SVM Prediction Model Interface for Plant Contaminates

In today's time, our nature is fighting against many life-threatening problems which can even threaten the existence of life on the Earth. Pollution is one of the deadliest problems among them. It is caused primarily by means of air, water and land but air pollution is the most severe and dreadful among them. It is caused by introduction of toxic substances like oxides of Sulphur, nitrogen and carbon into the atmosphere making it unfit for living beings. Along with humans, plants have also become a victim to it, and this fact is mostly ignored. A model has been designed to predict the effect of pollution on plants. Image samples of 5 Indian oxygen rich plants namely Ocimum Tenuiflorum, Sansevieria Trifasciata, Chlorophytum Comosum, and Azadirachta Indica have been taken for analysis and various properties like shape, color, corners and texture of the plants were considered from these input RGB images. As a consequence of these properties and the pollution index value, certain calculations have been performed and the results are compared with the threshold values. Based on the range in which the calculated results lie, the plants will be categorized into a category which depicts the severity level of pollution in the environment. After applying the model on the images, a dataset was prepared and SVM classification model has been trained on it which predict with an accuracy of 85%. It has been presented in the form of an interactive user interface to predict the effect of pollution on plants. Plants are an integral part of nature and should not be ignored.

Download Full-text

Development of a bio-monitoring system for toxicants in water with fish

Water Science & Technology Water Supply ◽

10.2166/ws.2001.0016 ◽

2001 ◽

Vol 1 (2) ◽

pp. 9-17

Author(s):

Y.-H. Lee ◽

H.-K. Lee ◽

C.-H. Chang ◽

W.-H. Kim

Keyword(s):

Monitoring System ◽

Treatment Plant ◽

Ccd Camera ◽

Water Treatment Plant ◽

Abnormal Behavior ◽

Time Interval ◽

Toxic Substances ◽

Bio Monitoring ◽

Index Value ◽

A Charge

A bio-monitoring system for toxicants in water has been developed and verified for actual applications. This system is based on the motionality of five Acheilognathus lanceolata, a fish known to be very sensitive to toxic substances, moving around in an aquarium. Their movements are continuously monitored with a charge coupled device (CCD) camera and analyzed to find and quantify any abnormal behavior in their motional characteristics in comparison with the pre-acquired data. That is, the images of fish captured by a CCD camera are digitalized to identify the location of fish in a constant time interval and the locations of each fish were then analyzed mathematically with a personal computer using the equations proposed to determine the motional characteristics such as floatness, fledness and mobility(agility). These data are then converted by means of fuzzy estimation to an index value, defined as the contamination index (CI), by which the system provides the information about the overall toxic strength of the toxicant in the water flowing into the aquarium. If the fish are exposed to toxicant(s), the CI value will be proportional to the strength of its toxicity. The pilot test was performed in a water treatment plant for six months in order to verify the reproducibility of the system over the unstable conditions such as highly turbid water after rainfall as well as in normal conditions. The test results revealed that this monitoring system has good reproducibility and sensitivity, proving our approach, described in this paper, is reliable. As a result, this approach seems to enable us to make a quick and easy detection of toxic substances contained in water, therefore, this system can be applied to a source of water supply as a toxicant watching system.

Download Full-text

KUALITAS AIR SUNGAI DI KAWASAN WISATA PANTAI PETITENGET, KEROBOKAN KABUPATEN BADUNG BALI

ECOTROPHIC Jurnal Ilmu Lingkungan (Journal of Environmental Science) ◽

10.24843/ejes.2018.v12.i02.p11 ◽

2018 ◽

Vol 12 (2) ◽

pp. 226

Author(s):

Wayan Budiarsa Suyasa ◽

Sri Kunti Pancadewi G. A ◽

Iryanti E. Suprihatin ◽

Dwi Adi Suastuti G. A.

