Search results for: deep supervision

Authors: Yazan Al-Kofahi, Jamal Alqawasmi.

Abstract:

In this study, a comprehensive literature review (SLR) was conducted, with the main goal of assessing the existing literature about how artificial intelligence (AI), machine learning (ML), deep learning (DL) models are used in sustainable architecture applications and issues including thermal comfort satisfaction, energy efficiency, cost prediction and many others issues. For this reason, the search strategy was initiated by using different databases, including Scopus, Springer and Google Scholar. The inclusion criteria were used by two research strings related to DL, ML and sustainable architecture. Moreover, the timeframe for the inclusion of the papers was open, even though most of the papers were conducted in the previous four years. As a paper filtration strategy, conferences and books were excluded from database search results. Using these inclusion and exclusion criteria, the search was conducted, and a sample of 59 papers was selected as the final included papers in the analysis. The data extraction phase was basically to extract the needed data from these papers, which were analyzed and correlated. The results of this SLR showed that there are many applications of ML and DL in Sustainable buildings, and that this topic is currently trendy. It was found that most of the papers focused their discussions on addressing Environmental Sustainability issues and factors using machine learning predictive models, with a particular emphasis on the use of Decision Tree algorithms. Moreover, it was found that the Random Forest repressor demonstrates strong performance across all feature selection groups in terms of cost prediction of the building as a machine-learning predictive model.

Keywords: machine learning, deep learning, artificial intelligence, sustainable building

Procedia PDF Downloads 67

Authors: Bharti Chogtu Magazine, Dhanya Soodana Mohan, Shruti Nair, Tanwi Trushna

Abstract:

The study was undertaken to analyse the cardiovascular drugs being prescribed in patients with concomitant reactive airway disease and hypertension or ischemic heart diseases (IHD). Also, the effect of beta-blockers on respiratory symptoms in these patients was recorded. Data was collected from medical records of patients with reactive airway disease and concomitant hypertension and IHD. It included demographic details of the patients, diagnosis, drugs prescribed and the patient outcome regarding the exacerbation of asthma symptoms with intake of beta blockers. Medical records of 250 patients were analysed.13% of patients were prescribed beta-blockers. 12% of hypertensive patients, 16.6% of IHD patients and 20% of patients with concomitant hypertension and IHD were prescribed beta blockers. Of the 33 (13%) patients who were on beta-blockers, only 3 patients had an exacerbation of bronchial asthma symptoms. Cardioselective beta-blockers under supervision appear to be safe in patients with reactive airway disease and concomitant hypertension and IHD.

Keywords: beta blockers, hypertension, ischemic heart disease, asthma

Procedia PDF Downloads 445

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 99

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 131

Authors: Mohamed Bekheit Gad Khaleil

Abstract:

The Maadi was a civilization .It is considered one of the oldest civilizations in the world and an area of prehistoric times, especially the civilization (Nakada 1&2 ) It contains the oldest stone house in the history. Many excavations have been done in this area. This report was prepared under my supervision and in cooperation with the German institute .The stone building was redocumented, photographed and drawn once again . The stone building has been built carefully. The measurements for this building are (8m x 4m).and the depth of this building is 2m underground and an entrance located at the eastern part of the northern wall and it has three huge pits in the middle of the building seem to have contained wooden posts, most probably to support the roof. The use of the building is unclear. Circular impressions in front of the north wall and in the south-eastern part of the floor indicate that much of it was a storehouse for numerous vessels such as unique feature may have not only served for private domestic purposes. Before starting work in any site, instruction must be followed :- 1-Gather as much information about this place as possible . (Historical background - previous excavations - maps - pictures) 2-Writing, recording, describing and documenting 3- Draw a map of the site showing the place’s division system (trenches) 4- Safe ( Workers & The Place )

Keywords: photographing, excavations, documentation, registration

Procedia PDF Downloads 40

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Electricity prices have sophisticated features such as high volatility, nonlinearity and high frequency that make forecasting quite difficult. Electricity price has a volatile and non-random character so that, it is possible to identify the patterns based on the historical data. Intelligent decision-making requires accurate price forecasting for market traders, retailers, and generation companies. So far, many shallow-ANN (artificial neural networks) models have been published in the literature and showed adequate forecasting results. During the last years, neural networks with many hidden layers, which are referred to as DNN (deep neural networks) have been using in the machine learning community. The goal of this study is to investigate electricity price forecasting performance of the shallow-ANN and DNN models for the Turkish day-ahead electricity market. The forecasting accuracy of the models has been evaluated with publicly available data from the Turkish day-ahead electricity market. Both shallow-ANN and DNN approach would give successful result in forecasting problems. Historical load, price and weather temperature data are used as the input variables for the models. The data set includes power consumption measurements gathered between January 2016 and December 2017 with one-hour resolution. In this regard, forecasting studies have been carried out comparatively with shallow-ANN and DNN models for Turkish electricity markets in the related time period. The main contribution of this study is the investigation of different shallow-ANN and DNN models in the field of electricity price forecast. All models are compared regarding their MAE (Mean Absolute Error) and MSE (Mean Square) results. DNN models give better forecasting performance compare to shallow-ANN. Best five MAE results for DNN models are 0.346, 0.372, 0.392, 0,402 and 0.409.

