Search results for: random forest algorithm
5772 ACOPIN: An ACO Algorithm with TSP Approach for Clustering Proteins in Protein Interaction Networks
Authors: Jamaludin Sallim, Rozlina Mohamed, Roslina Abdul Hamid
Abstract:
In this paper, we proposed an Ant Colony Optimization (ACO) algorithm together with Traveling Salesman Problem (TSP) approach to investigate the clustering problem in Protein Interaction Networks (PIN). We named this combination as ACOPIN. The purpose of this work is two-fold. First, to test the efficacy of ACO in clustering PIN and second, to propose the simple generalization of the ACO algorithm that might allow its application in clustering proteins in PIN. We split this paper to three main sections. First, we describe the PIN and clustering proteins in PIN. Second, we discuss the steps involved in each phase of ACO algorithm. Finally, we present some results of the investigation with the clustering patterns.Keywords: ant colony optimization algorithm, searching algorithm, protein functional module, protein interaction network
Procedia PDF Downloads 6025771 Carbon Sequestration Modeling in the Implementation of REDD+ Programmes in Nigeria
Authors: Oluwafemi Samuel Oyamakin
Abstract:
The forest in Nigeria is currently estimated to extend to around 9.6 million hectares, but used to expand over central and southern Nigeria decades ago. The forest estate is shrinking due to long-term human exploitation for agricultural development, fuel wood demand, uncontrolled forest harvesting and urbanization, amongst other factors, compounded by population growth in rural areas. Nigeria has lost more than 50% of its forest cover since 1990 and currently less than 10% of the country is forested. The current deforestation rate is estimated at 3.7%, which is one of the highest in the world. Reducing Emissions from Deforestation and forest Degradation plus conservation, sustainable management of forests and enhancement of forest carbon stocks constituted what is referred to as REDD+. This study evaluated some of the existing way of computing carbon stocks using eight indigenous tree species like Mansonia, Shorea, Bombax, Terminalia superba, Khaya grandifolia, Khaya senegalenses, Pines and Gmelina arborea. While these components are the essential elements of REDD+ programme, they can be brought under a broader framework of systems analysis designed to arrive at optimal solutions for future predictions through statistical distribution pattern of carbon sequestrated by various species of tree. Available data on height and diameter of trees in Ibadan were studied and their respective potentials of carbon sequestration level were assessed and subjected to tests so as to determine the best statistical distribution that would describe the carbon sequestration pattern of trees. The result of this study suggests a reasonable statistical distribution for carbons sequestered in simulation studies and hence, allow planners and government in determining resources forecast for sustainable development especially where experiments with real-life systems are infeasible. Sustainable management of forest can then be achieved by projecting future condition of forests under different management regimes thereby supporting conservation and REDD+ programmes in Nigeria.Keywords: REDD+, carbon, climate change, height and diameter
Procedia PDF Downloads 1615770 ANOVA-Based Feature Selection and Machine Learning System for IoT Anomaly Detection
Authors: Muhammad Ali
Abstract:
Cyber-attacks and anomaly detection on the Internet of Things (IoT) infrastructure is emerging concern in the domain of data-driven intrusion. Rapidly increasing IoT risk is now making headlines around the world. denial of service, malicious control, data type probing, malicious operation, DDos, scan, spying, and wrong setup are attacks and anomalies that can affect an IoT system failure. Everyone talks about cyber security, connectivity, smart devices, and real-time data extraction. IoT devices expose a wide variety of new cyber security attack vectors in network traffic. For further than IoT development, and mainly for smart and IoT applications, there is a necessity for intelligent processing and analysis of data. So, our approach is too secure. We train several machine learning models that have been compared to accurately predicting attacks and anomalies on IoT systems, considering IoT applications, with ANOVA-based feature selection with fewer prediction models to evaluate network traffic to help prevent IoT devices. The machine learning (ML) algorithms that have been used here are KNN, SVM, NB, D.T., and R.F., with the most satisfactory test accuracy with fast detection. The evaluation of ML metrics includes precision, recall, F1 score, FPR, NPV, G.M., MCC, and AUC & ROC. The Random Forest algorithm achieved the best results with less prediction time, with an accuracy of 99.98%.Keywords: machine learning, analysis of variance, Internet of Thing, network security, intrusion detection
