Search results for: empathic accuracy

Authors: Hozaifa Zaki, Ghada Soliman

Abstract:

In this paper, we introduced an approach for Automated Dotted Arabic Expiration Date Extraction using Optimized Convolutional Autoencoder (ARABEX) with bidirectional LSTM. This approach is used for translating the Arabic dot-matrix expiration dates into their corresponding filled-in dates. A custom lightweight Convolutional Recurrent Neural Network (CRNN) model is then employed to extract the expiration dates. Due to the lack of available dataset images for the Arabic dot-matrix expiration date, we generated synthetic images by creating an Arabic dot-matrix True Type Font (TTF) matrix to address this limitation. Our model was trained on a realistic synthetic dataset of 3287 images, covering the period from 2019 to 2027, represented in the format of yyyy/mm/dd. We then trained our custom CRNN model using the generated synthetic images to assess the performance of our model (ARABEX) by extracting expiration dates from the translated images. Our proposed approach achieved an accuracy of 99.4% on the test dataset of 658 images, while also achieving a Structural Similarity Index (SSIM) of 0.46 for image translation on our dataset. The ARABEX approach demonstrates its ability to be applied to various downstream learning tasks, including image translation and reconstruction. Moreover, this pipeline (ARABEX+CRNN) can be seamlessly integrated into automated sorting systems to extract expiry dates and sort products accordingly during the manufacturing stage. By eliminating the need for manual entry of expiration dates, which can be time-consuming and inefficient for merchants, our approach offers significant results in terms of efficiency and accuracy for Arabic dot-matrix expiration date recognition.

Keywords: computer vision, deep learning, image processing, character recognition

Procedia PDF Downloads 82

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 63

Authors: Iffat Ara Ebu, Fahmida Islam, Mohammad Abdus Shahid Rafi, Mahfuzur Rahman, Umar Iqbal, John Ball

Abstract:

The application of multi-sensor fusion for enhanced distance estimation accuracy in dynamic environments is crucial for advanced driver assistance systems (ADAS) and autonomous vehicles. Limitations of single sensors such as cameras or radar in adverse conditions motivate the use of combined camera and radar data to improve reliability, adaptability, and object recognition. A multi-sensor fusion approach using an extended Kalman filter (EKF) is proposed to combine sensor measurements with a dynamic system model, achieving robust and accurate distance estimation. The research utilizes the Mississippi State University Autonomous Vehicular Simulator (MAVS) to create a controlled environment for data collection. Data analysis is performed using MATLAB. Qualitative (visualization of fused data vs ground truth) and quantitative metrics (RMSE, MAE) are employed for performance assessment. Initial results with simulated data demonstrate accurate distance estimation compared to individual sensors. The optimal sensor measurement noise variance and plant noise variance parameters within the EKF are identified, and the algorithm is validated with real-world data from a Chevrolet Blazer. In summary, this research demonstrates that multi-sensor fusion with an EKF significantly improves distance estimation accuracy in dynamic environments. This is supported by comprehensive evaluation metrics, with validation transitioning from simulated to real-world data, paving the way for safer and more reliable autonomous vehicle control.

Keywords: sensor fusion, EKF, MATLAB, MAVS, autonomous vehicle, ADAS

Procedia PDF Downloads 43

Authors: Svanik Garg

Abstract:

Static Test Pads are stationary mechanisms that hold a solid rocket motor, measuring the different parameters of its operation including thrust and temperature to better calibrate it for launch. This paper outlines a specific STP designed to test high powered rocket motors with a thrust upwards of 4000N and limited to 6500N. The design includes a specific portable mechanism with cost an integral part of the design process to make it accessible to small scale rocket developers with limited resources. Using curved surfaces and an ergonomic design, the STP has a delicately engineered façade/case with a focus on stability and axial calibration of thrust. This paper describes the design, operation and working of the STP and its widescale uses given the growing market of aviation enthusiasts. Simulations on the CAD model in Fusion 360 provided promising results with a safety factor of 2 established and stress limited along with the load coefficient A PCB was also designed as part of the test pad design process to help obtain results, with visual output and various virtual terminals to collect data of different parameters. The circuitry was simulated using ‘proteus’ and a special virtual interface with auditory commands was also created for accessibility and wide-scale implementation. Along with this description of the design, the paper also emphasizes the design principle behind the STP including a description of its vertical orientation to maximize thrust accuracy along with a stable base to prevent micromovements. Given the rise of students and professionals alike building high powered rockets, the STP described in this paper is an appropriate option, with limited cost, portability, accuracy, and versatility. There are two types of STP’s vertical or horizontal, the one discussed in this paper is vertical to utilize the axial component of thrust.

Keywords: static test pad, rocket motor, thrust, load, circuit, avionics, drag

Procedia PDF Downloads 380

Authors: Hatem Abou-Senna, Essam Radwan

Abstract:

Transportation agencies and researchers in the past have estimated emissions using one average speed and volume on a long stretch of roadway. Other methods provided better accuracy utilizing annual average estimates. Travel demand models provided an intermediate level of detail through average daily volumes. Currently, higher accuracy can be established utilizing microscopic analyses by splitting the network links into sub-links and utilizing second-by-second trajectories to calculate emissions. The need to accurately quantify transportation-related emissions from vehicles is essential. This paper presents an examination of four different approaches to capture the environmental impacts of vehicular operations on a 10-mile stretch of Interstate 4 (I-4), an urban limited access highway in Orlando, Florida. First, (at the most basic level), emissions were estimated for the entire 10-mile section 'by hand' using one average traffic volume and average speed. Then, three advanced levels of detail were studied using VISSIM/MOVES to analyze smaller links: average speeds and volumes (AVG), second-by-second link drive schedules (LDS), and second-by-second operating mode distributions (OPMODE). This paper analyzes how the various approaches affect predicted emissions of CO, NOx, PM2.5, PM10, and CO2. The results demonstrate that obtaining precise and comprehensive operating mode distributions on a second-by-second basis provides more accurate emission estimates. Specifically, emission rates are highly sensitive to stop-and-go traffic and the associated driving cycles of acceleration, deceleration, and idling. Using the AVG or LDS approach may overestimate or underestimate emissions, respectively, compared to an operating mode distribution approach.