Keywords: deep learning, artificial neural networks, energy price forecasting, turkey

Procedia PDF Downloads 292

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 91

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 290

Authors: Bruno Cossu, Elio Carlo

Abstract:

The invention (patent pending) relates to the field of devices aimed to harness wave energy (WEC) especially for artificial upwelling, forced downwelling, production of compressed air. In its basic form, the pump consists of a hydro-pneumatic machine, driven by wave energy, characterised by the fact that it has no moving mechanical parts, and is made up of only two structural components: an hollow body, which is open at the bottom to the sea and partially immersed in sea water, and a tube, both joined together to form a single body. The shape of the hollow body is like a mushroom whose cap and stem are hollow; the stem is open at both ends and the lower part of its surface is crossed by holes; the tube is external and coaxial to the stem and is joined to it so as to form a single body. This shape of the hollow body and the type of connection to the tube allows the pump to operate simultaneously as an air compressor (OWC) on the cap side, and as an airlift on the stem side. The pump can be implemented in four versions, each of which provides different variants and methods of implementation: 1) firstly, for the artificial upwelling of cold, deep ocean water; 2) secondly, for the lifting and transfer of these waters to the place of use (above all, fish farming plants), even if kilometres away; 3) thirdly, for the forced downwelling of surface sea water; 4) fourthly, for the forced downwelling of surface water, its oxygenation, and the simultaneous production of compressed air. The transfer of the deep water or the downwelling of the raised surface water (as for pump versions indicated in points 2 and 3 above), is obtained by making the water raised by the airlift flow into the upper inlet of another pipe, internal or adjoined to the airlift; the downwelling of raised surface water, oxygenation, and the simultaneous production of compressed air (as for the pump version indicated in point 4), is obtained by installing a venturi tube on the upper end of the pipe, whose restricted section is connected to the external atmosphere, so that it also operates like a hydraulic air compressor (trompe). Furthermore, by combining one or more pumps for the upwelling of cold, deep water, with one or more pumps for the downwelling of the warm surface water, the system can be used in an Ocean Thermal Energy Conversion plant to supply the cold and the warm water required for the operation of the same, thus allowing to use, without increased costs, in addition to the mechanical energy of the waves, for the purposes indicated in points 1 to 4, the thermal one of the marine water treated in the process.

Keywords: air lifted upwelling, fish farming plant, hydraulic air compressor, wave energy converter

Procedia PDF Downloads 148

Authors: Erez Kita, Gil Luria

Abstract:

This study examines gender as a boundary condition for the relationship between the psychological variable of mindfulness and the social variable of income with regards to the use of smartphones by young drivers. The use of smartphones while driving increases the likelihood of a car accident, endangering young drivers and other road users. The study sample included 186 young drivers who were legally permitted to drive without supervision. The subjects were first asked to complete questionnaires on mindfulness and income. Next, their smartphone use while driving was monitored over a one-month period. This study is unique as it used an objective smartphone monitoring application (rather than self-reporting) to count the number of times the young participants actually touched their smartphones while driving. The findings show that gender moderates the effects of social and personal factors (i.e., income and mindfulness) on the use of smartphones while driving. The pattern of moderation was similar for both social and personal factors. For men, mindfulness and income are negatively associated with the use of smartphones while driving. These factors are not related to the use of smartphones by women drivers. Mindfulness and income can be used to identify male populations that are at risk of using smartphones while driving. Interventions that improve mindfulness can be used to reduce the use of smartphones by male drivers.

Keywords: mindfulness, using smartphones while driving, income, gender, young drivers

Procedia PDF Downloads 170

Authors: Kumar Divyendra

Abstract:

Underwater Sensor Networks (UWSNs) have wide applications in areas such as water quality monitoring, marine wildlife management etc. A typical UWSN system consists of a set of sensors deployed randomly underwater which communicate with each other using acoustic links. RF communication doesn't work underwater, and GPS too isn't available underwater. Additionally Automated Underwater Vehicles (AUVs) are deployed to collect data from some special nodes called Cluster Heads (CHs). These CHs aggregate data from their neighboring nodes and forward them to the AUVs using optical links when an AUV is in range. This helps reduce the number of hops covered by data packets and helps conserve energy. We consider the three-dimensional model of the UWSN. Nodes are initially deployed randomly underwater. They attach themselves to the surface using a rod and can only move upwards or downwards using a pump and bladder mechanism. We use graph theory concepts to maximize the coverage volume while every node maintaining connectivity with at least one surface node. We treat the surface nodes as landmarks and each node finds out its hop distance from every surface node. We treat these hop-distances as coordinates and use them for AUV navigation. An AUV intending to move closer to a node with given coordinates moves hop by hop through nodes that are closest to it in terms of these coordinates. In absence of GPS, multiple different approaches like Inertial Navigation System (INS), Doppler Velocity Log (DVL), computer vision-based navigation, etc., have been proposed. These systems have their own drawbacks. INS accumulates error with time, vision techniques require prior information about the environment. We propose a method that makes use of the earth's magnetic field values for navigation and combines it with other methods that simultaneously increase the coverage volume under the UWSN. The AUVs are fitted with magnetometers that measure the magnetic intensity (I), horizontal inclination (H), and Declination (D). The International Geomagnetic Reference Field (IGRF) is a mathematical model of the earth's magnetic field, which provides the field values for the geographical coordinateson earth. Researchers have developed an inverse deep learning model that takes the magnetic field values and predicts the location coordinates. We make use of this model within our work. We combine this with with the hop-by-hop movement described earlier so that the AUVs move in such a sequence that the deep learning predictor gets trained as quickly and precisely as possible We run simulations in MATLAB to prove the effectiveness of our model with respect to other methods described in the literature.

