Search results for: plant disease classification

Authors: Abebe Mulugojam Negash, Yongbin Yu, Ekong Favour, Bekalu Nigus Dawit, Molla Woretaw Teshome, Aynalem Birtukan Yirga

Abstract:

Breast cancer remains a significant health concern, necessitating advancements in diagnostic methodologies. Addressing this, our paper confronts the notable challenges in breast cancer classification, particularly the imbalance in datasets and the constraints in the accuracy and interpretability of prevailing deep learning approaches. We proposed an attention-based residual neural network (ResNet), which effectively combines the robust features of ResNet with an advanced attention mechanism. Enhanced through strategic data augmentation and positive weight adjustments, this approach specifically targets the issue of data imbalance. The proposed model is tested on the BreakHis dataset and achieved accuracies of 99.00%, 99.04%, 98.67%, and 98.08% in different magnifications (40X, 100X, 200X, and 400X), respectively. We evaluated the performance by using different evaluation metrics such as precision, recall, and F1-Score and made comparisons with other state-of-the-art methods. Our experiments demonstrate that the proposed model outperforms existing approaches, achieving higher accuracy in breast cancer classification.

Keywords: residual neural network, attention mechanism, positive weight, data augmentation

Procedia PDF Downloads 90

Authors: Oluyemi O. Awolusi, Abimbola M. Enitan, Sheena Kumari, Faizal Bux

Abstract:

Nitrification is essential to biological processes designed to remove ammonia and/or total nitrogen. It removes the excess nitrogenous compound in wastewater which could be very toxic to the aquatic fauna or cause a serious imbalance of such aquatic ecosystem. Efficient nitrification is linked to an in-depth knowledge of the structure and dynamics of the nitrifying community structure within the wastewater treatment systems. In this study, molecular technique was employed for characterizing the microbial structure of activated sludge [ammonia oxidizing bacteria (AOB) and nitrite oxidizing bacteria (NOB)] in a municipal wastewater treatment with intention of linking it to the plant efficiency. PCR-based phylogenetic analysis was also carried out for. The average operating and environmental parameters, as well as specific nitrification rate of a plant, was investigated during the study. During the investigation, the average temperature was 23±1.5oC. Other operational parameters such as mixed liquor suspended solids and chemical oxygen demand inversely correlated with ammonia removal. The dissolved oxygen level in the plant was constantly lower than the optimum (between 0.24 and 1.267 mg/l) during this study. The plant was treating wastewater with the influent ammonia concentration of 31.69 and 24.47 mg/l. The influent flow rates (ML/day) was 96.81 during the period. The dominant nitrifiers include: Nitrosomonas spp. Nitrobacter spp. and Nitrospira spp. The AOB had a correlation with nitrification efficiency and temperature. This study shows that the specific ammonia oxidizing rate and the specific nitrate formation rates can serve as a good indicator of the plant overall nitrification performance.

Keywords: Ammonia monooxygenase α-subunit gene, amoA, ammonia-oxidizing bacteria, AOB, nitrite-oxidizing bacteria, NOB, specific nitrification rate

Procedia PDF Downloads 456

Authors: Bliss Singhal

Abstract:

Machine learning (ML) is a branch of Artificial Intelligence (AI) where computers analyze data and find patterns in the data. The study focuses on the detection of metastatic cancer using ML. Metastatic cancer is the stage where cancer has spread to other parts of the body and is the cause of approximately 90% of cancer-related deaths. Normally, pathologists spend hours each day to manually classifying whether tumors are benign or malignant. This tedious task contributes to mislabeling metastasis being over 60% of the time and emphasizes the importance of being aware of human error and other inefficiencies. ML is a good candidate to improve the correct identification of metastatic cancer, saving thousands of lives and can also improve the speed and efficiency of the process, thereby taking fewer resources and time. So far, the deep learning methodology of AI has been used in research to detect cancer. This study is a novel approach to determining the potential of using preprocessing algorithms combined with classification algorithms in detecting metastatic cancer. The study used two preprocessing algorithms: principal component analysis (PCA) and the genetic algorithm, to reduce the dimensionality of the dataset and then used three classification algorithms: logistic regression, decision tree classifier, and k-nearest neighbors to detect metastatic cancer in the pathology scans. The highest accuracy of 71.14% was produced by the ML pipeline comprising of PCA, the genetic algorithm, and the k-nearest neighbor algorithm, suggesting that preprocessing and classification algorithms have great potential for detecting metastatic cancer.

Keywords: breast cancer, principal component analysis, genetic algorithm, k-nearest neighbors, decision tree classifier, logistic regression

Procedia PDF Downloads 78

Authors: Ayşe Defne Öz, Özlem Bozkurt

Abstract:

Alzheimer's Disease (AD) is counted as one of the most important global health problems and the main cause of dementia. The term dementia refers to a wide spectrum of disorders characterized by global, chronic, and generally irreversible cognitive deterioration. It is estimated that %60 % to 80 of the cases of dementia are because of AD. Alzheimer's is a slowly progressive brain disease. The reason for AD is unknown to the author's best knowledge, yet it is one of the topics that is most researched. AD shows the histopathologically abnormal accumulation of the protein beta-amyloid (plague) outside neurons and twisted strands of the protein tau (tangles) inside neurons in the brain. These changes are accompanied by damage to the brain tissue and the death of neurons. AD causes people to have difficulty remembering names or conversations. Some of the later symptoms are difficulty in talking and walking. Alzheimer's Disease is elevated by the illness and mortality of COVID-19. COVID-19 has affected many lives globally and had profound effects on human lives. COVID-19 is caused by SARS-CoV-2, which is a virus that attacks the respiratory and central nervous system and has neuroinvasive potential. More than %80 of COVID-19 patients have ageusia or anosmia, representing the pathognomic features of the disease. Patients with dementia are frail, and with the COVID-19 pandemic, including isolation, cognitive decline may exacerbate. Furthermore, patients with AD can be unable to follow the directions, such as covering their mouth and nose while coughing and can live in nursing homes which makes them more open to being infected. As COVID-19 is highly infectious and its management requires isolation and quarantine, the need for caregivers for AD management conflicts with that of COVID-19 and adds an extra burden on AD patients, caregivers, families, society, and the economy. Due to the entry of SARS-CoV-2 into the central nervous system, inflammation caused by COVID-19, prolonged hospitalization, and delirium, it has been reported that COVID-19 causes many neurological disorders and predisposition to AD.

Keywords: Alzheimer's disease, COVID-19, dementia, SARS-CoV-2

Procedia PDF Downloads 73

Authors: S. Mokhtar, R. Ibrahim, K. Abdan, A. Rashidi

Abstract:

The population in the world are growing in very fast rate. It is expected that urban growth and development would create serious questions of food production and processing, transport, and consumption. Future smart green city policies are emerging to support new ways of visualizing, organizing and managing the city and its flows towards developing more sustainable cities in ensuring food security while maintaining its biodiversity. This is a survey paper analyzing the feasibility of developing a smart vertical farming system for climbing food plant to meet the need of food consumption in urban cities with an alternative green material. This paper documents our investigation on specific requirement for farming high valued climbing type food plant suitable for vertical farming, development of appropriate biocomposite material composition, and design recommendations for developing a new smart vertical farming system inside urban buildings. Results include determination of suitable specific climbing food plant species and material manufacturing processes for reinforcing natural fiber for biocomposite material. The results are expected to become recommendations for developing alternative structural materials for climbing food plant later on towards the development of the future smart vertical farming system. This paper contributes to supporting urban farming in cities and promotes green materials for preserving the environment. Hence supporting efforts in food security agenda especially for developing nations.

Keywords: biocomposite, natural reinforce fiber, smart farming, vertical farming

Procedia PDF Downloads 162

Authors: Ashit Syngle, Inderjit Verma, Pawan Krishan

Abstract:

Therapeutic approaches used previously relied on disease-modifying antirheumatic drugs (DMARDs) that had only partial clinical benefit and were associated with significant toxicity. Spironolactone, an oral aldosterone antagonist, suppresses inflammatory mediators. Clinical efficacy of spironolactone compared with placebo in patients with active psoriatic arthritis despite treatment with prior traditional DMARDs. In the 24-week, placebo-controlled study patients (n=31) were randomized to placebo and spironolactone (2 m/kg/day). Patients on background concurrent DMARDs continued stable doses (methotrexate, leflunomide, and/or sulfasalazine). Primary outcome measures were the assessment of disease activity measures i.e. 28-joint disease activity score (DAS28) and diseases activity in psoriatic arthritis (DAPSA) at week 24. The key secondary endpoint was change from baseline in Health Assessment Questionnaire–Disability Index (HAQ-DI) at week 24. Additional efficacy outcome measures at week 24 included improvements in the markers of inflammation (ESR and CRP) and pro-inflammatory cytokines TNF-α, IL-6 and IL-1. At week 24, spironolactone significantly reduced disease activity measure DAS-28 (p<0.001) and DAPSA (p=0.001) compared with placebo. Significant improvements in key secondary measures HAQ-DI (disability index) were evident with spironolactone (p=0.02) versus placebo. After week 24, there was significant reduction in pro-inflammatory cytokines level TNF-α, IL-6 (p<0.01) as compared with placebo group. However, there was no significant improvement in IL-1 in both treatment and placebo groups. There were minor side effects which did not mandate stopping of spironolactone. No change in any biochemical profile was noted after spironolactone treatment. Spironolactone was effective in the treatment of PsA, improving disease activity, physical function and suppressing the level of pro-inflammatory cytokines. Spironolactone demonstrated an acceptable safety profile and was well tolerated.

Keywords: spironolactone, inflammation, inflammatory cytokine, psoriatic arthritis

Procedia PDF Downloads 332

Authors: Ghoul Rachid Brahim

Abstract:

Introduction: Back pain is a real public health problem with a significant socio-economic impact. It is the consequence of a degeneration of the lumbar intervertebral disc (IVD). This often asymptomatic pathology is compatible with an active life. As soon as it becomes symptomatic, conservative treatment is recommended in the majority of cases. The physical or functional disability is resistant to well-monitored conservative treatment, which justifies a surgical alternative which imposes a well-studied reflection on the objectives to be achieved. Objective: Evaluate the indication and short and medium term contribution of surgery in the management of painful degenerative lumbar disc disease. To prove the effectiveness of surgical treatment in the management of painful lumbar degenerative disc disease. Materials and methods: This is a prospective descriptive mono-centric study without comparison group, comprising a series of 104 patients suffering from lumbar painful degenerative disc disease treated surgically. Retrospective analysis of data collected prospectively. Comparison between pre and postoperative clinical status, by pain self-assessment scores and on the impact on pre and postoperative quality of life (3, 6 to 12 months). Results: This study showed that patients who received surgical treatment had great improvements in symptoms, function and several health-related quality of life in the first year after surgery. Conclusions: The surgery had a significantly positive impact on patients' pain, disability and quality of life. Overall, 97% of the patients were satisfied.