Keywords: limited access highways, MOVES, operating mode distribution (OPMODE), transportation emissions, vehicle specific power (VSP)

Procedia PDF Downloads 339

Authors: Warda Khan, Remo Lachmann, Adarsh S. Garakahally

Abstract:

The increasing complexity of software and its applicability in a wide range of industries, e.g., automotive, call for enhanced quality assurance techniques. Test automation is one option to tackle the prevailing challenges by supporting test engineers with fast, parallel, and repetitive test executions. A high degree of test automation allows for a shift from mundane (manual) testing tasks to a more analytical assessment of the software under test. However, a high initial investment of test resources is required to establish test automation, which is, in most cases, a limitation to the time constraints provided for quality assurance of complex software systems. Hence, a computer-aided creation of automated test cases is crucial to increase the benefit of test automation. This paper proposes the application of machine learning for the generation of automated test cases. It is based on supervised learning to analyze test specifications and existing test implementations. The analysis facilitates the identification of patterns between test steps and their implementation with test automation components. For the test case generation, this approach exploits historical data of test automation projects. The identified patterns are the foundation to predict the implementation of unknown test case specifications. Based on this support, a test engineer solely has to review and parameterize the test automation components instead of writing them manually, resulting in a significant time reduction for establishing test automation. Compared to other generation approaches, this ML-based solution can handle different writing styles, authors, application domains, and even languages. Furthermore, test automation tools require expert knowledge by means of programming skills, whereas this approach only requires historical data to generate test cases. The proposed solution is evaluated using various multi-label evaluation criteria (EC) and two small-sized real-world systems. The most prominent EC is ‘Subset Accuracy’. The promising results show an accuracy of at least 86% for test cases, where a 1:1 relationship (Multi-Class) between test step specification and test automation component exists. For complex multi-label problems, i.e., one test step can be implemented by several components, the prediction accuracy is still at 60%. It is better than the current state-of-the-art results. It is expected the prediction quality to increase for larger systems with respective historical data. Consequently, this technique facilitates the time reduction for establishing test automation and is thereby independent of the application domain and project. As a work in progress, the next steps are to investigate incremental and active learning as additions to increase the usability of this approach, e.g., in case labelled historical data is scarce.

Keywords: machine learning, multi-class, multi-label, supervised learning, test automation

Procedia PDF Downloads 132

Authors: Vadim Vagin, Marina Fomina, Oleg Morosin

Abstract:

This paper contains the description of argumentation approach for the problem of inductive concept formation. It is proposed to use argumentation, based on defeasible reasoning with justification degrees, to improve the quality of classification models, obtained by generalization algorithms. The experiment’s results on both clear and noisy data are also presented.

Keywords: argumentation, justification degrees, inductive concept formation, noise, generalization

Procedia PDF Downloads 442

Authors: Dhanya Nair, Nicholas Mirchandani

Abstract:

Musical haptic systems can enhance a listener’s musical experience while providing an alternative platform for the hearing impaired to experience music. Current music tactile technologies focus on representing tactile metronomes to synchronize performers or encoding musical notes into distinguishable (albeit distracting) tactile patterns. There is growing interest in the development of musical haptic systems to augment the auditory experience, although the haptic-music relationship is still not well understood. This paper represents a tactile music interface that provides vibrations to multiple fingertips in synchronicity with auditory music. Like an audio equalizer, different frequency bands are filtered out, and the power in each frequency band is computed and converted to a corresponding vibrational strength. These vibrations are felt on different fingertips, each corresponding to a different frequency band. Songs with music from different spectrums, as classified by their energy and valence, were used to test the effectiveness of the system and to understand the relationship between music and tactile sensations. Three participants were trained on one song categorized as sad (low energy and low valence score) and one song categorized as happy (high energy and high valence score). They were trained both with and without auditory feedback (listening to the song while experiencing the tactile music on their fingertips and then experiencing the vibrations alone without the music). The participants were then tested on three songs from both categories, without any auditory feedback, and were asked to classify the tactile vibrations they felt into either category. The participants were blinded to the songs being tested and were not provided any feedback on the accuracy of their classification. These participants were able to classify the music with 100% accuracy. Although the songs tested were on two opposite spectrums (sad/happy), the preliminary results show the potential of utilizing a vibrotactile equalizer, like the one presented, for augmenting musical experience while furthering the current understanding of music tactile relationship.

Keywords: haptic music relationship, tactile equalizer, tactile music, vibrations and mood

Procedia PDF Downloads 181

Authors: Ferry Kurniawan

Abstract:

In this paper, we nowcast quarterly output growth in Indonesia by exploiting higher frequency data (monthly indicators) using a mixed-frequency factor model and exploiting both quarterly and monthly data. Nowcasting quarterly GDP in Indonesia is particularly relevant for the central bank of Indonesia which set the policy rate in the monthly Board of Governors Meeting; whereby one of the important step is the assessment of the current state of the economy. Thus, having an accurate and up-to-date quarterly GDP nowcast every time new monthly information becomes available would clearly be of interest for central bank of Indonesia, for example, as the initial assessment of the current state of the economy -including nowcast- will be used as input for longer term forecast. We consider a small scale mixed-frequency factor model to produce nowcasts. In particular, we specify variables as year-on-year growth rates thus the relation between quarterly and monthly data is expressed in year-on-year growth rates. To assess the performance of the model, we compare the nowcasts with two other approaches: autoregressive model –which is often difficult when forecasting output growth- and Mixed Data Sampling (MIDAS) regression. In particular, both mixed frequency factor model and MIDAS nowcasts are produced by exploiting the same set of monthly indicators. Hence, we compare the nowcasts performance of the two approaches directly. To preview the results, we find that by exploiting monthly indicators using mixed-frequency factor model and MIDAS regression we improve the nowcast accuracy over a benchmark simple autoregressive model that uses only quarterly frequency data. However, it is not clear whether the MIDAS or mixed-frequency factor model is better. Neither set of nowcasts encompasses the other; suggesting that both nowcasts are valuable in nowcasting GDP but neither is sufficient. By combining the two individual nowcasts, we find that the nowcast combination not only increases the accuracy - relative to individual nowcasts- but also lowers the risk of the worst performance of the individual nowcasts.