Keywords: clustering, deep learning, network backbone, parallel computing

Procedia PDF Downloads 98

Authors: Joel M. De La Rosa R.

Abstract:

In this paper, the results obtained when monitoring the horizontal deformations of the soil mass are detailed, during each of the construction stages of several vertical shafts located in the soft soils of the Valley of Mexico, by means of the flotation method. From the analysis of these results, the magnitude and percentage relationship with respect to the diameter and depth of excavation of the horizontal deformations that occurred during the monitoring period is established. Based on the horizontal deformation monitoring system and the information provided by the supervisor's site log, the construction stages that have the greatest impact on deformations are established. Additionally, an analysis of the deformations is carried out, which takes into account the resistance and deformability characteristics of the excavated soils, as well as the prevailing hydraulic conditions. This work will allow construction engineers and institutions in charge of infrastructure works in the Valley of Mexico to establish permissible ranges for horizontal deformations that can occur in very soft and saturated soils, during the different construction stages; improving response protocols to potentially dangerous behaviors.

Keywords: vertical shaft, flotation method, very soft clays, construction supervision

Procedia PDF Downloads 188

Authors: Maryam Fallahpoor, Biswajeet Pradhan

Abstract:

Background: Artificial intelligence (AI) serves as a valuable tool in mitigating the scarcity of human resources required for the evaluation and categorization of vast quantities of medical imaging data. When AI operates with optimal precision, it minimizes the demand for human interpretations and, thereby, reduces the burden on radiologists. Among various AI approaches, deep learning (DL) stands out as it obviates the need for feature extraction, a process that can impede classification, especially with intricate datasets. The advent of DL models has ushered in a new era in medical imaging, particularly in the context of COVID-19 detection. Traditional 2D imaging techniques exhibit limitations when applied to volumetric data, such as Computed Tomography (CT) scans. Medical images predominantly exist in one of two formats: neuroimaging informatics technology initiative (NIfTI) and digital imaging and communications in medicine (DICOM). Purpose: This study aims to employ DL for the classification of COVID-19-infected pulmonary patients and normal cases based on 3D CT scans while investigating the impact of image format. Material and Methods: The dataset used for model training and testing consisted of 1245 patients from IranMehr Hospital. All scans shared a matrix size of 512 × 512, although they exhibited varying slice numbers. Consequently, after loading the DICOM CT scans, image resampling and interpolation were performed to standardize the slice count. All images underwent cropping and resampling, resulting in uniform dimensions of 128 × 128 × 60. Resolution uniformity was achieved through resampling to 1 mm × 1 mm × 1 mm, and image intensities were confined to the range of (−1000, 400) Hounsfield units (HU). For classification purposes, positive pulmonary COVID-19 involvement was designated as 1, while normal images were assigned a value of 0. Subsequently, a U-net-based lung segmentation module was applied to obtain 3D segmented lung regions. The pre-processing stage included normalization, zero-centering, and shuffling. Four distinct 3D CNN models (ResNet152, ResNet50, DensNet169, and DensNet201) were employed in this study. Results: The findings revealed that the segmentation technique yielded superior results for DICOM images, which could be attributed to the potential loss of information during the conversion of original DICOM images to NIFTI format. Notably, ResNet152 and ResNet50 exhibited the highest accuracy at 90.0%, and the same models achieved the best F1 score at 87%. ResNet152 also secured the highest Area under the Curve (AUC) at 0.932. Regarding sensitivity and specificity, DensNet201 achieved the highest values at 93% and 96%, respectively. Conclusion: This study underscores the capacity of deep learning to classify COVID-19 pulmonary involvement using real 3D hospital data. The results underscore the significance of employing DICOM format 3D CT images alongside appropriate pre-processing techniques when training DL models for COVID-19 detection. This approach enhances the accuracy and reliability of diagnostic systems for COVID-19 detection.

Keywords: deep learning, COVID-19 detection, NIFTI format, DICOM format

Procedia PDF Downloads 88

Authors: Yahya Almurtadha, Mukhtar Ghaleb, Ahmed M. Shamsan Saleh

Abstract:

The world witnessed a fierce attack from the Covid-19 virus, which affected public life socially, economically, healthily and psychologically. The world's governments tried to confront the pandemic by imposing a number of precautionary measures such as general closure, curfews and social distancing. Scientists have also made strenuous efforts to develop an effective vaccine to train the immune system to develop antibodies to combat the virus, thus reducing its symptoms and limiting its spread. Artificial intelligence, along with researchers and medical authorities, has accelerated the vaccine development process through big data processing and simulation. On the other hand, one of the most important negatives of the impact of Covid 19 was the state of anxiety and fear due to the blowout of rumors through social media, which prompted governments to try to reassure the public with the available means. This study aims to proposed using Sentiment Analysis (AKA Opinion Mining) and deep learning as efficient artificial intelligence techniques to work on retrieving the tweets of the public from Twitter and then analyze it automatically to extract their opinions, expression and feelings, negatively or positively, about the symptoms they may feel after vaccination. Sentiment analysis is characterized by its ability to access what the public post in social media within a record time and at a lower cost than traditional means such as questionnaires and interviews, not to mention the accuracy of the information as it comes from what the public expresses voluntarily.