Keywords: degenerative disc disease, intervertebral disc, several health-related quality, lumbar painful

Procedia PDF Downloads 100

Authors: Mouli Banga, Chaya Ravindra

Abstract:

Wound classification is a crucial step in wound diagnosis. An effective classifier can aid wound specialists in identifying wound types with reduced financial and time investments, facilitating the determination of optimal treatment procedures. This study presents a deep neural network-based classifier that leverages wound images and their corresponding locations to categorize wounds into various classes, such as diabetic, pressure, surgical, and venous ulcers. By incorporating a developed body map, the process of tagging wound locations is significantly enhanced, providing healthcare specialists with a more efficient tool for wound analysis. We conducted a comparative analysis between two prominent convolutional neural network models, ResNet50 and MobileNetV2, utilizing a dataset of 730 images. Our findings reveal that the RestNet50 outperforms MovileNetV2, achieving an accuracy of approximately 90%, compared to MobileNetV2’s 83%. This disparity highlights the superior capability of ResNet50 in the context of this dataset. The results underscore the potential of integrating deep learning with spatial data to improve the precision and efficiency of wound diagnosis, ultimately contributing to better patient outcomes and reducing healthcare costs.

Keywords: wound classification, MobileNetV2, ResNet50, multimodel

Procedia PDF Downloads 24

Authors: Ali Kassem, Yaser Kamal, Mohamed Abdel Wahab, Mohamed Hussen

Abstract:

Introduction: Atherosclerosis is one of the leading causes of death all over the world. Recently, there is an increasing interest in Carotid Intima-Medial Thickness (CIMT) and Ankle Brachial Index (ABI) as non-invasive tools for identifying subclinical atherosclerosis. We aim to examine the role of CIMT and ABI as predictors of the severity of angiographically documented coronary artery disease (CAD). Methods: A cross-sectional study conducted on 60 patients who were investigated by coronary angiography at Sohag University Hospital, Egypt. CIMT: After the carotid arteries were located by transverse scans, the probe was rotated 90 ° to obtain and record longitudinal images of bilateral carotid arteries ABI: Each patient was evaluated in the supine position after resting for 5 min. ABI was measured in each leg using a Doppler Ultrasound while the patient remained in the same position. The lowest ABI obtained for either leg was taken as the ABI measurement for the patient. Results: Patients with carotid mean IMT ≥ 0.9 mm had significantly more severe coronary artery disease than patients without thickening (mean IMT > 0.9 mm). Similarly, patients with low ABI (< 0.9) had significantly more severe coronary artery disease than patients with ABI ≥ 0.9. When the patients were divided into 4 groups (group A, n = 15, mean IMT < 0.9 mm, ABI ≥ 0.9; group B, n = 25, mean IMT < 0.9 mm, low ABI; group C, n = 5, mean IMT ≥ 0.9 mm, ABI ≥ 0.9; group D, n = 19, mean IMT ≤ 0.9 mm, low ABI), the presence of significant coronary stenosis (> 50%) of the groups were significantly different (group A, n = 5: (33.3%); group B, n = 11: (52.4%); group C, n = 4: (60%); group D, n=15, (78.9%), P = 0.001). Conclusion: CIMT and ABI provide useful information on the severity of CAD. Early and aggressive intervention should be considered in patients with CAD and abnormalities in one or both of these non-invasive modalities.

Keywords: ankle brachial index, carotid intima media thickness, coronary artery disease, predictors of severity

Procedia PDF Downloads 228

Authors: Rajrupa Ghosh, Abhijit Mitra

Abstract:

Future use of animal protein sources in prawn feeds is expected to be considerably reduced as a consequence of increasing economical, environmental and safety issues. Of main concern has been the use of expensive marine protein sources, such as fish meal which often results in fouling of water quality and disease outbreak in cultured species. To determine prawn capacity to use practical feeds with plant proteins as replacement ingredients to animal protein sources, 8-months growth trial was conducted in two sets of ponds using juvenile (0.02 gm) Macrobrachium rosenbergii. Among the two sets, one set (comprising of three ponds) is experimental pond included formulated feed prepared with 30% Porteresia coarctata dust along with other general ingredients and another set (comprising of another three ponds) is control pond with commercial feed. Mean final weight, percent weight gain, final net yield, feed conversion ratio and survival were evaluated. Higher condition index values, survival rate and gain in prawn weight were observed in experimental pond compared to control pond. Low FCR values were observed in the experimental pond than the control pond. Evaluation of production parameters at the end of the study demonstrated significant differences (P ≥ 0.05) among two ponds. The variation may be attributed to specially formulated plant based feed that not only boosted up the growth of prawns, but also upgraded the ambient aquatic health. These results indicate that fish meal can be replaced with algal protein sources in diets without affecting prawn growth and production.

