Search results for: data acquisition

Authors: Amreth Chandrasehar

Abstract:

Machine Learning (ML) Models are developed and run in production to solve various use cases that help organizations to be more efficient and help drive the business. But this comes at a massive development cost and lost business opportunities. According to the Gartner report, 85% of data science projects fail, and one of the factors impacting this is not paying attention to Model Observability. Model Observability helps the developers and operators to pinpoint the model performance issues data drift and help identify root cause of issues. This paper focuses on providing insights into incorporating model observability in model development and operationalizing it in production.

Keywords: model observability, monitoring, drift detection, ML observability platform

Procedia PDF Downloads 88

Authors: Precious Roselyn Obuobi

Abstract:

Background: In Ghana, water-borne diseases remain a public health concern due to its impact. While marine pollution has been linked to outbreak of diseases especially in communities along the coast, associated risks such as oil spillage, marine debris, erosion, improper waste disposal and management practices persist. Objective: The study seeks to investigate sanitation practices that contribute to marine pollution in Prampram and the prevalence of selected water-borne diseases (diarrhea and typhoid fever). Method: This study used a descriptive cross-sectional design, employing the mix-method (qualitative and quantitative) approach. Twenty-two (22) participants were selected and semistructured questionnaire were administered to them. Additionally, interviews were conducted to collect more information. Further, an observation check-list was used to aid the data collection process. Secondary data comprising information on water-borne diseases in the district was acquired from the district health directorate to determine the prevalence of selected water-borne diseases in the community. Data Analysis: The qualitative data was analyzed using NVIVO® software by adapting the six steps thematic analysis by Braun and Clarke whiles STATA® version 16 was used to analyze the secondary data collected from the district health directorate. A descriptive statistic employed using mean, standard deviation, frequencies and proportions were used to summarize the results. Results: The results showed that open defecation and indiscriminate waste disposal were the main practices contributing to marine pollution in Prampram and its effect on public health. Conclusion: These findings have implications on public health and the environment, thus effort needs to be stepped up in educating the community on best sanitation practices.

Keywords: environment, sanitation, marine pollution, water-borne diseases

Procedia PDF Downloads 53

Authors: Ilham S. M. Elsayed

Abstract:

The purpose of this study is to investigate Alahsa Governorate status and its vulnerability to generate urban heat islands. Alahsa Governorate is a famous oasis in the Arabic Peninsula including several oil centers. Extensive literature review was done to collect previous relative data on the urban heat island of Alahsa Governorate. Data used for the purpose of this research were collected from authorized bodies who control weather station networks over Alahsa Governorate, Eastern Province, Saudi Arabia. Although, the number of weather station networks within the region is very limited and the analysis using GIS software and its techniques is difficult and limited, the data analyzed confirm an increase in temperature for more than 2 °C from 2004 to 2014. Such increase is considerable whenever human health and comfort are the concern. The increase of temperature within one decade confirms the availability of urban heat islands. The study concludes that, Alahsa Governorate is vulnerable to create urban heat islands and more attention should be drawn to strategic planning of the governorate that is developing with a high pace and considerable increasing levels of urbanization.

Keywords: Alahsa Governorate, population density, Urban Heat Island, weather station

Procedia PDF Downloads 231

Authors: Anucha Wittayakorn-Puripunpinyoo

Abstract:

The research objectives were 1) to study the situation and its trend of agricultural product export of Thailand 2) to study the impact of agricultural product export on income of Thai economy 3) the impact of agricultural product export on employment of Thai economy and 4) to find out the recommendations of agricultural product export policy of Thailand. In this research, secondary data were collected as yearly time series data from 1990 to 2016 accounted for 27 years. Data were collected from the Bank of Thailand database. Primary data were collected from the steakholders of agricultural product export policy of Thailand. Data analysis was applied descriptive statistics such as arithmetic mean, standard deviation. The forecasting of agricultural product was applied Mote Carlo Simulation technique as well as time trend analysis. In addition, the impact of agricultural product export on income and employment by applying econometric model while the estimated parameters were utilized the ordinary least square technique. The research results revealed that 1) agricultural product export value of Thailand from 1990 to 2016 was 338,959.5 Million Thai baht with its growth rate of 4.984 percent yearly, in addition, the forecasting of agricultural product export value of Thailand has increased but its growth rate has been declined 2) the impact of agricultural product export has positive impact on income in Thai economy, increasing in agricultural product export of Thailand by 1 percent would lead income increased by 0.0051 percent 3) the impact of agricultural product export has positive impact on employment in Thai economy, increasing in agricultural product export of Thailand by 1 percent would lead income increased by 0.079 percent and 4) in the future, agricultural product export policy would focused on finished or semi-finished agricultural product instead of raw material by applying technology and innovation in to make value added of agricultural product export. The public agricultural product export policy would support exporters in private sector in order to encourage them as agricultural exporters in Thailand.