Keywords: deep learning, opinion mining, natural language processing, sentiment analysis

Procedia PDF Downloads 171

Authors: Sophia Shi

Abstract:

Acute kidney injury (AKI) is the sudden onset of kidney damage in which the kidneys cannot filter waste from the blood, requiring emergency hospitalization. AKI patient mortality rate is high in the ICU and is virtually impossible for doctors to predict because it is so unexpected. Currently, there is no hybrid model predicting AKI that takes advantage of two types of data. De-identified patient data from the MIMIC-III database and de-identified kidney images and corresponding patient records from the Beijing Hospital of the Ministry of Health were collected. Using data features including serum creatinine among others, two numeric models using MIMIC and Beijing Hospital data were built, and with the hospital ultrasounds, an image-only model was built. Convolutional neural networks (CNN) were used, VGG and Resnet for numeric data and Resnet for image data, and they were combined into a hybrid model by concatenating feature maps of both types of models to create a new input. This input enters another CNN block and then two fully connected layers, ending in a binary output after running through Softmax and additional code. The hybrid model successfully predicted AKI and the highest AUROC of the model was 0.953, achieving an accuracy of 90% and F1-score of 0.91. This model can be implemented into urgent clinical settings such as the ICU and aid doctors by assessing the risk of AKI shortly after the patient’s admission to the ICU, so that doctors can take preventative measures and diminish mortality risks and severe kidney damage.

Keywords: Acute kidney injury, Convolutional neural network, Hybrid deep learning, Patient record data, ResNet, Ultrasound kidney images, VGG

Procedia PDF Downloads 131

Authors: Qin Wei

Abstract:

There has been an increased number of immigrants arriving in Canada and a concurrent rise in the number of immigrant youth suffering from drug abuse. Immigrant youths’ drug abuse has become a significant social and public health concern for researchers. This literature review explores the nature of immigrant youths’ drug abuse by examining the factors influencing the onset of substance misuse, the barriers that discourage youth to seek out treatment, and how to resolve addictions amidst immigrant youth. Findings from the literature demonstrate that diminished parental supervision, acculturation challenges, peer conformity, discrimination, and ethnic marginalization are all significant factors influencing youth to use drugs as an outlet for their pain, while culturally competent care and fear of family and culture-based addiction stigma act as barriers discouraging youth from seeking out addiction support. To resolve addiction challenges amidst immigrant youth, future research should focus on promoting and implementing culturally sensitive practices and psychoeducational initiatives into immigrant communities and within public health policies.

Keywords: approaches, barriers, drug abuse, Canada, immigrant youth, reasons

Procedia PDF Downloads 232

Authors: Kedar Nath Nepal, Dyutiman Choudhary, Naba Raj Pandit, Yam Gahire

Abstract:

Crop fertilizer recommendations are outdated as these are based on the response trails conducted over half a century ago. Further, these recommendations were based on the response trials conducted over large geographical area ignoring the large spatial variability in indigenous nutrient supplying capacity of soils typical of most smallholder systems. Application of fertilizer following such blanket recommendation in fields with varying native nutrient supply capacity leads to under application in some places and over application in others leading to reduced nutrient-use-efficiency (NUE), loss of profitability, and increased environmental risks associated with loss of unutilized nutrient through emissions or leaching. Opportunities exist to further increase yield and profitability through a significant gain in fertilizer use efficiency with commercialization of affordable and precise application technologies. We conducted participatory trails in Maize (Zea Mays), Cauliflower (Brassica oleracea var. botrytis) and Tomato (Solanum lycopersicum) in Mid Hills of Nepal to evaluate the efficacy of Urea Deep Placement (UDP and Polymer Coated Urea (PCU);. UDP contains 46% of N having individual briquette size 2.7 gm each and PCU contains 44% of N . Both PCU and urea briquette applied at reduced amount (100 kg N/ha) during planting produced similar yields (p>0.05) compared with regular urea (200 Kg N/ha). . These fertilizers also reduced N fertilizer by 35 - 50% over government blanket recommendations. Further, PCU and urea briquette increased farmer’s net income by USD 60 to 80.

Keywords: high efficiency fertilizers, urea deep placement, briquette polymer coated urea, zea mays, brassica, lycopersicum, Nepal

Procedia PDF Downloads 173

Authors: Mangala Kohli, P. A. Athira, Reeha Mahajan

Abstract:

The subthalamic nucleus (STN) is a biconvex nucleus situated in the diencephalon. The knowledge of the morphometry of the subthalamic nucleus is essential for accurate targeting of the nucleus during Deep Brain Stimulation. The present study aims to note the morphometry of the subthalamic nucleus in both the cerebral hemispheres which will prove to be of great value to radiologists and neurosurgeons. A cross‐sectional observational study was conducted in the Departments of Anatomy and Forensic Medicine, Lady Hardinge Medical College & Associated Hospitals, New Delhi on thirty adult cadaveric brain specimens of unclaimed and donated corpses. The specimens were categorized into 3 age groups: 20-35, 35-50 and above 50 years. All samples were collected after following the standard protocol for ethical clearance. The morphometric study of 60 subthalamic nucleus was thus conducted. Transverse section of the brain was made at a plane 4mm ventral to the plane containing mid commissural point. The dimensions of the subthalamic nucleus were measured bilaterally with the aid of digital Vernier caliper and magnifying glass. In the present study, the mean length and width and AC-PC length of the subthalamic nucleus was recorded on the right and left side in Group A, B and C. On comparison of mean of subthalamic nucleus dimensions between the right and left side in Group C, no statistically significant difference was observed. The length and width of subthalamic nucleus measured in the 3 age groups were compared with each other and the p value calculated. There was no statistically significant difference between the dimensions of Group A and B, Group B and C as well as Group A and C. The present study reveals that there is no significant reduction in the size of the nucleus was noted with increasing age. Thus, the values obtained in the present study can be used as a reference for various invasive and non-invasive procedures on subthalamic nucleus.