Keywords: macrobrachium rosenbergii, porteresia coarctata, Indian sundarbans, feed

Procedia PDF Downloads 349

Authors: Kim Kennedy, Daren Gibson, Stephanie Flukes, Chandra Diwakarla, Lisa Spalding, Leanne Pilkington, Andrew Redfern

Abstract:

Introduction: The mortality gap in Aboriginal Head and Neck Cancer is well known, but the reasons for poorer survival are not well established. Aim: We aimed to evaluate the locoregional and metastatic involvement, and stage at diagnosis, in Aboriginal compared with non-Aboriginal patients. Methods: We performed a retrospective cohort analysis of 320 HNC patients from a single centre in Western Australia, identifying 80 Aboriginal patients and 240 non-Aboriginal patients matched on a 1:3 ratio by sites, histology, rurality, and age. We collected data on the patient characteristics, tumour features, regions involved, stage at diagnosis, treatment history, and survival and relapse patterns, including sites of metastatic and locoregional involvement. Results: Aboriginal patients had a significantly higher incidence of lung metastases (26.3% versus 13.7%, p=0.009). Aboriginal patients also had a numerically but non-statistically significant higher incidence of thoracic nodal involvement (10% vs 5.8%) and malignant pleural effusions (3.8% vs 2.5%). Aboriginal patients also had a numerically but not statistically significantly higher incidence of adrenal and bony involvement. Interestingly, non-Aboriginal patients had an increased rate of cutaneous (2.1% vs 0%) and liver metastases (4.6% vs 2.5%) compared with Aboriginal patients. In terms of locoregional involvement, Aboriginal patients were more than twice as likely to have contralateral neck involvement (58.8% vs 24.2%, p<0.00001), and 30% more likely to have ipsilateral neck lymph node involvement (78.8% vs 60%, p=0.002) than non-Aboriginal patients. Aboriginal patients had significantly more advanced disease at diagnosis (p=0.008). Aboriginal compared with non-Aboriginal patients were less likely to present with stage I (7.5% vs 22.5%), stage II (11.3% vs 13.8%), or stage III disease (13.8% vs 17.1%), and more likely to present with more advanced stage IVA (42.5% vs 34.6%), stage IVB (15% vs 7.1%), or stage IVC (10% vs 5%) disease (p=0.008). Number of regions of disease involvement was higher in Aboriginal patients (median 3, mean 3.64, range 1-10) compared with non-Aboriginal patients (median 2, mean 2.80, range 1-12). Conclusion: Aboriginal patients had a significantly higher incidence of lung metastases, and significantly more frequent involvement of ipsilateral and contralateral neck lymph nodes. Aboriginal patients also had significantly more advanced disease at presentation with a higher stage at diagnosis. We are performing further analyses to investigate explanations for these findings.

Keywords: head and neck cancer, Aboriginal, metastases, locoregional, pattern of relapse, sites of disease

Procedia PDF Downloads 66

Authors: Valerija Dunkić, Nada Bezić

Abstract:

Salvia is a genus of the well-known medicinal plant of Lamiaceae family and growing wild throughout the world. This abstract reports the comparation of the essential oils from leaves and flowers composition of Salvia pratensis L. from mountain Velebit, Croatia. Water distilled essential oils from aerial parts of investigation plant have been analysed by GC and GC/MS using VF-5ms capillary column. Fifty-three constituents, representing 99.4% of the leaf oil composition; 51 constituents, representing 86.8% of the flower oil composition. Essential oil yield varied from 0.9% to 1.3% in the leaf and flower parts of the plant. The flower essential oil was characterized by a high concentration of E-caryophyllene (21.9%) and germacrene D (10.2%). Major constituents of the leaf oil were linalool (17.7%), linalool acetate (15.3%) and limonene (9.8%). The comparative results clearly indicated that the leaf and flower oil compositions of S. pratensis were quite different in terms of major components content. The present study gives additional knowledge about secondary metabolites contents on the genus Salvia.

Keywords: essential oil, leaf, flower, Salvia pratensis L.

Procedia PDF Downloads 299

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

The widespread use of machine learning applications in production is significantly accelerated by improved computing power and increasing data availability. Predictive quality enables the assurance of product quality by using machine learning models as a basis for decisions on test results. The use of real Bosch production data based on geometric gauge blocks from machining, mating data from assembly and hydraulic measurement data from final testing of directional valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: machine learning, classification, predictive quality, hydraulics, supervised learning

Procedia PDF Downloads 205

Authors: Yuntao Liu, Lei Wang, Haoran Xia

Abstract:

Machine learning has shown extensive applications in the development of classification models for autism spectrum disorder (ASD) using neural image data. This paper proposes a fusion multi-modal classification network based on a graph neural network. First, the brain is segmented into 116 regions of interest using a medical segmentation template (AAL, Anatomical Automatic Labeling). The image features of sMRI and the signal features of fMRI are extracted, which build the node and edge embedding representations of the brain map. Then, we construct a dynamically updated brain map neural network and propose a method based on a dynamic brain map adjacency matrix update mechanism and learnable graph to further improve the accuracy of autism diagnosis and recognition results. Based on the Autism Brain Imaging Data Exchange I dataset(ABIDE I), we reached a prediction accuracy of 74% between ASD and TD subjects. Besides, to study the biomarkers that can help doctors analyze diseases and interpretability, we used the features by extracting the top five maximum and minimum ROI weights. This work provides a meaningful way for brain disorder identification.