Keywords: nowcasting, mixed-frequency data, factor model, nowcasts combination

Procedia PDF Downloads 331

Authors: B. Petrović, L. Rutonjski, M. Baucal, M. Teodorović, O. Čudić, B. Basarić

Abstract:

Purpose/Objective: Radiotherapy treatment planning requires use of CT simulator, in order to acquire CT images. The overall performance of CT simulator determines the quality of radiotherapy treatment plan, and at the end, the outcome of treatment for every single patient. Therefore, it is strongly advised by international recommendations, to set up a quality control procedures for every machine involved in radiotherapy treatment planning process, including the CT scanner/ simulator. The overall process requires number of tests, which are used on daily, weekly, monthly or yearly basis, depending on the feature tested. Materials/Methods: Two phantoms were used: a dedicated phantom CIRS 062QA, and a QA phantom obtained with the CT simulator. The examined CT simulator was Siemens Somatom Definition as Open, dedicated for radiation therapy treatment planning. The CT simulator has a built in software, which enables fast and simple evaluation of CT QA parameters, using the phantom provided with the CT simulator. On the other hand, recommendations contain additional test, which were done with the CIRS phantom. Also, legislation on ionizing radiation protection requires CT testing in defined periods of time. Taking into account the requirements of law, built in tests of a CT simulator, and international recommendations, the intitutional QC programme for CT imulator is defined, and implemented. Results: The CT simulator parameters evaluated through the study were following: CT number accuracy, field uniformity, complete CT to ED conversion curve, spatial and contrast resolution, image noise, slice thickness, and patient table stability.The following limits are established and implemented: CT number accuracy limits are +/- 5 HU of the value at the comissioning. Field uniformity: +/- 10 HU in selected ROIs. Complete CT to ED curve for each tube voltage must comply with the curve obtained at comissioning, with deviations of not more than 5%. Spatial and contrast resultion tests must comply with the tests obtained at comissioning, otherwise machine requires service. Result of image noise test must fall within the limit of 20% difference of the base value. Slice thickness must meet manufacturer specifications, and patient stability with longitudinal transfer of loaded table must not differ of more than 2mm vertical deviation. Conclusion: The implemented QA tests gave overall basic understanding of CT simulator functionality and its clinical effectiveness in radiation treatment planning. The legal requirement to the clinic is to set up it’s own QA programme, with minimum testing, but it remains user’s decision whether additional testing, as recommended by international organizations, will be implemented, so to improve the overall quality of radiation treatment planning procedure, as the CT image quality used for radiation treatment planning, influences the delineation of a tumor and calculation accuracy of treatment planning system, and finally delivery of radiation treatment to a patient.

Keywords: CT simulator, radiotherapy, quality control, QA programme

Procedia PDF Downloads 533

Authors: Xiang Zhang, Daohong Yang, Ziyuan Wu, Lei Li, Wanting Zhou

Abstract:

Visual Simultaneous Localization and Mapping (VSLAM) uses cameras to collect information in unknown environments to realize simultaneous localization and environment map construction, which has a wide range of applications in autonomous driving, virtual reality and other related fields. At present, the related research achievements about VSLAM can maintain high accuracy in static environment. But in dynamic environment, due to the presence of moving objects in the scene, the movement of these objects will reduce the stability of VSLAM system, resulting in inaccurate localization and mapping, or even failure. In this paper, a robust VSLAM method was proposed to effectively deal with the problem in dynamic environment. We proposed a dynamic region removal scheme based on semantic segmentation neural networks and geometric constraints. Firstly, semantic extraction neural network is used to extract prior active motion region, prior static region and prior passive motion region in the environment. Then, the light weight frame tracking module initializes the transform pose between the previous frame and the current frame on the prior static region. A motion consistency detection module based on multi-view geometry and scene flow is used to divide the environment into static region and dynamic region. Thus, the dynamic object region was successfully eliminated. Finally, only the static region is used for tracking thread. Our research is based on the ORBSLAM3 system, which is one of the most effective VSLAM systems available. We evaluated our method on the TUM RGB-D benchmark and the results demonstrate that the proposed VSLAM method improves the accuracy of the original ORBSLAM3 by 70%˜98.5% under high dynamic environment.

Keywords: dynamic scene, dynamic visual SLAM, semantic segmentation, scene flow, VSLAM

Procedia PDF Downloads 116

Authors: Amal Sellami, Ahlem Ammar

Abstract:

Writing is acknowledged to be a cognitively demanding and complex task. Indeed, the writing process is composed of three iterative sub-processes, namely planning, translating (writing), and reviewing. Not only do second or foreign language learners need to write according to this process, but they also need to respect the norms and rules of language and writing in the text to-be-produced. Accordingly, researchers have suggested to approach writing as a collaborative task in order to al leviate its complexity. Consequently, collaboration has been implemented during the whole writing process or only during planning orreviewing. Researchers report that implementing collaboration during the whole process might be demanding in terms of time in comparison to individual writing tasks. Consequently, because of time constraints, teachers may avoid it. For this reason, it might be pedagogically more realistic to limit collaboration to one of the writing sub-processes(i.e., planning or reviewing). However, previous research implementing collaboration in planning or reviewing is limited and fails to explore the effects of the seconditionson the written text. Consequently, the present study examines the effects of collaboration in planning and collaboration in reviewing on the written text. To reach this objective, quantitative as well as qualitative methods are deployed to examine the written texts holistically and in terms of fluency, complexity, and accuracy. Participants of the study include 4 pairs in each group (n=8). They participated in two experimental conditions, which are: (1) collaborative planning followed by individual writing and individual reviewing and (2) individual planning followed by individual writing and collaborative reviewing. The comparative research findings indicate that while collaborative planning resulted in better overall text quality (precisely better content and organization ratings), better fluency, better complexity, and fewer lexical errors, collaborative reviewing produces better accuracy and less syntactical and mechanical errors. The discussion of the findings suggests the need to conduct more comparative research in order to further explore the effects of collaboration in planning or in reviewing. Pedagogical implications of the current study include advising teachers to choose between implementing collaboration in planning or in reviewing depending on their students’ need and what they need to improve.