Keywords: cerebral hemisphere, deep brain stimulation, morphometry, subthalamic nucleus

Procedia PDF Downloads 184

Authors: Jinan Fiaidhi, Hashmath Shaik

Abstract:

Breaking the barrier for practicing evidence-based medicine relies on effective methods for rapidly identifying relevant evidence from the body of biomedical literature. An important challenge confronted by medical practitioners is the long time needed to browse, filter, summarize and compile information from different medical resources. Deep learning can help in solving this based on automatic question answering (Q&A) and transformers. However, Q&A and transformer technologies are not trained to answer clinical queries that can be used for evidence-based practice, nor can they respond to structured clinical questioning protocols like PICO (Patient/Problem, Intervention, Comparison and Outcome). This article describes the use of deep learning techniques for Q&A that are based on transformer models like BERT and GPT to answer PICO clinical questions that can be used for evidence-based practice extracted from sound medical research resources like PubMed. We are reporting acceptable clinical answers that are supported by findings from PubMed. Our transformer methods are reaching an acceptable state-of-the-art performance based on two staged bootstrapping processes involving filtering relevant articles followed by identifying articles that support the requested outcome expressed by the PICO question. Moreover, we are also reporting experimentations to empower our bootstrapping techniques with patch attention to the most important keywords in the clinical case and the PICO questions. Our bootstrapped patched with attention is showing relevancy of the evidence collected based on entropy metrics.

Keywords: automatic question answering, PICO questions, evidence-based medicine, generative models, LLM transformers

Procedia PDF Downloads 43

Authors: Somayeh Komeylian

Abstract:

The direction of arrival (DoA) estimation is the crucial aspect of the radar technologies for detecting and dividing several signal sources. In this scenario, the antenna array output modeling involves numerous parameters including noise samples, signal waveform, signal directions, signal number, and signal to noise ratio (SNR), and thereby the methods of the DoA estimation rely heavily on the generalization characteristic for establishing a large number of the training data sets. Hence, we have analogously represented the two different optimization models of the DoA estimation; (1) the implementation of the decision directed acyclic graph (DDAG) for the multiclass least-squares support vector machine (LS-SVM), and (2) the optimization method of the deep neural network (DNN) radial basis function (RBF). We have rigorously verified that the LS-SVM DDAG algorithm is capable of accurately classifying DoAs for the three classes. However, the accuracy and robustness of the DoA estimation are still highly sensitive to technological imperfections of the antenna arrays such as non-ideal array design and manufacture, array implementation, mutual coupling effect, and background radiation and thereby the method may fail in representing high precision for the DoA estimation. Therefore, this work has a further contribution on developing the DNN-RBF model for the DoA estimation for overcoming the limitations of the non-parametric and data-driven methods in terms of array imperfection and generalization. The numerical results of implementing the DNN-RBF model have confirmed the better performance of the DoA estimation compared with the LS-SVM algorithm. Consequently, we have analogously evaluated the performance of utilizing the two aforementioned optimization methods for the DoA estimation using the concept of the mean squared error (MSE).

Keywords: DoA estimation, Adaptive antenna array, Deep Neural Network, LS-SVM optimization model, Radial basis function, and MSE

Procedia PDF Downloads 100

Authors: S. Nickolas, Shobha K.

Abstract:

The treatment of incomplete data is an important step in the data pre-processing. Missing values creates a noisy environment in all applications and it is an unavoidable problem in big data management and analysis. Numerous techniques likes discarding rows with missing values, mean imputation, expectation maximization, neural networks with evolutionary algorithms or optimized techniques and hot deck imputation have been introduced by researchers for handling missing data. Among these, imputation techniques plays a positive role in filling missing values when it is necessary to use all records in the data and not to discard records with missing values. In this paper we propose a novel artificial neural network based clustering algorithm, Adaptive Resonance Theory-2(ART2) for imputation of missing values in mixed attribute data sets. The process of ART2 can recognize learned models fast and be adapted to new objects rapidly. It carries out model-based clustering by using competitive learning and self-steady mechanism in dynamic environment without supervision. The proposed approach not only imputes the missing values but also provides information about handling the outliers.

Keywords: ART2, data imputation, clustering, missing data, neural network, pre-processing

Procedia PDF Downloads 274

Authors: Ricky Saputra, Rashmi Walvekar, Mohammad Khalid, Kaveh Shahbaz, Suganti Ramarad

Abstract:

This particular study of interest aims to study the effect of coupling ultrasonic treatment with eutectic solvents in devulcanization process of waste rubber tyre. Specifically, three different types of Deep Eutectic Solvents (DES) were utilized, namely ChCl:Urea (1:2), ChCl:ZnCl₂ (1:2) and ZnCl₂:urea (2:7) in which their physicochemical properties were analysed and proven to have permissible water content that is less than 3.0 wt%, degradation temperature below 200ᵒC and freezing point below 60ᵒC. The mass ratio of rubber to DES was varied from 1:20-1:40, sonicated for 1 hour at 37 kHz and heated at variable time of 5-30 min at 180ᵒC. Energy dispersive x-rays (EDX) results revealed that the first two DESs give the highest degree of sulphur removal at 74.44 and 76.69% respectively with optimum heating time at 15 minutes whereby if prolonged, reformation of crosslink network would be experienced. Such is supported by the evidence shown by both FTIR and FESEM results where di-sulfide peak reappears at 30 minutes and morphological structures from 15 to 30 minutes change from smooth with high voidage to rigid with low voidage respectively. Furthermore, TGA curve reveals similar phenomena whereby at 15 minutes thermal decomposition temperature is at the lowest due to the decrease of molecular weight as a result of sulphur removal but increases back at 30 minutes. Type of bond change was also analysed whereby it was found that only di-sulphide bond was cleaved and which indicates partial-devulcanization. Overall, the results show that DES has a great potential to be used as devulcanizing solvent.

