Search results for: classification of soils

Authors: V. Ibujes, A. Guevara, P. Barreto

Abstract:

Concentration of arsenic represents a serious threat to human health. It is a bioaccumulable toxic element and is transferred through the food chain. In Ecuador, values of 0.0423 mg/kg As are registered in potatoes of the skirts of the Tungurahua volcano. The increase of arsenic contamination in Ecuador is mainly due to mining activity, since the process of gold extraction generates toxic tailings with mercury. In the Province of Azuay, due to the mining activity, the soil reaches concentrations of 2,500 to 6,420 mg/kg As whereas in the province of Tungurahua it can be found arsenic concentrations of 6.9 to 198.7 mg/kg due to volcanic eruptions. Since the contamination by arsenic, the present investigation is directed to the remediation of the soils in the provinces of Azuay and Tungurahua by phytoremediation technique and the definition of a methodology of extraction by means of analysis of arsenic in the system soil-plant. The methodology consists in selection of two types of plants that have the best arsenic removal capacity in synthetic solutions 60 μM As, a lower percentage of mortality and hydroponics resistance. The arsenic concentrations in each plant were obtained from taking 10 ml aliquots and the subsequent analysis of the ICP-OES (inductively coupled plasma-optical emission spectrometry) equipment. Soils were contaminated with synthetic solutions of arsenic with the capillarity method to achieve arsenic concentration of 13 and 15 mg/kg. Subsequently, two types of plants were evaluated to reduce the concentration of arsenic in soils for 7 weeks. The global variance for soil types was obtained with the InfoStat program. To measure the changes in arsenic concentration in the soil-plant system, the Rhizo and Wenzel arsenic extraction methodology was used and subsequently analyzed with the ICP-OES (optima 8000 Pekin Elmer). As a result, the selected plants were bluegrass and llanten, due to the high percentages of arsenic removal of 55% and 67% and low mortality rates of 9% and 8% respectively. In conclusion, Azuay soil with an initial concentration of 13 mg/kg As reached the concentrations of 11.49 and 11.04 mg/kg As for bluegrass and llanten respectively, and for the initial concentration of 15 mg/kg As reached 11.79 and 11.10 mg/kg As for blue grass and llanten after 7 weeks. For the Tungurahua soil with an initial concentration of 13 mg/kg As it reached the concentrations of 11.56 and 12.16 mg/kg As for the bluegrass and llanten respectively, and for the initial concentration of 15 mg/kg As reached 11.97 and 12.27 mg/kg Ace for bluegrass and llanten after 7 weeks. The best arsenic extraction methodology of soil-plant system is Wenzel.

Keywords: blue grass, llanten, phytoremediation, soil of Azuay, soil of Tungurahua, synthetic arsenic solution

Procedia PDF Downloads 87

Authors: Maher Z. Mohammed, Barry G. Clarke

Abstract:

As an alternative to stone column in fine grained soils, it is possible to create stiffened columns of soils using electroosmosis (electroosmotic piles). This program of this research is to establish the effectiveness and efficiency of the process in different soils. The aim of this study is to assess the capability of electroosmosis treatment in a range of composite soils. The combined electroosmotic and preloading equipment developed by Nizar and Clarke (2013) was used with an octagonal array of anodes surrounding a single cathode in a nominal 250mm diameter 300mm deep cylinder of soil and 80mm anode to cathode distance. Copper coiled springs were used as electrodes to allow the soil to consolidate either due to an external vertical applied load or electroosmosis. The equipment was modified to allow the temperature to be monitored during the test. Electroosmotic tests were performed on China Clay Grade E kaolin and calcium bentonite (Bentonex CB) mixed with sand fraction C (BS 1881 part 131) at different ratios by weight; (0, 23, 33, 50 and 67%) subjected to applied voltages (5, 10, 15 and 20). The soil slurry was prepared by mixing the dry soil with water to 1.5 times the liquid limit of the soil mixture. The mineralogical and geotechnical properties of the tested soils were measured before the electroosmosis treatment began. In the electroosmosis cell tests, the settlement, expelled water, variation of electrical current and applied voltage, and the generated heat was monitored during the test time for 24 osmotic tests. Water content was measured at the end of each test. The electroosmotic tests are divided into three phases. In Phase 1, 15 kPa was applied to simulate a working platform and produce a uniform soil which had been deposited as a slurry. 50 kPa was used in Phase 3 to simulate a surcharge load. The electroosmotic treatment was only performed during Phase 2 where a constant voltage was applied through the electrodes in addition to the 15 kPa pressure. This phase was stopped when no further water was expelled from the cell, indicating the electroosmotic process had stopped due to either the degradation of the anode or the flow due to the hydraulic gradient exactly balanced the electroosmotic flow resulting in no flow. Control tests for each soil mixture were carried out to assess the behaviour of the soil samples subjected to only an increase of vertical pressure, which is 15kPa in Phase 1 and 50kPa in Phase 3. Analysis of the experimental results from this study showed a significant dewatering effect on the soil slurries. The water discharged by the electroosmotic treatment process decreased as the sand content increased. Soil temperature increased significantly when electrical power was applied and drops when applied DC power turned off or when the electrode degraded. The highest increase in temperature was found in pure clays at higher applied voltage after about 8 hours of electroosmosis test.

