Search results for: comprehensive feature extraction

Authors: Muhammad Ahmad

Abstract:

In this research, Chrysanthemum (morifolium) flowers are used as a natural dye to reduce synthetic dyes and take a step toward sustainability in the fashion industry. The aqueous extraction method is utilized for natural dye extraction and then applied to silk and cotton fabric samples. The color of the dye extracted from dried chrysanthemum flowers is originally a shade of rich green, but after being washed with detergent, it turns to a shade of yellow. Traditional salt and vinegar are used as a natural mordant to fix the dye color. This study also includes a phenolic and chemical analysis of the natural dye (Chrysanthemum flowers) and the textiles (cotton and silk). Compared to cotton fabric, silk fabric has far superior chemical qualities to use in natural dyeing. The results of this study show that the Chrysanthemum flower offers a variety of colors when treated with detergent, without detergent, and with mordants. Chrysanthemum flowers have long been used in other fields, such as medicine; therefore, it is time to start using them in the fashion industry as a natural dye to lessen the harm that synthetic dyes cause.

Keywords: natural dyes, Chrysanthemum flower, sustainability, textile fabrics, chemical and phenolic analysis

Procedia PDF Downloads 20

Authors: P. V. Pramila , V. Mahesh

Abstract:

Pulmonary Function Tests are important non-invasive diagnostic tests to assess respiratory impairments and provides quantifiable measures of lung function. Spirometry is the most frequently used measure of lung function and plays an essential role in the diagnosis and management of pulmonary diseases. However, the test requires considerable patient effort and cooperation, markedly related to the age of patients esulting in incomplete data sets. This paper presents, a nonlinear model built using Multivariate adaptive regression splines and Random forest regression model to predict the missing spirometric features. Random forest based feature selection is used to enhance both the generalization capability and the model interpretability. In the present study, flow-volume data are recorded for N= 198 subjects. The ranked order of feature importance index calculated by the random forests model shows that the spirometric features FVC, FEF 25, PEF,FEF 25-75, FEF50, and the demographic parameter height are the important descriptors. A comparison of performance assessment of both models prove that, the prediction ability of MARS with the `top two ranked features namely the FVC and FEF 25 is higher, yielding a model fit of R2= 0.96 and R2= 0.99 for normal and abnormal subjects. The Root Mean Square Error analysis of the RF model and the MARS model also shows that the latter is capable of predicting the missing values of FEV1 with a notably lower error value of 0.0191 (normal subjects) and 0.0106 (abnormal subjects). It is concluded that combining feature selection with a prediction model provides a minimum subset of predominant features to train the model, yielding better prediction performance. This analysis can assist clinicians with a intelligence support system in the medical diagnosis and improvement of clinical care.

Keywords: FEV, multivariate adaptive regression splines pulmonary function test, random forest

Procedia PDF Downloads 310

Authors: Chen Wang, Qiuxiao Chen

Abstract:

With the advent of the information age and the era of big data, urban planning research is no longer satisfied with the analysis and application of traditional data. Because of the limitations of traditional urban commercial center system research, big data provides new opportunities for urban research. Therefore, based on the quantitative evaluation method of big data, the commercial center system of the main city of Hangzhou is analyzed and evaluated, and the scale and hierarchical structure characteristics of the urban commercial center system are studied. In order to make up for the shortcomings of the existing POI extraction method, it proposes a POI extraction method based on adaptive adjustment of search window, which can accurately and efficiently extract the POI data of commercial business in the main city of Hangzhou. Through the visualization and nuclear density analysis of the extracted Point of Interest (POI) data, the current situation of the commercial center system in the main city of Hangzhou is evaluated. Then it compares with the commercial center system structure of 'Hangzhou City Master Plan (2001-2020)', analyzes the problems existing in the planned urban commercial center system, and provides corresponding suggestions and optimization strategy for the optimization of the planning of Hangzhou commercial center system. Then get the following conclusions: The status quo of the commercial center system in the main city of Hangzhou presents a first-level main center, a two-level main center, three third-level sub-centers, and multiple community-level business centers. Generally speaking, the construction of the main center in the commercial center system is basically up to standard, and there is still a big gap in the construction of the sub-center and the regional-level commercial center, further construction is needed. Therefore, it proposes an optimized hierarchical functional system, organizes commercial centers in an orderly manner; strengthens the central radiation to drive surrounding areas; implements the construction guidance of the center, effectively promotes the development of group formation and further improves the commercial center system structure of the main city of Hangzhou.