Keywords: crosslink network, devulcanization, eutectic solvents, reformation, ultrasonic

Procedia PDF Downloads 173

Authors: Reggie Chandra

Abstract:

Trafficaccidents and traffic signal optimization are correlated. However, 70-90% of the traffic signals across the USA are not synchronized. The reason behind that is insufficient resources to create and implement timing plans. In this work, we will discuss the use of a breakthrough Artificial Intelligence (AI) technology to optimize traffic flow and collect 24/7/365 accurate traffic data using a vehicle detection system. We will discuss what are recent advances in Artificial Intelligence technology, how does AI work in vehicles, pedestrians, and bike data collection, creating timing plans, and what is the best workflow for that. Apart from that, this paper will showcase how Artificial Intelligence makes signal timing affordable. We will introduce a technology that uses Convolutional Neural Networks (CNN) and deep learning algorithms to detect, collect data, develop timing plans and deploy them in the field. Convolutional Neural Networks are a class of deep learning networks inspired by the biological processes in the visual cortex. A neural net is modeled after the human brain. It consists of millions of densely connected processing nodes. It is a form of machine learning where the neural net learns to recognize vehicles through training - which is called Deep Learning. The well-trained algorithm overcomes most of the issues faced by other detection methods and provides nearly 100% traffic data accuracy. Through this continuous learning-based method, we can constantly update traffic patterns, generate an unlimited number of timing plans and thus improve vehicle flow. Convolutional Neural Networks not only outperform other detection algorithms but also, in cases such as classifying objects into fine-grained categories, outperform humans. Safety is of primary importance to traffic professionals, but they don't have the studies or data to support their decisions. Currently, one-third of transportation agencies do not collect pedestrian and bike data. We will discuss how the use of Artificial Intelligence for data collection can help reduce pedestrian fatalities and enhance the safety of all vulnerable road users. Moreover, it provides traffic engineers with tools that allow them to unleash their potential, instead of dealing with constant complaints, a snapshot of limited handpicked data, dealing with multiple systems requiring additional work for adaptation. The methodologies used and proposed in the research contain a camera model identification method based on deep Convolutional Neural Networks. The proposed application was evaluated on our data sets acquired through a variety of daily real-world road conditions and compared with the performance of the commonly used methods requiring data collection by counting, evaluating, and adapting it, and running it through well-established algorithms, and then deploying it to the field. This work explores themes such as how technologies powered by Artificial Intelligence can benefit your community and how to translate the complex and often overwhelming benefits into a language accessible to elected officials, community leaders, and the public. Exploring such topics empowers citizens with insider knowledge about the potential of better traffic technology to save lives and improve communities. The synergies that Artificial Intelligence brings to traffic signal control and data collection are unsurpassed.

Keywords: artificial intelligence, convolutional neural networks, data collection, signal control, traffic signal

Procedia PDF Downloads 169

Authors: Seyed Ali Mohammadiborna, Mehdi Ravanshadnia

Abstract:

Project delays usually detrimentally affect perceptions of project success and can in some instances, result in increased costs and other time-related damages to project stakeholders. One of the realities in the national infrastructure projects is that since the primary stakeholders are state-affiliated, the delay factors of the projects have not been seriously taken into account despite the importance of on-time completion of projects. Project postponement has different economic and social consequences and leads to the technical and economic infeasibility of the infrastructure projects in the form of reduced productivity and exploitation capacity. The present study aimed at investigating delay factors of Iranian national infrastructure projects according to regulatory reports of the Plan and Budget Organization (BPO) of Iran. The present study scrutinized the influence of each of the factors that caused delays in national Iranian infrastructure projects according to the supervision reports of the planning and budget organization in 8 years. For this purpose, the study analyzed the information regarding the impact of 12 key delay factors causing delays in average 4867 projects per year in all provinces. The said factors were classified into the three groups of executive, credit, and financial and environmental-procurement factors.

Keywords: delays, infrastructure, projects, regulatory

Procedia PDF Downloads 137

Authors: Antonio Espingardeiro

Abstract:

It is likely that robots will cross the boundaries of industry into households over the next decades. With demographic challenges worldwide, the future ageing populations will require the introduction of assistive technologies capable of providing, care, human dignity and quality of life through the aging process. Robotics technology has a high potential for being used in the areas of social and healthcare by promoting a wide range of activities such as entertainment, companionship, supervision or cognitive and physical assistance. However, such close Human Robotics Interactions (HRIs) encompass a rich set of ethical scenarios that need to be addressed before Socially Assistive Robots (SARs) reach the global markets. Such interactions with robots may seem a worthy goal for many technical/financial reasons but inevitably require close attention to the ethical dimensions of such interactions. This article investigates the current HRI benchmark of social success. It revises it according to the ethical principles of beneficence, non-maleficence and justice aligned with social care ethos. An extension of such benchmark is proposed based on an empirical study of HRIs with elderly groups.