Keywords: electrokinetic treatment, electrical conductivity, electroosmotic consolidation, electroosmosis permeability ratio

Procedia PDF Downloads 148

Authors: Mayank Gupta, Siba Prasad Samal, Vasu Kakkirala

Abstract:

The internet world and its priorities have changed considerably in the last decade. Browsing on smart phones has increased manifold and is set to explode much more. Users spent considerable time browsing different websites, that gives a great deal of insight into user’s preferences. Instead of plain information classifying different aspects of browsing like Bookmarks, History, and Download Manager into useful categories would improve and enhance the user’s experience. Most of the classification solutions are server side that involves maintaining server and other heavy resources. It has security constraints and maybe misses on contextual data during classification. On device, classification solves many such problems, but the challenge is to achieve accuracy on classification with resource constraints. This on device classification can be much more useful in personalization, reducing dependency on cloud connectivity and better privacy/security. This approach provides more relevant results as compared to current standalone solutions because it uses content rendered by browser which is customized by the content provider based on user’s profile. This paper proposes a Naive Bayes based lightweight classification engine targeted for a resource constraint devices. Our solution integrates with Web Browser that in turn triggers classification algorithm. Whenever a user browses a webpage, this solution extracts DOM Tree data from the browser’s rendering engine. This DOM data is a dynamic, contextual and secure data that can’t be replicated. This proposal extracts different features of the webpage that runs on an algorithm to classify into multiple categories. Naive Bayes based engine is chosen in this solution for its inherent advantages in using limited resources compared to other classification algorithms like Support Vector Machine, Neural Networks, etc. Naive Bayes classification requires small memory footprint and less computation suitable for smartphone environment. This solution has a feature to partition the model into multiple chunks that in turn will facilitate less usage of memory instead of loading a complete model. Classification of the webpages done through integrated engine is faster, more relevant and energy efficient than other standalone on device solution. This classification engine has been tested on Samsung Z3 Tizen hardware. The Engine is integrated into Tizen Browser that uses Chromium Rendering Engine. For this solution, extensive dataset is sourced from dmoztools.net and cleaned. This cleaned dataset has 227.5K webpages which are divided into 8 generic categories ('education', 'games', 'health', 'entertainment', 'news', 'shopping', 'sports', 'travel'). Our browser integrated solution has resulted in 15% less memory usage (due to partition method) and 24% less power consumption in comparison with standalone solution. This solution considered 70% of the dataset for training the data model and the rest 30% dataset for testing. An average accuracy of ~96.3% is achieved across the above mentioned 8 categories. This engine can be further extended for suggesting Dynamic tags and using the classification for differential uses cases to enhance browsing experience.

Keywords: chromium, lightweight engine, mobile computing, Naive Bayes, Tizen, web browser, webpage classification

Procedia PDF Downloads 143

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

Most well-known classifiers, including the decision tree algorithm, can make predictions on balanced datasets efficiently. However, the decision tree algorithm tends to be biased towards imbalanced datasets because of the skewness of the distribution of such datasets. To overcome this problem, this study proposes a weighted decision tree algorithm that aims to remove the bias toward the majority class and prevents the reduction of majority observations in imbalance datasets classification. The proposed weighted decision tree algorithm was tested on three imbalanced datasets- cancer dataset, german credit dataset, and banknote dataset. The specificity, sensitivity, and accuracy metrics were used to evaluate the performance of the proposed decision tree algorithm on the datasets. The evaluation results show that for some of the weights of our proposed decision tree, the specificity, sensitivity, and accuracy metrics gave better results compared to that of the ID3 decision tree and decision tree induced with minority entropy for all three datasets.