Keywords: collaboration, writing, collaborative planning, collaborative reviewing

Procedia PDF Downloads 99

Authors: Christine Böckmann, Julia Rosemann

Abstract:

We present an inversion algorithm that is used in the European Aerosol Lidar Network for the inversion of data collected with multi-wavelength Raman lidar. These instruments measure backscatter coefficients at 355, 532, and 1064 nm, and extinction coefficients at 355 and 532 nm. The algorithm is based on manually controlled inversion of optical data which allows for detailed sensitivity studies and thus provides us with comparably high quality of the derived data products. The algorithm allows us to derive particle effective radius, volume, surface-area concentration with comparably high confidence. The retrieval of the real and imaginary parts of the complex refractive index still is a challenge in view of the accuracy required for these parameters in climate change studies in which light-absorption needs to be known with high accuracy. Single-scattering albedo (SSA) can be computed from the retrieve microphysical parameters and allows us to categorize aerosols into high and low absorbing aerosols. From mathematical point of view the algorithm is based on the concept of using truncated singular value decomposition as regularization method. This method was adapted to work for the retrieval of the particle size distribution function (PSD) and is called hybrid regularization technique since it is using a triple of regularization parameters. The inversion of an ill-posed problem, such as the retrieval of the PSD, is always a challenging task because very small measurement errors will be amplified most often hugely during the solution process unless an appropriate regularization method is used. Even using a regularization method is difficult since appropriate regularization parameters have to be determined. Therefore, in a next stage of our work we decided to use two regularization techniques in parallel for comparison purpose. The second method is an iterative regularization method based on Pade iteration. Here, the number of iteration steps serves as the regularization parameter. We successfully developed a semi-automated software for spherical particles which is able to run even on a parallel processor machine. From a mathematical point of view, it is also very important (as selection criteria for an appropriate regularization method) to investigate the degree of ill-posedness of the problem which we found is a moderate ill-posedness. We computed the optical data from mono-modal logarithmic PSD and investigated particles of spherical shape in our simulations. We considered particle radii as large as 6 nm which does not only cover the size range of particles in the fine-mode fraction of naturally occurring PSD but also covers a part of the coarse-mode fraction of PSD. We considered errors of 15% in the simulation studies. For the SSA, 100% of all cases achieve relative errors below 12%. In more detail, 87% of all cases for 355 nm and 88% of all cases for 532 nm are well below 6%. With respect to the absolute error for non- and weak-absorbing particles with real parts 1.5 and 1.6 in all modes the accuracy limit +/- 0.03 is achieved. In sum, 70% of all cases stay below +/-0.03 which is sufficient for climate change studies.

Keywords: aerosol particles, inverse problem, microphysical particle properties, regularization

Procedia PDF Downloads 343

Authors: Mark Joseph Quinto, Roan Beronilla, Guiller Damian, Eliza Camaso, Ronaldo Alberto

Abstract:

Forest inventories are essential to assess the composition, structure and distribution of forest vegetation that can be used as baseline information for management decisions. Classical forest inventory is labor intensive and time-consuming and sometimes even dangerous. The use of Light Detection and Ranging (LiDAR) in forest inventory would improve and overcome these restrictions. This study was conducted to determine the possibility of using LiDAR derived data in extracting high accuracy forest biophysical parameters and as a non-destructive method for forest status analysis of San Manual, Pangasinan. Forest resources extraction was carried out using LAS tools, GIS, Envi and .bat scripts with the available LiDAR data. The process includes the generation of derivatives such as Digital Terrain Model (DTM), Canopy Height Model (CHM) and Canopy Cover Model (CCM) in .bat scripts followed by the generation of 17 composite bands to be used in the extraction of forest classification covers using ENVI 4.8 and GIS software. The Diameter in Breast Height (DBH), Above Ground Biomass (AGB) and Carbon Stock (CS) were estimated for each classified forest cover and Tree Count Extraction was carried out using GIS. Subsequently, field validation was conducted for accuracy assessment. Results showed that the forest of San Manuel has 73% Forest Cover, which is relatively much higher as compared to the 10% canopy cover requirement. On the extracted canopy height, 80% of the tree’s height ranges from 12 m to 17 m. CS of the three forest covers based on the AGB were: 20819.59 kg/20x20 m for closed broadleaf, 8609.82 kg/20x20 m for broadleaf plantation and 15545.57 kg/20x20m for open broadleaf. Average tree counts for the tree forest plantation was 413 trees/ha. As such, the forest of San Manuel has high percent forest cover and high CS.

Keywords: carbon stock, forest inventory, LiDAR, tree count

Procedia PDF Downloads 388

Authors: Shraddha Chaudhary, Raksha Agarwal, Niladri Chatterjee

Abstract:

This work demonstrates a web crawler-based generalized end-to-end open domain Question Answering (QA) system. An efficient QA system requires a significant amount of domain knowledge to answer any question with the aim to find an exact and correct answer in the form of a number, a noun, a short phrase, or a brief piece of text for the user's questions. Analysis of the question, searching the relevant document, and choosing an answer are three important steps in a QA system. This work uses a web scraper (Beautiful Soup) to extract K-documents from the web. The value of K can be calibrated on the basis of a trade-off between time and accuracy. This is followed by a passage ranking process using the MS-Marco dataset trained on 500K queries to extract the most relevant text passage, to shorten the lengthy documents. Further, a QA system is used to extract the answers from the shortened documents based on the query and return the top 3 answers. For evaluation of such systems, accuracy is judged by the exact match between predicted answers and gold answers. But automatic evaluation methods fail due to the linguistic ambiguities inherent in the questions. Moreover, reference answers are often not exhaustive or are out of date. Hence correct answers predicted by the system are often judged incorrect according to the automated metrics. One such scenario arises from the original Google Natural Question (GNQ) dataset which was collected and made available in the year 2016. Use of any such dataset proves to be inefficient with respect to any questions that have time-varying answers. For illustration, if the query is where will be the next Olympics? Gold Answer for the above query as given in the GNQ dataset is “Tokyo”. Since the dataset was collected in the year 2016, and the next Olympics after 2016 were in 2020 that was in Tokyo which is absolutely correct. But if the same question is asked in 2022 then the answer is “Paris, 2024”. Consequently, any evaluation based on the GNQ dataset will be incorrect. Such erroneous predictions are usually given to human evaluators for further validation which is quite expensive and time-consuming. To address this erroneous evaluation, the present work proposes an automated approach for evaluating time-dependent question-answer pairs. In particular, it proposes a metric using the current timestamp along with top-n predicted answers from a given QA system. To test the proposed approach GNQ dataset has been used and the system achieved an accuracy of 78% for a test dataset comprising 100 QA pairs. This test data was automatically extracted using an analysis-based approach from 10K QA pairs of the GNQ dataset. The results obtained are encouraging. The proposed technique appears to have the possibility of developing into a useful scheme for gathering precise, reliable, and specific information in a real-time and efficient manner. Our subsequent experiments will be guided towards establishing the efficacy of the above system for a larger set of time-dependent QA pairs.