Keywords: HRI, SARs, social success, benchmark, elderly care

Procedia PDF Downloads 523

Authors: Vignesh Ratnaraj, Jaewon Chang

Abstract:

Background: Frailty is associated with poorer outcomes in cardiac surgery, but the heterogeneity in frailty assessment tools makes it difficult to ascertain its true impact in cardiac surgery. Slow gait speed is a simple, validated, and reliable marker of frailty. We performed a systematic review and meta-analysis to examine the effect of slow gait speed on postoperative cardiac surgical patients. Methods: PubMED, MEDLINE, and EMBASE databases were searched from January 2000 to August 2021 for studies comparing slow gait speed and “normal” gait speed. The primary outcome was in-hospital mortality. Secondary outcomes were composite mortality and major morbidity, AKI, stroke, deep sternal wound infection, prolonged ventilation, discharge to a healthcare facility, and ICU length of stay. Results: There were seven eligible studies with 36,697 patients. Slow gait speed was associated with an increased likelihood of in-hospital mortality (risk ratio [RR]: 2.32; 95% confidence interval [CI]: 1.87–2.87). Additionally, they were more likely to suffer from composite mortality and major morbidity (RR: 1.52; 95% CI: 1.38–1.66), AKI (RR: 2.81; 95% CI: 1.44–5.49), deep sternal wound infection (RR: 1.77; 95% CI: 1.59–1.98), prolonged ventilation >24 h (RR: 1.97; 95% CI: 1.48–2.63), reoperation (RR: 1.38; 95% CI: 1.05–1.82), institutional discharge (RR: 2.08; 95% CI: 1.61–2.69), and longer ICU length of stay (MD: 21.69; 95% CI: 17.32–26.05). Conclusion: Slow gait speed is associated with poorer outcomes in cardiac surgery. Frail patients are twofold more likely to die during hospital admission than non-frail counterparts and are at an increased risk of developing various perioperative complications.

Keywords: cardiac surgery, gait speed, recovery, frailty

Procedia PDF Downloads 72

Authors: Mourad Bédir, Sami Khomsi, Hakim Gabtni, Hajer Azaiez, Ramzi Gharsalli, Riadh Chebbi

Abstract:

Eastern Tunisia is a semi-arid area; located in the northern Africa plate; southern Mediterranean side. It is facing water scarcity, overexploitation, and decreasing of water quality of phreatic water table. Water supply and storage will not respond to the demographic and economic growth and demand. In addition, only 5 109 m3 of rainwater from 35 109 m3 per year renewable rain water supply can be retained and remobilized. To remediate this water deficiency, researches had been focused to near new subsurface deep aquifers resources. Among them, Upper Miocene sandstone deposits of Béglia, Saouaf, and Somaa Formations. These sandstones are known for their proven Hydrogeologic and hydrocarbon reservoir characteristics in the Tunisian margin. They represent semi-confined to confined aquifers. This work is based on new integrated approaches of seismic stratigraphy, seismic tectonics, and hydrogeology, to highlight and characterize these reservoirs levels for aquifer exploitation in semi-arid area. As a result, five to six third order sequence deposits had been highlighted. They are composed of multi-layered extended sandstones reservoirs; separated by shales packages. These reservoir deposits represent lowstand and highstand system tracts of these sequences, which represent lowstand and highstand system tracts of these sequences. They constitute important strategic water resources volumes for the region.

Keywords: Tunisia, Hydrogeology, sandstones, basin, seismic, aquifers, modeling

Procedia PDF Downloads 177

Authors: Ardiansyah I. Ryan, Ashsholih K. R., Fathurrohman G. R., Kurniadi M. R., Huda P. A

Abstract:

The burden of brain-related disease is very high. There are a lot of brain-related diseases with limited treatment result and thus raise the burden more. The Parkinson Disease (PD), Mental Health Problem, or Paralysis of extremities treatments had risen concern, as the patients for those diseases usually had a low quality of life and low chance to recover fully. There are also many other brain or related neural diseases with the similar condition, mainly the treatments for those conditions are still limited as our understanding of the brain function is insufficient. Brain Implant Technology had given hope to help in treating this condition. In this paper, we examine the current update of the brain implant technology. Neurotechnology is growing very rapidly worldwide. The United States Food and Drug Administration (FDA) has approved the use of Deep Brain Stimulation (DBS) as a brain implant in humans. As for neural implant both the cochlear implant and retinal implant are approved by FDA too. All of them had shown a promising result. DBS worked by stimulating a specific region in the brain with electricity. This device is planted surgically into a very specific region of the brain. This device consists of 3 main parts: Lead (thin wire inserted into the brain), neurostimulator (pacemaker-like device, planted surgically in the chest) and an external controller (to turn on/off the device by patient/programmer). FDA had approved DBS for the treatment of PD, Pain Management, Epilepsy and Obsessive Compulsive Disorder (OCD). The target treatment of DBS in PD is to reduce the tremor and dystonia symptoms. DBS has been showing the promising result in animal and limited human trial for other conditions such as Alzheimer, Mental Health Problem (Major Depression, Tourette Syndrome), etc. Every surgery has risks of complications, although in DBS the chance is very low. DBS itself had a very satisfying result as long as the subject criteria to be implanted this device based on indication and strictly selection. Other than DBS, there are several brain implant devices that still under development. It was included (not limited to) implant to treat paralysis (In Spinal Cord Injury/Amyotrophic Lateral Sclerosis), enhance brain memory, reduce obesity, treat mental health problem and treat epilepsy. The potential of neurotechnology is unlimited. When brain function and brain implant were fully developed, it may be one of the major breakthroughs in human history like when human find ‘fire’ for the first time. Support from every sector for further research is very needed to develop and unveil the true potential of this technology.

