Search results for: physiological data extraction
21985 Ensemble of Deep CNN Architecture for Classifying the Source and Quality of Teff Cereal
Authors: Belayneh Matebie, Michael Melese
Abstract:
The study focuses on addressing the challenges in classifying and ensuring the quality of Eragrostis Teff, a small and round grain that is the smallest cereal grain. Employing a traditional classification method is challenging because of its small size and the similarity of its environmental characteristics. To overcome this, this study employs a machine learning approach to develop a source and quality classification system for Teff cereal. Data is collected from various production areas in the Amhara regions, considering two types of cereal (high and low quality) across eight classes. A total of 5,920 images are collected, with 740 images for each class. Image enhancement techniques, including scaling, data augmentation, histogram equalization, and noise removal, are applied to preprocess the data. Convolutional Neural Network (CNN) is then used to extract relevant features and reduce dimensionality. The dataset is split into 80% for training and 20% for testing. Different classifiers, including FVGG16, FINCV3, QSCTC, EMQSCTC, SVM, and RF, are employed for classification, achieving accuracy rates ranging from 86.91% to 97.72%. The ensemble of FVGG16, FINCV3, and QSCTC using the Max-Voting approach outperforms individual algorithms.Keywords: Teff, ensemble learning, max-voting, CNN, SVM, RF
Procedia PDF Downloads 3821984 Mapping of Siltations of AlKhod Dam, Muscat, Sultanate of Oman Using Low-Cost Multispectral Satellite Data
Authors: Sankaran Rajendran
Abstract:
Remote sensing plays a vital role in mapping of resources and monitoring of environments of the earth. In the present research study, mapping and monitoring of clay siltations occurred in the Alkhod Dam of Muscat, Sultanate of Oman are carried out using low-cost multispectral Landsat and ASTER data. The dam is constructed across the Wadi Samail catchment for ground water recharge. The occurrence and spatial distribution of siltations in the dam are studied with five years of interval from the year 1987 of construction to 2014. The deposits are mainly due to the clay, sand, and silt occurrences derived from the weathering rocks of ophiolite sequences occurred in the Wadi Samail catchment. The occurrences of clays are confirmed by minerals identification using ASTER VNIR-SWIR spectral bands and Spectral Angle Mapper supervised image processing method. The presence of clays and their spatial distribution are verified in the field. The study recommends the technique and the low-cost satellite data to similar region of the world.Keywords: Alkhod Dam, ASTER siltation, Landsat, remote sensing, Oman
Procedia PDF Downloads 42921983 Software Development to Empowering Digital Libraries with Effortless Digital Cataloging and Access
Authors: Abdul Basit Kiani
Abstract:
The software for the digital library system is a cutting-edge solution designed to revolutionize the way libraries manage and provide access to their vast collections of digital content. This advanced software leverages the power of technology to offer a seamless and user-friendly experience for both library staff and patrons. By implementing this software, libraries can efficiently organize, store, and retrieve digital resources, including e-books, audiobooks, journals, articles, and multimedia content. Its intuitive interface allows library staff to effortlessly manage cataloging, metadata extraction, and content enrichment, ensuring accurate and comprehensive access to digital materials. For patrons, the software offers a personalized and immersive digital library experience. They can easily browse the digital catalog, search for specific items, and explore related content through intelligent recommendation algorithms. The software also facilitates seamless borrowing, lending, and preservation of digital items, enabling users to access their favorite resources anytime, anywhere, on multiple devices. With robust security features, the software ensures the protection of intellectual property rights and enforces access controls to safeguard sensitive content. Integration with external authentication systems and user management tools streamlines the library's administration processes, while advanced analytics provide valuable insights into patron behavior and content usage. Overall, this software for the digital library system empowers libraries to embrace the digital era, offering enhanced access, convenience, and discoverability of their vast collections. It paves the way for a more inclusive and engaging library experience, catering to the evolving needs of tech-savvy patrons.Keywords: software development, empowering digital libraries, digital cataloging and access, management system
Procedia PDF Downloads 6921982 Development of Sleep Quality Index Using Heart Rate
Authors: Dongjoo Kim, Chang-Sik Son, Won-Seok Kang
Abstract:
Adequate sleep affects various parts of one’s overall physical and mental life. As one of the methods in determining the appropriate amount of sleep, this research presents a heart rate based sleep quality index. In order to evaluate sleep quality using the heart rate, sleep data from 280 subjects taken over one month are used. Their sleep data are categorized by a three-part heart rate range. After categorizing, some features are extracted, and the statistical significances are verified for these features. The results show that some features of this sleep quality index model have statistical significance. Thus, this heart rate based sleep quality index may be a useful discriminator of sleep.Keywords: sleep, sleep quality, heart rate, statistical analysis
Procedia PDF Downloads 33321981 Adsorption of Methyl Violet Dye from Aqueous Solution onto Modified Kapok Sawdust : Characteristics and Equilibrium Studies
Authors: Widi Astuti, Triastuti Sulistyaningsih, Masni Maksiola
Abstract:
Kapok sawdust, an inexpensive material, has been utilized as an adsorbent for the removal of methyl violet in aqueous solution. To increase the adsorption capacity, kapok sawdust was reacted with sodium hydroxide (NaOH) solution having various concentrations. Various physico-chemical parameters such as solution pH, contact time and initial dye concentration were studied. Langmuir, Freundlich and Redlich-Peterson isotherm model were used to analyze the equilibrium data. The research shows that the experimental data fitted well with the Redlich-Peterson model, with the value of constants are 41.001 for KR, 0.523 for aR and 0.799 for g.Keywords: kapok sawdust, methyl violet, dye, adsorption
Procedia PDF Downloads 30621980 Health Monitoring and Failure Detection of Electronic and Structural Components in Small Unmanned Aerial Vehicles
Authors: Gopi Kandaswamy, P. Balamuralidhar
Abstract:
Fully autonomous small Unmanned Aerial Vehicles (UAVs) are increasingly being used in many commercial applications. Although a lot of research has been done to develop safe, reliable and durable UAVs, accidents due to electronic and structural failures are not uncommon and pose a huge safety risk to the UAV operators and the public. Hence there is a strong need for an automated health monitoring system for UAVs with a view to minimizing mission failures thereby increasing safety. This paper describes our approach to monitoring the electronic and structural components in a small UAV without the need for additional sensors to do the monitoring. Our system monitors data from four sources; sensors, navigation algorithms, control inputs from the operator and flight controller outputs. It then does statistical analysis on the data and applies a rule based engine to detect failures. This information can then be fed back into the UAV and a decision to continue or abort the mission can be taken automatically by the UAV and independent of the operator. Our system has been verified using data obtained from real flights over the past year from UAVs of various sizes that have been designed and deployed by us for various applications.Keywords: fault detection, health monitoring, unmanned aerial vehicles, vibration analysis
Procedia PDF Downloads 25121979 Effect of the Interference of Political Elected Members on the Performance of Public Schools
Authors: Farhat Ullah
Abstract:
It is very unfortunate that in Pakistani public schools political interference is on its peak. The present study tries to find out the effect of the interference of political elected members in the affairs of public schools. The objectives of the study were to find out, the degree of interference of political members in public school, the positive and negative effects of political members, influence in public schools, students, and its administrators. This study was quantitative in nature. All the public schools in Khyber Pakhtunkhwa were the population of this study. A sample of 400 teachers and 100 schools heads were selected for this study. A survey questionnaire consisted of 50 items related to objectives, was used for this study. The questionnaire consisted of five options based on Likert scale. Data were collected by the researcher himself from the respondents. Data were analyzed using chi square test. It was concluded from the analysis of data that recently the political members are involved in the process of school activities, which had badly affected the freedom and autonomy of school administrators. Mostly teachers are transferred from schools on political influence, which had created uncertainty among the schools teachers. Further, the student’s academic performance was also affected badly. It is recommended that schools must be free from political involvement for the smooth running of schools.Keywords: public schools, politics, interference, performance
Procedia PDF Downloads 12921978 Accuracy Improvement of Traffic Participant Classification Using Millimeter-Wave Radar by Leveraging Simulator Based on Domain Adaptation
Authors: Tokihiko Akita, Seiichi Mita
Abstract:
A millimeter-wave radar is the most robust against adverse environments, making it an essential environment recognition sensor for automated driving. However, the reflection signal is sparse and unstable, so it is difficult to obtain the high recognition accuracy. Deep learning provides high accuracy even for them in recognition, but requires large scale datasets with ground truth. Specially, it takes a lot of cost to annotate for a millimeter-wave radar. For the solution, utilizing a simulator that can generate an annotated huge dataset is effective. Simulation of the radar is more difficult to match with real world data than camera image, and recognition by deep learning with higher-order features using the simulator causes further deviation. We have challenged to improve the accuracy of traffic participant classification by fusing simulator and real-world data with domain adaptation technique. Experimental results with the domain adaptation network created by us show that classification accuracy can be improved even with a few real-world data.Keywords: millimeter-wave radar, object classification, deep learning, simulation, domain adaptation
Procedia PDF Downloads 8721977 Microclimate Variations in Rio de Janeiro Related to Massive Public Transportation
Authors: Marco E. O. Jardim, Frederico A. M. Souza, Valeria M. Bastos, Myrian C. A. Costa, Nelson F. F. Ebecken
Abstract:
Urban public transportation in Rio de Janeiro is based on bus lines, powered by diesel, and four limited metro lines that support only some neighborhoods. This work presents an infrastructure built to better understand microclimate variations related to massive urban transportation in some specific areas of the city. The use of sensor nodes with small analytics capacity provides environmental information to population or public services. The analyses of data collected from a few small sensors positioned near some heavy traffic streets show the harmful impact due to poor bus route plan.Keywords: big data, IoT, public transportation, public health system
Procedia PDF Downloads 24121976 Evaluation of the Surveillance System for Rift Valley Fever in Ruminants in Mauritania, 2019
Authors: Mohamed El Kory Yacoub, Ahmed Bezeid El Mamy Beyatt, Djibril Barry, Yanogo Pauline, Nicolas Meda
Abstract:
Introduction: Rift Valley Fever is a zoonotic arbovirosis that severely affects ruminants, as well as humans. It causes abortions in pregnant females and deaths in young animals. The disease occurs during heavy rains followed by large numbers of mosquito vectors. The objective of this work is to evaluate the surveillance system for Rift Valley Fever. Methods: We conducted an evaluation of the Rift Valley Fiver surveillance system. Data were collected from the analysis of the national database of the Mauritanian Network of Animal Disease Epidemiological Surveillance at the Ministry of Rural Development, of RVF cases notified from the whole national territory, of questionnaires and interviews with all persons involved in RVF surveillance at the central level. The quality of the system was assessed by analyzing the quantitative attributes defined by the Centers for Disease Control and Prevention. Results: In 2019, 443 cases of RVF were notified by the surveillance system, of which 36 were positive. Among the notified cases of Rift Valley Fever, the 0- to the 3-year-old age group of small ruminants was the most represented with 49.21% of cases, followed by 33.33%, which was recorded in large ruminants in the 0 to 7-year-old age group, 11.11% of cases were older than seven years. The completeness of the data varied between 14.2% (age) and 100% (species). Most positive cases were recorded between October and November 2019 in seven different regions. Attribute analysis showed that 87% of the respondents were able to use the case definition well, and 78.8% said they were familiar with the reporting and feedback loop of the Rift Valley Fever data. 90.3% of the respondents found it easy, while 95% of them responded that it was easy for them to transmit their data to the next level. Conclusions: The epidemiological surveillance system for Rift Valley Fever in Mauritania is simple and representative. However, data quality, stability, and responsiveness are average, as the diagnosis of the disease requires laboratory confirmation and the average delay for this confirmation is long (13 days). Consequently, the lack of completeness of the recorded data and of description of cases in terms of time-place-animal, associated with the delay between the stages of the surveillance system can make prevention, early detection of epidemics, and the initiation of measures for an adequate response difficult.Keywords: evaluation, epidemiological surveillance system, rift valley fever, mauritania, ruminants