Procedia PDF Downloads 1125769 An Efficient Acquisition Algorithm for Long Pseudo-Random Sequence
Authors: Wan-Hsin Hsieh, Chieh-Fu Chang, Ming-Seng Kao
Abstract:
In this paper, a novel method termed the Phase Coherence Acquisition (PCA) is proposed for pseudo-random (PN) sequence acquisition. By employing complex phasors, the PCA requires only complex additions in the order of N, the length of the sequence, whereas the conventional method utilizing fast Fourier transform (FFT) requires complex multiplications and additions both in the order of Nlog2N . In order to combat noise, the input and local sequences are partitioned and mapped into complex phasors in PCA. The phase differences between pairs of input and local phasors are utilized for acquisition, and thus complex multiplications are avoided. For more noise-robustness capability, the multi-layer PCA is developed to extract the code phase step by step. The significant reduction of computational loads makes the PCA an attractive method, especially when the sequence length of is extremely large which becomes intractable for the FFT-based acquisition.Keywords: FFT, PCA, PN sequence, convolution theory
Procedia PDF Downloads 4725768 An Algorithm for the Map Labeling Problem with Two Kinds of Priorities
Authors: Noboru Abe, Yoshinori Amai, Toshinori Nakatake, Sumio Masuda, Kazuaki Yamaguchi
Abstract:
We consider the problem of placing labels of the points on a plane. For each point, its position, the size of its label and a priority are given. Moreover, several candidates of its label positions are prespecified, and each of such label positions is assigned a priority. The objective of our problem is to maximize the total sum of priorities of placed labels and their points. By refining a labeling algorithm that can use these priorities, we propose a new heuristic algorithm which is more suitable for treating the assigned priorities.Keywords: map labeling, greedy algorithm, heuristic algorithm, priority
Procedia PDF Downloads 4255767 Stochastic Model Predictive Control for Linear Discrete-Time Systems with Random Dither Quantization
Authors: Tomoaki Hashimoto
Abstract:
Recently, feedback control systems using random dither quantizers have been proposed for linear discrete-time systems. However, the constraints imposed on state and control variables have not yet been taken into account for the design of feedback control systems with random dither quantization. Model predictive control is a kind of optimal feedback control in which control performance over a finite future is optimized with a performance index that has a moving initial and terminal time. An important advantage of model predictive control is its ability to handle constraints imposed on state and control variables. Based on the model predictive control approach, the objective of this paper is to present a control method that satisfies probabilistic state constraints for linear discrete-time feedback control systems with random dither quantization. In other words, this paper provides a method for solving the optimal control problems subject to probabilistic state constraints for linear discrete-time feedback control systems with random dither quantization.Keywords: optimal control, stochastic systems, random dither, quantization
Procedia PDF Downloads 4355766 A Hybrid Distributed Algorithm for Multi-Objective Dynamic Flexible Job Shop Scheduling Problem
Authors: Aydin Teymourifar, Gurkan Ozturk
Abstract:
In this paper, a hybrid distributed algorithm has been suggested for multi-objective dynamic flexible job shop scheduling problem. The proposed algorithm is high level, in which several algorithms search the space on different machines simultaneously also it is a hybrid algorithm that takes advantages of the artificial intelligence, evolutionary and optimization methods. Distribution is done at different levels and new approaches are used for design of the algorithm. Apache spark and Hadoop frameworks have been used for the distribution of the algorithm. The Pareto optimality approach is used for solving the multi-objective benchmarks. The suggested algorithm that is able to solve large-size problems in short times has been compared with the successful algorithms of the literature. The results prove high speed and efficiency of the algorithm.Keywords: distributed algorithms, apache-spark, Hadoop, flexible dynamic job shop scheduling, multi-objective optimization
Procedia PDF Downloads 3465765 Assessing the High Rate of Deforestation Caused by the Operations of Timber Industries in Ghana
Authors: Obed Asamoah
Abstract:
Forests are very vital for human survival and our well-being. During the past years, the world has taken an increasingly significant role in the modification of the global environment. The high rate of deforestation in Ghana is of primary national concern as the forests provide many ecosystem services and functions that support the country’s predominantly agrarian economy and foreign earnings. Ghana forest is currently major source of carbon sink that helps to mitigate climate change. Ghana forests, both the reserves and off-reserves, are under pressure of deforestation. The causes of deforestation are varied but can broadly be categorized into anthropogenic and natural factors. For the anthropogenic factors, increased wood fuel collection, clearing of forests for agriculture, illegal and poorly regulated timber extraction, social and environmental conflicts, increasing urbanization and industrialization are the primary known causes for the loss of forests and woodlands. Mineral exploitation in the forest areas is considered as one of the major causes of deforestation in Ghana. Mining activities especially mining of gold by both the licensed mining companies and illegal mining groups who are locally known as "gallantly mining" also cause damage to the nation's forest reserves. Several works have been conducted regarding the causes of the high rate of deforestation in Ghana, major attention has been placed on illegal logging and using forest lands for illegal farming and mining activities. Less emphasis has been placed on the timber production companies on their harvesting methods in the forests in Ghana and other activities that are carried out in the forest. The main objective of the work is to find out the harvesting methods and the activities of the timber production companies and their effects on the forests in Ghana. Both qualitative and quantitative research methods were engaged in the research work. The study population comprised of 20 Timber industries (Sawmills) forest areas of Ghana. These companies were selected randomly. The cluster sampling technique was engaged in selecting the respondents. Both primary and secondary data were employed. In the study, it was observed that most of the timber production companies do not know the age, the weight, the distance covered from the harvesting to the loading site in the forest. It was also observed that old and heavy machines are used by timber production companies in their operations in the forest, which makes the soil compact prevents regeneration and enhances soil erosion. It was observed that timber production companies do not abide by the rules and regulations governing their operations in the forest. The high rate of corruption on the side of the officials of the Ghana forestry commission makes the officials relax and do not embark on proper monitoring on the operations of the timber production companies which makes the timber companies to cause more harm to the forest. In other to curb this situation the Ghana forestry commission with the ministry of lands and natural resources should monitor the activities of the timber production companies and sanction all the companies that make foul play in their activities in the forest. The commission should also pay more attention to the policy “fell one plant 10” to enhance regeneration in both reserves and off-reserves forest.Keywords: companies, deforestation, forest, Ghana, timber
Procedia PDF Downloads 1895764 Economic Perspectives for Agriculture and Forestry Owners in Bulgaria
Authors: Todor Nickolov Stoyanov
Abstract:
These factors appear as a reason for difficulties in financing from programs for rural development of the European Union. Credit conditions for commercial banks are difficult to implement, and its interest rate is too high. One of the possibilities for short-term loans at preferential conditions for the small and medium-sized agricultural and forest owners is credit cooperative. After the changes, occurred in the country after 1990, the need to restore credit cooperatives raised. The purpose for the creation of credit cooperatives is to assist private agricultural and forest owners to take care for them, to assist in the expansion and strengthening of their farms, to increase the quality of life and to improve the local economy. It was found that: in Bulgaria there is a legal obstacle for credit cooperatives to expand their business in the deposit and lending sphere; private forest and agricultural owners need small loans to solve a small problem for a certain season; providing such loans is not attractive for banks, but it is extremely necessary for owners of small forests and lands; if a special law on credit cooperatives is adopted, as required by the Cooperatives Act, it will allow more local people to be members of such credit structures and receive the necessary loans. In conclusion, proposals to create conditions for the development of credit cooperatives in the country are made and positive results expected from the creation of credit cooperatives, are summarized.Keywords: cooperatives, credit cooperatives, forestry, forest owners