Keywords: data mining, decision tree, classification, imbalance dataset

Procedia PDF Downloads 106

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 347

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 28

Authors: Mohammad Tarek Al Muallim, Ozhan Duzenli, Ceyhun Ilguy

Abstract:

Harbor protection systems are so important. The need for automatic protection systems has increased over the last years. Diver detection active sonar has great significance. It used to detect underwater threats such as divers and autonomous underwater vehicle. To automatically detect such threats the sonar image is processed by algorithms. These algorithms used to detect, track and classify of underwater objects. In this work, divers tracking and classification algorithm is improved be proposing a robust wake detection method. To detect objects the sonar images is normalized then segmented based on fixed threshold. Next, the centroids of the segments are found and clustered based on distance metric. Then to track the objects linear Kalman filter is applied. To reduce effect of noise and creation of false tracks, the Kalman tracker is fine tuned. The tuning is done based on our active sonar specifications. After the tracks are initialed and updated they are subjected to a filtering stage to eliminate the noisy and unstable tracks. Also to eliminate object with a speed out of the diver speed range such as buoys and fast boats. Afterwards the result tracks are subjected to a classification stage to deiced the type of the object been tracked. Here the classification stage is to deice wither if the tracked object is an open circuit diver or a close circuit diver. At the classification stage, a small area around the object is extracted and a novel wake detection method is applied. The morphological features of the object with his wake is extracted. We used support vector machine to find the best classifier. The sonar training images and the test images are collected by ARMELSAN Defense Technologies Company using the portable diver detection sonar ARAS-2023. After applying the algorithm to the test sonar data, we get fine and stable tracks of the divers. The total classification accuracy achieved with the diver type is 97%.

Keywords: harbor protection, diver detection, active sonar, wake detection, diver classification

Procedia PDF Downloads 217

Authors: Salima Smiti, Ines Gasmi, Makram Soui

Abstract:

Credit risk is the most important issue for financial institutions. Its assessment becomes an important task used to predict defaulter customers and classify customers as good or bad payers. To this objective, numerous techniques have been applied for credit risk assessment. However, to our knowledge, several evaluation techniques are black-box models such as neural networks, SVM, etc. They generate applicants’ classes without any explanation. In this paper, we propose to assess credit risk using rules classification method. Our output is a set of rules which describe and explain the decision. To this end, we will compare seven classification algorithms (JRip, Decision Table, OneR, ZeroR, Fuzzy Rule, PART and Genetic programming (GP)) where the goal is to find the best rules satisfying many criteria: accuracy, sensitivity, and specificity. The obtained results confirm the efficiency of the GP algorithm for German and Australian datasets compared to other rule-based techniques to predict the credit risk.

Keywords: credit risk assessment, classification algorithms, data mining, rule extraction

Procedia PDF Downloads 159

Authors: Yulong Wang, Yuan Yan Tang, Cuiming Zou, Lina Yang

Abstract:

This paper presents a novel sparse representation method for robust pattern classification. Generalized orthogonal matching pursuit (GOMP) is a recently proposed efficient sparse representation technique. However, GOMP adopts the mean square error (MSE) criterion and assign the same weights to all measurements, including both severely and slightly corrupted ones. To reduce the limitation, we propose an information-theoretic GOMP (ITGOMP) method by exploiting the correntropy induced metric. The results show that ITGOMP can adaptively assign small weights on severely contaminated measurements and large weights on clean ones, respectively. An ITGOMP based classifier is further developed for robust pattern classification. The experiments on public real datasets demonstrate the efficacy of the proposed approach.

Keywords: correntropy induced metric, matching pursuit, pattern classification, sparse representation

Procedia PDF Downloads 338

Authors: Qi Xiu, Hiromu Hota, Yohsuke Ishii, Takuya Oda

Abstract:

Recently, collectable manufacturing data are rapidly increasing. On the other hand, mega recall is getting serious as a social problem. Under such circumstances, there are increasing needs for preventing mega recalls by defect analysis such as root cause analysis and abnormal detection utilizing manufacturing data. However, the time to classify strings in manufacturing data by traditional method is too long to meet requirement of quick defect analysis. Therefore, we present String Length Distribution Classification method (SLDC) to correctly classify strings in a short time. This method learns character features, especially string length distribution from Product ID, Machine ID in BOM and asset list. By applying the proposal to strings in actual manufacturing data, we verified that the classification time of strings can be reduced by 80%. As a result, it can be estimated that the requirement of quick defect analysis can be fulfilled.