Keywords: business center system, business format, main city of Hangzhou, POI extraction method

Procedia PDF Downloads 140

Authors: S. Nandagopalan, N. Pradeep

Abstract:

The aim of this paper is to propose a general framework for storing, analyzing, and extracting knowledge from two-dimensional echocardiographic images, color Doppler images, non-medical images, and general data sets. A number of high performance data mining algorithms have been used to carry out this task. Our framework encompasses four layers namely physical storage, object identification, knowledge discovery, user level. Techniques such as active contour model to identify the cardiac chambers, pixel classification to segment the color Doppler echo image, universal model for image retrieval, Bayesian method for classification, parallel algorithms for image segmentation, etc., were employed. Using the feature vector database that have been efficiently constructed, one can perform various data mining tasks like clustering, classification, etc. with efficient algorithms along with image mining given a query image. All these facilities are included in the framework that is supported by state-of-the-art user interface (UI). The algorithms were tested with actual patient data and Coral image database and the results show that their performance is better than the results reported already.

Keywords: active contour, Bayesian, echocardiographic image, feature vector

Procedia PDF Downloads 445

Authors: Ming-Hong Chen

Abstract:

In the study, the mechanical and financial feasibility for the compressed air energy storage (CAES) system in the porous media reservoir in Taiwan is evaluated. In 2035, Taiwan aims to install 16.7 GW of wind power and 40 GW of photovoltaic (PV) capacity. However, renewable energy sources often generate more electricity than needed, particularly during winter. Consequently, Taiwan requires long-term, large-scale energy storage systems to ensure the security and stability of its power grid. Currently, the primary large-scale energy storage options are Pumped Hydro Storage (PHS) and Compressed Air Energy Storage (CAES). Taiwan has not ventured into CAES-related technologies due to geological and cost constraints. However, with the imperative of achieving net-zero carbon emissions by 2050, there's a substantial need for the development of a considerable amount of renewable energy. PHS has matured, boasting an overall installed capacity of 4.68 GW. CAES, presenting a similar scale and power generation duration to PHS, is now under consideration. Taiwan's geological composition, being a porous medium unlike salt caves, introduces flow field resistance affecting gas injection and extraction. This study employs a program analysis model to establish the system performance analysis capabilities of CAES. The finite volume model is then used to assess the impact of porous media, and the findings are fed back into the system performance analysis for correction. Subsequently, the financial implications are calculated and compared with existing literature. For Taiwan, the strategic development of CAES technology is crucial, not only for meeting energy needs but also for decentralizing energy allocation, a feature of great significance in regions lacking alternative natural resources.

Keywords: compressed-air energy storage, efficiency, porous media, financial feasibility

Procedia PDF Downloads 66

Authors: A. Yamaoka, S. Yukawa

Abstract:

Mind wandering is a mental phenomenon of drifting away from a current task or external environment toward inner thought. This research examines the feature of mind wandering which people who have high creativity and high mental health engage in because it is expected that mind wandering which such kind of people engage in may not induce negative affect, although it can improve creativity. Sixty-seven participants were required to complete questionnaires which measured their creativity and mental health. After that, researchers conducted experience sampling method and measured the details of their mind wandering and the situation when mind wandering was generated in daily life for three days. The result showed that high creative people and high mental health people more think about positive things during mind wandering and less think about negative things. In further research, researchers will examine how to induce positive thought during mind wandering and how to inhibit negative thought during mind wandering. Doing so will contribute to improve creative problem solving without generation of negative affect.