Procedia PDF Downloads 2175763 Dynamic Variation in Nano-Scale CMOS SRAM Cells Due to LF/RTS Noise and Threshold Voltage
Authors: M. Fadlallah, G. Ghibaudo, C. G. Theodorou
Abstract:
The dynamic variation in memory devices such as the Static Random Access Memory can give errors in read or write operations. In this paper, the effect of low-frequency and random telegraph noise on the dynamic variation of one SRAM cell is detailed. The effect on circuit noise, speed, and length of time of processing is examined, using the Supply Read Retention Voltage and the Read Static Noise Margin. New test run methods are also developed. The obtained results simulation shows the importance of noise caused by dynamic variation, and the impact of Random Telegraph noise on SRAM variability is examined by evaluating the statistical distributions of Random Telegraph noise amplitude in the pull-up, pull-down. The threshold voltage mismatch between neighboring cell transistors due to intrinsic fluctuations typically contributes to larger reductions in static noise margin. Also the contribution of each of the SRAM transistor to total dynamic variation has been identified.Keywords: low-frequency noise, random telegraph noise, dynamic variation, SRRV
Procedia PDF Downloads 1685762 Empirical Study of Running Correlations in Exam Marks: Same Statistical Pattern as Chance
Authors: Weisi Guo
Abstract:
It is well established that there may be running correlations in sequential exam marks due to students sitting in the order of course registration patterns. As such, a random and non-sequential sampling of exam marks is a standard recommended practice. Here, the paper examines a large number of exam data stretching several years across different modules to see the degree to which it is true. Using the real mark distribution as a generative process, it was found that random simulated data had no more sequential randomness than the real data. That is to say, the running correlations that one often observes are statistically identical to chance. Digging deeper, it was found that some high running correlations have students that indeed share a common course history and make similar mistakes. However, at the statistical scale of a module question, the combined effect is statistically similar to the random shuffling of papers. As such, there may not be the need to take random samples for marks, but it still remains good practice to mark papers in a random sequence to reduce the repetitive marking bias and errors.Keywords: data analysis, empirical study, exams, marking
Procedia PDF Downloads 1775761 A Variant of a Double Structure-Preserving QR Algorithm for Symmetric and Hamiltonian Matrices
Authors: Ahmed Salam, Haithem Benkahla
Abstract:
Recently, an efficient backward-stable algorithm for computing eigenvalues and vectors of a symmetric and Hamiltonian matrix has been proposed. The method preserves the symmetric and Hamiltonian structures of the original matrix, during the whole process. In this paper, we revisit the method. We derive a way for implementing the reduction of the matrix to the appropriate condensed form. Then, we construct a novel version of the implicit QR-algorithm for computing the eigenvalues and vectors.Keywords: block implicit QR algorithm, preservation of a double structure, QR algorithm, symmetric and Hamiltonian structures
Procedia PDF Downloads 4055760 A New Tool for Global Optimization Problems: Cuttlefish Algorithm
Authors: Adel Sabry Eesa, Adnan Mohsin Abdulazeez Brifcani, Zeynep Orman
Abstract:
This paper presents a new meta-heuristic bio-inspired optimization algorithm which is called Cuttlefish Algorithm (CFA). The algorithm mimics the mechanism of color changing behavior of the cuttlefish to solve numerical global optimization problems. The colors and patterns of the cuttlefish are produced by reflected light from three different layers of cells. The proposed algorithm considers mainly two processes: reflection and visibility. Reflection process simulates light reflection mechanism used by these layers, while visibility process simulates visibility of matching patterns of the cuttlefish. To show the effectiveness of the algorithm, it is tested with some other popular bio-inspired optimization algorithms such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO) and Bees Algorithm (BA) that have been previously proposed in the literature. Simulations and obtained results indicate that the proposed CFA is superior when compared with these algorithms.Keywords: Cuttlefish Algorithm, bio-inspired algorithms, optimization, global optimization problems
Procedia PDF Downloads 5565759 Using Genetic Algorithms and Rough Set Based Fuzzy K-Modes to Improve Centroid Model Clustering Performance on Categorical Data
Authors: Rishabh Srivastav, Divyam Sharma
Abstract:
We propose an algorithm to cluster categorical data named as ‘Genetic algorithm initialized rough set based fuzzy K-Modes for categorical data’. We propose an amalgamation of the simple K-modes algorithm, the Rough and Fuzzy set based K-modes and the Genetic Algorithm to form a new algorithm,which we hypothesise, will provide better Centroid Model clustering results, than existing standard algorithms. In the proposed algorithm, the initialization and updation of modes is done by the use of genetic algorithms while the membership values are calculated using the rough set and fuzzy logic.Keywords: categorical data, fuzzy logic, genetic algorithm, K modes clustering, rough sets
Procedia PDF Downloads 2415758 Characterization of Single-Walled Carbon Nano Tubes Forest Decorated with Chromium
Authors: Ana Paula Mousinho, Ronaldo D. Mansano, Nelson Ordonez
Abstract:
Carbon nanotubes are one of the main elements in nanotechnologies; their applications are in microelectronics, nano-electronics devices (photonics, spintronic), chemical sensors, structural material and currently in clean energy devices (supercapacitors and fuel cells). The use of magnetic particle decorated carbon nanotubes increases the applications in magnetic devices, magnetic memory, and magnetic oriented drug delivery. In this work, single-walled carbon nanotubes (CNTs) forest decorated with chromium were deposited at room temperature by high-density plasma chemical vapor deposition (HDPCVD) system. The CNTs forest was obtained using pure methane plasmas and chromium, as precursor material (seed) and for decorating the CNTs. Magnetron sputtering deposited the chromium on silicon wafers before the CNTs' growth. Scanning electron microscopy, atomic force microscopy, micro-Raman spectroscopy, and X-ray diffraction characterized the single-walled CNTs forest decorated with chromium. In general, the CNTs' spectra show a unique emission band, but due to the presence of the chromium, the spectra obtained in this work showed many bands that are related to the CNTs with different diameters. The CNTs obtained by the HDPCVD system are highly aligned and showed metallic features, and they can be used as photonic material, due to the unique structural and electrical properties. The results of this work proved the possibility of obtaining the controlled deposition of aligned single-walled CNTs forest films decorated with chromium by high-density plasma chemical vapor deposition system.Keywords: CNTs forest, high density plasma deposition, high-aligned CNTs, nanomaterials
Procedia PDF Downloads 1135757 Assessing the Impacts of Long-Range Forest Fire Emission Transport on Air Quality in Toronto, Ontario, Using MODIS Fire Data and HYSPLIT Trajectories
Authors: Bartosz Osiecki, Jane Liu
Abstract:
Pollutants emitted from forest fires such as PM₂.₅ and carbon monoxide (CO) have been found to impact the air quality of distant regions through long-range transport. PM₂.₅ is of particular concern due to its transport capacity and implications for human respiratory and cardiovascular health. As such, significant increases in PM₂.₅ concentrations have been exhibited in urban areas downwind of fire sources. This study seeks to expand on this literature by evaluating the impacts of long-range forest fire emission transport on air quality in Toronto, Ontario, as a means of evaluating the vulnerability of this major urban center to distant fire events. In order to draw correlations between the fire event and air pollution episode in Toronto, MODIS fire count data and HYPLSIT trajectories are used to assess the date, location, and severity of the fire and track the trajectory of emissions (respectively). Forward and back-trajectories are run, terminating at the West Toronto air monitoring station. PM₂.₅ and CO concentrations in Toronto during September 2017 are found to be significantly elevated, which is likely attributable to the fire activity. Other sites in Ontario including Toronto (East, North, Downtown), Mississauga, Brampton, and Hamilton (Downtown) exhibit similar peaks in PM₂.₅ concentrations. This work sheds light on the non-local, natural factors influencing air quality in urban areas. This is especially important in the context of climate change which is expected to exacerbate intense forest fire events in the future.Keywords: air quality, forest fires, PM₂.₅, Toronto
Procedia PDF Downloads 1245756 An Improved Ant Colony Algorithm for Genome Rearrangements
Authors: Essam Al Daoud
Abstract:
Genome rearrangement is an important area in computational biology and bioinformatics. The basic problem in genome rearrangements is to compute the edit distance, i.e., the minimum number of operations needed to transform one genome into another. Unfortunately, unsigned genome rearrangement problem is NP-hard. In this study an improved ant colony optimization algorithm to approximate the edit distance is proposed. The main idea is to convert the unsigned permutation to signed permutation and evaluate the ants by using Kaplan algorithm. Two new operations are added to the standard ant colony algorithm: Replacing the worst ants by re-sampling the ants from a new probability distribution and applying the crossover operations on the best ants. The proposed algorithm is tested and compared with the improved breakpoint reversal sort algorithm by using three datasets. The results indicate that the proposed algorithm achieves better accuracy ratio than the previous methods.Keywords: ant colony algorithm, edit distance, genome breakpoint, genome rearrangement, reversal sort