Keywords: string classification, data quality, feature selection, probability distribution, string length

Procedia PDF Downloads 305

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 230

Authors: Amritanshu Sandilya, M. V. Shah

Abstract:

Collapsible soils such as loess are a common geotechnical challenge due to their potential to undergo sudden and severe settlement under certain loading conditions. The need for filling engineering to increase developing land has grown significantly in recent years, which has created several difficulties in managing soil strength and stability during compaction. Numerous engineering problems, such as roadbed subsidence and pavement cracking, have been brought about by insufficient fill strength. Therefore, strict control of compaction parameters is essential to reduce these distresses. Accurately measuring the degree of compaction, which is often represented by compactness is an important component of compaction control. For credible predictions of how collapsible soils will behave under complicated loading situations, the accuracy of laboratory studies is essential. Therefore, this study aims to investigate the energy transfer in collapsible soils during laboratory Proctor compaction tests to provide insights into how energy transfer can be optimized to achieve more accurate and reliable results in compaction testing. The compaction characteristics in terms of energy of loess soil have been studied at moisture content corresponding to dry of optimum, at the optimum and wet side of optimum and at different compaction energy levels. The hammer impact force (E0) and soil bottom force (E) were measured using an impact load cell mounted at the bottom of the compaction mould. The variation in energy consumption ratio (E/ E0) was observed and compared with the compaction curve of the soil. The results indicate that the plot of energy consumption ratio versus moisture content can serve as a reliable indicator of the compaction characteristics of the soil in terms of energy.

Keywords: soil compaction, proctor compaction test, collapsible soil, energy transfer

Procedia PDF Downloads 68

Authors: Stephan P. Barkhuizen, Deon Greyling, Ryan J. Miller

Abstract:

The accurate determination of the engineering parameters of soil is necessary for the design of geotechnical structures, such as Tailings Storage Facilities. The shear strength and saturated permeability of soil and tailings samples obtained from 14 sites located in the copper belt in the Democratic Republic of the Congo have been tested at six commercial soil laboratories in South Africa. This study compiles a database of the test results proved by the soil laboratories. The samples have been categorised into clay, silt, and sand, based on the Unified Soil Classification System, with tailings kept separate. The effective friction angle (Φ’) and cohesion (c’) were interpreted from the stress paths, in s’:t space, obtained from triaxial tests. The minimum, lower quartile, median, upper quartile, and maximum values for Φ’,c’, and saturated hydraulic conductivity (k) have been determined for the soil sample. The objective is to provide statistics of the measured values of the engineering properties for the TSF borrow material, foundation soils and tailings of this region.

Keywords: Democratic Republic of the Congo, laboratory test work, soil engineering parameter variation, tailings storage facilities

Procedia PDF Downloads 42

Authors: Jularat Chumnaul

Abstract:

In forensic science, corpses from various homicides are different; there are both complete and incomplete, depending on causes of death or forms of homicide. For example, some corpses are cut into pieces, some are camouflaged by dumping into the river, some are buried, some are burned to destroy the evidence, and others. If the corpses are incomplete, it can lead to the difficulty of personally identifying because some tissues and bones are destroyed. To specify gender of the corpses from skeletal remains, the most precise method is DNA identification. However, this method is costly and takes longer so that other identification techniques are used instead. The first technique that is widely used is considering the features of bones. In general, an evidence from the corpses such as some pieces of bones, especially the skull and pelvis can be used to identify their gender. To use this technique, forensic scientists are required observation skills in order to classify the difference between male and female bones. Although this technique is uncomplicated, saving time and cost, and the forensic scientists can fairly accurately determine gender by using this technique (apparently an accuracy rate of 90% or more), the crucial disadvantage is there are only some positions of skeleton that can be used to specify gender such as supraorbital ridge, nuchal crest, temporal lobe, mandible, and chin. Therefore, the skeletal remains that will be used have to be complete. The other technique that is widely used for gender specifying in forensic science and archeology is skeletal measurements. The advantage of this method is it can be used in several positions in one piece of bones, and it can be used even if the bones are not complete. In this study, the classification and cluster analysis are applied to this technique, including the Kth Nearest Neighbor Classification, Classification Tree, Ward Linkage Cluster, K-mean Cluster, and Two Step Cluster. The data contains 507 particular individuals and 9 skeletal measurements (diameter measurements), and the performance of five methods are investigated by considering the apparent error rate (APER). The results from this study indicate that the Two Step Cluster and Kth Nearest Neighbor method seem to be suitable to specify gender from human skeletal remains because both yield small apparent error rate of 0.20% and 4.14%, respectively. On the other hand, the Classification Tree, Ward Linkage Cluster, and K-mean Cluster method are not appropriate since they yield large apparent error rate of 10.65%, 10.65%, and 16.37%, respectively. However, there are other ways to evaluate the performance of classification such as an estimate of the error rate using the holdout procedure or misclassification costs, and the difference methods can make the different conclusions.