Keyword(s):

Water Quality ◽

Structural Changes ◽

Pollution Index ◽

Basic Structure ◽

Physical Damage ◽

E Coli ◽

Pollutant Source ◽

Quality Category ◽

Index Value ◽

The Impact

In order to maintain the environmental carrying capacity of coastal tourism, this research was conducted to determine the condition of river water environmental pollution in the Petitenget beach area and pollutant source activities. Determination of water quality is carried out by analyzing the water quality taken at several sampling points in the four rivers that lead to the Petitenget beach. Determined the pollution index value (IP) of the physical chemical and biological pollution parameters. The results showed that the four rivers that flow into the Petitenget Beach area had been contaminated with indications of pH, BOD, COD, ammonia, Coliform and E. coli which exceeded water quality category III class quality (PerGub Bali No 16 Year 2016). The four rivers are included in the criteria of severe contamination. The four rivers have experienced physical damage or structural changes that have very high discharge fluctuations both in quantity and quality. Slimy basic structure, smelly and slum aesthetic waters. While the indication of the impact of pollution is waste water which is directly discharged into the river from hotels, restaurants, homestays, commercial centers and settlements.

Download Full-text

An efficient technique for CT scan images classification of COVID-19

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-201985 ◽

2020 ◽

pp. 1-14

Author(s):

Esraa Hassan ◽

Noha A. Hikal ◽

Samir Elmuogy

Keyword(s):

Neural Network ◽

Diagnostic Tool ◽

Deep Neural Network ◽

Data Augmentation ◽

Performance Metrics ◽

Classification Model ◽

Data Set ◽

Training Models ◽

The Earth ◽

Diagnostic Time

Nowadays, Coronavirus (COVID-19) considered one of the most critical pandemics in the earth. This is due its ability to spread rapidly between humans as well as animals. COVID_19 expected to outbreak around the world, around 70 % of the earth population might infected with COVID-19 in the incoming years. Therefore, an accurate and efficient diagnostic tool is highly required, which the main objective of our study. Manual classification was mainly used to detect different diseases, but it took too much time in addition to the probability of human errors. Automatic image classification reduces doctors diagnostic time, which could save human’s life. We propose an automatic classification architecture based on deep neural network called Worried Deep Neural Network (WDNN) model with transfer learning. Comparative analysis reveals that the proposed WDNN model outperforms by using three pre-training models: InceptionV3, ResNet50, and VGG19 in terms of various performance metrics. Due to the shortage of COVID-19 data set, data augmentation was used to increase the number of images in the positive class, then normalization used to make all images have the same size. Experimentation is done on COVID-19 dataset collected from different cases with total 2623 where (1573 training,524 validation,524 test). Our proposed model achieved 99,046, 98,684, 99,119, 98,90 In terms of Accuracy, precision, Recall, F-score, respectively. The results are compared with both the traditional machine learning methods and those using Convolutional Neural Networks (CNNs). The results demonstrate the ability of our classification model to use as an alternative of the current diagnostic tool.

Download Full-text

Clustering of Extremes in Financial Returns: A Study of Developed and Emerging Markets

Journal of Risk and Financial Management ◽

10.3390/jrfm13070141 ◽

2020 ◽

Vol 13 (7) ◽

pp. 141

Author(s):

Sara Ali Alokley ◽

Mansour Saleh Albarrak

Keyword(s):

Emerging Markets ◽

Extremal Index ◽

Threshold Values ◽

Financial Returns ◽

Dependency Structure ◽

Developed Markets ◽

Financial Events ◽

Index Value ◽

Shed Light ◽

Interval Estimator

This paper investigates the clustering or dependency of extremes in financial returns by estimating the extremal index value, in which smaller values of the extremal index correspond to more clustering. We apply the interval estimator method to determine the extremal index for a range of threshold values in the developed and emerging markets from 2007–2017. The indices we used to represent developed markets are from France, Germany, Italy, Japan, USA, UK, Spain, and Sweden. For the emerging markets, we use indices from China, Brazil, India, Malaysia, Russia, Saudi Arabia, and Portugal. The results show that clustering occurs in the emerging and developed markets under several threshold values. This study will shed light on the dependency structure of financial returns data and the proprieties of the extremes returns. Moreover, understanding clustering of extremes in these markets can help investors reduce the exposure to extreme financial events, such as the financial crisis.