Keywords: agricultural product export, income, employment, Thai economy

Procedia PDF Downloads 290

Authors: Magdalena Idzikowska, Katarzyna Pająk, Kamil Kowalczyk

Abstract:

Seafloor topography is a fundamental issue in geological, geophysical, and oceanographic studies. Single-beam or multibeam sonars attached to the hulls of ships are used to emit a hydroacoustic signal from transducers and reproduce the topography of the seabed. This solution provides relevant accuracy and spatial resolution. Bathymetric data from ships surveys provides National Centers for Environmental Information – National Oceanic and Atmospheric Administration. Unfortunately, most of the seabed is still unidentified, as there are still many gaps to be explored between ship survey tracks. Moreover, such measurements are very expensive and time-consuming. The solution is raster bathymetric models shared by The General Bathymetric Chart of the Oceans. The offered products are a compilation of different sets of data - raw or processed. Indirect data for the development of bathymetric models are also measurements of gravity anomalies. Some forms of seafloor relief (e.g. seamounts) increase the force of the Earth's pull, leading to changes in the sea surface. Based on satellite altimetry data, Sea Surface Height and marine gravity anomalies can be estimated, and based on the anomalies, it’s possible to infer the structure of the seabed. The main goal of the work is to create regional bathymetric models and models of the sea surface in the area of the east coast of North America – a region of seamounts and undulating seafloor. The research includes an analysis of the methods and techniques used, an evaluation of the interpolation algorithms used, model thickening, and the creation of grid models. Obtained data are raster bathymetric models in NetCDF format, survey data from multibeam soundings in MB-System format, and satellite altimetry data from Copernicus Marine Environment Monitoring Service. The methodology includes data extraction, processing, mapping, and spatial analysis. Visualization of the obtained results was carried out with Geographic Information System tools. The result is an extension of the state of the knowledge of the quality and usefulness of the data used for seabed and sea surface modeling and knowledge of the accuracy of the generated models. Sea level is averaged over time and space (excluding waves, tides, etc.). Its changes, along with knowledge of the topography of the ocean floor - inform us indirectly about the volume of the entire water ocean. The true shape of the ocean surface is further varied by such phenomena as tides, differences in atmospheric pressure, wind systems, thermal expansion of water, or phases of ocean circulation. Depending on the location of the point, the higher the depth, the lower the trend of sea level change. Studies show that combining data sets, from different sources, with different accuracies can affect the quality of sea surface and seafloor topography models.

Keywords: seafloor, sea surface height, bathymetry, satellite altimetry

Procedia PDF Downloads 64

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

Abstract:

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

Keywords: deep learning, delirium, healthcare, pervasive sensing

Procedia PDF Downloads 78

Authors: M. D. Dogara, G. C. Afuwai, O. O. Esther, A. M. Dawai

Abstract:

The geology of Northern Nigeria is under intense investigation particularly that of the northwest believed to be of the basement complex. The variability of the lithology is consistently inconsistent. Hence, the need for a close range study, it is, in view of the above that, two geophysical techniques, the vertical electrical sounding employing the Schlumberger array and seismic refraction methods, were used to delineate the geoelectric and geovelocity parameters of the basement complex of northwestern Nigeria. A total area of 400,000 m² was covered with sixty geoelectric stations established and sixty sets of seismic refraction data collected using the forward and reverse method. From the interpretation of the resistivity data, it is suggestive that the area is underlain by not more than five geoelectric layers of varying thicknesses and resistivities when a maximum half electrode spread of 100m was used. The result of the interpreted seismic data revealed two geovelocity layers, with velocities ranging between 478m/s to 1666m/s for the first layer and 1166m/s to 7141m/s for the second layer. The results of the two techniques, suggests that the area of study has an undulating bedrock topography with geoeletric and geovelocity layers composed of weathered rock materials.

Keywords: basement complex, delineation, geoelectric, geovelocity, Nigeria

Procedia PDF Downloads 135

Authors: Longlong Zhang, Xiaohua Zhu, Ping Zhao, Yu Wang

Abstract:

The construction of mines, railways, highways, water conservancy projects, etc., have formed a large number of high steep slope wounds in China. Under the premise of slope stability and safety, the minimum cost, green and close to natural wound space repair, has become a new problem. Nowadays, in situ element testing and analysis, monitoring, field quantitative factor classification, and assignment evaluation will produce vast amounts of data. Data processing and analysis will inevitably differentiate the morphology, mineral composition, physicochemical properties between rock wounds, by which to dynamically match the appropriate techniques and materials for restoration. In the present research, based on the grid partition of the slope surface, tested the content of the combined oxide of rock mineral (SiO₂, CaO, MgO, Al₂O₃, Fe₃O₄, etc.), and classified and assigned values to the hardness and breakage of rock texture. The data of essential factors are interpolated and normalized in GIS, which formed the differential zoning map of slope space. According to the physical and chemical properties and spatial morphology of rocks in different zones, organic acids (plant waste fruit, fruit residue, etc.), natural mineral powder (zeolite, apatite, kaolin, etc.), water-retaining agent, and plant gum (melon powder) were mixed in different proportions to form rock aging agents. To spray the aging agent with different formulas on the slopes in different sections can affectively age the fresh rock wound, providing convenience for seed implantation, and reducing the transformation of heavy metals in the rocks. Through many practical engineering practices, a dynamic data platform of rock aging agent formula system is formed, which provides materials for the restoration of different slopes. It will also provide a guideline for the mixed-use of various natural materials to solve the complex, non-uniformity ecological restoration problem.