Keywords: web-based information retrieval, open domain question answering system, time-varying QA, QA evaluation

Procedia PDF Downloads 101

Authors: Tomas Premoli, Sareh Rowlands

Abstract:

In this study, we investigate the impact of various convolutional neural network (CNN) architectures on the accuracy of diagnosing Alzheimer’s disease (AD) using patient MRI scans. Alzheimer’s disease is a debilitating neurodegenerative disorder that affects millions worldwide. Early, accurate, and non-invasive diagnostic methods are required for providing optimal care and symptom management. Deep learning techniques, particularly CNNs, have shown great promise in enhancing this diagnostic process. We aim to contribute to the ongoing research in this field by comparing the effectiveness of different CNN architectures and providing insights for future studies. Our methodology involved preprocessing MRI data, implementing multiple CNN architectures, and evaluating the performance of each model. We employed intensity normalization, linear registration, and skull stripping for our preprocessing. The selected architectures included VGG, ResNet, and DenseNet models, all implemented using the Keras library. We employed transfer learning and trained models from scratch to compare their effectiveness. Our findings demonstrated significant differences in performance among the tested architectures, with DenseNet201 achieving the highest accuracy of 86.4%. Transfer learning proved to be helpful in improving model performance. We also identified potential areas for future research, such as experimenting with other architectures, optimizing hyperparameters, and employing fine-tuning strategies. By providing a comprehensive analysis of the selected CNN architectures, we offer a solid foundation for future research in Alzheimer’s disease diagnosis using deep learning techniques. Our study highlights the potential of CNNs as a valuable diagnostic tool and emphasizes the importance of ongoing research to develop more accurate and effective models.

Keywords: Alzheimer’s disease, convolutional neural networks, deep learning, medical imaging, MRI

Procedia PDF Downloads 73

Authors: Arin Ghazarian, Cyril Rakovski

Abstract:

Differential privacy has become the leading technique to protect the privacy of individuals in a database while allowing useful analysis to be done and the results to be shared. It puts a guarantee on the amount of privacy loss in the worst-case scenario. Differential privacy is not a toggle between full privacy and zero privacy. It controls the tradeoff between the accuracy of the results and the privacy loss using a single key parameter called

Keywords: arrhythmia, cardiology, differential privacy, ECG, epsilon, medi-cal data, privacy preserving analytics, statistical databases

Procedia PDF Downloads 152

Authors: Maryam Kheirollahpour, Mahmoud Danaee, Amir Faisal Merican, Asma Ahmad Shariff

Abstract:

Background: The presence of nonlinearity among the risk factors of eating behavior causes a bias in the prediction models. The accuracy of estimation of eating behaviors risk factors in the primary prevention of obesity has been established. Objective: The aim of this study was to explore the potential of a hybrid model of structural equation modeling (SEM) and Artificial Neural Networks (ANN) to predict eating behaviors. Methods: The Partial Least Square-SEM (PLS-SEM) and a hybrid model (SEM-Artificial Neural Networks (SEM-ANN)) were applied to evaluate the factors affecting eating behavior patterns among university students. 340 university students participated in this study. The PLS-SEM analysis was used to check the effect of emotional eating scale (EES), body shape concern (BSC), and body appreciation scale (BAS) on different categories of eating behavior patterns (EBP). Then, the hybrid model was conducted using multilayer perceptron (MLP) with feedforward network topology. Moreover, Levenberg-Marquardt, which is a supervised learning model, was applied as a learning method for MLP training. The Tangent/sigmoid function was used for the input layer while the linear function applied for the output layer. The coefficient of determination (R²) and mean square error (MSE) was calculated. Results: It was proved that the hybrid model was superior to PLS-SEM methods. Using hybrid model, the optimal network happened at MPLP 3-17-8, while the R² of the model was increased by 27%, while, the MSE was decreased by 9.6%. Moreover, it was found that which one of these factors have significantly affected on healthy and unhealthy eating behavior patterns. The p-value was reported to be less than 0.01 for most of the paths. Conclusion/Importance: Thus, a hybrid approach could be suggested as a significant methodological contribution from a statistical standpoint, and it can be implemented as software to be able to predict models with the highest accuracy.

Keywords: hybrid model, structural equation modeling, artificial neural networks, eating behavior patterns

Procedia PDF Downloads 156

Authors: Mehrnaz Mostafavi

Abstract:

The assessment and categorization of incidental lung nodules present a considerable challenge in healthcare, often necessitating resource-intensive multiple computed tomography (CT) scans for growth confirmation. This research addresses this issue by introducing a distinct computational approach leveraging radiomics and deep-learning methods. However, understanding local services is essential before implementing these advancements. With diverse tracking methods in place, there is a need for efficient and accurate identification approaches, especially in the context of managing lung nodules alongside pre-existing cancer scenarios. This study explores the integration of text-based algorithms in medical data curation, indicating their efficacy in conjunction with machine learning and deep-learning models for identifying lung nodules. Combining medical images with text data has demonstrated superior data retrieval compared to using each modality independently. While deep learning and text analysis show potential in detecting previously missed nodules, challenges persist, such as increased false positives. The presented research introduces a Structured-Query-Language (SQL) algorithm designed for identifying pulmonary nodules in a tertiary cancer center, externally validated at another hospital. Leveraging natural language processing (NLP) and machine learning, the algorithm categorizes lung nodule reports based on sentence features, aiming to facilitate research and assess clinical pathways. The hypothesis posits that the algorithm can accurately identify lung nodule CT scans and predict concerning nodule features using machine-learning classifiers. Through a retrospective observational study spanning a decade, CT scan reports were collected, and an algorithm was developed to extract and classify data. Results underscore the complexity of lung nodule cohorts in cancer centers, emphasizing the importance of careful evaluation before assuming a metastatic origin. The SQL and NLP algorithms demonstrated high accuracy in identifying lung nodule sentences, indicating potential for local service evaluation and research dataset creation. Machine-learning models exhibited strong accuracy in predicting concerning changes in lung nodule scan reports. While limitations include variability in disease group attribution, the potential for correlation rather than causality in clinical findings, and the need for further external validation, the algorithm's accuracy and potential to support clinical decision-making and healthcare automation represent a significant stride in lung nodule management and research.