Procedia PDF Downloads 14221975 Assessing the Theoretical Suitability of Sentinel-2 and Worldview-3 Data for Hydrocarbon Mapping of Spill Events, Using Hydrocarbon Spectral Slope Model
Authors: K. Tunde Olagunju, C. Scott Allen, Freek Van Der Meer
Abstract:
Identification of hydrocarbon oil in remote sensing images is often the first step in monitoring oil during spill events. Most remote sensing methods adopt techniques for hydrocarbon identification to achieve detection in order to model an appropriate cleanup program. Identification on optical sensors does not only allow for detection but also for characterization and quantification. Until recently, in optical remote sensing, quantification and characterization are only potentially possible using high-resolution laboratory and airborne imaging spectrometers (hyperspectral data). Unlike multispectral, hyperspectral data are not freely available, as this data category is mainly obtained via airborne survey at present. In this research, two (2) operational high-resolution multispectral satellites (WorldView-3 and Sentinel-2) are theoretically assessed for their suitability for hydrocarbon characterization, using the hydrocarbon spectral slope model (HYSS). This method utilized the two most persistent hydrocarbon diagnostic/absorption features at 1.73 µm and 2.30 µm for hydrocarbon mapping on multispectral data. In this research, spectra measurement of seven (7) different hydrocarbon oils (crude and refined oil) taken on ten (10) different substrates with the use of laboratory ASD Fieldspec were convolved to Sentinel-2 and WorldView-3 resolution, using their full width half maximum (FWHM) parameter. The resulting hydrocarbon slope values obtained from the studied samples enable clear qualitative discrimination of most hydrocarbons, despite the presence of different background substrates, particularly on WorldView-3. Due to close conformity of central wavelengths and narrow bandwidths to key hydrocarbon bands used in HYSS, the statistical significance for qualitative analysis on WorldView-3 sensors for all studied hydrocarbon oil returned with 95% confidence level (P-value ˂ 0.01), except for Diesel. Using multifactor analysis of variance (MANOVA), the discriminating power of HYSS is statistically significant for most hydrocarbon-substrate combinations on Sentinel-2 and WorldView-3 FWHM, revealing the potential of these two operational multispectral sensors as rapid response tools for hydrocarbon mapping. One notable exception is highly transmissive hydrocarbons on Sentinel-2 data due to the non-conformity of spectral bands with key hydrocarbon absorptions and the relatively coarse bandwidth (> 100 nm).Keywords: hydrocarbon, oil spill, remote sensing, hyperspectral, multispectral, hydrocarbon-substrate combination, Sentinel-2, WorldView-3
Procedia PDF Downloads 21221974 A Support Vector Machine Learning Prediction Model of Evapotranspiration Using Real-Time Sensor Node Data
Authors: Waqas Ahmed Khan Afridi, Subhas Chandra Mukhopadhyay, Bandita Mainali
Abstract:
The research paper presents a unique approach to evapotranspiration (ET) prediction using a Support Vector Machine (SVM) learning algorithm. The study leverages real-time sensor node data to develop an accurate and adaptable prediction model, addressing the inherent challenges of traditional ET estimation methods. The integration of the SVM algorithm with real-time sensor node data offers great potential to improve spatial and temporal resolution in ET predictions. In the model development, key input features are measured and computed using mathematical equations such as Penman-Monteith (FAO56) and soil water balance (SWB), which include soil-environmental parameters such as; solar radiation (Rs), air temperature (T), atmospheric pressure (P), relative humidity (RH), wind speed (u2), rain (R), deep percolation (DP), soil temperature (ST), and change in soil moisture (∆SM). The one-year field data are split into combinations of three proportions i.e. train, test, and validation sets. While kernel functions with tuning hyperparameters have been used to train and improve the accuracy of the prediction model with multiple iterations. This paper also outlines the existing methods and the machine learning techniques to determine Evapotranspiration, data collection and preprocessing, model construction, and evaluation metrics, highlighting the significance of SVM in advancing the field of ET prediction. The results demonstrate the robustness and high predictability of the developed model on the basis of performance evaluation metrics (R2, RMSE, MAE). The effectiveness of the proposed model in capturing complex relationships within soil and environmental parameters provide insights into its potential applications for water resource management and hydrological ecosystem.Keywords: evapotranspiration, FAO56, KNIME, machine learning, RStudio, SVM, sensors
Procedia PDF Downloads 5821973 Explanation of the Main Components of the Unsustainability of Cooperative Institutions in Cooperative Management Projects to Combat Desertification in South Khorasan Province
Authors: Yaser Ghasemi Aryan, Firoozeh Moghiminejad, Mohammadreza Shahraki
Abstract:
Background: The cooperative institution is considered the first and most essential pillar of strengthening social capital, whose sustainability is the main guarantee of survival and continued participation of local communities in natural resource management projects. The Village Development Group and the Microcredit Fund are two important social and economic institutions in the implementation of the International Project for the Restoration of Degraded Forest Lands (RFLDL) in Sarayan City, South Khorasan Province, which has learned positive lessons from the participation of the beneficiaries in the implementation. They have brought more effective projects to deal with desertification. However, the low activity or liquidation of some of these institutions has become one of the important challenges and concerns of project executive experts. The current research was carried out with the aim of explaining the main components of the instability of these institutions. Materials and Methods: This research is descriptive-analytical in terms of method, practical in terms of purpose, and the method of collecting information is two documentary and survey methods. The statistical population of the research included all the members of the village development groups and microcredit funds in the target villages of the RFLDL project of Sarayan city, based on the Kochran formula and matching with the Karjesi and Morgan table. Net people were selected as a statistical sample. After confirming the validity of the expert's opinions, the reliability of the questionnaire was 0.83, which shows the appropriate reliability of the researcher-made questionnaire. Data analysis was done using SPSS software. Results: The results related to the extraction of obstacles to the stability of social and economic networks were classified and prioritized in the form of 5 groups of social-cultural, economic, administrative, educational-promotional and policy-management factors. Based on this, in the socio-cultural factors, the items ‘not paying attention to the structural characteristics and composition of groups’, ‘lack of commitment and moral responsibility in some members of the group,’ and ‘lack of a clear pattern for the preservation and survival of groups’, in the disciplinary factors, The items ‘Irregularity in holding group meetings’ and ‘Irregularity of members to participate in meetings’, in the economic factors of the items "small financial capital of the fund’, ‘the low amount of loans of the fund’ and ‘the fund's inability to conclude contracts and attract capital from other sources’, in the educational-promotional factors of the items ‘non-simultaneity of job training with the granting of loans to create jobs’ and ‘insufficient training for the effective use of loans and job creation’ and in the policy-management factors of the item ‘failure to provide government facilities for support From the funds, they had the highest priority. Conclusion: In general, the results of this research show that policy-management factors and social factors, especially the structure and composition of social and economic institutions, are the most important obstacles to their sustainability. Therefore, it is suggested to form cooperative institutions based on network analysis studies in order to achieve the appropriate composition of members.Keywords: cooperative institution, social capital, network analysis, participation, Sarayan.
Procedia PDF Downloads 4321972 FPGA Implementation of RSA Encryption Algorithm for E-Passport Application
Authors: Khaled Shehata, Hanady Hussien, Sara Yehia
Abstract:
Securing the data stored on E-passport is a very important issue. RSA encryption algorithm is suitable for such application with low data size. In this paper the design and implementation of 1024 bit-key RSA encryption and decryption module on an FPGA is presented. The module is verified through comparing the result with that obtained from MATLAB tools. The design runs at a frequency of 36.3 MHz on Virtex-5 Xilinx FPGA. The key size is designed to be 1024-bit to achieve high security for the passport information. The whole design is achieved through VHDL design entry which makes it a portable design and can be directed to any hardware platform.Keywords: RSA, VHDL, FPGA, modular multiplication, modular exponential
Procedia PDF Downloads 38221971 An Experimental Study for Assessing Email Classification Attributes Using Feature Selection Methods
Authors: Issa Qabaja, Fadi Thabtah
Abstract:
Email phishing classification is one of the vital problems in the online security research domain that have attracted several scholars due to its impact on the users payments performed daily online. One aspect to reach a good performance by the detection algorithms in the email phishing problem is to identify the minimal set of features that significantly have an impact on raising the phishing detection rate. This paper investigate three known feature selection methods named Information Gain (IG), Chi-square and Correlation Features Set (CFS) on the email phishing problem to separate high influential features from low influential ones in phishing detection. We measure the degree of influentially by applying four data mining algorithms on a large set of features. We compare the accuracy of these algorithms on the complete features set before feature selection has been applied and after feature selection has been applied. After conducting experiments, the results show 12 common significant features have been chosen among the considered features by the feature selection methods. Further, the average detection accuracy derived by the data mining algorithms on the reduced 12-features set was very slight affected when compared with the one derived from the 47-features set.Keywords: data mining, email classification, phishing, online security
Procedia PDF Downloads 42421970 Knowledge Development: How New Information System Technologies Affect Knowledge Development
Authors: Yener Ekiz
Abstract:
Knowledge development is a proactive process that covers collection, analysis, storage and distribution of information that helps to contribute the understanding of the environment. To transfer knowledge correctly and fastly, you have to use new emerging information system technologies. Actionable knowledge is only of value if it is understandable and usable by target users. The purpose of the paper is to enlighten how technology eases and affects the process of knowledge development. While preparing the paper, literature review, survey and interview methodology will be used. The hypothesis is that the technology and knowledge development are inseparable and the technology will formalize the DIKW hierarchy again. As a result, today there is huge data. This data must be classified sharply and quickly.Keywords: DIKW hierarchy, knowledge development, technology
Procedia PDF Downloads 43121969 A Study on Utilizing Temporary Water Treatment Facilities to Tackle Century-Long Drought and Emergency Water Supply
Authors: Yu-Che Cheng, Min-Lih Chang, Ke-Hao Cheng, Chuan-Cheng Wang
Abstract:
Taiwan is an island located along the southeastern coast of the Asian continent, located between Japan and the Philippines. It is surrounded by the sea on all sides. However, due to the presence of the Central Mountain Range, the rivers on the east and west coasts of Taiwan are relatively short. This geographical feature results in a phenomenon where, despite having rainfall that is 2.6 times the world average, 58.5% of the rainwater flows into the ocean. Moreover, approximately 80% of the annual rainfall occurs between May and October, leading to distinct wet and dry periods. To address these challenges, Taiwan relies on large reservoirs, storage ponds, and groundwater extraction for water resource allocation. It is necessary to construct water treatment facilities at suitable locations to provide the population with a stable and reliable water supply. In general, the construction of a new water treatment plant requires careful planning and evaluation. The process involves acquiring land and issuing contracts for construction in a sequential manner. With the increasing severity of global warming and climate change, there is a heightened risk of extreme hydrological events and severe water situations in the future. In cases of urgent water supply needs in a region, relying on traditional lengthy processes for constructing water treatment plants might not be sufficient to meet the urgent demand. Therefore, this study aims to explore the use of simplified water treatment procedures and the construction of rapid "temporary water treatment plants" to tackle the challenges posed by extreme climate conditions (such as a century-long drought) and situations where water treatment plant construction cannot keep up with the pace of water source development.Keywords: temporary water treatment plant, emergency water supply, construction site groundwater, drought