Keywords: data-driven, dynamic state, high steep slope, rock aging agent, wounds

Procedia PDF Downloads 101

Authors: Fatemeh Jannesarvatan, Ghazaal Parastooei, Jimmy frerejan, Saedeh Mokhtari, Peter Van Rosmalen

Abstract:

Medical and dental education increasingly emphasizes the acquisition, integration, and coordination of complex knowledge, skills, and attitudes that can be applied in practical situations. Instructional design approaches have focused on using real-life tasks in order to facilitate complex learning in both real and simulated environments. The Four component instructional design (4C/ID) model has become a useful guideline for designing instructional materials that improve learning transfer, especially in health profession education. The objective of this study was to apply the 4C/ID model in the creation of virtual patients (VPs) that dental students can use to practice their clinical management and clinical reasoning skills. The study first explored the context and concept of complication factors and common errors for novices and how they can affect the design of a virtual patient program. The study then selected key dental information and considered the content needs of dental students. The design of virtual patients was based on the 4C/ID model's fundamental principles, which included: Designing learning tasks that reflect real patient scenarios and applying different levels of task complexity to challenge students to apply their knowledge and skills in different contexts. Creating varied learning materials that support students during the VP program and are closely integrated with the learning tasks and students' curricula. Cognitive feedback was provided at different levels of the program. Providing procedural information where students followed a step-by-step process from history taking to writing a comprehensive treatment plan. Four virtual patients were designed using the 4C/ID model's principles, and an experimental design was used to test the effectiveness of the principles in achieving the intended educational outcomes. The 4C/ID model provides an effective framework for designing engaging and successful virtual patients that support the transfer of knowledge and skills for dental students. However, there are some challenges and pitfalls that instructional designers should take into account when developing these educational tools.

Keywords: 4C/ID model, virtual patients, education, dental, instructional design

Procedia PDF Downloads 65

Authors: Inayat Ur Rehman, Georgia Sakellari

Abstract:

Cloud computing has evolved into a vital technology for businesses, offering scalability, flexibility, and cost-effectiveness. However, maintaining high availability and optimal performance in the cloud is crucial for reliable services. This paper explores the significance of cloud monitoring and performance optimization in sustaining the high availability of cloud-based systems. It discusses diverse monitoring tools, techniques, and best practices for continually assessing the health and performance of cloud resources. The paper also delves into performance optimization strategies, including resource allocation, load balancing, and auto-scaling, to ensure efficient resource utilization and responsiveness. Addressing potential challenges in cloud monitoring and optimization, the paper offers insights into data security and privacy considerations. Through this thorough analysis, the paper aims to underscore the importance of cloud monitoring and performance optimization for ensuring a seamless and highly available cloud computing environment.

Keywords: cloud computing, cloud monitoring, performance optimization, high availability, scalability, resource allocation, load balancing, auto-scaling, data security, data privacy

Procedia PDF Downloads 38

Authors: Camila Penido Gomes

Abstract:

Over the past decade, an emerging body of research has been pointing to artificial intelligence´s great potential to improve the use of open data, increase transparency and curb corruption in the public sector. Nonetheless, studies on this subject are scant and usually lack evidence to validate AI-based technologies´ effectiveness in addressing corruption, especially in developing countries. Aiming to fill this void in the literature, this paper sets out to examine how AI has been deployed by civil society to improve the use of open data and prevent congresspeople from misusing public resources in Brazil. Building on the current debates and carrying out a systematic literature review and extensive document analyses, this research reveals that AI should not be deployed as one silver bullet to fight corruption. Instead, this technology is more powerful when adopted by a multidisciplinary team as a civic tool in conjunction with other strategies. This study makes considerable contributions, bringing to the forefront discussion a more accurate understanding of the factors that play a decisive role in the successful implementation of AI-based technologies in anti-corruption efforts.

Keywords: artificial intelligence, civil society organization, corruption, open data, transparency

Procedia PDF Downloads 186

Authors: Rana Alaa El-Deen Ahmed, M. Elemam Shehab, Shereen Morsy, Nermeen Mekawie

Abstract:

With the growing popularity and acceptance of e-commerce platforms, users face an ever increasing burden in actually choosing the right product from the large number of online offers. Thus, techniques for personalization and shopping guides are needed by users. For a pleasant and successful shopping experience, users need to know easily which products to buy with high confidence. Since selling a wide variety of products has become easier due to the popularity of online stores, online retailers are able to sell more products than a physical store. The disadvantage is that the customers might not find products they need. In this research the customer will be able to find the products he is searching for, because recommender systems are used in some ecommerce web sites. Recommender system learns from the information about customers and products and provides appropriate personalized recommendations to customers to find the needed product. In this paper eleven classification algorithms are comparatively tested to find the best classifier fit for consumer online shopping attitudes and behavior in the experimented dataset. The WEKA knowledge analysis tool, which is an open source data mining workbench software used in comparing conventional classifiers to get the best classifier was used in this research. In this research by using the data mining tool (WEKA) with the experimented classifiers the results show that decision table and filtered classifier gives the highest accuracy and the lowest accuracy classification via clustering and simple cart.