Keywords: lung cancer diagnosis, structured-query-language (SQL), natural language processing (NLP), machine learning, CT scans

Procedia PDF Downloads 100

Authors: Yunwei Tang, Linhai Jing, Hui Li, Qingjie Liu, Xiuxia Li, Qi Yan, Haifeng Ding

Abstract:

The giant panda (Ailuropoda melanoleuca) is an endangered species, mainly live in central China, where bamboos act as the main food source of wild giant pandas. Knowledge of spatial distribution of bamboos therefore becomes important for identifying the habitat of giant pandas. There have been ongoing studies for mapping bamboos and other tree species using remote sensing. WorldView-2 (WV-2) is the first high resolution commercial satellite with eight Multi-Spectral (MS) bands. Recent studies demonstrated that WV-2 imagery has a high potential in classification of tree species. The advanced classification techniques are important for utilising high spatial resolution imagery. It is generally agreed that object-based image analysis is a more desirable method than pixel-based analysis in processing high spatial resolution remotely sensed data. Classifiers that use spatial information combined with spectral information are known as contextual classifiers. It is suggested that contextual classifiers can achieve greater accuracy than non-contextual classifiers. Thus, spatial correlation can be incorporated into classifiers to improve classification results. The study area is located at Wuyipeng area in Wolong, Sichuan Province. The complex environment makes it difficult for information extraction since bamboos are sparsely distributed, mixed with brushes, and covered by other trees. Extensive fieldworks in Wuyingpeng were carried out twice. The first one was on 11th June, 2014, aiming at sampling feature locations for geometric correction and collecting training samples for classification. The second fieldwork was on 11th September, 2014, for the purposes of testing the classification results. In this study, spectral separability analysis was first performed to select appropriate MS bands for classification. Also, the reflectance analysis provided information for expanding sample points under the circumstance of knowing only a few. Then, a spatially weighted object-based k-nearest neighbour (k-NN) classifier was applied to the selected MS bands to identify seven land cover types (bamboo, conifer, broadleaf, mixed forest, brush, bare land, and shadow), accounting for spatial correlation within classes using geostatistical modelling. The spatially weighted k-NN method was compared with three alternatives: the traditional k-NN classifier, the Support Vector Machine (SVM) method and the Classification and Regression Tree (CART). Through field validation, it was proved that the classification result obtained using the spatially weighted k-NN method has the highest overall classification accuracy (77.61%) and Kappa coefficient (0.729); the producer’s accuracy and user’s accuracy achieve 81.25% and 95.12% for the bamboo class, respectively, also higher than the other methods. Photos of tree crowns were taken at sample locations using a fisheye camera, so the canopy density could be estimated. It is found that it is difficult to identify bamboo in the areas with a large canopy density (over 0.70); it is possible to extract bamboos in the areas with a median canopy density (from 0.2 to 0.7) and in a sparse forest (canopy density is less than 0.2). In summary, this study explores the ability of WV-2 imagery for bamboo extraction in a mountainous region in Sichuan. The study successfully identified the bamboo distribution, providing supporting knowledge for assessing the habitats of giant pandas.

Keywords: bamboo mapping, classification, geostatistics, k-NN, worldview-2

Procedia PDF Downloads 313

Authors: J. Ritonja, B. Grcar

Abstract:

For the synchronous generator simulation and analysis and for the power system stabilizer design and synthesis a mathematical model of synchronous generator is needed. The model has to accurately describe dynamics of oscillations, while at the same time has to be transparent enough for an analysis and sufficiently simplified for design of control system. To study the oscillations of the synchronous generator against to the rest of the power system, the model of the synchronous machine connected to an infinite bus through a transmission line having resistance and inductance is needed. In this paper, the linearized reduced order dynamic model of the synchronous generator connected to the infinite bus is presented and analysed in details. This model accurately describes dynamics of the synchronous generator only in a small vicinity of an equilibrium state. With the digression from the selected equilibrium point the accuracy of this model is decreasing considerably. In this paper, the equations’ descriptions and the parameters’ determinations for the linearized reduced order mathematical model of the synchronous generator are explained and summarized and represent the useful origin for works in the areas of synchronous generators’ dynamic behaviour analysis and synchronous generator’s control systems design and synthesis. The main contribution of this paper represents the detailed analysis of the accuracy of the linearized reduced order dynamic model in the entire synchronous generator’s operating range. Borders of the areas where the linearized reduced order mathematical model represents accurate description of the synchronous generator’s dynamics are determined with the systemic numerical analysis. The thorough eigenvalue analysis of the linearized models in the entire operating range is performed. In the paper, the parameters of the linearized reduced order dynamic model of the laboratory salient poles synchronous generator were determined and used for the analysis. The theoretical conclusions were confirmed with the agreement of experimental and simulation results.