Keywords: skeletal measurements, classification, cluster, apparent error rate

Procedia PDF Downloads 235

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 190

Authors: Mohamed Eladham Fadl M. E. Fadl

Abstract:

In Egypt, wastewater has been used for irrigation in areas with fresh water scarcity. However, continuous applications may cause potential risks. Thus, the current study aims at screening the impacts of long-term wastewater irrigation on soil pollution and human health due to the exposure of heavy metals. Soils of nine sites in Al-Qalyubiyah Governorate, Egypt were sampled and analyzed for different properties. Wastewater resulted in a build-up of metals in soils. The pollution index (PI) showed the order of Cd > Pb > Ni > Zn. The integrated pollution index of Nemerow’s (IPIN) exceeded the safe limit of 0.7. The enrichment factor (EF) surpassed 1.0 value proving anthropogenic effects. The geo-accumulation index (Igeo) indicated that Pb, Ni, and Zn-induced none to moderate pollution, while high threats were associated with Cd. The calculated hazard index proved a potential health risk for humans, particularly children. It is recommended to perform a treatment to the wastewater used in irrigation to avoid such threats.

Keywords: pollution, health risks, heavy metals, effluent, irrigation, GIS techniques

Procedia PDF Downloads 325

Authors: Javier Alfonso Bonilla-Chávez, Angélica Lozano

Abstract:

In North America, more than 2,000 people annually die in accidents related to railroad tracks. In 2020, collisions at grade crossings were the main cause of deaths related to railway accidents in Mexico. Railway networks have constant interaction with motor transport users, cyclists, and pedestrians, mainly in grade crossings, where is the greatest vulnerability and risk of accidents. Usually, accidents at grade crossings are directly related to risky behavior and non-compliance with regulations by motorists, cyclists, and pedestrians, especially in developing countries. Around the world, countries classify these crossings in different ways. In Mexico, according to their dangerousness (high, medium, or low), types A, B and C have been established, recommending for each one different type of auditive and visual signaling and gates, as well as horizontal and vertical signaling. This classification is based in a weighting, but regrettably, it is not explained how the weight values were obtained. A review of the variables and the current approach for the grade crossing classification is required, since it is inadequate for some crossings. In contrast, North America (USA and Canada) and European countries consider a broader classification so that attention to each crossing is addressed more precisely and equipment costs are adjusted. Lack of a proper classification, could lead to cost overruns in the equipment and a deficient operation. To exemplify the lack of a good classification, six crossings are studied, three located in the rural area of Mexico and three in Mexico City. These cases show the need of: improving the current regulations, improving the existing infrastructure, and implementing technological systems, including informative signals with nomenclature of the involved crossing and direct telephone line for reporting emergencies. This implementation is unaffordable for most municipal governments. Also, an inventory of the most dangerous grade crossings in urban and rural areas must be obtained. Then, an approach for improving the classification of grade crossings is suggested. This approach must be based on criteria design, characteristics of adjacent roads or intersections which can influence traffic flow through the crossing, accidents related to motorized and non-motorized vehicles, land use and land management, type of area, and services and economic activities in the zone where the grade crossings is located. An expanded classification of grade crossing in Mexico could reduce accidents and improve the efficiency of the railroad.