Keywords: brain implant, deep brain stimulation (DBS), deep brain stimulation, Parkinson

Procedia PDF Downloads 155

Authors: Michael Karnes, Alper Yilmaz

Abstract:

This paper presents the application of the omni-modeler towards pedestrian redetection. The pedestrian redetection task creates several challenges when applying deep neural networks (DNN) due to the variety of pedestrian appearance with camera position, the variety of environmental conditions, and the specificity required to recognize one pedestrian from another. DNNs require significant training sets and are not easily adapted for changes in class appearances or changes in the set of classes held in its knowledge domain. Pedestrian redetection requires an algorithm that can actively manage its knowledge domain as individuals move in and out of the scene, as well as learn individual appearances from a few frames of a video. The Omni-Modeler is a dynamically learning few-shot visual recognition algorithm developed for tasks with limited training data availability. The Omni-Modeler adapts the knowledge domain of pre-trained deep neural networks to novel concepts with a calculated localized language encoder. The Omni-Modeler knowledge domain is generated by creating a dynamic dictionary of concept definitions, which are directly updatable as new information becomes available. Query images are identified through nearest neighbor comparison to the learned object definitions. The study presented in this paper evaluates its performance in re-identifying individuals as they move through a scene in both single-camera and multi-camera tracking applications. The results demonstrate that the Omni-Modeler shows potential for across-camera view pedestrian redetection and is highly effective for single-camera redetection with a 93% accuracy across 30 individuals using 64 example images for each individual.

Keywords: dynamic learning, few-shot learning, pedestrian redetection, visual recognition

Procedia PDF Downloads 76

Authors: Aurela Jahja, Katarzyna Wątor, Arjan Beqiraj, Piotr Rusiniak, Nevton Kodhelaj

Abstract:

Albanian geological terrains represent an important node of the Alpine – Mediterranean mountain belt and are divided into several predominantly NNW - SSE striking geotectonic units, which, based on the presence or lack of Cretaceous transgression and magmatic rocks, belong to Internal or External Albanides. The internal (Korabi, Mirdita and Gashi) units are characterized by the Lower Cretaceous discordance and the presence of abundant magmatic rocks whereas in the external (Alps, Krasta-Cukali, Kruja, Ionian, Sazani and Peri Adriatic Depression) units an almost continuous sedimentation from Triassic to Paleogene is evidenced. The internal and external units show relevant differences in both geothermal and heat flow density values. The gradient values vary from 15-21.3 to 36 mK/m, while the heat flow density ranges from 42 to 60 mW/m2, in the external (Preadriatic Depression) and internal (ophiolitic belt) units, respectively. The geothermal fluids, which are found in natural springs and deep oil wells of Albania, are located in four thermo-mineral provinces: a) Peshkopi (Korabi) province; b) Kruja province; c) Preadriatic basin province, and d) South Ionian province. Thirteen geothermal waters were sampled from 11 natural springs and 2 deep wells, of which 6 springs and 2 wells from Kruja, 1 spring from Peshkopia, 2 springs from Preadriatic basin and 2 springs South Ionian province. Temperature, pH and Electrical Conductivity were measured in situ, while in laboratory were analyzed by ICP method major anions and cations and several trace elements (B, Li, Sr, Rb, I, Br, etc.). The measured values of temperature, pH and electrical conductivity range within 17-63°C, 6.26-7.92 and 724- 26856µS/cm intervals, respectively. The chemical type of the Albania thermal waters is variable. In the Kruja province prevail the Cl-SO4-NaCa and Cl-Na-Ca water types; while SO4-Ca, HCO3-Ca and Cl-HCO3-Na-Ca, and Cl-Na are found in the provinces of Peshkopi, Ionian and Preadriatic basin, respectively. In the Cl-SO4-HCO3 triangular diagram most of the geothermal waters are close to the chloride corner that belong to “mature waters”, typical of geothermal deep and hot fluids. Only samples from the Ionian province are located within the region of high bicarbonate concentration and they can be classified as peripheral waters that may have mixed with cold groundwater. In the Na-Ca-Mg and Na-K-Mg triangular diagram the majority of waters fall in the corner of sodium, suggesting that their cation ratios are controlled by mineral-solution equilibrium. There is a linear relationship between Cl and B which indicates the mixing of geothermal water with cold water, where the low-chlorine thermal waters from Ionian basin and Preadriatic depression provinces are distinguished by high-chlorine thermal waters from Kruja province. The Cl/Br molar ration of the thermal waters from Kruja province ranges from 1000 to 2660 and separates them from the thermal waters of Ionian basin and Preadriatic depression provinces having Cl/Br molar ratio lower than 650. The apparent increase of Cl/Br molar ratio that correlates with the increasing of the chloride, is probably related with dissolution of the Halite.

Keywords: geothermal fluids, geotectonic units, natural springs, deep wells, mature waters, peripheral waters

Procedia PDF Downloads 217