Keywords: classification, data mining, machine learning, online shopping, WEKA

Procedia PDF Downloads 339

Authors: Andrea Catorci, Federico Maria Tardella, Alessandro Brica, Muhammad Umair

Abstract:

Climate change models predict for the Mediterranean region a strong increase of intensity and frequency of drought events, with an expected effect on grassland biodiversity and functioning. The research aim was to understand how the grassland species modulate their resource acquisition and conservation strategies to short-term variation of the pattern of summer water supply. The study area is mountain meadows located in the ‘‘Montagna di Torricchio’’ (1130 m a.s.l.) a Nature Reserve in central Italy. In 2017 we started a manipulative experiment for 2 year (2017-2018), and we defined two treatments, one with increasing water (watering condition) and the other with less water (drought condition). Then, we investigated how species change their resource strategies at different amount of water availability by measuring the specific leaf area (SLA) and leaf area (LA). We used ANOVAs to test the effect of treatment over time on leaf area and specific leaf area, considering all the species together and also separately according to their growth form (forb, grass, legume). Our results showed that species may respond differently depending on their growth form and that using all the species together may cover more detailed variation. Overall, resource retaining strategies (lower SLA, LA) are resulted by increase of drought condition, while increase in water amount and number of watering events fosters acquisitive strategies (higher SLA, LA). However, this pattern is not constant for all growth form. Grass species are able to maintain their strategies to variation of the pattern of water availability. Forb and legume species on the other side have shown decreasing trend of SLA, LA values with increasing drought condition, a pattern more marked for the latter growth form. These variations suggest not only an increase of slow-growing strategies for both growth form, but also a decrease of their nutrient pastoral values since their leaves are supposed to become harder. Local farmers should consider the effect of climate change on grassland and adapt their management practices to guarantee the cattle welfare.

Keywords: function strategies, grasslands, climate change, sub Mediterranean region

Procedia PDF Downloads 114

Authors: Gorkem Algan, Ilkay Ulusoy, Saban Gonul, Banu Turgut, Berker Bakbak

Abstract:

Computer vision systems recently made a big leap thanks to deep neural networks. However, these systems require correctly labeled large datasets in order to be trained properly, which is very difficult to obtain for medical applications. Two main reasons for label noise in medical applications are the high complexity of the data and conflicting opinions of experts. Moreover, medical imaging datasets are commonly tiny, which makes each data very important in learning. As a result, if not handled properly, label noise significantly degrades the performance. Therefore, a label-noise-robust learning algorithm that makes use of the meta-learning paradigm is proposed in this article. The proposed solution is tested on retinopathy of prematurity (ROP) dataset with a very high label noise of 68%. Results show that the proposed algorithm significantly improves the classification algorithm's performance in the presence of noisy labels.

Keywords: deep learning, label noise, robust learning, meta-learning, retinopathy of prematurity

Procedia PDF Downloads 141

Authors: Alona Faktor

Abstract:

In this work, we present a NN-based computational model that can perform attention shifts according to high-level instruction. The instruction specifies the type of attentional shift using explicit geometrical relation. The instruction also can be of cognitive nature, specifying more complex human-human interaction or human-object interaction, or object-object interaction. Applying this approach sequentially allows obtaining a structural description of an image. A novel data-set of interacting humans and objects is constructed using a computer graphics engine. Using this data, we perform systematic research of relational segmentation shifts.

Keywords: cognitive science, attentin, deep learning, generalization

Procedia PDF Downloads 180

Authors: Sajjad Akbar, Rabia Bashir

Abstract:

With the growth of the number of users, the Internet usage has evolved. Due to its key design principle, there is an incredible expansion in its size. This tremendous growth of the Internet has brought new applications (mobile video and cloud computing) as well as new user’s requirements i.e. content distribution environment, mobility, ubiquity, security and trust etc. The users are more interested in contents rather than their communicating peer nodes. The current Internet architecture is a host-centric networking approach, which is not suitable for the specific type of applications. With the growing use of multiple interactive applications, the host centric approach is considered to be less efficient as it depends on the physical location, for this, Information Centric Networking (ICN) is considered as the potential future Internet architecture. It is an approach that introduces uniquely named data as a core Internet principle. It uses the receiver oriented approach rather than sender oriented. It introduces the naming base information system at the network layer. Although ICN is considered as future Internet architecture but there are lot of criticism on it which mainly concerns that how ICN will manage the most relevant content. For this Web Content Mining(WCM) approaches can help in appropriate data management of ICN. To address this issue, this paper contributes by (i) discussing multiple ICN approaches (ii) analyzing different Web Content Mining approaches (iii) creating a new Internet architecture by merging ICN and WCM to solve the data management issues of ICN. From ICN, Content-Centric Networking (CCN) is selected for the new architecture, whereas, Agent-based approach from Web Content Mining is selected to find most appropriate data.