Keywords: autism spectrum disorder, brain map, supervised machine learning, graph network, multimodal data, model interpretability

Procedia PDF Downloads 59

Authors: Weiwei Cui, Dejian Lin, Leigang Zhang, Yao Wang, Zheng Sun, Lianfeng Li

Abstract:

Built-in test (BIT) is an important technology in testability field, and it is widely used in state monitoring and fault diagnosis. With the improvement of modern equipment performance and complexity, the scope of BIT becomes larger, and it leads to the emergence of false alarm problem. The false alarm makes the health assessment unstable, and it reduces the effectiveness of BIT. The conventional false alarm suppression methods such as repeated test and majority voting cannot meet the requirement for a complicated system, and the intelligence algorithms such as artificial neural networks (ANN) are widely studied and used. However, false alarm has a very low frequency and small sample, yet a method based on ANN requires a large size of training sample. To recognize the false alarm, we propose a method based on multi-classification support vector machine (SVM) in this paper. Firstly, we divide the state of a system into three states: healthy, false-alarm, and faulty. Then we use multi-classification with '1 vs 1' policy to train and recognize the state of a system. Finally, an example of fault injection system is taken to verify the effectiveness of the proposed method by comparing ANN. The result shows that the method is reasonable and effective.

Keywords: false alarm, fault diagnosis, SVM, k-means, BIT

Procedia PDF Downloads 153

Authors: Komal Rathore, Aydin Sunol, Gita Iranipour, Luke Mulford

Abstract:

Advanced wastewater treatment plants have complex biological kinetics, time variant influent flow rates and long processing times. Due to these factors, the modeling and operational control of advanced wastewater treatment plants become complicated. However, development of a robust model for advanced wastewater treatment plants has become necessary in order to increase the efficiency of the plants, reduce energy costs and meet the discharge limits set by the government. A dynamic model was designed using the Envirosim (Canada) platform software called BioWin for several wastewater treatment plants in Hillsborough County, Florida. Proper control strategies for various parameters such as mixed liquor suspended solids, recycle activated sludge and waste activated sludge were developed for models to match the plant performance. The models were tuned using both the influent and effluent data from the plant and their laboratories. The plant SCADA was used to predict the influent wastewater rates and concentration profiles as a function of time. The kinetic parameters were tuned based on sensitivity analysis and trial and error methods. The dynamic models were validated by using experimental data for influent and effluent parameters. The dissolved oxygen measurements were taken to validate the model by coupling them with Computational Fluid Dynamics (CFD) models. The Biowin models were able to exactly mimic the plant performance and predict effluent behavior for extended periods. The models are useful for plant engineers and operators as they can take decisions beforehand by predicting the plant performance with the use of BioWin models. One of the important findings from the model was the effects of recycle and wastage ratios on the mixed liquor suspended solids. The model was also useful in determining the significant kinetic parameters for biological wastewater treatment systems.

Keywords: BioWin, kinetic modeling, flowsheet simulation, dynamic modeling

Procedia PDF Downloads 149

Authors: Khalid Al Mutairi, Mashhor Mansor, Magdy El-Bana, Saud L. Al-Rowaily, Asyraf Mansor

Abstract:

The present study was carried out in 20 islands of Farasan Archipelago in Saudi Arabia to describe the biogeography patterns of plants. A total of 191 species belonging to 129 genera and 53 families were identified. Following island biogeography theory, total plant species richness and their ecological groups were positively influenced by island size, number of habitats,elevation and were not affected by isolation. The high level of nestedness, the strong effect of area on total plant species richness and ecological groups, and the similarity of vegetation composition on the islands has several implications for conservation. In conclusion the large and richest islands in Farasan Archipelago such as Farasan Alkbir would conserve higher diversity than several smaller islands. This island also includes rare habitats like coral rocks and rare species. The invasion of the unique habitats such as wadi channels and water catchments in this island by the exotic tree Prosopis juliflora should be managed to conserve the native biodiversity. The protection of such critical habitats is very important on the other large island (e.g. Zufaf), due to their limited distribution in the country.

Keywords: island biogeography, conservation, farasan archipelago, saudi arabia, plant diversity

Procedia PDF Downloads 343

Authors: Soumaya Mrabet, Taieb Ach, Imen Akkari, Amira Atig, Neirouz Ghannouchi, Koussay Ach, Elhem Ben Jazia

Abstract:

Introduction: Celiac disease (CD) is an immune-mediated small intestinal disorder that occurs in genetically susceptible people. It is significantly associated with other autoimmune disorders represented mainly by type 1 diabetes and autoimmune dysthyroidism. The aim of our study is to determine the prevalence and the type of the various autoimmune diseases associated with CD in adult patients. Material and methods: This is a retrospective study including patients diagnosed with CD, explored in Internal Medicine, Gastroenterology and Endocrinology and Diabetology Departments of the Farhat Hached University Hospital, between January 2005 and January 2016. The diagnosis of CD was confirmed by serological tests and duodenal biopsy. The screening of autoimmune diseases was based on physical examination, biological and serological tests. Results: Sixty five patients with a female predominance were included, 48women (73.8%) and 17 men (26.2%). The mean age was 31.8 years (17-75). A family history of CD or other autoimmune diseases was present in 5 and 10 patients respectively. Clinical presentation of CD was made by recurrent abdominal pain in 49 cases, diarrhea in 29 cases, bloating in 17 cases, constipation in 25 cases and vomiting in 8 cases. Autoimmune diseases associated with CD were found in 30 cases (46.1%): type 1 diabetes in 15 patients attested by the positivity of anti-GAD antibodies in 11 cases and anti-IA2 in 4 cases, Hashimoto thyroiditis in 8 cases confirmed by the positivity of anti-TPO antibodies, Addison's disease in 2 patients, Anemia of Biermer in 2 patients, autoimmune hepatitis, Systemic erythematosus lupus, Gougerot Sjögren syndrome, rheumatoid arthritis, Vitiligo and antiphospholipid syndrome in one patient each. CD was associated with more than one autoimmune disease defining multiple autoimmune syndrome in 2 female patients. The first patient had Basedow disease, Addison disease and type 1 diabetes. The second patient had systemic erythematosus lupus and Gougerot Sjögren syndrome. Conclusion: In our study autoimmune diseases were associated with CD in 46.1% of cases and were dominated by diabetes and dysthroidism. After establishing the diagnosis of CD the search of associated autoimmune diseases is necessary in order to avoid any therapeutic delay which can alter the prognosis of the patient.

Keywords: association, autoimmune thyroiditis, celiac disease, diabetes

Procedia PDF Downloads 276

Authors: Zdenek Silar, Martin Dobrovolny

Abstract:

This article deals with the obstacle detection on a railway crossing (clearance detection). Detection is based on the optical flow estimation and classification of the flow vectors by K-means clustering algorithm. For classification of passing vehicles is used optical flow direction determination. The optical flow estimation is based on a modified Lucas-Kanade method.

Keywords: background estimation, direction of optical flow, K-means clustering, objects detection, railway crossing monitoring, velocity vectors

Procedia PDF Downloads 514

Authors: A. K. Faizah, G. Vadamalai, S. K. Balasundram, W. L. Lim

Abstract:

Pineapple (Ananas comosus) is a common crop in tropical and subtropical areas of the world. Malaysia once ranked as one of the top 3 pineapple producers in the world in the 60's and early 70's, after Hawaii and Brazil. Moreover, government’s recognition of the pineapple crop as one of priority commodities to be developed for the domestics and international markets in the National Agriculture Policy. However, pineapple industry in Malaysia still faces numerous challenges, one of which is the management of disease and pest. Red tip disease on pineapple was first recognized about 20 years ago in a commercial pineapple stand located in Simpang Renggam, Johor, Peninsular Malaysia. Since its discovery, there has been no confirmation on its causal agent of this disease. The epidemiology of red tip disease is still not fully understood. Nevertheless, the disease symptoms and the spread within the field seem to point toward viral infection. Bioassay test on nucleic acid extracted from the red tip-affected pineapple was done on Nicotiana tabacum cv. Coker by rubbing the extracted sap. Localised lesions were observed 3 weeks after inoculation. Negative staining of the fresh inoculated Nicotiana tabacum cv. Coker showed the presence of membrane-bound spherical particles with an average diameter of 94.25nm under transmission electron microscope. The shape and size of the particles were similar to tospovirus. SDS-PAGE analysis of partial purified virions from inoculated N. tabacum produced a strong and a faint protein bands with molecular mass of approximately 29 kDa and 55 kDa. Partial purified virions of symptomatic pineapple leaves from field showed bands with molecular mass of approximately 29 kDa, 39 kDa and 55kDa. These bands may indicate the nucleocapsid protein identity of tospovirus. Furthermore, a handheld sensor, Greenseeker, was used to detect red tip symptoms on pineapple non-destructively based on spectral reflectance, measured as Normalized Difference Vegetation Index (NDVI). Red tip severity was estimated and correlated with NDVI. Linear regression models were calibrated and tested developed in order to estimate red tip disease severity based on NDVI. Results showed a strong positive relationship between red tip disease severity and NDVI (r= 0.84).

Keywords: pineapple, diagnosis, virus, NDVI

Procedia PDF Downloads 788

Authors: H. Hotait, X. Chiementin, L. Rasolofondraibe

Abstract:

This paper presents a continuous work to detect the abnormal state in the rolling bearing by studying the vibration signature analysis and calculation of the remaining useful life. To achieve these aims, two methods; the first method is the classification to detect the degradation state by the AOM-OPTICS (Acousto-Optic Modulator) method. The second one is the prediction of the degradation state using least-squares support vector regression and then compared with the linear degradation model. An experimental investigation on ball-bearing was conducted to see the effectiveness of the used method by applying the acquired vibration signals. The proposed model for predicting the state of bearing gives us accurate results with the experimental and numerical data.