Keywords: creativity, experience sampling method, mental health, mind wandering

Procedia PDF Downloads 173

Authors: Lorena Coelho, David Ramada, Catarina Nobre, Joaquim Gaião, Juliana Duarte

Abstract:

The development of processes that allows the valorization of waste and by-products generated by industries is crucial to promote symbiotic relationships between different sectors and is mandatory to “close the loop” in the circular economy paradigm. In recent years, by-products and waste from agro-food and forestry sector have attracted attention due to their potential application and technical characteristics. The extraction of bio-based active compounds to be reused is in line with the circular bioeconomy concept trends, combining the use of renewable resources with the process’s circularity, aiming the waste reduction and encouraging reuse and recycling. Among different types of bio-based materials, which are being explored and can be extracted, proteins fractions are becoming an attractive new raw material. Within this context, BioTrace4Leather project, a collaboration between two Technological Centres – CeNTI and CTIC, and a company of Tanning and Finishing of Leather – Curtumes Aveneda, aims to develop innovative and biologically sustainable solutions for leather industry and accomplish the market circularity trends. Specifically, it aims to the valorisation of waste and by-products from the tannery industry through proteins extraction and the development of an innovative and biologically sustainable materials. The achieved results show that keratin, gelatine, and collagen fractions can be successfully extracted from hair and leather bovine waste. These products could be reintegrated into the industrial manufacturing process to attain innovative and functional textile and leather substrates. ACKNOWLEDGEMENT This work has been developed under BioTrace4Leather scope, a project co-funded by Operational Program for Competitiveness and Internationalization (COMPETE) of PORTUGAL2020, through the European Regional Development Fund (ERDF), under grant agreement Nº POCI-01-0247-FEDER-039867.

Keywords: leather by-products, circular economy, sustainability, protein fractions

Procedia PDF Downloads 158

Authors: Supakan Rattanakon, Jakkrapan Boonpimon, Akkaragiat Bhuangsaeng, Aphiwat Ratriphruek

Abstract:

Rice bran oil (RBO) has been found to lower the level of serum cholesterol, has antioxidant and anti-carcinogenic property, and attenuate allergic inflammation. These properties of RBO are due to antioxidant compositions, especially, phenolic compounds. The higher amount of these active compounds in RBO, the greater value of RBO is. Thermal process of rice bran before solvent RBO extraction has been found to have a higher phenolic contents. Therefore, the purpose of this study is to using different heating methods on rice bran before the solvent extraction. Then, % yield of RBO, total phenolic content (TPC), and antioxidant property of two white Thai rice; KDML105 and RD6 were determined. The Folin-Ciocalteu colorimetric assay was used to determine TPC and scavenging of free radicals (DPPH) was used to determine antioxidant property expressed as EC50. The result showed that thermal process did not increase % yield of RBO but increase the TPC with 1.41 mg gallic acid equivalent (GAEmg-1). The highest TPC was found in KDML105 by using sonicator. The highest antioxidant activity was found in RD6 using autoclave. The EC50 of RBO was 0.04 mg/mL. Further study should be performed on different pretreatments to increase the TPC and antioxidant property.

Keywords: antioxidant, rice bran oil, total phenol content, white rice

Procedia PDF Downloads 252

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 315

Authors: Sherif Keddis, Mohamed Azzam, Norbert Schwesinger

Abstract:

Harvesting mechanical energy from footsteps or other impacts is a possibility to enable wireless autonomous sensor nodes. These can be used for a highly efficient control of connected devices such as lights, security systems, air conditioning systems or other smart home applications. They can also be used for accurate location or occupancy monitoring. Converting the mechanical energy into useful electrical energy can be achieved using the piezoelectric effect offering simple harvesting setups and low deflections. The challenge facing piezoelectric transducers is the achievable amount of energy per impact in the lower mJ range and the management of such low energies. Simple setups for energy extraction such as a full wave bridge connected directly to a capacitor are problematic due to the mismatch between high impedance sources and low impedance storage elements. Efficient energy circuits for piezoelectric harvesters are commonly designed for vibration harvesters and require periodic input energies with predictable frequencies. Due to the sporadic nature of impact harvesters, such circuits are not well suited. This paper presents a self-powered circuit that avoids the impedance mismatch during energy extraction by disconnecting the load until the source reaches its charge peak. The switch is implemented with passive components and works independent from the input frequency. Therefore, this circuit is suited for impact harvesting and sporadic inputs. For the same input energy, this circuit stores 150% of the energy in comparison to a directly connected capacitor to a bridge rectifier. The total efficiency, defined as the ratio of stored energy on a capacitor to available energy measured across a matched resistive load, is 63%. Although the resulting energy is already sufficient to power certain autonomous applications, further optimization of the circuit are still under investigation in order to improve the overall efficiency.