Keywords: eigenvalue analysis, mathematical model, power system stability, synchronous generator

Procedia PDF Downloads 245

Authors: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 71

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 115

Authors: Sitarrine Thongpussawal, Dasarath Jayasuriya, Thanaroj Woraratprasert, Sakawtree Prajamwong

Abstract:

Thailand grapples with recurrent floods causing substantial repercussions on its economy, society, and environment. In 2021, the economic toll of these floods amounted to an estimated 53,282 million baht, primarily impacting the agricultural sector. The existing flood monitoring system in Thailand suffers from inaccuracies and insufficient information, resulting in delayed warnings and ineffective communication to the public. The Office of the National Water Resources (OWNR) is tasked with developing and integrating data and information systems for efficient water resources management, yet faces challenges in monitoring accuracy, forecasting, and timely warnings. This study endeavors to evaluate the viability of enhancing Thailand's Flood Forecasting and Warning (FFW) systems. Additionally, it aims to formulate a comprehensive work package grounded in international best practices to enhance the country's FFW systems. Employing qualitative research methodologies, the study conducted in-depth interviews and focus groups with pertinent agencies. Data analysis involved techniques like note-taking and document analysis. The study substantiates the feasibility of developing and enhancing FFW systems in Thailand. Implementation of international best practices can augment the precision of flood forecasting and warning systems, empowering local agencies and residents in high-risk areas to prepare proactively, thereby minimizing the adverse impact of floods on lives and property. This research underscores that Thailand can feasibly advance its FFW systems by adopting international best practices, enhancing accuracy, and improving preparedness. Consequently, the study enriches the theoretical understanding of flood forecasting and warning systems and furnishes valuable recommendations for their enhancement in Thailand.

Keywords: flooding, forecasting, warning, monitoring, communication, Thailand

Procedia PDF Downloads 61

Authors: Fernanda A. P. Peres, Thiago N. Peres, Flavio S. Fogliatto, Michel J. Anzanello

Abstract:

Batch processes are widely used in food industry and have an important role in the production of high added value products, such as chocolate. Process performance is usually described by variables that are monitored as the batch progresses. Data arising from these processes are likely to display a strong correlation-autocorrelation structure, and are usually monitored using control charts based on multiway principal components analysis (MPCA). Process control of a new batch is carried out comparing the trajectories of its relevant process variables with those in a reference set of batches that yielded products within specifications; it is clear that proper determination of the reference set is key for the success of a correct signalization of non-conforming batches in such quality control schemes. In chocolate manufacturing, misclassifications of non-conforming batches in the conching phase may lead to significant financial losses. In such context, the accuracy of process control grows in relevance. In addition to that, the main assumption in MPCA-based monitoring strategies is that all batches are synchronized in duration, both the new batch being monitored and those in the reference set. Such assumption is often not satisfied in chocolate manufacturing process. As a consequence, traditional techniques as MPCA-based charts are not suitable for process control and monitoring. To address that issue, the objective of this work is to compare the performance of three dynamic time warping (DTW) methods in the alignment and synchronization of chocolate conching process variables’ trajectories, aimed at properly determining the reference distribution for multivariate statistical process control. The power of classification of batches in two categories (conforming and non-conforming) was evaluated using the k-nearest neighbor (KNN) algorithm. Real data from a milk chocolate conching process was collected and the following variables were monitored over time: frequency of soybean lecithin dosage, rotation speed of the shovels, current of the main motor of the conche, and chocolate temperature. A set of 62 batches with durations between 495 and 1,170 minutes was considered; 53% of the batches were known to be conforming based on lab test results and experts’ evaluations. Results showed that all three DTW methods tested were able to align and synchronize the conching dataset. However, synchronized datasets obtained from these methods performed differently when inputted in the KNN classification algorithm. Kassidas, MacGregor and Taylor’s (named KMT) method was deemed the best DTW method for aligning and synchronizing a milk chocolate conching dataset, presenting 93.7% accuracy, 97.2% sensitivity and 90.3% specificity in batch classification, being considered the best option to determine the reference set for the milk chocolate dataset. Such method was recommended due to the lowest number of iterations required to achieve convergence and highest average accuracy in the testing portion using the KNN classification technique.

Keywords: batch process monitoring, chocolate conching, dynamic time warping, reference set distribution, variable duration

Procedia PDF Downloads 167

Authors: Zermina Q., Wasif Y., Naeem S., Urooj S., Sajid R. A.

Abstract:

Land degradation, a leading environemtnal problem and a decrease in the quality of land has become a major global issue, caused by human activities. By land degradation, more than half of the world’s drylands are affected. The worldwide scope of main saline soils is approximately 955 M ha, whereas inferior salinization affected approximately 77 M ha. In irrigated areas, a total of 58% of these soils is found. As most of the vegetation types requires fertile soil for their growth and quality production, salinity causes serious problem to the production of these vegetation types and agriculture demands. This research aims to identify the salt affected areas in the selected part of Indus Delta, Sindh province, Pakistan. This particular mangroves dominating coastal belt is important to the local community for their crop growth. Object based image analysis approach has been adopted on Landsat TM imagery of year 2011 by incorporating different mathematical band ratios, thermal radiance and salinity index. Accuracy assessment of developed salinity landcover map was performed using Erdas Imagine Accuracy Assessment Utility. Rain factor was also considered before acquiring satellite imagery and conducting field survey, as wet soil can greatly affect the condition of saline soil of the area. Dry season considered best for the remote sensing based observation and monitoring of the saline soil. These areas were trained with the ground truth data w.r.t pH and electric condutivity of the soil samples. The results were obtained from the object based image analysis of Keti bunder and Kharo chan shows most of the region under low saline soil.Total salt affected soil was measured to be 46,581.7 ha in Keti Bunder, which represents 57.81 % of the total area of 80,566.49 ha. High Saline Area was about 7,944.68 ha (9.86%). Medium Saline Area was about 17,937.26 ha (22.26 %) and low Saline Area was about 20,699.77 ha (25.69%). Where as total salt affected soil was measured to be 52,821.87 ha in Kharo Chann, which represents 55.87 % of the total area of 94,543.54 ha. High Saline Area was about 5,486.55 ha (5.80 %). Medium Saline Area was about 13,354.72 ha (14.13 %) and low Saline Area was about 33980.61 ha (35.94 %). These results show that the area is low to medium saline in nature. Accuracy of the soil salinity map was found to be 83 % with the Kappa co-efficient of 0.77. From this research, it was evident that this area as a whole falls under the category of low to medium saline area and being close to coastal area, mangrove forest can flourish. As Mangroves are salt tolerant plant so this area is consider heaven for mangrove plantation. It would ultimately benefit both the local community and the environment. Increase in mangrove forest control the problem of soil salinity and prevent sea water to intrude more into coastal area. So deforestation of mangrove should be regularly monitored.

