Keywords: depthwise separable convolutions, feature pyramid network, human pose estimation, light-weight backbone

Procedia PDF Downloads 149

Authors: D. S. Mohale, A. P. Dewani, A. S.tripathi, A. V. Chandewar

Abstract:

Present work demonstrates the applicability of high-performance liquid chromatography (HPLC) with UV-Vis detection for the quantification of malondialdehyde as malondialdehyde-thiobarbituric acid complex (MDA-TBA) in-vivo in rats. The HPLC method for MDA-TBA was achieved by isocratic mode on a reverse-phase C18 column (250mm×4.6mm) at a flow rate of 1.0mLmin−1 followed by detection at 532 nm. The chromatographic conditions were optimized by varying the concentration and pH of water followed by changes in percentage of organic phase optimal mobile phase consisted of mixture of water (0.2% triethylamine pH adjusted to 2.3 by ortho-phosphoric acid) and acetonitrile in ratio (80:20v/v). The retention time of MDA-TBA complex was 3.7 min. The developed method was sensitive as limit of detection and quantification (LOD and LOQ) for MDA-TBA complex were (standard deviation and slope of calibration curve) 110 ng/ml and 363 ng/ml respectively. Calibration studies were done by spiking MDA into rat plasma at concentrations ranging from 500 to 1000 ng/ml. The precision of developed method measured in terms of relative standard deviations for intra-day and inter-day studies was 1.6–5.0% and 1.9–3.6% respectively. The HPLC method was applied for monitoring MDA levels in rats subjected to chronic treatment of levofloxacin (LEV) (5mg/kg/day) for 21 days. Results were compared by findings in control group rats. Mean peak areas of both study groups was subjected for statistical treatment to unpaired student t-test to find p-values. The p value was <0.001 indicating significant results and suggesting increased MDA levels in rats subjected to chronic treatment of LEV of 21 days.

Keywords: malondialdehyde-thiobarbituric acid complex, levofloxacin, HPLC, oxidative stress

Procedia PDF Downloads 329

Authors: Beng Yew Low, Cher Liang Cha, Cheng Yong Teoh

Abstract:

Due to a lack of continual assessment or grade related data, identifying first-year engineering students in a polytechnic education at risk of failing is challenging. Our experience over the years tells us that there is no strong correlation between having good entry grades in Mathematics and the Sciences and excelling in hardcore engineering subjects. Hence, identifying students at risk of failure cannot be on the basis of entry grades in Mathematics and the Sciences alone. These factors compound the difficulty of early identification and intervention. This paper describes the development of a predictive analytics model in the early detection of students at risk of failing and evaluates its effectiveness. Data from continual assessments conducted in term one, supplemented by data of student psychological profiles such as interests and study habits, were used. Three classification techniques, namely Logistic Regression, K Nearest Neighbour, and Random Forest, were used in our predictive model. Based on our findings, Random Forest was determined to be the strongest predictor with an Area Under the Curve (AUC) value of 0.994. Correspondingly, the Accuracy, Precision, Recall, and F-Score were also highest among these three classifiers. Using this Random Forest Classification technique, students at risk of failure could be identified at the end of term one. They could then be assigned to a Learning Support Programme at the beginning of term two. This paper gathers the results of our findings. It also proposes further improvements that can be made to the model.

Keywords: continual assessment, predictive analytics, random forest, student psychological profile

Procedia PDF Downloads 128

Authors: Hossein Navid, Maryam Adeli Khadem, Shahin Oustan, Mahmoud Zareie

Abstract:

Among the nutrients needed by the plants, three elements containing nitrate, phosphorus and potassium are more important. The objective of this research was measuring these nutrient amounts in soil using Fourier transform infrared spectroscopy in range of 400- 4000 cm-1. Soil samples for different soil types (sandy, clay and loam) were collected from different areas of East Azerbaijan. Three types of fertilizers in conventional farming (urea, triple superphosphate, potassium sulphate) were used for soil treatment. Each specimen was divided into two categories: The first group was used in the laboratory (direct measurement) to extract nitrate, phosphorus and potassium uptake by colorimetric method of Olsen and ammonium acetate. The second group was used to measure drug absorption spectrometry. In spectrometry, the small amount of soil samples mixed with KBr and was taken in a small pill form. For the tests, the pills were put in the center of infrared spectrometer and graphs were obtained. Analysis of data was done using MINITAB and PLSR software. The data obtained from spectrometry method were compared with amount of soil nutrients obtained from direct drug absorption using EXCEL software. There were good fitting between these two data series. For nitrate, phosphorus and potassium R2 was 79.5%, 92.0% and 81.9%, respectively. Also, results showed that the range of MIR (mid-infrared) is appropriate for determine the amount of soil nitrate and potassium and can be used in future research to obtain detailed maps of land in agricultural use.