Procedia PDF Downloads 3385755 Evaluation of Random Forest and Support Vector Machine Classification Performance for the Prediction of Early Multiple Sclerosis from Resting State FMRI Connectivity Data
Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone
Abstract:
The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine
Procedia PDF Downloads 2335754 Developing New Algorithm and Its Application on Optimal Control of Pumps in Water Distribution Network
Authors: R. Rajabpour, N. Talebbeydokhti, M. H. Ahmadi
Abstract:
In recent years, new techniques for solving complex problems in engineering are proposed. One of these techniques is JPSO algorithm. With innovative changes in the nature of the jump algorithm JPSO, it is possible to construct a graph-based solution with a new algorithm called G-JPSO. In this paper, a new algorithm to solve the optimal control problem Fletcher-Powell and optimal control of pumps in water distribution network was evaluated. Optimal control of pumps comprise of optimum timetable operation (status on and off) for each of the pumps at the desired time interval. Maximum number of status on and off for each pumps imposed to the objective function as another constraint. To determine the optimal operation of pumps, a model-based optimization-simulation algorithm was developed based on G-JPSO and JPSO algorithms. The proposed algorithm results were compared well with the ant colony algorithm, genetic and JPSO results. This shows the robustness of proposed algorithm in finding near optimum solutions with reasonable computational cost.Keywords: G-JPSO, operation, optimization, pumping station, water distribution networks
Procedia PDF Downloads 3965753 Forensic Speaker Verification in Noisy Environmental by Enhancing the Speech Signal Using ICA Approach
Authors: Ahmed Kamil Hasan Al-Ali, Bouchra Senadji, Ganesh Naik
Abstract:
We propose a system to real environmental noise and channel mismatch for forensic speaker verification systems. This method is based on suppressing various types of real environmental noise by using independent component analysis (ICA) algorithm. The enhanced speech signal is applied to mel frequency cepstral coefficients (MFCC) or MFCC feature warping to extract the essential characteristics of the speech signal. Channel effects are reduced using an intermediate vector (i-vector) and probabilistic linear discriminant analysis (PLDA) approach for classification. The proposed algorithm is evaluated by using an Australian forensic voice comparison database, combined with car, street and home noises from QUT-NOISE at a signal to noise ratio (SNR) ranging from -10 dB to 10 dB. Experimental results indicate that the MFCC feature warping-ICA achieves a reduction in equal error rate about (48.22%, 44.66%, and 50.07%) over using MFCC feature warping when the test speech signals are corrupted with random sessions of street, car, and home noises at -10 dB SNR.Keywords: noisy forensic speaker verification, ICA algorithm, MFCC, MFCC feature warping
Procedia PDF Downloads 4035752 Ecological and Cartographic Study of the Cork OAK of the Forest of Mahouna, North-Eastern of Algeria
Authors: Amina Beldjazia, Djamel Alatou, Khaled Missaoui
Abstract:
The forest of Mahouna is a part of the mountain range of the Tell Atlas in the northeast of Algeria. It is characterized by a significant biodiversity. The management of this resource requires thorough the understanding of the current state of the vegetation (inventories), degradation factors and ongoing monitoring of the various long-term ecological changes. Digital mapping is a very effective way to in-depth knowledge of natural resources. The realization of a vegetation map based on satellite images, aerial photographs and the use of geographic information system (GIS), shows large values results of the vegetation of the massif in the scientific view point (the development of a database of the different formations that exist on the site, ecological conditions) and economic (GIS facilitate our task of managing the various resources and diversity of the forest). The methodology is divided into three stages: the first involves an analysis of climate data (1988 to 2013); the second is to conduct field surveys (soil and phytoecological) during the months of June and July 2013 (10 readings), the third is based on the development of different themes and synthetic cards by software of GIS (ENVI 4.6 and 10 