Keywords: agent based web content mining, content centric networking, information centric networking

Procedia PDF Downloads 458

Authors: Vangelis Drosos, Dimitrios Tsoukalos, Dimitrios Tsolis

Abstract:

We present a simple algorithm for capturing a 3D scene (focused on the usage of mobile device cameras in the context of augmented/mixed reality) by using a floating origin camera solution and storing the resulting information in a linear voxel octree. Data is derived from cloud points captured by a mobile device camera. For the purposes of this paper, we assume a scene of fixed size (known to us or determined beforehand) and a fixed voxel resolution. The resulting data is stored in a linear voxel octree using a hashtable. We commence by briefly discussing the logic behind floating origin approaches and the usage of linear voxel octrees for efficient storage. Following that, we present the algorithm for translating captured feature points into voxel data in the context of a fixed origin world and storing them. Finally, we discuss potential applications and areas of future development and improvement to the efficiency of our solution.

Keywords: voxel, octree, computer vision, XR, floating origin

Procedia PDF Downloads 119

Authors: Masomeh Jamshid Nejad

Abstract:

Nowadays, statistical literacy is no longer a necessary skill but an essential skill with broad applications across diverse fields, especially in operational decision areas such as business management, finance, and economics. As such, learning and deep understanding of statistical concepts are essential in the context of business studies. One of the crucial topics in statistical theory and its application is the normal distribution, often called a bell-shaped curve. To interpret data and conduct hypothesis tests, comprehending the properties of normal distribution (the mean and standard deviation) is essential for business students. This requires undergraduate students in the field of economics and business management to visualize and work with data following a normal distribution. Since technology is interconnected with education these days, it is important to teach statistics topics in the context of Python, R-studio, and Microsoft Excel to undergraduate students. This research endeavours to shed light on the effect of Excel-based instruction on learners’ knowledge of statistics, specifically the central concept of normal distribution. As such, two groups of undergraduate students (from the Business Management program) were compared in this research study. One group underwent Excel-based instruction and another group relied only on traditional teaching methods. We analyzed experiential data and BBA participants’ responses to statistic-related questions focusing on the normal distribution, including its key attributes, such as the mean and standard deviation. The results of our study indicate that exposing students to Excel-based learning supports learners in comprehending statistical concepts more effectively compared with the other group of learners (teaching with the traditional method). In addition, students in the context of Excel-based instruction showed ability in picturing and interpreting data concentrated on normal distribution.

Keywords: statistics, excel-based instruction, data visualization, pedagogy

Procedia PDF Downloads 39

Authors: Kyoung-Jae Kim

Abstract:

Collaborative Filtering (CF) is a popular technique for the personalization in the E-commerce domain to reduce information overload. In general, CF provides recommending items list based on other similar users’ preferences from the user-item matrix and predicts the focal user’s preference for particular items by using them. Many recommender systems in real-world use CF techniques because it’s excellent accuracy and robustness. However, it has some limitations including sparsity problems and complex dimensionality in a user-item matrix. In addition, traditional CF does not consider the emotional interaction between users. In this study, we propose recommender systems using social network and singular value decomposition (SVD) to alleviate some limitations. The purpose of this study is to reduce the dimensionality of data set using SVD and to improve the performance of CF by using emotional information from social network data of the focal user. In this study, we test the usability of hybrid CF, SVD and social network information model using the real-world data. The experimental results show that the proposed model outperforms conventional CF models.

Keywords: recommender systems, collaborative filtering, social network information, singular value decomposition

Procedia PDF Downloads 275

Authors: Boris Barbolyas, Kristina Buckova, Tomas Volensky, Cyril Belavy, Ladislav Dedik

Abstract:

Background: Based on statokinezigram, the human balance control is often studied. Approach to human postural reaction analysis is based on a combination of stabilometry output signal with retroreflective marker data signal processing, analysis, and understanding, in this study. The study shows another original application of Method of Developed Statokinesigram Trajectory (MDST), too. Methods: In this study, the participants maintained quiet bipedal standing for 10 s on stabilometry platform. Consequently, bilateral vibration stimuli to Achilles tendons in 20 s interval was applied. Vibration stimuli caused that human postural system took the new pseudo-steady state. Vibration frequencies were 20, 60 and 80 Hz. Participant's body segments - head, shoulders, hips, knees, ankles and little fingers were marked by 12 retroreflective markers. Markers positions were scanned by six cameras system BTS SMART DX. Registration of their postural reaction lasted 60 s. Sampling frequency was 100 Hz. For measured data processing were used Method of Developed Statokinesigram Trajectory. Regression analysis of developed statokinesigram trajectory (DST) data and retroreflective marker developed trajectory (DMT) data were used to find out which marker trajectories most correlate with stabilometry platform output signals. Scaling coefficients (λ) between DST and DMT by linear regression analysis were evaluated, too. Results: Scaling coefficients for marker trajectories were identified for all body segments. Head markers trajectories reached maximal value and ankle markers trajectories had a minimal value of scaling coefficient. Hips, knees and ankles markers were approximately symmetrical in the meaning of scaling coefficient. Notable differences of scaling coefficient were detected in head and shoulders markers trajectories which were not symmetrical. The model of postural system behavior was identified by MDST. Conclusion: Value of scaling factor identifies which body segment is predisposed to postural instability. Hypothetically, if statokinesigram represents overall human postural system response to vibration stimuli, then markers data represented particular postural responses. It can be assumed that cumulative sum of particular marker postural responses is equal to statokinesigram.