Keywords: bearings, automatization, optimization, prognosis, classification, defect detection

Procedia PDF Downloads 115

Authors: David Hasurungan

Abstract:

This paper objective is to assess the power distribution reliability improvement by retrofitting obsolete vacuum contactor. The case study in Badak Liquefied Natural Gas (LNG) plant is presented in this paper. To support plant operational, Badak LNG is equipped with 4.16 kV switchgear for supplying the storage and loading facilities, utilities facilities, and train facilities. However, there is a problem in two switch gears of sixteen switch gears. The problem is the obsolescence issue in its vacuum contactor. Not only that, but the same switchgear also has suffered from electrical fault due to contact fingering misalignment. In order to improve the reliability in switchgear, the vacuum contactor retrofit project is done. The retrofit will introduce new vacuum contactor design. The comparison between existing design and the new design is presented in this paper. Meanwhile, The reliability assessment and calculation are performed using software Reliasoft 7.

Keywords: reliability, obsolescence, retrofit, vacuum contactor

Procedia PDF Downloads 288

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 166

Authors: Mequanent Wale Mekonen, Edoardo Otranto, Angela Alibrandi

Abstract:

Diabetic kidney disease is one of the main microvascular complications caused by diabetes. Several clinical and biochemical variables are reported to be associated with diabetic kidney disease in people with type 2 diabetes. However, their interrelations could distort the effect estimation of these variables for the disease's progression. The objective of the study is to determine how the biochemical and clinical variables in people with type 2 diabetes are interrelated with each other and their effects on kidney disease progression through advanced statistical methods. First, principal component analysis was used to explore how the biochemical and clinical variables intercorrelate with each other, which helped us reduce a set of correlated biochemical variables to a smaller number of uncorrelated variables. Then, ordered logit regression models (cumulative, stage, and adjacent) were employed to assess the effect of biochemical and clinical variables on the order-level response variable (progression of kidney function) by considering the proportionality assumption for more robust effect estimation. This retrospective cross-sectional study retrieved data from a type 2 diabetic cohort in a polyclinic hospital at the University of Messina, Italy. The principal component analysis yielded three uncorrelated components. These are principal component 1, with negative loading of glycosylated haemoglobin, glycemia, and creatinine; principal component 2, with negative loading of total cholesterol and low-density lipoprotein; and principal component 3, with negative loading of high-density lipoprotein and a positive load of triglycerides. The ordered logit models (cumulative, stage, and adjacent) showed that the first component (glycosylated haemoglobin, glycemia, and creatinine) had a significant effect on the progression of kidney disease. For instance, the cumulative odds model indicated that the first principal component (linear combination of glycosylated haemoglobin, glycemia, and creatinine) had a strong and significant effect on the progression of kidney disease, with an effect or odds ratio of 0.423 (P value = 0.000). However, this effect was inconsistent across levels of kidney disease because the first principal component did not meet the proportionality assumption. To address the proportionality problem and provide robust effect estimates, alternative ordered logit models, such as the partial cumulative odds model, the partial adjacent category model, and the partial continuation ratio model, were used. These models suggested that clinical variables such as age, sex, body mass index, medication (metformin), and biochemical variables such as glycosylated haemoglobin, glycemia, and creatinine have a significant effect on the progression of kidney disease.

Keywords: diabetic kidney disease, ordered logit model, principal component analysis, type 2 diabetes

Procedia PDF Downloads 34

Authors: S. Nandagopalan, N. Pradeep

Abstract:

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

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

Procedia PDF Downloads 416

Authors: M. Abdullah, Al-Wadud

Abstract:

Sensor-based activity recognition systems usually accounts which sensors have been activated to perform an activity. The system then combines the conditional probabilities of those sensors to represent different activities and takes the decision based on that. However, the information about the sensors which are not activated may also be of great help in deciding which activity has been performed. This paper proposes an approach where the sensory data related to both usage and non-usage of objects are utilized to make the classification of activities. Experimental results also show the promising performance of the proposed method.

Keywords: Naïve Bayesian, based classification, activity recognition, sensor data, object-usage model

Procedia PDF Downloads 318

Authors: C. G. Sawant, C. S. Patil

Abstract:

The investigation was conducted during January 2016 on Farmer’s field at Nandur Madhyameshwar, Tq. Niphad, Dist. Nashik (Maharashtra: India) on bio-efficacy of newer insecticides against Plutella xylostella L. infesting cabbage. The cabbage crop (var. Saint) was raised according to package of practices except for plant protection measures. Six newer insecticides along with two conventional insecticides and one synthetic pyrethroid were applied twice at 30 and 55 days after transplanting. Insecticidal solutions were diluted in water (375-500 L ha-1) and applied using knapsack sprayer (16L) with hollow cone nozzle. Treatments included indoxacarb @ 40 g a.i.ha-1, spinosad @ 17.5 g a.i.ha-1, flubendiamide @18.24 g a.i. ha-1, diafenthiuron @ 300 g a. i. ha-1, emamectin benzoate @ 10 g a. i. ha-1, chlorantraniliprole @ 10 g a. i. ha-1, quinalphos @ 250 g a. i. ha-1, triazophos @ 500 g a. i. ha-1, bifenthrin @ 50 g a.i. ha-1 and untreated control. The larvae were counted on head and outside the head. Observations were recorded one day before spray (Precount) and 1,3,7,14 days after spray. Results revealed that all the insecticidal treatments were significantly superior over untreated control by recording lower larval count. Among the insecticidal treatments, significantly lowest number of larvae of diamondback moth was recorded in chlorantraniliprole @ 10 g a.i.ha-1 (1.00 larvae plant-1) followed by spinosad @ 17.5 g a.i. ha-1 (1.45 larvae plant-1 and flubendiamide 18.24 g a.i. ha-1(1.53 larvae plant-1). The efficacy of insecticides reflected on yield of marketable cabbage heads by recording 242.27 qt ha-1 (1:33.38) in the treatment of chlorantraniliprole @ 10 g a.i.ha-1. It was followed by spinosad @ 17.5 g a.i. ha-1 with 236.91 qt ha-1 (1:24.92) and flubendiamide 18.24 g a.i. ha-1 with 228.49 qt ha-1 (1:30.43).