Keywords: accidents, grade crossing, railroad, traffic safety

Procedia PDF Downloads 93

Authors: P. S. Jagadeesh Kumar, Yang Yung, Wenli Hu

Abstract:

Speech emotion classification is a dominant research field in finding a sturdy and profligate classifier appropriate for different real-life applications. This effort accentuates on classifying different emotions from speech signal quarried from the features related to pitch, formants, energy contours, jitter, shimmer, spectral, perceptual and temporal features. Tensor deep stacking neural networks were supported to examine the factors that influence the classification success rate. Facial electromyography signals were composed of several forms of focuses in a controlled atmosphere by means of audio-visual stimuli. Proficient facial electromyography signals were pre-processed using moving average filter, and a set of arithmetical features were excavated. Extracted features were mapped into consistent emotions using bilinear mapping. With facial electromyography signals, a database comprising diverse emotions will be exposed with a suitable fine-tuning of features and training data. A success rate of 92% can be attained deprived of increasing the system connivance and the computation time for sorting diverse emotional states.

Keywords: speech emotion classification, tensor deep stacking neural networks, facial electromyography, bilinear mapping, audio-visual stimuli

Procedia PDF Downloads 228

Authors: M. Imran Hamid, Muzammil Hussain, Yunpeng Wu, Meichun Xiang, Xingzhong Liu

Abstract:

The rhizosphere microbiome elucidate multiple functioning in the soil suppressiveness against plant pathogens. Soybean rhizosphere microbial communities may involve in the natural suppression of soybean cyst nematode (SCN) populations in disease suppressive soils. To explore these ecological mechanisms of microbes, a long term monoculture suppressive soil were taken into account for further investigation to test the disease suppressive ability by using different treatments. The designed treatments are as, i) suppressive soil (S), ii) conducive soil (C), iii) conducive soil mixed with 10% (w/w) suppressive soil (CS), iv) suppressive soil treated at 80°C for 1 hr (S80), and v) suppressive soil treated with formalin (SF). By using an ultra-high-throughput sequencing approach, we identified the key bacterial and fungal taxa involved in SCN suppression. The Phylum-level investigation of bacteria revealed that Actinobacteria, Bacteroidetes, and Proteobacteria in the rhizosphere soil of soybean seedlings were more abundant in the suppressive soil than in the conducive soil. The phylum-level analysis of fungi in rhizosphere soil indicated that relative abundance of Ascomycota was higher in suppressive soil than in the conducive soil, where Basidiomycota was more abundant. Transferring suppressive soil to conducive soil increased the population of Ascomycota in the conducive soil by lowering the populations of Basidiomycota. The genera, such as, Pochonia, Purpureocillium, Fusarium, Stachybotrys that have been well documented as bio-control agents of plant nematodes were far more in the disease suppressive soils. Our results suggested that the plants engage a subset of functional microbial groups in the rhizosphere for initial defense upon nematode attack and protect the plant roots later on by nematodes to response for suppression of SCN in disease-suppressive soils.

Keywords: disease suppressive soil, high-throughput sequencing, rhizosphere microbiome, soybean cyst nematode

Procedia PDF Downloads 138

Authors: Li Kewen, Su Zhaoxin, Wang Xingmou, Zhu Jian Bing

Abstract:

Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.

Keywords: convolutional neural network, lithology, prediction of reservoir, seismic attributes

Procedia PDF Downloads 159

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 79

Authors: Md. Shoffikul Islam, Hongqing Hu

Abstract:

Immobilizing trace elements by reducing their mobility and bioavailability through amendment application, especially biochar (BC), is a cost-effective and efficient method to address their toxicity in the soil environment. However, the low molecular weight organic acids (LMWOAs) in the rhizosphere could affect BC's efficiency to immobilize trace metals as the LMWOAs could either mobilize or fix metals in the soils. Therefore, understanding the BC's and LMWOAs' interaction mechanisms on metals stabilization in the rhizosphere is crucial. The present study examined the impact of BC derived from rice husk, tartaric acid (TA), and oxalic acid (OA), and the combination of BC and TA/OA on the changes of cadmium (Cd), lead (Pb), and zinc (Zn) among their geochemical forms through incubation experiment. The changes of zeta potential and X-ray diffraction (XRD) pattern of BC and BC-amended soils to investigate the probable mechanisms of trace elements' immobilization by BC under the attacks of TA and OA were also examined. The rice husk BC at 5% (w/w) was mixed with the air-dry soil (an Anthrosols) contaminated with Cd, Pb, and Zn in the plastic pot. The TA and OA each at 2, 5, 10, and 20 mM kg-1 (w/v) were added separately into the pot. All the ingredients were mixed thoroughly with the soil. A control (CK) treatment was also prepared without BC, TA, and OA addition. After 7, 15, and 60 days of incubation with 60% (w/v) moisture level at 25 °C, the incubated soils were determined for pH and EC and were sequentially extracted to assess the metals' transformation in soil. The electronegative charges and XRD peaks of BC and BC-amended soils were also measured. The BC, low level of TA (2 mM kg-1 soil), and BC plus the low concentration of TA (BC-TA2) addition considerably declined the acid-soluble Cd, Pb, and Zn in which BC-TA2 was found to be the most effective treatment. The trends were reversed concerning the high levels of TA (>5-20 mM kg-1 soil), all levels of OA (2-20 mM kg-1 soil), and the BC plus high levels of TA/OA treatments. BC-TA2 changed the highest amounts of acid-soluble and reducible metals to the oxidizable and residual fractions with time. The most increased electronegative charges of BC-TA2 indicate its (BC-TA2) highest metals' immobilizing efficiency, probably through metals adsorption and fixation with the negative charge sites. The XRD study revealed the presence of P, O, CO32-, and Cl1- in BC, which might be responsible for the precipitation of CdCO3, pyromorphite, and hopeite concerning Cd, Pb, and Zn immobilization, respectively. The findings demonstrated that the low level of TA increased metals immobilization, while the high levels of TA and all levels of OA enhanced their mobilization. The BC-TA2 was the best treatment in stabilizing metals in soil.

Keywords: biochar, immobilization, low molecular weight organic acids, trace elements contaminated soil

Procedia PDF Downloads 61

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 415

Authors: Nicholas Milburn, Yu Liang, Dalei Wu

Abstract:

Athlete performance scoring within the climbing do-main presents interesting challenges as the sport does not have an objective way to assign skill. Assessing skill levels within any sport is valuable as it can be used to mark progress while training, and it can help an athlete choose appropriate climbs to attempt. Machine learning-based methods are popular for complex problems like this. The dataset available was composed of dynamic force data recorded during climbing; however, this dataset came with challenges such as data scarcity, imbalance, and it was temporally heterogeneous. Investigated solutions to these challenges include data augmentation, temporal normalization, conversion of time series to the spectral domain, and cross validation strategies. The investigated solutions to the classification problem included light weight machine classifiers KNN and SVM as well as the deep learning with CNN. The best performing model had an 80% accuracy. In conclusion, there seems to be enough information within climbing force data to accurately categorize climbers by skill.

Keywords: classification, climbing, data imbalance, data scarcity, machine learning, time sequence

Procedia PDF Downloads 128

Authors: Y. Hajjam, I. T. Alami, S. M. Udupa, S. Cherkaoui

Abstract:

Faba bean (Vicia faba L.) is an important food legume crop in Morocco. It is mainly used as human food and feed for animals. Faba bean also plays an important role in cereal-based cropping systems, when rotated with cereals it improves soil fertility by fixing N2 in root nodules mediated by Rhizobium. Both faba bean and its biological nitrogen fixation symbiotic bacterium Rhizobium are affected by different stresses such as: salinity, drought, pH, heavy metal, and the uptake of inorganic phosphate compounds. Therefore, the aim of the present study was to evaluate the phenotypic diversity among the faba bean rhizobial isolates and to select the tolerant strains that can fix N2 under environmental constraints for inoculation particularly for affected soils, in order to enhance the productivity of faba bean and to improve soil fertility. Result have shown that 62% of isolates were fast growing with the ability of producing acids compounds , while 38% of isolates are slow growing with production of alkalins. Moreover, 42.5% of these isolates were able to solubilize inorganic phosphate Ca3(PO4)2 and the index of solubilization was ranged from 2.1 to 3.0. The resistance to extreme pH, temperature, water stress heavy metals and antibiotics lead us to classify rhizobial isolates into different clusters. Finally, the authentication test under greenhouse conditions showed that 55% of the rhizobial isolates could induce nodule formation on faba bean (Vicia faba L.) under greenhouse experiment. This phenotypic characterization may contribute to improve legumes and non legumes crops especially in affected soils and also to increase agronomic yield in the dry areas.