Download Full-text

A new re-encoding ECOC using reject option

Applied Intelligence ◽

10.1007/s10489-020-01642-2 ◽

2020 ◽

Vol 50 (10) ◽

pp. 3090-3100 ◽

Cited By ~ 3

Author(s):

Lei Lei ◽

Yafei Song ◽

Xi Luo

Keyword(s):

Loss Function ◽

Operating Characteristic ◽

Classification Model ◽

Threshold Values ◽

Reject Option ◽

Roc Convex Hull ◽

Low Degree ◽

New Variant ◽

Cost Sensitive Classification ◽

The Cost

Abstract When training base classifier by ternary Error Correcting Output Codes (ECOC), it is well know that some classes are ignored. On this account, a non-competent classifier emerges when it classify an instance whose real label does not belong to the meta-subclasses. Meanwhile, the classic ECOC dichotomizers can only produce binary outputs and have no capability of rejection for classification. To overcome the non-competence problem and better model the multi-class problem for reducing the classification cost, we embed reject option to ECOC and present a new variant of ECOC algorithm called as Reject-Option-based Re-encoding ECOC (ROECOC). The cost-sensitive classification model and cost-loss function based on Receiver Operating Characteristic (ROC) curve are built respectively. The optimal reject threshold values are obtained by combing the condition to be met for minimizing the loss function and the ROC convex hull. In so doing, reject option (t1, t2) provides a three-symbol output to make dichotomizers more competent and ROECOC more universal and practical for cost-sensitive classification issue. Experimental results on two kinds of datasets show that our scheme with low-degree freedom of initialized ECOC can effectively enhance accuracy and reduce cost.

Download Full-text

ENHANCED CLASSIFICATION MODEL FOR MULTISPECTRAL OBSERVATIONS FROM THE EARTH

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-iv-4-221-2018 ◽

2018 ◽

Vol IV-4 ◽

pp. 221-226

Author(s):

I. E. Villalon-Turrubiates ◽

M. J. Llovera-Torres

Keyword(s):

Remote Sensing ◽

Decision Model ◽

Accurate Result ◽

Classification Model ◽

Multispectral Images ◽

Performance Study ◽

Spectral Bands ◽

The Earth ◽

Multispectral Remote Sensing ◽

Decision Making Rule

<p><strong>Abstract.</strong> The image classification procedure to identify remote sensing signatures from a particular geographical region can be performed with an identification model that has the ability to use large datasets to reach an accurate result. This novel methodology is referred to as the Statistical Enhanced Classification algorithm, which has been developed to employ multispectral images based in the statistical supervised learning theory and can be used for applications in environmental monitoring and analysis. This paper presents the performance study of the proposed methodology using both, multispectral synthetic images and multispectral remote sensing images. The obtained results are accurate due to the use of several spectral bands, the use of statistics such as mean and standard deviation for the training classes and for the pixel neighborhood, which provides more robust information, and the decision-making rule that has the ability to decide if the pixel is not belonging to a predefined class, which leads to an accurate decision model.</p>

Download Full-text

Deep-Learning-Based Segmentation of Fresh or Young Concrete Sections from Images of Construction Sites

Materials ◽

10.3390/ma14216311 ◽

2021 ◽

Vol 14 (21) ◽

pp. 6311

Author(s):

Woldeamanuel Minwuye Mesfin ◽

Soojin Cho ◽

Jeongmin Lee ◽

Hyeong-Ki Kim ◽

Taehoon Kim

Keyword(s):

Deep Learning ◽

Training Image ◽

Threshold Values ◽

Construction Sites ◽

Softmax Classifier ◽

Incorrect Prediction ◽

Young Concrete ◽

Rgb Images ◽

The Difference ◽

Segmentation Models

The objective of this study is to evaluate the feasibility of deep-learning-based segmentation of the area covered by fresh and young concrete in the images of construction sites. The RGB images of construction sites under various actual situations were used as an input into several types of convolutional neural network (CNN)–based segmentation models, which were trained using training image sets. Various ranges of threshold values were applied for the classification, and their accuracy and recall capacity were quantified. The trained models could segment the concrete area overall although they were not able to judge the difference between concrete of different ages as professionals can. By increasing the threshold values for the softmax classifier, the cases of incorrect prediction as concrete became almost zero, while some areas of concrete became segmented as not concrete.