Keywords: autonomous sensors, circuit design, energy harvesting, energy management, impact harvester, piezoelectricity

Procedia PDF Downloads 154

Authors: Tarikayehu Amanuel, Abraham Mohammed

Abstract:

The production of biodiesel from waste materials is becoming an increasingly important research area in the field of renewable energy. One potential waste material source is avocado, a fruit with a large seed and peel that are typically discarded after consumption. This research aims to investigate the feasibility of using avocado waste as a feedstock for the production of biodiesel. The study focuses on extracting oil from the waste material using the transesterification technique and then characterizing the properties of oil to determine its suitability for conversion to biodiesel. The study was conducted experimentally, and a maximum oil yield of 11.583% (150g of oil produced from 1.295kg of avocado waste powder) was obtained from avocado waste powder at an extraction time of 4hr. An 87% fatty acid methyl ester (biodiesel) conversion was also obtained using a methanol/oil ratio of 6:1, 1.3g NaOH, reaction time 60min, and 65°C reaction temperature. Furthermore, from 145 ml of avocado waste oil, 126.15 ml of biodiesel was produced, indicating a high percentage of conversion (87%). Conclusively, the produced biodiesel showed comparable physical and chemical characteristics to that of standard biodiesel samples considered for the study. The results of this research could help to identify a new source of biofuel production while also addressing the issue of waste disposal in the food industry.

Keywords: biodiesel, avocado, transesterification, soxhlet extraction

Procedia PDF Downloads 69

Authors: Jinan Fiaidhi, Sabah Mohammed, Petros Zezos

Abstract:

Capsule endoscopy (CE) is an established noninvasive diagnostic modality in investigating small bowel disease. CE has a pivotal role in assessing patients with suspected bleeding or identifying evidence of active Crohn's disease in the small bowel. However, CE produces lengthy videos with at least eighty thousand frames, with a frequency rate of 2 frames per second. Gastroenterologists cannot dedicate 8 to 15 hours to reading the CE video frames to arrive at a diagnosis. This is why the issue of analyzing CE videos based on modern artificial intelligence techniques becomes a necessity. However, machine learning, including deep learning, has failed to report robust results because of the lack of large samples to train its neural nets. In this paper, we are describing a thick data approach that learns from a few anchor images. We are using sound datasets like KVASIR and CrohnIPI to filter candidate frames that include interesting anomalies in any CE video. We are identifying candidate frames based on feature extraction to provide representative measures of the anomaly, like the size of the anomaly and the color contrast compared to the image background, and later feed these features to a decision tree that can classify the candidate frames as having a condition like the Crohn's Disease. Our thick data approach reported accuracy of detecting Crohn's Disease based on the availability of ulcer areas at the candidate frames for KVASIR was 89.9% and for the CrohnIPI was 83.3%. We are continuing our research to fine-tune our approach by adding more thick data methods for enhancing diagnosis accuracy.

Keywords: thick data analytics, capsule endoscopy, Crohn’s disease, siamese neural network, decision tree

Procedia PDF Downloads 156

Authors: K. M. Jananni, R. Nandini

Abstract:

The proposed wireless, inverter type design of a LPG leakage monitoring system aims to provide a smart and safe kitchen. The system detects the LPG gas leak using Nano-sensors and alerts the concerned individual through GSM system. The system uses two sensors, one attached to the chimney and other to the regulator of the LPG cylinder. Upon a leakage being detected, the sensor at the regulator actuates the system to cut off the gas supply immediately using a solenoid control valve. The sensor at the chimney checks for the permissible level of LPG mix in the air and when the level exceeds the threshold, the system sends an automatic SMS to the numbers saved. Further the sensor actuates the mini suction system fixed at the chimney within 20 seconds of a leakage to suck out the gas until the level falls well below the threshold. As a safety measure, an automatic window opening and alarm feature is also incorporated into the system. The key feature of this design is that the system is provided with a special inverter designed to make the device function effectively even during power failures. In this paper, utilization of sensors in the kitchen area is discussed and this gives the proposed architecture for real time field monitoring with a PIC Micro-controller.