Keywords: rhizobia, vicia faba, phenotypic characterization, nodule formation, environmental constraints

Procedia PDF Downloads 233

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: classification, singing, spectral analysis, vocal emission, vocal register

Procedia PDF Downloads 288

Authors: Comfort Adeoye, Anthony Eneji

Abstract:

Lead pollution by mining, industrial dumping, and other anthropogenic uses are corroding the environment. Efforts being made to control it include physical, chemical and biological methods. The failure of the aforementioned methods are largely due to the fact that they are cumbersome, expensive, and not eco-friendly. Some plant species can be used for remediation of these pollutants. The objective of this work is to investigate the abilities of two native weed species to remediate two lead-polluted soils: a) Battery dumpsite and, (b) Naturally occurring lead mine. Soil samples were taken from the two sites: a) Kumapayi in Ibadan, a battery dumpsite, (b) Zamfara, a natural lead mine. Screen house experiment in Complete Randomized Design (CRD) replicated three times was carried out at I.I.T.A. Unpolluted soils were collected and polluted with various rates of lead concentrations of 0, 0.1, 0.2, and 0.5%. These were planted with weed species. Plant growth parameters were monitored for twelve weeks, after which the plants were harvested. Dry weight and plant uptake of the lead were taken. Analysis of data was carried out using, Genstat, Excel and descriptive statistics. Relative concentration of lead (Pb) in the above and below ground parts of Gomphrena celusoides revealed that a higher amount of Pb is taken up in the root compared with the shoots at different levels of Pb pollution. However, lead uptake at 0.5% > 0.2% > 0.1% > Control. In essence, phytoremediation of Gomphrena is highest at soil pollution of 0.5% and its retention is greater in the root than the shoot.In S. pyramidalis, soil retention ranges from 0.1% > 0.5% > 0.2% > control. Uptake is highest at 0.5% > 0.1% > 0.2 in stem. Uptake in leaves is highest at 0.2%, but none in the 0.5% pollution. Therefore, different plant species exhibited different accumulative mode probably due to their physiological and rooting systems. Gomphrena spp. rooting system is tap root,while that of S.pyramidalis is fibrous.

Keywords: grass, lead, phytoremediation, pollution

Procedia PDF Downloads 308

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 167

Authors: Sateesh Kumar Pisini, Swetha Priya Darshini Thammadi, Sanjay Kumar Shukla

Abstract:

Granular piles are a popular ground improvement technique in soft cohesive soils as well as for loose non-cohesive soils. The present experimental study has been carried out on granular piles in loose (Relative density = 30%) and medium dense (Relative density = 60%) sands with geogrid reinforcement within the sand bed over the granular piles. A group of five piles were installed in the sand at different spacing, s = 2d, 3d and 4d, d being the diameter of the pile. The length (L = 0.4 m) and diameter (d = 50 mm) of the piles were kept constant for all the series of experiments. The load-settlement behavior of reinforced sand bed and granular piles system was studied by applying the load on a square footing. The results show that the effect of reinforcement increases the load bearing capacity of the piles. It is also found that an increase in spacing between piles decreases the settlement for both loose and medium dense soil.

Keywords: granular pile, load-carrying capacity, settlement, geogrid reinforcement, sand

Procedia PDF Downloads 370

Authors: Sarra Arbaoui, Taoufik Bettaieb

Abstract:

Contaminated soils and problems related to them have increasingly become a matter of concern. The most common the contaminants generated by industrial urban emissions and agricultural practices are trace metals). Remediation of trace metals which pollute soils can be carried out using physico-chemical processes. Nevertheless, these techniques damage the soil’s biological activity and require expensive equipment. Phytoremediation is a relatively low-cost technology based on the use of selected plants to remove, degrades or contains pollutants. The potential of kenaf for phytoremediation on Cd-contaminated soil was investigated. kenaf plants have been grown in pots containing different concentrations of cadmium. The observations made were for biomass production and cadmium content in different organs determinate by atomic emission spectrometry. Cadmium transfer from a contaminated soil to plants and into plant tissues are discussed in terms of the Bioconcentration Factor (BCF) and the Transfer Factor (TF). Results showed that Cd was found in kenaf plants at different levels. Tolerance and accumulation potential and biomass productivity indicated that kenaf could be used in phytoremediation.

Keywords: kenaf, cadmium, phytoremediation, contaminated soil

Procedia PDF Downloads 501