Keywords: center of pressure (CoP), method of developed statokinesigram trajectory (MDST), model of postural system behavior, retroreflective marker data

Procedia PDF Downloads 331

Authors: Vishwanath Pethri Kamath, Jayantha Gowda Sarapanahalli, Vishal Mishra, Siddhesh Balwant Bandgar

Abstract:

Recognition of emotional information is essential in any form of communication. Growing HCI (Human-Computer Interaction) in recent times indicates the importance of understanding of emotions expressed and becomes crucial for improving the system or the interaction itself. In this research work, textual data for emotion recognition is used. The text being the least expressive amongst the multimodal resources poses various challenges such as contextual information and also sequential nature of the language construction. In this research work, the proposal is made for a neural architecture to resolve not less than 8 emotions from textual data sources derived from multiple datasets using google pre-trained word2vec word embeddings and a Multi-head attention-based bidirectional LSTM model with a one-vs-all Multi-Level Classification. The emotions targeted in this research are Anger, Disgust, Fear, Guilt, Joy, Sadness, Shame, and Surprise. Textual data from multiple datasets were used for this research work such as ISEAR, Go Emotions, Affect datasets for creating the emotions’ dataset. Data samples overlap or conflicts were considered with careful preprocessing. Our results show a significant improvement with the modeling architecture and as good as 10 points improvement in recognizing some emotions.

Keywords: text emotion recognition, bidirectional LSTM, multi-head attention, multi-level classification, google word2vec word embeddings

Procedia PDF Downloads 161

Authors: Shivalinge Gowda

Abstract:

The total mass attenuation coefficients m/r, of some halides such as, NaCl, KCl, CuCl, NaBr, KBr, RbCl, AgCl, NaI, KI, AgBr, CsI, HgCl₂, CdI₂ and HgI₂ were determined at photon energies 279.2, 320.07, 514.0, 661.6, 1115.5, 1173.2 and 1332.5 keV in a well-collimated narrow beam good geometry set-up using a high resolution, hyper pure germanium detector. The mass attenuation coefficients and the effective atomic cross sections are found to be in good agreement with the XCOM values. From these mass attenuation coefficients, the effective atomic cross sections s_a, of the compounds were determined. These effective atomic cross section s_a data so obtained are then used to compute the effective atomic numbers Z_eff. For this, the interpolation of total attenuation cross-sections of photons of energy E in elements of atomic number Z was performed by using the logarithmic regression analysis of the data measured by the authors and reported earlier for the above said energies along with XCOM data for standard energies. The best-fit coefficients in the photon energy range of 250 to 350 keV, 350 to 500 keV, 500 to 700 keV, 700 to 1000 keV and 1000 to 1500 keV by a piecewise interpolation method were then used to find the Z_eff of the compounds with respect to the effective atomic cross section s_a from the relation obtained by piece wise interpolation method. Using these Z_eff values, the electron densities N_el of halides were also determined. The present Z_eff and N_el values of halides are found to be in good agreement with the values calculated from XCOM data and other available published values.

Keywords: mass attenuation coefficient, atomic cross-section, effective atomic number, electron density

Procedia PDF Downloads 365

Authors: W. Pungchompoo, A. Richardson, L. Brindle

Abstract:

Background: The developing of a culturally acceptable end of life survey (the VOICES-ESRD/Thai questionnaire) is an essential instrument for evaluation health services provision of older persons with ESRD in Thailand. The focus of the questionnaire was on symptoms, symptom control and the health care needs of older people with ESRD who are managed without dialysis. Objective: The objective of this study was to develop and adapt VOICES to make it suitable for use in a population survey in Thailand. Methods: The mixed methods exploratory sequential design was focussed on modifying an instrument. Data collection: A cognitive interviewing technique was implemented, using two cycles of data collection with a sample of 10 bereaved carers and a prototype of the Thai VOICES questionnaire. Qualitative study was used to modify the developing a culturally acceptable end of life survey (the VOICES-ESRD/Thai questionnaire). Data analysis: The data were analysed by using content analysis. Results: The revisions to the prototype questionnaire were made. The results were used to adapt the VOICES questionnaire for use in a population-based survey with older ESRD patients in Thailand. Conclusions: A culturally specific questionnaire was generated during this second phase and issues with questionnaire design were rectified.

Keywords: VOICES-ESRD/Thai questionnaire, cognitive interviewing, end of life survey, health services provision, older persons with ESRD

Procedia PDF Downloads 270

Authors: Emel Kızılkaya Aydogan, Mihrimah Ozmen, Yılmaz Delice

Abstract:

In recent days, there is a change and the ongoing development of the telecommunications sector in the global market. In this sector, churn analysis techniques are commonly used for analysing why some customers terminate their service subscriptions prematurely. In addition, customer churn is utmost significant in this sector since it causes to important business loss. Many companies make various researches in order to prevent losses while increasing customer loyalty. Although a large quantity of accumulated data is available in this sector, their usefulness is limited by data quality and relevance. In this paper, a cost-sensitive feature selection framework is developed aiming to obtain the feature reducts to predict customer churn. The framework is a cost based optional pre-processing stage to remove redundant features for churn management. In addition, this cost-based feature selection algorithm is applied in a telecommunication company in Turkey and the results obtained with this algorithm.