Download Full-text

The role of green space in the urbanization of Hanoi city

E3S Web of Conferences ◽

10.1051/e3sconf/20199701013 ◽

2019 ◽

Vol 97 ◽

pp. 01013 ◽

Cited By ~ 5

Author(s):

Minh Tuan Le ◽

Thi Anh Tuyet Cao ◽

Nguyen Anh Quan Tran

Keyword(s):

Green Space ◽

Ground Surface ◽

Heat Island ◽

Cooling Efficiency ◽

Threshold Values ◽

Excess Temperature ◽

Rapid Urbanization ◽

The Earth

Rapid urbanization causes significant changes on the earth surface directly and internal itself temperature. The transformation of land use purposes crucially affects the surface temperature and exacerbates the effect of the negative heat island. It is necessary to develope a long-term strategy optimize urban cooling. In this study, the determinated object is Hanoi - city - a widen urbanized city in Vietnam. The authors proposed, defined and calculated the concept of cooling efficiency and threshold values. The results show that the surface heat capacity increases in proportion to the reduction of green space. Plots with excess temperature difference of the ground surface of 4.34 ℃ with reduced green space.

Download Full-text

Identification of unknown compound extracted from the hair of exhumed human remains using mass spectrometric and gas chromatographic data

Аналитика и контроль ◽

10.15826/analitika.2020.25.1.002 ◽

2021 ◽

Vol 25 (1) ◽

pp. 34-42

Author(s):

Sergei A. Savchuk ◽

◽

Igor G. Zenkevich ◽

Keyword(s):

Stationary Phases ◽

Toxic Substances ◽

Polydimethyl Siloxane ◽

Unknown Compound ◽

Original Algorithm ◽

Pharmaceutical Application ◽

Tautomeric Forms ◽

Structural Analogues ◽

Molecular Masses ◽

Index Value

The real example of GC-MS identification of unknown constituent of human hair extract belonging to the exhumed remains is considered. The identification of this constituent (molecular weight 238 Da) was unsuccessful using both its standard mass spectrum (electron ionization) in combination with library search, and its GC retention index value (~1540 on semi-standard non-polar polydimethyl siloxane stationary phases with 5% phenyl groups). However, its identification appeared to be possible using the original algorithm of data processing. This approach implies revealing the structural analogues of unknown analytes, primarily their homologues which differ by molecular masses on ± 14 Da and by composition on CH2 homologous difference. This approach allowed revealing such analogues of unknown analyte as Flavesone (2,2,4,4-tetramethyl-2-isobutyrylcyclohexa-1,3,5-trione), Leptospermone (2,2,4,4-tetramethyl-2-isopentanoylcyclohexa-1,3,5-trione), and some others. All these compounds belong to a rather “exotic” class of natural compounds knows as cyclic b-triketones. Based on the obtained data, the possible structure of the constituent under the consideration was proposed as 2,2,4,4-tetramethyl-2-propionylcyclohexa-1,3,5-trione. The principal feature of cyclic b-triketones is their existence in a few tautomeric forms. Another tautomer of triketone under discussion is 5-hydroxy-2,2,6,6-tetramethyl-4-propionyl-4-en-1,3-dione (CAS № 87552-01-0). This compound is found to be the constituent of Leptospermum scoparium essential oil and some other plants, and it belongs to the group of structural analogues of Flavesone. The most known pharmaceutical application of essential oils containing these compounds are the components of conditioners for hair and skin. The results confirm this formerly unknown component does not belong to the group of toxic substances. This excludes the criminal origin of the remains.

Download Full-text

Pengaruh Keberadaan Bandar Udara Kelas III Seko Luwu Utara Terhadap Index Pencemaran Air

Jurnal Teknik ◽

10.37031/jt.v18i1.58 ◽

2020 ◽

Vol 18 (1) ◽

pp. 1-6

Author(s):

M.Ichsan Ali ◽

Muh. Rais Abidin

Keyword(s):

Population Growth ◽

Local Community ◽

Pollution Index ◽

Transportation Systems ◽

Illegal Logging ◽

Chemical Parameters ◽

Rapid Population Growth ◽

Index Method ◽

Index Value ◽

Physical And Chemical

The airport is one of the best transportation systems capable of moving people quickly as fast economic growth is followed by rapid population growth. Also, rapid population growth leads to massive exploitation of natural resources which causes environmental degradation such as illegal logging. Seko Airport, located in North Luwu is indicated to have caused environmental pollution, especially in watersheds. Therefore, this study aims to identify water pollution through physical and chemical parameters. Data were analyzed using the pollution index method to find the index value. The results showed that the waters around Seko Airport had an index value of 0.78 which was categorized as not polluted. This happens because the airport has a good water treatment system. Besides, there are strict regulations and guidance for all visitors and the local community to not throw rubbish into water bodies.

Download Full-text