Keywords: nitrate, phosphorus, potassium, soil nutrients, spectroscopy

Procedia PDF Downloads 396

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

The assessment of disease levels in crop fields is an important and time-consuming task that generally relies on expert knowledge of trained individuals. Image classification in agriculture problems historically has been based on classical machine learning strategies that make use of hand-engineered features in the top of a classification algorithm. This approach tends to not produce results with high accuracy and generalization to the classes classified by the system when the nature of the elements has a significant variability. The advent of deep convolutional neural networks has revolutionized the field of machine learning, especially in computer vision tasks. These networks have great resourcefulness of learning and have been applied successfully to image classification and object detection tasks in the last years. The objective of this work was to propose a new method based on deep learning convolutional neural networks towards the task of disease level monitoring. Common RGB images of winter wheat were obtained during a growing season. Five categories of disease levels presence were produced, in collaboration with agronomists, for the algorithm classification. Disease level tasks performed by experts provided ground truth data for the disease score of the same winter wheat plots were RGB images were acquired. The system had an overall accuracy of 84% on the discrimination of the disease level classes.

Keywords: crop disease assessment, deep learning, precision agriculture, residual neural networks

Procedia PDF Downloads 322

Authors: Alba Luna Jimenez, Maria Dolores Hernando

Abstract:

The administration of veterinary treatments at higher doses than the recommended Varroa mite control in beehive matrices has the potential to generate residues in the honeybee colony and in the derived products for consumption. Honeybee colonies can also be indirectly exposed to residues of plant protection products when foraging in crops, wildflowers near the crops, or in urban gardens just after spraying. The study evaluates the presence of both types of residues, veterinary treatments, and pesticides in beeswax, bee bread, and honey. The study was carried out in apiaries located in agricultural zones and forest areas in Andalusia, Spain. Up to nineteen residues were identified above LOQ using gas chromatography-triple quadrupole-mass spectrometry analysis (GC-MS/MS). Samples were extracted by a modified QuEChERs method. Chlorfenvinphos was detected in beeswax and bee bread despite its use is not authorized for Varroa mite control. Residues of fluvalinate-tau, authorized as veterinary treatment, were detected in most of the samples of beeswax and bee bread, presumably due to overdose or also to its potential for accumulation associated with its marked liposolubility. Residues of plant protection products were also detected in samples of beeswax and bee bread. Pesticide residues were detected above the LOQ that was established at 5 µg.kg⁻¹, which is the minimum concentration that can be quantified with acceptable accuracy and precision, as described in the European guidelines for pesticide residue analysis SANTE/11945/2015. No residues of phytosanitary treatments used in agriculture were detected in honey.

Keywords: honeybee colony, mass spectrometry analysis, pesticide residues, Varroa destructor, veterinary treatment

Procedia PDF Downloads 155

Authors: Nagalingam Arun Prasanth, Ahmed Syed Adnan, S. H. Yeo

Abstract:

Surface topography plays a significant role in the functional performance of engineered parts. It is important to have a control on the surface geometry and understanding on the surface details to get the desired performance. Hence, in the current research contribution, a non-contact micro-texturing technique has been explored and developed. The technique involves ultrasonic excitation of a tool as a prime source of surface texturing for aluminum alloy workpieces. The specimen surface is polished first and is then immersed in a liquid bath containing 10% weight concentration of Ti6Al4V grade 5 spherical powders. A submerged slurry jet is used to recirculate the spherical powders under the ultrasonic horn which is excited at an ultrasonic frequency and amplitude of 40 kHz and 70 µm respectively. The distance between the horn and workpiece surface was remained fixed at 200 µm using a precision control stage. Texturing effects were investigated for different process timings of 1, 3 and 5 s. Thereafter, the specimens were cleaned in an ultrasonic bath for 5 mins to remove loose debris on the surface. The developed surfaces are characterized by optical and contact surface profiler. The optical microscopic images show a texture of circular spots on the workpiece surface indented by titanium spherical balls. Waviness patterns obtained from contact surface profiler supports the texturing effect produced from the proposed technique. Furthermore, water droplet tests were performed to show the efficacy of the proposed technique to develop hydrophilic surfaces and to quantify the texturing effect produced.

Keywords: surface texturing, surface modification, topography, ultrasonic

Procedia PDF Downloads 218