Procedia PDF Downloads 7521968 Intelligent Technology for Real-Time Monitor and Data Analysis of the Aquaculture Toxic Water Concentration
Authors: Chin-Yuan Hsieh, Wei-Chun Lu, Yu-Hong Zeng
Abstract:
The situation of a group of fish die is frequently found due to the fish disease caused by the deterioration of aquaculture water quality. The toxic ammonia is produced by animals as a byproduct of protein. The system is designed by the smart sensor technology and developed by the mathematical model to monitor the water parameters 24 hours a day and predict the relationship among twelve water quality parameters for monitoring the water quality in aquaculture. All data measured are stored in cloud server. In productive ponds, the daytime pH may be high enough to be lethal to the fish. The sudden change of the aquaculture conditions often results in the increase of PH value of water, lack of oxygen dissolving content, water quality deterioration and yield reduction. From the real measurement, the system can send the message to user’s smartphone successfully on the bad conditions of water quality. From the data comparisons between measurement and model simulation in fish aquaculture site, the difference of parameters is less than 2% and the correlation coefficient is at least 98.34%. The solubility rate of oxygen decreases exponentially with the elevation of water temperature. The correlation coefficient is 98.98%.Keywords: aquaculture, sensor, ammonia, dissolved oxygen
Procedia PDF Downloads 27021967 DMBR-Net: Deep Multiple-Resolution Bilateral Networks for Real-Time and Accurate Semantic Segmentation
Authors: Pengfei Meng, Shuangcheng Jia, Qian Li
Abstract:
We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling
Procedia PDF Downloads 13921966 Monitoring Soil Organic Amendments Under Arid Climate: Evolution of Soil Quality and of Two Consecutive Barley Crops
Authors: Houda Oueriemmi, Petra Susan Kidd, Carmen Trasar-Cepeda, Beatriz Rodríguez-Garrido, Mohamed Moussa, Ángeles Prieto-Fernández, Mohamed Ouessar
Abstract:
Organic amendments are generally used for improving the fertility of arid and semi-arid soils. However, the price of farmyard manure, the organic amendment typically applied to many arid and semi-arid soils has highly increased in the last years. To investigate at field scale whether cheap, highly available organic amendments, such as sewage sludge compost and municipal solid waste compost, may be acceptable as substitutes for farmyard manure is therefore of great interest. A field plots experiment was carried out to assess the effects of a single application of three organic amendments on soil fertility, distribution of trace elements and on barley yield. Municipal solid waste compost (MSWC), farmyard manure (FYM) and sewage sludge compost (SSC) were applied at rates of 0, 20, 40 and 60 t ha⁻¹, and barley was cultivated in two consecutive years. Plant samples and soils were collected for laboratory analyses after two consecutive harvests. Compared with unamended soil, the application of the three organic residues improved the fertility of the topsoil, showing a significant dose-dependent increase of TOC, N, P contents up to the highest dose of 60 t ha⁻¹ (0.74%, 0.06% and 40 mg kg⁻¹, respectively). The enhancement of soil nutrient status impacted positively on grain yield (up to 51%). The distribution of trace elements in the soil, analysed by a sequential extraction procedure, revealed that the MSWC increased the acid-extractable Co and Cu and reducible Ni, while SSC increased reducible Co and Ni and oxidisable Cu, relative to the control soil.Keywords: municipal solid waste compost, sewage sludge compost, fertility, trace metals
Procedia PDF Downloads 8121965 Recent Findings of Late Bronze Age Mining and Archaeometallurgy Activities in the Mountain Region of Colchis (Southern Lechkhumi, Georgia)
Authors: Rusudan Chagelishvili, Nino Sulava, Tamar Beridze, Nana Rezesidze, Nikoloz Tatuashvili
Abstract:
The South Caucasus is one of the most important centers of prehistoric metallurgy, known for its Colchian bronze culture. Modern Lechkhumi – historical Mountainous Colchis where the existence of prehistoric metallurgy is confirmed by the discovery of many artifacts is a part of this area. Studies focused on prehistoric smelting sites, related artefacts, and ore deposits have been conducted during last ten years in Lechkhumi. More than 20 prehistoric smelting sites and artefacts associated with metallurgical activities (ore roasting furnaces, slags, crucible, and tuyères fragments) have been identified so far. Within the framework of integrated studies was established that these sites were operating in 13-9 centuries B.C. and used for copper smelting. Palynological studies of slags revealed that chestnut (Castanea sativa) and hornbeam (Carpinus sp.) wood were used as smelting fuel. Geological exploration-analytical studies revealed that copper ore mining, processing, and smelting sites were distributed close to each other. Despite recent complex data, the signs of prehistoric mines (trenches) haven’t been found in this part of the study area so far. Since 2018 the archaeological-geological exploration has been focused on the southern part of Lechkhumi and covered the areas of villages Okureshi and Opitara. Several copper smelting sites (Okureshi 1 and 2, Opitara 1), as well as a Colchian Bronze culture settlement, have been identified here. Three mine workings have been found in the narrow gorge of the river Rtkhmelebisgele in the vicinities of the village Opitara. In order to establish a link between the Opitara-Okureshi archaeometallurgical sites, Late Bronze Age settlements, and mines, various scientific analytical methods -mineralized rock and slags petrography and atomic absorption spectrophotometry (AAS) analysis have been applied. The careful examination of Opitara mine workings revealed that there is a striking difference between the mine #1 on the right bank of the river and mines #2 and #3 on the left bank. The first one has all characteristic features of the Soviet period mine working (e. g. high portal with angular ribs and roof showing signs of blasting). In