Keywords: nano sensors, global system for mobile communication, GSM, micro controller, inverter

Procedia PDF Downloads 473

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 78

Authors: Wang Zhaoming, Shao Shegang, Chen Xiaorong, Qi Yanan, Tian Lei, Wang Jian

Abstract:

This study conducts a comparative analysis of the spectral curves of asphalt pavements at various aging stages to improve road information extraction from high-resolution remote sensing imagery. By examining the distinguishing capabilities and spectral characteristics, the research aims to establish a pavement information extraction methodology based on China's high-resolution satellite images. The process begins by analyzing the spectral features of asphalt pavements to construct a spectral assessment model suitable for evaluating pavement health. This model is then tested at a national highway traffic testing site in China, validating its effectiveness in distinguishing different pavement aging levels. The study's findings demonstrate that the proposed model can accurately assess road health, offering a valuable tool for road maintenance planning and infrastructure management.

Keywords: spectral analysis, asphalt pavement aging, high-resolution remote sensing, pavement health assessment

Procedia PDF Downloads 21

Authors: Heng Yang, Tao Luo, Yakun Zhang, Kai Wang, Wei Qin, Liang Xie, Ye Yan, Erwei Yin

Abstract:

Recent years have seen that audio-visual recognition has shown great potential in a strong noise environment. The existing method of audio-visual recognition has explored methods with ResNet and feature fusion. However, on the one hand, ResNet always occupies a large amount of memory resources, restricting the application in engineering. On the other hand, the feature merging also brings some interferences in a high noise environment. In order to solve the problems, we proposed an effective framework with bidirectional distillation. At first, in consideration of the good performance in extracting of features, we chose the light model, Efficientnet as our extractor of spatial features. Secondly, self-distillation was applied to learn more information from raw data. Finally, we proposed a bidirectional distillation in decision-level fusion. In more detail, our experimental results are based on a multi-model dataset from 24 volunteers. Eventually, the lipreading accuracy of our framework was increased by 2.3% compared with existing systems, and our framework made progress in audio-visual fusion in a high noise environment compared with the system of audio recognition without visual.

Keywords: lipreading, audio-visual, Efficientnet, distillation

Procedia PDF Downloads 134

Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride

Abstract:

In this work, we use machine learning and novel data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. To the best of our knowledge, this is the first work to apply modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.

Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning

Procedia PDF Downloads 134

Authors: Yusuf Nugroho Doyo Yekti, Budi Praptono, Fransiskus Tatas Dwi Atmaji

Abstract:

There is no ergonomic prototype testing method for manual material handling yet. This study has been carried out to demonstrate the comprehensive ergonomic assessment. The ergonomic assessment is important to improve safety of products and to ensure usefulness of the product. The prototype testing is conducted by involving few intended users and ordinary people. In this study, there are four operators who participated in several tests. Also, there are 30 ordinary people who joined the usability test. All the ordinary people never do material handling activity nor use material handling device. The methods used in the tests are Rapid Entire Body Assessment (REBA), Recommended Weight Limit (RWL), and Cardiovascular Load (%CVL) other than usability test and questionnaire. The proposed testing methods cover comprehensive ergonomic aspects, i.e. physical aspect, mental aspect, emotional aspects of human.

Keywords: ergonomic, manual material handling, prototype testing, assessment

Procedia PDF Downloads 517

Authors: Hussain Ali Bekhet, Nor Hamisham Harun

Abstract:

The main objective of this paper is to give a comprehensive review of non-renewable energy and renewable energy utilization in Malaysia, including hydropower, solar photovoltaic, biomass and biogas technologies. Malaysia mainly depends on non-renewable energy (natural gas, coal and crude oil) for electricity generation. Therefore, this paper provides a comprehensive review of the energy sector and discusses diversification of electricity generation as a strategy for providing sustainable energy in Malaysia. Energy policies and strategies to protect the non-renewable energy utilization also are highlighted, focusing in the different sources of energy available for high and sustained economic growth. Emphasis is also placed on a discussion of the role of renewable energy as an alternative source for the increase of electricity supply security. It is now evident that to achieve sustainable development through renewable energy, energy policies and strategies have to be well designed and supported by the government, industries (firms), and individual or community participation. The hope is to create a positive impact on sustainable development through renewable sources for current and future generations.