Keywords: indus delta, object based image analysis, soil salinity, thematic mapper

Procedia PDF Downloads 619

Authors: Ákos Wolf, Richard P. Ray

Abstract:

Due to the introduction of Eurocode 8, the structural design for seismic and dynamic effects has become more significant in Hungary. This has emphasized the need for more effort to describe the behavior of structures under these conditions. Soil conditions have a significant effect on the response of structures by modifying the stiffness and damping of the soil-structural system and by modifying the seismic action as it reaches the ground surface. Shear modulus (G) and shear wave velocity (v_s), which are often measured in the field, are the fundamental dynamic soil properties for foundation vibration problems, liquefaction potential and earthquake site response analysis. There are several laboratory and in-situ measurement techniques to evaluate dynamic soil properties, but unfortunately, they are often too expensive for general design practice. However, a significant number of correlations have been proposed to determine shear wave velocity or shear modulus from Cone Penetration Tests (CPT), which are used more and more in geotechnical design practice in Hungary. This allows the designer to analyze and compare CPT and seismic test result in order to select the best correlation equations for Hungarian soils and to improve the recommendations for the Hungarian geologic conditions. Based on a literature review, as well as research experience in Hungary, the influence of various parameters on the accuracy of results will be shown. This study can serve as a basis for selecting and modifying correlation equations for Hungarian soils. Test data are taken from seven locations in Hungary with similar geologic conditions. The shear wave velocity values were measured by seismic CPT. Several factors are analyzed including soil type, behavior index, measurement depth, geologic age etc. for their effect on the accuracy of predictions. The final results show an improved prediction method for Hungarian soils

Keywords: CPT correlation, dynamic soil properties, seismic CPT, shear wave velocity

Procedia PDF Downloads 246

Authors: Ermias A. Tegegn, Million Meshesha

Abstract:

Human Immunodeficiency Virus and Acquired Immunodeficiency Syndrome (HIV/AIDS) is a major cause of death for most African countries. Ethiopia is one of the seriously affected countries in sub Saharan Africa. Previously in Ethiopia, having HIV/AIDS was almost equivalent to a death sentence. With the introduction of Antiretroviral Therapy (ART), HIV/AIDS has become chronic, but manageable disease. The study focused on a data mining technique to predict future living status of HIV/AIDS patients at the time of drug regimen change when the patients become toxic to the currently taking ART drug combination. The data is taken from University of Gondar Hospital ART program database. Hybrid methodology is followed to explore the application of data mining on ART program dataset. Data cleaning, handling missing values and data transformation were used for preprocessing the data. WEKA 3.7.9 data mining tools, classification algorithms, and expertise are utilized as means to address the research problem. By using four different classification algorithms, (i.e., J48 Classifier, PART rule induction, Naïve Bayes and Neural network) and by adjusting their parameters thirty-two models were built on the pre-processed University of Gondar ART program dataset. The performances of the models were evaluated using the standard metrics of accuracy, precision, recall, and F-measure. The most effective model to predict the status of HIV patients with drug regimen substitution is pruned J48 decision tree with a classification accuracy of 98.01%. This study extracts interesting attributes such as Ever taking Cotrim, Ever taking TbRx, CD4 count, Age, Weight, and Gender so as to predict the status of drug regimen substitution. The outcome of this study can be used as an assistant tool for the clinician to help them make more appropriate drug regimen substitution. Future research directions are forwarded to come up with an applicable system in the area of the study.

Keywords: HIV drug regimen, data mining, hybrid methodology, predictive model

Procedia PDF Downloads 142

Authors: Shanlong Lu, Jiming Jin, Xiaochun Wang

Abstract:

The Tibetan Plateau has the largest number of inland lakes with the highest elevation on the planet. These massive and large lakes are mostly in natural state and are less affected by human activities. Their shrinking or expansion can truly reflect regional climate and environmental changes and are sensitive indicators of global climate change. However, due to the sparsely populated nature of the plateau and the poor natural conditions, it is difficult to effectively obtain the change data of the lake, which has affected people's understanding of the temporal and spatial processes of lake water changes and their influencing factors. By using the MODIS (Moderate Resolution Imaging Spectroradiometer) MOD09Q1 surface reflectance images as basic data, this study produced the 8-day lake water surface data set of the Tibetan Plateau from 2000 to 2012 at 250 m spatial resolution, with a lake water surface extraction method of combined with lake water surface boundary buffer analyzing and lake by lake segmentation threshold determining. Then based on the dataset, the lake water surface variations and their influencing factors were analyzed, by using 4 typical natural geographical zones of Eastern Qinghai and Qilian, Southern Qinghai, Qiangtang, and Southern Tibet, and the watersheds of the top 10 lakes of Qinghai, Siling Co, Namco, Zhari NamCo, Tangra Yumco, Ngoring, UlanUla, Yamdrok Tso, Har and Gyaring as the analysis units. The accuracy analysis indicate that compared with water surface data of the 134 sample lakes extracted from the 30 m Landsat TM (Thematic Mapper ) images, the average overall accuracy of the lake water surface data set is 91.81% with average commission and omission error of 3.26% and 5.38%; the results also show strong linear (R2=0.9991) correlation with the global MODIS water mask dataset with overall accuracy of 86.30%; and the lake area difference between the Second National Lake Survey and this study is only 4.74%, respectively. This study provides reliable dataset for the lake change research of the plateau in the recent decade. The change trends and influencing factors analysis indicate that the total water surface area of lakes in the plateau showed overall increases, but only lakes with areas larger than 10 km2 had statistically significant increases. Furthermore, lakes with area larger than 100 km2 experienced an abrupt change in 2005. In addition, the annual average precipitation of Southern Tibet and Southern Qinghai experienced significant increasing and decreasing trends, and corresponding abrupt changes in 2004 and 2006, respectively. The annual average temperature of Southern Tibet and Qiangtang showed a significant increasing trend with an abrupt change in 2004. The major reason for the lake water surface variation in Eastern Qinghai and Qilian, Southern Qinghai and Southern Tibet is the changes of precipitation, and that for Qiangtang is the temperature variations.

Keywords: lake water surface variation, MODIS MOD09Q1, remote sensing, Tibetan Plateau

Procedia PDF Downloads 231

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 170