Keywords: churn prediction, data mining, decision-theoretic rough set, feature selection

Procedia PDF Downloads 430

Authors: Huinan Zhang, Wenjie Jiang

Abstract:

Accurate estimation of tropical cyclone intensity is of great importance for disaster prevention and mitigation. Existing techniques are largely based on satellite imagery data, and research and utilization of the inner thermal core structure characteristics of tropical cyclones still pose challenges. This paper presents a two-stage tropical cyclone intensity estimation network based on the fusion of coarse and fine-grained features from microwave brightness temperature data. The data used in this network are obtained from the thermal core structure of tropical cyclones through the Advanced Technology Microwave Sounder (ATMS) inversion. Firstly, the thermal core information in the pressure direction is comprehensively expressed through the maximal intensity projection (MIP) method, constructing coarse-grained thermal core images that represent the tropical cyclone. These images provide a coarse-grained feature range wind speed estimation result in the first stage. Then, based on this result, fine-grained features are extracted by combining thermal core information from multiple view profiles with a distributed network and fused with coarse-grained features from the first stage to obtain the final two-stage network wind speed estimation. Furthermore, to better capture the long-tail distribution characteristics of tropical cyclones, focal loss is used in the coarse-grained loss function of the first stage, and ordinal regression loss is adopted in the second stage to replace traditional single-value regression. The selection of tropical cyclones spans from 2012 to 2021, distributed in the North Atlantic (NA) regions. The training set includes 2012 to 2017, the validation set includes 2018 to 2019, and the test set includes 2020 to 2021. Based on the Saffir-Simpson Hurricane Wind Scale (SSHS), this paper categorizes tropical cyclone levels into three major categories: pre-hurricane, minor hurricane, and major hurricane, with a classification accuracy rate of 86.18% and an intensity estimation error of 4.01m/s for NA based on this accuracy. The results indicate that thermal core data can effectively represent the level and intensity of tropical cyclones, warranting further exploration of tropical cyclone attributes under this data.

Keywords: Artificial intelligence, deep learning, data mining, remote sensing

Procedia PDF Downloads 42

Authors: Ninlawat Phuangchoke, Waraporn Viyanon, Setta Sasananan

Abstract:

The most important process of the water treatment plant process is the coagulation using alum and poly aluminum chloride (PACL), and the value of usage per day is a hundred thousand baht. Therefore, determining the dosage of alum and PACL are the most important factors to be prescribed. Water production is economical and valuable. This research applies an artificial neural network (ANN), which uses the Levenberg–Marquardt algorithm to create a mathematical model (Soft Jar Test) for prediction chemical dose used to coagulation such as alum and PACL, which input data consists of turbidity, pH, alkalinity, conductivity, and, oxygen consumption (OC) of Bangkhen water treatment plant (BKWTP) Metropolitan Waterworks Authority. The data collected from 1 January 2019 to 31 December 2019 cover changing seasons of Thailand. The input data of ANN is divided into three groups training set, test set, and validation set, which the best model performance with a coefficient of determination and mean absolute error of alum are 0.73, 3.18, and PACL is 0.59, 3.21 respectively.

Keywords: soft jar test, jar test, water treatment plant process, artificial neural network

Procedia PDF Downloads 151

Authors: Dilip K. De, Olukunle C. Olawole, Emmanuel S. Joel, Moses Emetere

Abstract:

A good number of electronic properties such as electrical and thermal conductivities depend on charge carrier densities of nanomaterials. By controlling the charge carrier densities during the fabrication (or growth) processes, the physical properties can be tuned. In this paper, we discuss a new technique of estimating the charge carrier densities of nanomaterials from the thermionic emission data using the newly modified Richardson-Dushman equation. We find that the technique yields excellent results for graphene and carbon nanotube.

Keywords: charge carrier density, nano materials, new technique, thermionic emission

Procedia PDF Downloads 304

Authors: Tatsuya Yamazaki, Kazuya Miyakawa, Tomohiko Sugiyama, Toshitaka Iwatani

Abstract:

The introduction of sensor technologies into agriculture is a necessary step to realize Precision Agriculture. Although sensing methodologies themselves have been prevailing owing to miniaturization and reduction in costs of sensors, there are some difficulties to analyze and understand the sensing data. Targeting at pears ’Le Lectier’, which is particular to Niigata in Japan, cultivation environmental data have been collected at pear fields by eight sorts of sensors: field temperature, field humidity, rain gauge, soil water potential, soil temperature, soil moisture, inner-bag temperature, and inner-bag humidity sensors. With regard to the inner-bag temperature and humidity sensors, they are used to measure the environment inside the fruit bag used for pre-harvest bagging of pears. In this experiment, three kinds of fruit bags were used for the pre-harvest bagging. After over 100 days continuous measurement, volumes of sensing data have been collected. Firstly, correlation analysis among sensing data measured by respective sensors reveals that one sensor can replace another sensor so that more efficient and cost-saving sensing systems can be proposed to pear farmers. Secondly, differences in characteristic and performance of the three kinds of fruit bags are clarified by the measurement results by the inner-bag environmental sensing. It is found that characteristic and performance of the inner-bags significantly differ from each other by statistical analysis. Lastly, a relational model between the sensing data and the pear outlook quality is established by use of Structural Equation Model (SEM). Here, the pear outlook quality is related with existence of stain, blob, scratch, and so on caused by physiological impair or diseases. Conceptually SEM is a combination of exploratory factor analysis and multiple regression. By using SEM, a model is constructed to connect independent and dependent variables. The proposed SEM model relates the measured sensing data and the pear outlook quality determined on the basis of farmer judgement. In particularly, it is found that the inner-bag humidity variable relatively affects the pear outlook quality. Therefore, inner-bag humidity sensing might help the farmers to control the pear outlook quality. These results are supported by a large quantity of inner-bag humidity data measured over the years 2014, 2015, and 2016. The experimental and analytical results in this research contribute to spreading Precision Agriculture technologies among the farmers growing ’Le Lectier’.