Keywords: Malaysia, non-renewable energy, renewable energy, sustainable energy

Procedia PDF Downloads 402

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 278

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 240

Authors: Qaiser uz Zaman Khan

Abstract:

This research article provides a comprehensive study of combining steel fiber and polypropylene fibers in concrete at different mix ratios. This blending of various fibers has led to the development of hybrid fiber-reinforced concrete (HFRC), which offers notable improvements in mechanical properties and increased resistance to cracking. Steel fibers are known for their high tensile strength and excellent crack control abilities, while polypropylene fibers offer increased toughness and impact resistance. The synergistic use of these two fiber types in concrete has yielded promising outcomes, effectively enhancing its overall performance. This article explores the key aspects of hybridization, including fiber types, proportions, mixing methods, and the resulting properties of the concrete. Additionally, challenges, potential applications, and future research directions in the field are discussed.

Keywords: FRC, fiber-reinforced concrete, split tensile testing, HFRC, mechanical properties, steel fibers, reinforced concrete, polypropylene fibers

Procedia PDF Downloads 91

Authors: Swathi Gopakumar, Sruthi Krishna, Shivasubramani Krishnamoorthy

Abstract:

Contactless, painless and radiation-free thermal imaging technology is one of the preferred screening modalities for detection of breast cancer. However, poor signal to noise ratio and the inexorable need to preserve edges defining cancer cells and normal cells, make the segmentation process difficult and hence unsuitable for computer-aided diagnosis of breast cancer. This paper presents key findings from a research conducted on the appraisal of two promising techniques, for the detection of breast cancer: (I) marker-controlled, Level-set segmentation of anisotropic diffusion filtered preprocessed image versus (II) Segmentation using marker-controlled level-set on a Gaussian-filtered image. Gaussian-filtering processes the image uniformly, whereas anisotropic filtering processes only in specific areas of a thermographic image. The pre-processed (Gaussian-filtered and anisotropic-filtered) images of breast samples were then applied for segmentation. The segmentation of breast starts with initial level-set function. In this study, marker refers to the position of the image to which initial level-set function is applied. The markers are generally placed on the left and right side of the breast, which may vary with the breast size. The proposed method was carried out on images from an online database with samples collected from women of varying breast characteristics. It was observed that the breast was able to be segmented out from the background by adjustment of the markers. From the results, it was observed that as a pre-processing technique, anisotropic filtering with level-set segmentation, preserved the edges more effectively than Gaussian filtering. Segmented image, by application of anisotropic filtering was found to be more suitable for feature extraction, enabling automated computer-aided diagnosis of breast cancer.

Keywords: anisotropic diffusion, breast, Gaussian, level-set, thermograms

Procedia PDF Downloads 380

Authors: Jaishree Ellis

Abstract:

The United States Centers for Disease Control tells us that many women with disabilities will not receive regular health screenings, including Pap Smears and mammograms. This article was comprised and written to recognize the barriers to care, gaps in existing healthcare implementation, and viable methodologies for the provision of comprehensive and robust gynecologic care for women with disabilities. According to the World Health Organization, 15% of the world's population, or approximately 1 billion people, have disabilities, most of whom are identified as women. Women with disabilities are described as being multi-disabled, as in some places, they suffer exclusion because of their disabilities as well as their gender. The paucity of information regarding how to create a healthcare system that is inclusive of every woman, regardless of her type of disability (physical, mental, intellectual or medical), has made it challenging to establish an environment that makes it possible for individuals to access care in an equitable, respectful and comprehensive way. A review of the current literature, institutional websites within the United States and American resource guides was implemented to determine where comprehensive models of care for women with disabilities exist, as well as the modalities that are being employed to meet their healthcare needs. The many barriers to care that women with disabilities face were also extracted from various sources within the literature to provide an exhaustive list that can be tackled, one by one. Of the 637 Hospital Systems in the United States, only 7 provide website documentation of health care services that address the unique needs of women with disabilities. The presumption is that if institutions have not marketed such interventions to the community, then it is likely that they do not have a robust suite of services with which to make gynecologic care available to patients with disabilities. Through this review, 7 main barriers to comprehensive gynecologic care were identified, with more than 20 sub-categories existing within those. As with many other areas of community life, inclusion remains lacking in the delivery of healthcare for women with disabilities. There are at least 7 barriers that must be overcome in order to provide equity in the medical office, the exam room, the hospital and the operating room. While few institutions have prioritized this, those few have provided blueprints that can easily be adopted by others. However, as the general population lives longer and ages, the incidence of disabilities increases, as do the healthcare disparities surrounding them. Further compounded by this is a lack of formal education for medical providers in the United States.