Keywords: bio-efficacy, cabbage, chlorantraniliprole, Plutella xylostella L.

Procedia PDF Downloads 142

Authors: Akhad Ibrokhimov

Abstract:

Update of preventive medicine has exacerbated the problem of cause-and-effect relationship between the presence of herpetic stomatitis (HS) and periodontal disease. Comprehensive survey of children with herpetic stomatitis, according to WHO equirements, on the territory of Tashkent years was conducted. Objective: To analyze the prevalence and intensity of periodontal tissue diseases in children with herpetic stomatitis. Materials and methods. Dental disease in Tashkent was studied in 156 children with herpetic stomatitis, as a control, the incidence of dental studied in 153 children of comparable age and sex never without a history of herpetic stomatitis. Results and discussion. The study revealed that 42,86 ± 13,23% of children with Herpetic stomatitis in the age group 6 years, 1 month - 10 years suffered from periodontal disease, the incidence of periodontal disease in the control group was 14,29 ± 9,35% (R≥0 05) corresponding to the frequency of detection of sextants with bleeding and tartar was equal to 35,71 ± 12,80% vs. 7,14 ± 6,88% (R≥0,05) and 14,29 ± 9,35% against 7 14 ± 6,88% (R≥0,05). Status of periodontal tissues was assessed in age groups 6 years, 1 month - 10 years and 10 years, 1 month - 15 years. The intensity of periodontal lesions observed at the level of 1,79 ± 0,06 vs. 0,66 ± 0,03 (P ≤ 0,05) affected sextant, including sextants with bleeding 1,62 ± 0,07 vs. 0.65 ± 0 , 03 (P ≤ 0,05) and sextants tartar - 0,17 ± 0,008 vs. 0,10 ± 0,008 (P ≤ 0,05). At age 10 years, 1 month - 15 years, a higher prevalence of signs of periodontal lesion was identified in patients with table of contents in 80,00 ± 12,65% of cases versus 30,00 ± 14,49% (P ≤ 0,05), and prevailed bleeding gums 70,00 ± 14,49% against 20,00 ± 11,83% (p ≤ 0.05), tartar was diagnosed respectively in 30,00 ± 14,49% against 10,00 ± 9,48% (R≥0,05) surveyed.

Keywords: vestibular surface, abnormal abrasion, composites, prosthesis

Procedia PDF Downloads 340

Authors: S. Athiralakshmi, B.E. Bhojaraja, U. Pruthviraj

Abstract:

In agriculture, remote sensing is applied for monitoring of plant development, evaluating of physiological processes and growth conditions. Especially valuable are the spatio-temporal aspects of the remotely sensed data in detecting crop state differences and stress situations. In this study, hyperion imagery is used for classifying arecanut crops based on their age so that these maps can be used in yield estimation of crops, irrigation purposes, applying fertilizers etc. Traditional hard classifiers assigns the mixed pixels to the dominant classes. The proposed method uses a sub pixel level classifier called linear spectral unmixing available in ENVI software. It provides the relative abundance of surface materials and the context within a pixel that may be a potential solution to effectively identifying the land-cover distribution. Validation is done referring to field spectra collected using spectroradiometer and the ground control points obtained from GPS.

Keywords: FLAASH, Hyperspectral remote sensing, Linear Spectral Unmixing, Spectral Angle Mapper Classifier.

Procedia PDF Downloads 518

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Digitalisation in production technology is a driver for the application of machine learning methods. Through the application of predictive quality, the great potential for saving necessary quality control can be exploited through the data-based prediction of product quality and states. However, the serial use of machine learning applications is often prevented by various problems. Fluctuations occur in real production data sets, which are reflected in trends and systematic shifts over time. To counteract these problems, data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets to extract stable features. Successful process control of the target variables aims to centre the measured values around a mean and minimise variance. Competitive leaders claim to have mastered their processes. As a result, much of the real data has a relatively low variance. For the training of prediction models, the highest possible generalisability is required, which is at least made more difficult by this data availability. The implementation of a machine learning application can be interpreted as a production process. The CRoss Industry Standard Process for Data Mining (CRISP-DM) is a process model with six phases that describes the life cycle of data science. As in any process, the costs to eliminate errors increase significantly with each advancing process phase. For the quality prediction of hydraulic test steps of directional control valves, the question arises in the initial phase whether a regression or a classification is more suitable. In the context of this work, the initial phase of the CRISP-DM, the business understanding, is critically compared for the use case at Bosch Rexroth with regard to regression and classification. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. Suitable methods for leakage volume flow regression and classification for inspection decision are applied. Impressively, classification is clearly superior to regression and achieves promising accuracies.

Keywords: classification, CRISP-DM, machine learning, predictive quality, regression

Procedia PDF Downloads 140