Keywords: precision agriculture, pre-harvest bagging, sensor fusion, structural equation model

Procedia PDF Downloads 294

Authors: Adriana Postal, Silvio C. Sampaio, Marcio A. Villas Boas, Josué P. Castro

Abstract:

This study deals with the estimation of reference evapotranspiration (ET₀) in an agricultural context, focusing on efficient irrigation management to meet the growing interest in the sustainable management of water resources. Given the importance of water in agriculture and its scarcity in many regions, efficient use of this resource is essential to ensure food security and environmental sustainability. The methodology used involved the application of artificial intelligence techniques, specifically Multilayer Perceptron (MLP) Artificial Neural Networks (ANNs), to predict ET₀ in the state of Paraná, Brazil. The models were trained and validated with meteorological data from the Brazilian National Institute of Meteorology (INMET), together with data obtained from a producer's weather station in the western region of Paraná. Two optimizers (SGD and Adam) and different meteorological variables, such as temperature, humidity, solar radiation, and wind speed, were explored as inputs to the models. Nineteen configurations with different input variables were tested; amidst them, configuration 9, with 8 input variables, was identified as the most efficient of all. Configuration 10, with 4 input variables, was considered the most effective, considering the smallest number of variables. The main conclusions of this study show that MLP ANNs are capable of accurately estimating ET₀, providing a valuable tool for irrigation management in agriculture. Both configurations (9 and 10) showed promising performance in predicting ET₀. The validation of the models with cultivator data underlined the practical relevance of these tools and confirmed their generalization ability for different field conditions. The results of the statistical metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²), showed excellent agreement between the model predictions and the observed data, with MAE as low as 0.01 mm/day and 0.03 mm/day, respectively. In addition, the models achieved an R² between 0.99 and 1, indicating a satisfactory fit to the real data. This agreement was also confirmed by the Kolmogorov-Smirnov test, which evaluates the agreement of the predictions with the statistical behavior of the real data and yields values between 0.02 and 0.04 for the producer data. In addition, the results of this study suggest that the developed technique can be applied to other locations by using specific data from these sites to further improve ET₀ predictions and thus contribute to sustainable irrigation management in different agricultural regions. The study has some limitations, such as the use of a single ANN architecture and two optimizers, the validation with data from only one producer, and the possible underestimation of the influence of seasonality and local climate variability. An irrigation management application using the most efficient models from this study is already under development. Future research can explore different ANN architectures and optimization techniques, validate models with data from multiple producers and regions, and investigate the model's response to different seasonal and climatic conditions.

Keywords: agricultural technology, neural networks in agriculture, water efficiency, water use optimization

Procedia PDF Downloads 29

Authors: Tambe Daniel Atem

Abstract:

Background: Clinical Research is an organized research on human beings intended to provide adequate information on the drug use as a therapeutic agent on its safety and efficacy. The significance of the study is to educate the global health and life science graduates in Clinical Research in depth to perform better as it involves testing drugs on human beings. Objectives: to provide an overall understanding of the scientific approach to the evaluation of new and existing medical interventions and to apply ethical and regulatory principles appropriate to any individual research. Methodology: It is based on – Primary data analysis and Secondary data analysis. Primary data analysis: means the collection of data from journals, the internet, and other online sources. Secondary data analysis: a survey was conducted with a questionnaire to interview the Clinical Research Professionals to understand the need of training to perform clinical trials globally. The questionnaire consisted details of the professionals working with the expertise. It also included the areas of clinical research which needed intense training before entering into hardcore clinical research domain. Results: The Clinical Trials market worldwide worth over USD 26 billion and the industry has employed an estimated 2,10,000 people in the US and over 70,000 in the U.K, and they form one-third of the total research and development staff. There are more than 2,50,000 vacant positions globally with salary variations in the regions for a Clinical Research Coordinator. R&D cost on new drug development is estimated at US$ 70-85 billion. The cost of doing clinical trials for a new drug is US$ 200-250 million. Due to an increase trained Clinical Research Professionals India has emerged as a global hub for clinical research. The Global Clinical Trial outsourcing opportunity in India in the pharmaceutical industry increased to more than $2 billion in 2014 due to increased outsourcing from U.S and Europe to India. Conclusion: Assessment of training need is recommended for newer Clinical Research Professionals and trial sites, especially prior the conduct of larger confirmatory clinical trials.

Keywords: clinical research, clinical trials, clinical research professionals

Procedia PDF Downloads 440