contrast, mines #2 and #3, which are located very close to each other, have round-shaped portals/entrances, low roofs, and fairly smooth ribs and are filled with thick layers of river sediments and collapsed weathered rock mass. A thorough review of the publications related to prehistoric mine workings revealed some striking similarities between mines #2 and #3 with their worldwide analogues. Apparently, the ore extraction from these mines was conducted by fire-setting applying primitive tools. It was also established that mines are cut in Jurassic mineralized volcanic rocks. Ore minerals (chalcopyrite, pyrite, galena) are related to calcite and quartz veins. The results obtained through the petrochemical and petrography studies of mineralized rock samples from Opitara mines and prehistoric slags are in complete correlation with each other, establishing the direct link between copper mining and smelting within the study area. Acknowledgment: This work was supported by the Shota Rustaveli National Science Foundation of Georgia (grant # FR-19-13022).Keywords: archaeometallurgy, Mountainous Colchis, mining, ore minerals
Procedia PDF Downloads 17221964 A Stochastic Diffusion Process Based on the Two-Parameters Weibull Density Function
Authors: Meriem Bahij, Ahmed Nafidi, Boujemâa Achchab, Sílvio M. A. Gama, José A. O. Matos
Abstract:
Stochastic modeling concerns the use of probability to model real-world situations in which uncertainty is present. Therefore, the purpose of stochastic modeling is to estimate the probability of outcomes within a forecast, i.e. to be able to predict what conditions or decisions might happen under different situations. In the present study, we present a model of a stochastic diffusion process based on the bi-Weibull distribution function (its trend is proportional to the bi-Weibull probability density function). In general, the Weibull distribution has the ability to assume the characteristics of many different types of distributions. This has made it very popular among engineers and quality practitioners, who have considered it the most commonly used distribution for studying problems such as modeling reliability data, accelerated life testing, and maintainability modeling and analysis. In this work, we start by obtaining the probabilistic characteristics of this model, as the explicit expression of the process, its trends, and its distribution by transforming the diffusion process in a Wiener process as shown in the Ricciaardi theorem. Then, we develop the statistical inference of this model using the maximum likelihood methodology. Finally, we analyse with simulated data the computational problems associated with the parameters, an issue of great importance in its application to real data with the use of the convergence analysis methods. Overall, the use of a stochastic model reflects only a pragmatic decision on the part of the modeler. According to the data that is available and the universe of models known to the modeler, this model represents the best currently available description of the phenomenon under consideration.Keywords: diffusion process, discrete sampling, likelihood estimation method, simulation, stochastic diffusion process, trends functions, bi-parameters weibull density function
Procedia PDF Downloads 30221963 Knowledge Graph Development to Connect Earth Metadata and Standard English Queries
Authors: Gabriel Montague, Max Vilgalys, Catherine H. Crawford, Jorge Ortiz, Dava Newman
Abstract:
There has never been so much publicly accessible atmospheric and environmental data. The possibilities of these data are exciting, but the sheer volume of available datasets represents a new challenge for researchers. The task of identifying and working with a new dataset has become more difficult with the amount and variety of available data. Datasets are often documented in ways that differ substantially from the common English used to describe the same topics. This presents a barrier not only for new scientists, but for researchers looking to find comparisons across multiple datasets or specialists from other disciplines hoping to collaborate. This paper proposes a method for addressing this obstacle: creating a knowledge graph to bridge the gap between everyday English language and the technical language surrounding these datasets. Knowledge graph generation is already a well-established field, although there are some unique challenges posed by working with Earth data. One is the sheer size of the databases – it would be infeasible to replicate or analyze all the data stored by an organization like The National Aeronautics and Space Administration (NASA) or the European Space Agency. Instead, this approach identifies topics from metadata available for datasets in NASA’s Earthdata database, which can then be used to directly request and access the raw data from NASA. By starting with a single metadata standard, this paper establishes an approach that can be generalized to different databases, but leaves the challenge of metadata harmonization for future work. Topics generated from the metadata are then linked to topics from a collection of English queries through a variety of standard and custom natural language processing (NLP) methods. The results from this method are then compared to a baseline of elastic search applied to the metadata. This comparison shows the benefits of the proposed knowledge graph system over existing methods, particularly in interpreting natural language queries and interpreting topics in metadata. For the research community, this work introduces an application of NLP to the ecological and environmental sciences, expanding the possibilities of how machine learning can be applied in this discipline. But perhaps more importantly, it establishes the foundation for a platform that can enable common English to access knowledge that previously required considerable effort and experience. By making this public data accessible to the full public, this work has the potential to transform environmental understanding, engagement, and action.Keywords: earth metadata, knowledge graphs, natural language processing, question-answer systems
Procedia PDF Downloads 14021962 Parabolic Impact Law of High Frequency Exchanges on Price Formation in Commodities Market
Authors: L. Maiza, A. Cantagrel, M. Forestier, G. Laucoin, T. Regali
Abstract:
Evaluation of High Frequency Trading (HFT) impact on financial markets is very important for traders who use market analysis to detect winning transaction opportunity. Analysis of HFT data on tobacco commodity market is discussed here and interesting linear relationship has been shown between trading frequency and difference between averaged trading prices above and below considered trading frequency. This may open new perspectives on markets data understanding and could provide possible interpretation of Adam Smith invisible hand.Keywords: financial market, high frequency trading, analysis, impacts, Adam Smith invisible hand