Keywords: health equity, inclusion, healthcare disparities, education

Procedia PDF Downloads 54

Authors: Abdul Khalique Baloch, Ali Okatan

Abstract:

The quality analysis of food and vegetable from image is hot topic now a day, where researchers make them better then pervious findings through different technique and methods. In this research we have review the literature, and find gape from them, and suggest better proposed approach, design the algorithm, developed a software to measure the quality from images, where accuracy of image show better results, and compare the results with Perouse work done so for. The Application we uses an open-source dataset and python language with tensor flow lite framework. In this research we focus to sort food and vegetable from image, in the images, the application can sorts and make them grading after process the images, it could create less errors them human base sorting errors by manual grading. Digital pictures datasets were created. The collected images arranged by classes. The classification accuracy of the system was about 94%. As fruits and vegetables play main role in day-to-day life, the quality of fruits and vegetables is necessary in evaluating agricultural produce, the customer always buy good quality fruits and vegetables. This document is about quality detection of fruit and vegetables using images. Most of customers suffering due to unhealthy foods and vegetables by suppliers, so there is no proper quality measurement level followed by hotel managements. it have developed software to measure the quality of the fruits and vegetables by using images, it will tell you how is your fruits and vegetables are fresh or rotten. Some algorithms reviewed in this thesis including digital images, ResNet, VGG16, CNN and Transfer Learning grading feature extraction. This application used an open source dataset of images and language used python, and designs a framework of system.

Keywords: deep learning, computer vision, image processing, rotten fruit detection, fruits quality criteria, vegetables quality criteria

Procedia PDF Downloads 70

Authors: Yindi Zhao, Yun Zhang, Silu Xia, Lixin Wu

Abstract:

The contours and areas of water surfaces, especially lakes, often change due to natural disasters and construction activities. It is an effective way to extract and update water contours from satellite images using image processing algorithms. However, to produce optimal water surface contours that are close to true boundaries is still a challenging task. This paper compares the performances of three different level set models, including the Chan-Vese (CV) model, the signed pressure force (SPF) model, and the region-scalable fitting (RSF) energy model for extracting lake contours. After experiment testing, it is indicated that the RSF model, in which a region-scalable fitting (RSF) energy functional is defined and incorporated into a variational level set formulation, is superior to CV and SPF, and it can get desirable contour lines when there are “holes” in the regions of waters, such as the islands in the lake. Therefore, the RSF model is applied to extracting lake contours from Landsat satellite images. Four temporal Landsat satellite images of the years of 2000, 2005, 2010, and 2014 are used in our study. All of them were acquired in May, with the same path/row (121/036) covering Xuzhou City, Jiangsu Province, China. Firstly, the near infrared (NIR) band is selected for water extraction. Image registration is conducted on NIR bands of different temporal images for information update, and linear stretching is also done in order to distinguish water from other land cover types. Then for the first temporal image acquired in 2000, lake contours are extracted via the RSF model with initialization of user-defined rectangles. Afterwards, using the lake contours extracted the previous temporal image as the initialized values, lake contours are updated for the current temporal image by means of the RSF model. Meanwhile, the changed and unchanged lakes are also detected. The results show that great changes have taken place in two lakes, i.e. Dalong Lake and Panan Lake, and RSF can actually extract and effectively update lake contours using multi-temporal satellite image.