Procedia PDF Downloads 35221961 Improving Data Completeness and Timely Reporting: A Joint Collaborative Effort between Partners in Health and Ministry of Health in Remote Areas, Neno District, Malawi
Authors: Wiseman Emmanuel Nkhomah, Chiyembekezo Kachimanga, Moses Banda Aron, Julia Higgins, Manuel Mulwafu, Kondwani Mpinga, Mwayi Chunga, Grace Momba, Enock Ndarama, Dickson Sumphi, Atupere Phiri, Fabien Munyaneza
Abstract:
Background: Data is key to supporting health service delivery as stakeholders, including NGOs rely on it for effective service delivery, decision-making, and system strengthening. Several studies generated debate on data quality from national health management information systems (HMIS) in sub-Saharan Africa. This limits the utilization of data in resource-limited settings, which already struggle to meet standards set by the World Health Organization (WHO). We aimed to evaluate data quality improvement of Neno district HMIS over a 4-year period (2018 – 2021) following quarterly data reviews introduced in January 2020 by the district health management team and Partners In Health. Methods: Exploratory Mixed Research was used to examine report rates, followed by in-depth interviews using Key Informant Interviews (KIIs) and Focus Group Discussions (FGDs). We used the WHO module desk review to assess the quality of HMIS data in the Neno district captured from 2018 to 2021. The metrics assessed included the completeness and timeliness of 34 reports. Completeness was measured as a percentage of non-missing reports. Timeliness was measured as the span between data inputs and expected outputs meeting needs. We computed T-Test and recorded P-values, summaries, and percentage changes using R and Excel 2016. We analyzed demographics for key informant interviews in Power BI. We developed themes from 7 FGDs and 11 KIIs using Dedoose software, from which we picked perceptions of healthcare workers, interventions implemented, and improvement suggestions. The study was reviewed and approved by Malawi National Health Science Research Committee (IRB: 22/02/2866). Results: Overall, the average reporting completeness rate was 83.4% (before) and 98.1% (after), while timeliness was 68.1% and 76.4 respectively. Completeness of reports increased over time: 2018, 78.8%; 2019, 88%; 2020, 96.3% and 2021, 99.9% (p< 0.004). The trend for timeliness has been declining except in 2021, where it improved: 2018, 68.4%; 2019, 68.3%; 2020, 67.1% and 2021, 81% (p< 0.279). Comparing 2021 reporting rates to the mean of three preceding years, both completeness increased from 88% to 99% (in 2021), while timeliness increased from 68% to 81%. Sixty-five percent of reports have maintained meeting a national standard of 90%+ in completeness while only 24% in timeliness. Thirty-two percent of reports met the national standard. Only 9% improved on both completeness and timeliness, and these are; cervical cancer, nutrition care support and treatment, and youth-friendly health services reports. 50% of reports did not improve to standard in timeliness, and only one did not in completeness. On the other hand, factors associated with improvement included improved communications and reminders using internal communication, data quality assessments, checks, and reviews. Decentralizing data entry at the facility level was suggested to improve timeliness. Conclusion: Findings suggest that data quality in HMIS for the district has improved following collaborative efforts. We recommend maintaining such initiatives to identify remaining quality gaps and that results be shared publicly to support increased use of data. These results can inform Ministry of Health and its partners on some interventions and advise initiatives for improving its quality.Keywords: data quality, data utilization, HMIS, collaboration, completeness, timeliness, decision-making
Procedia PDF Downloads 7721960 Entrepreneurs’ Perceptions of the Economic, Social and Physical Impacts of Tourism
Authors: Oktay Emir
Abstract:
The objective of this study is to determine how entrepreneurs perceive the economic, social and physical impacts of tourism. The study was conducted in the city of Afyonkarahisar, Turkey, which is rich in thermal tourism resources and investments. A survey was used as the data collection method, and the questionnaire was applied to 472 entrepreneurs. A simple random sampling method was used to identify the sample. Independent sampling t-tests and ANOVA tests were used to analyse the data obtained. Additionally, some statistically significant differences (p<0.05) were found based on the participants’ demographic characteristics regarding their opinions about the social, economic and physical impacts of tourism activities.Keywords: tourism, perception, entrepreneurship, entrepreneurs, structural equation modelling
Procedia PDF Downloads 44521959 Unsupervised Learning and Similarity Comparison of Water Mass Characteristics with Gaussian Mixture Model for Visualizing Ocean Data
Authors: Jian-Heng Wu, Bor-Shen Lin
Abstract:
The temperature-salinity relationship is one of the most important characteristics used for identifying water masses in marine research. Temperature-salinity characteristics, however, may change dynamically with respect to the geographic location and is quite sensitive to the depth at the same location. When depth is taken into consideration, however, it is not easy to compare the characteristics of different water masses efficiently for a wide range of areas of the ocean. In this paper, the Gaussian mixture model was proposed to analyze the temperature-salinity-depth characteristics of water masses, based on which comparison between water masses may be conducted. Gaussian mixture model could model the distribution of a random vector and is formulated as the weighting sum for a set of multivariate normal distributions. The temperature-salinity-depth data for different locations are first used to train a set of Gaussian mixture models individually. The distance between two Gaussian mixture models can then be defined as the weighting sum of pairwise Bhattacharyya distances among the Gaussian distributions. Consequently, the distance between two water masses may be measured fast, which allows the automatic and efficient comparison of the water masses for a wide range area. The proposed approach not only can approximate the distribution of temperature, salinity, and depth directly without the prior knowledge for assuming the regression family, but may restrict the complexity by controlling the number of mixtures when the amounts of samples are unevenly distributed. In addition, it is critical for knowledge discovery in marine research to represent, manage and share the temperature-salinity-depth characteristics flexibly and responsively. The proposed approach has been applied to a real-time visualization system of ocean data, which may facilitate the comparison of water masses by aggregating the data without degrading the discriminating capabilities. This system provides an interface for querying geographic locations with similar temperature-salinity-depth characteristics interactively and for tracking specific patterns of water masses, such as the Kuroshio near Taiwan or those in the South China Sea.Keywords: water mass, Gaussian mixture model, data visualization, system framework
Procedia PDF Downloads 13521958 Optimal Data Selection in Non-Ergodic Systems: A Tradeoff between Estimator Convergence and Representativeness Errors
Authors: Jakob Krause
Abstract:
Past Financial Crisis has shown that contemporary risk management models provide an unjustified sense of security and fail miserably in situations in which they are needed the most. In this paper, we start from the assumption that risk is a notion that changes over time and therefore past data points only have limited explanatory power for the current situation. Our objective is to derive the optimal amount of representative information by optimizing between the two adverse forces of estimator convergence, incentivizing us to use as much data as possible, and the aforementioned non-representativeness doing the opposite. In this endeavor, the cornerstone assumption of having access to identically distributed random variables is weakened and substituted by the assumption that the law of the data generating process changes over time. Hence, in this paper, we give a quantitative theory on how to perform statistical analysis in non-ergodic systems. As an application, we discuss the impact of a paragraph in the last iteration of proposals by the Basel Committee on Banking Regulation. We start from the premise that the severity of assumptions should correspond to the robustness of the system they describe. Hence, in the formal description of physical systems, the level of assumptions can be much higher. It follows that every concept that is carried over from the natural sciences to economics must be checked for its plausibility in the new surroundings. Most of the probability theory has been developed for the analysis of physical systems and is based on the independent and identically distributed (i.i.d.) assumption. In Economics both parts of the i.i.d. assumption are inappropriate. However, only dependence has, so far, been weakened to a sufficient degree. In this paper, an appropriate class of non-stationary processes is used, and their law is tied to a formal object measuring representativeness. Subsequently, that data set is identified that on average minimizes the estimation error stemming from both, insufficient and non-representative, data. Applications are far reaching in a variety of fields. In the paper itself, we apply the results in order to analyze a paragraph in the Basel 3 framework on banking regulation with severe implications on financial stability. Beyond the realm of finance, other potential applications include the reproducibility crisis in the social sciences (but not in the natural sciences) and modeling limited understanding and learning behavior in economics.Keywords: banking regulation, non-ergodicity, risk management, semimartingale modeling
Procedia PDF Downloads 13821957 Sustainable Happiness of Thai People: Monitoring the Thai Happiness Index
Authors: Kalayanee Senasu
Abstract:
This research investigates the influences of different factors on the happiness of Thai people, including both general factors and sustainable ones. Additionally, this study also monitors Thai people’s happiness via Thai Happiness Index developed in 2017. Besides reflecting happiness level of Thai people, this index also identifies related important issues. The data were collected by both secondary related data and primary survey data collected by interviewed questionnaires. The research data were from stratified multi-stage sampling in region, province, district, and enumeration area, and simple random sampling in each enumeration area. The research data cover 20 provinces, including Bangkok and 4-5 provinces in each region of the North, Northeastern, Central, and South. There were 4,960 usable respondents who were at least 15 years old. Statistical analyses included both descriptive and inferential statistics, including hierarchical regression and one-way ANOVA. The Alkire and Foster method was adopted to develop and calculate the Thai happiness index. The results reveal that the quality of household economy plays the most important role in predicting happiness. The results also indicate that quality of family, quality of health, and effectiveness of public administration in the provincial level have positive effects on happiness at about similar levels. For the socio-economic factors, the results reveal that age, education level, and household revenue have significant effects on happiness. For computing Thai happiness index (THaI), the result reveals the 2018 THaI value is 0.556. When people are divided into four groups depending upon their degree of happiness, it is found that a total of 21.1% of population are happy, with 6.0% called deeply happy and 15.1% called extensively happy. A total of 78.9% of population are not-yet-happy, with 31.8% called narrowly happy, and 47.1% called unhappy. A group of happy population reflects the happiness index THaI valued of 0.789, which is much higher than the THaI valued of 0.494 of the not-yet-happy population. Overall Thai people have higher happiness compared to 2017 when the happiness index was 0.506.Keywords: happiness, quality of life, sustainability, Thai Happiness Index
Procedia PDF Downloads 16121956 Using Electrical Impedance Tomography to Control a Robot
Authors: Shayan Rezvanigilkolaei, Shayesteh Vefaghnematollahi
Abstract:
Electrical impedance tomography is a non-invasive medical imaging technique suitable for medical applications. This paper describes an electrical impedance tomography device with the ability to navigate a robotic arm to manipulate a target object. The design of the device includes various hardware and software sections to perform medical imaging and control the robotic arm. In its hardware section an image is formed by 16 electrodes which are located around a container. This image is used to navigate a 3DOF robotic arm to reach the exact location of the target object. The data set to form the impedance imaging is obtained by having repeated current injections and voltage measurements between all electrode pairs. After performing the necessary calculations to obtain the impedance, information is transmitted to the computer. This data is fed and then executed in MATLAB which is interfaced with EIDORS (Electrical Impedance Tomography Reconstruction Software) to reconstruct the image based on the acquired data. In the next step, the coordinates of the center of the target object are calculated by image processing toolbox of MATLAB (IPT). Finally, these coordinates are used to calculate the angles of each joint of the robotic arm. The robotic arm moves to the desired tissue with the user command.Keywords: electrical impedance tomography, EIT, surgeon robot, image processing of electrical impedance tomography
Procedia PDF Downloads 268