Keywords: level set model, multi-temporal image, lake contour extraction, contour update

Procedia PDF Downloads 366

Authors: Y. B. Idris, M. Sirajo, L. G. Hassan, T. Izuagie, T. Muktar, I. Lawal, A. U. Abubakar

Abstract:

This study investigates the extraction, phytochemical composition, and antimicrobial activity of bioactive compounds from red millipedes using three different solvents: n-Hexane, Chloroform, and Methanol. The largest yield was obtained from the methanol extract, which had percentage yields of 0.8%, 2.2%, and 5.6%, respectively. Terpenoids and sterols were found in all extracts according to preliminary zoochemical screening, but only the methanol extract included saponins and phenols. With a maximum zone of inhibition of 9 mm at 1000 µg/ml, antimicrobial susceptibility tests revealed that the methanol extract had the strongest antibacterial activity, especially against Escherichia coli and Staphylococcus aureus. Significant activity was also shown by the n-hexane extract, although the chloroform extract had only mild antibacterial activity. Tests for minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) verified that the methanol extract was more effective than the other extracts, particularly against S. aureus and S. typhi. None of the extracts, nonetheless, showed any discernible antifungal action. The potential of red millipede extracts, especially those based on methanol, as a source of antimicrobial chemicals for use in the future is highlighted by this work.

Keywords: millipedes, defensive extraction, antibacterial, antifungal, antimicrobial, minimum inhibitory concentration (MIC), minimum bacterial concentration (MBC)

Procedia PDF Downloads 12

Authors: S. Nandagopalan, N. Pradeep

Abstract:

The aim of this paper is to propose a general framework for storing, analyzing, and extracting knowledge from two-dimensional echocardiographic images, color Doppler images, non-medical images, and general data sets. A number of high performance data mining algorithms have been used to carry out this task. Our framework encompasses four layers namely physical storage, object identification, knowledge discovery, user level. Techniques such as active contour model to identify the cardiac chambers, pixel classification to segment the color Doppler echo image, universal model for image retrieval, Bayesian method for classification, parallel algorithms for image segmentation, etc., were employed. Using the feature vector database that have been efficiently constructed, one can perform various data mining tasks like clustering, classification, etc. with efficient algorithms along with image mining given a query image. All these facilities are included in the framework that is supported by state-of-the-art user interface (UI). The algorithms were tested with actual patient data and Coral image database and the results show that their performance is better than the results reported already.

Keywords: active contour, bayesian, echocardiographic image, feature vector

Procedia PDF Downloads 420

Authors: Zaida Perez-Bassart, Berta Polanco-Estibalez, Maria Jose Fabra, Amparo Lopez-Rubio, Antonio Martinez-Abad

Abstract:

Mushroom production has enormously increased in recent years, not only as food products but also for applications in pharmaceuticals, nutraceuticals, and cosmetics. Consequently, interest in its chemical composition, nutritional value, and therapeutic properties has also increased. Fungi are rich in bioactive compounds such as polysaccharides, polyphenols, glycopeptides, and ergosterol, of great medicinal value, but within polysaccharides, β-glucans are the most prominent molecules. They are formed by D-glucose monomers, linked by β-glucosidic bonds β-(1,3) with side chains linked by β-(1,6) bonds. The number and position of the β-(1,6) branches strongly influence the arrangement of the tertiary structure, which, together with the molecular weight, determine the different attributed bioactivities (immunostimulating, anticancer, antimicrobial, prebiotic, etc.) and physico-chemical properties (solubility, bioaccessibility, viscosity or emulsifying). On the other hand, there is a growing interest in the study of fungi as an alternative source of chitin obtained from the by-products of the fungal industry. In this work, a cascade extraction process using aqueous neutral and alkaline treatments was carried out for Grifola frondosa and Lentinula edodes, and the compositional analysis and functional properties of each fraction were characterized. Interestingly, the first fraction obtained by using aqueous treatment at room temperature was the richest in polysaccharides, proteins, and polyphenols, thus obtaining a greater antioxidant capacity than in the other fractions. In contrast, the fractions obtained by alkaline treatments showed a higher degree of β-glucans purification compared to aqueous extractions but a lower extraction yield. Results revealed the different structural recalcitrance of β-glucans, preferentially linked to proteins or chitin depending on the fungus type, which had a direct impact on the functionalities and bioactivities of each fraction.

Keywords: fungi, mushroom, β-glucans, chitin

Procedia PDF Downloads 136

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

Abstract:

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

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

Procedia PDF Downloads 72