ARCMAP). The results show: cork oak covers an area of 1147 ha. Depending on the environmental conditions, it rests on sandstone and individualizes between 3 layers of vegetation from thermo-mediterranean (the North East part with 40ha), meso-Mediterranean (1061 ha) and finally the supra-Mediterranean (46ha ). The map shows the current actual state of the cork oak forest massif of Mahouna, it is an older forest (>150 years) where regeneration is absent because of several factors (fires, overgrazing, leaching, erosion, etc.). The cork oak is in the form of dense forest with Laburnum and heather as the dominant species. It may also present in open forest dominated by scrub species: Daphne gniduim, Erica arborea, Calycotome spinosa, Phillyrea angustifolia, Lavandula stoechas, Cistus salvifolius.Keywords: biodiversity, environmental, Mahouna, Cork oak
Procedia PDF Downloads 4365751 A Comparison of Single of Decision Tree, Decision Tree Forest and Group Method of Data Handling to Evaluate the Surface Roughness in Machining Process
Authors: S. Ghorbani, N. I. Polushin
Abstract:
The machinability of workpieces (AISI 1045 Steel, AA2024 aluminum alloy, A48-class30 gray cast iron) in turning operation has been carried out using different types of cutting tool (conventional, cutting tool with holes in toolholder and cutting tool filled up with composite material) under dry conditions on a turning machine at different stages of spindle speed (630-1000 rpm), feed rate (0.05-0.075 mm/rev), depth of cut (0.05-0.15 mm) and tool overhang (41-65 mm). Experimentation was performed as per Taguchi’s orthogonal array. To evaluate the relative importance of factors affecting surface roughness the single decision tree (SDT), Decision tree forest (DTF) and Group method of data handling (GMDH) were applied.Keywords: decision tree forest, GMDH, surface roughness, Taguchi method, turning process
Procedia PDF Downloads 4345750 A Fast Silhouette Detection Algorithm for Shadow Volumes in Augmented Reality
Authors: Hoshang Kolivand, Mahyar Kolivand, Mohd Shahrizal Sunar, Mohd Azhar M. Arsad
Abstract:
Real-time shadow generation in virtual environments and Augmented Reality (AR) was always a hot topic in the last three decades. Lots of calculation for shadow generation among AR needs a fast algorithm to overcome this issue and to be capable of implementing in any real-time rendering. In this paper, a silhouette detection algorithm is presented to generate shadows for AR systems. Δ+ algorithm is presented based on extending edges of occluders to recognize which edges are silhouettes in the case of real-time rendering. An accurate comparison between the proposed algorithm and current algorithms in silhouette detection is done to show the reduction calculation by presented algorithm. The algorithm is tested in both virtual environments and AR systems. We think that this algorithm has the potential to be a fundamental algorithm for shadow generation in all complex environments.Keywords: silhouette detection, shadow volumes, real-time shadows, rendering, augmented reality
Procedia PDF Downloads 4345749 An Enhanced Harmony Search (ENHS) Algorithm for Solving Optimization Problems
Authors: Talha A. Taj, Talha A. Khan, M. Imran Khalid
Abstract:
Optimization techniques attract researchers to formulate a problem and determine its optimum solution. This paper presents an Enhanced Harmony Search (ENHS) algorithm for solving optimization problems. The proposed algorithm increases the convergence and is more efficient than the standard Harmony Search (HS) algorithm. The paper discusses the novel techniques in detail and also provides the strategy for tuning the decisive parameters that affects the efficiency of the ENHS algorithm. The algorithm is tested on various benchmark functions, a real world optimization problem and a constrained objective function. Also, the results of ENHS are compared to standard HS, and various other optimization algorithms. The ENHS algorithms prove to be significantly better and more efficient than other algorithms. The simulation and testing of the algorithms is performed in MATLAB.Keywords: optimization, harmony search algorithm, MATLAB, electronic
Procedia PDF Downloads 4545748 A Novel Algorithm for Production Scheduling
Authors: Ali Mohammadi Bolban Abad, Fariborz Ahmadi
Abstract:
Optimization in manufacture is a method to use limited resources to obtain the best performance and reduce waste. In this paper a new algorithm based on eurygaster life is introduced to obtain a plane in which task order and completion time of resources are defined. Evaluation results show our approach has less make span when the resources are allocated with some products in comparison to genetic algorithm.Keywords: evolutionary computation, genetic algorithm, particle swarm optimization, NP-Hard problems, production scheduling
Procedia PDF Downloads 3705747 Downscaling Daily Temperature with Neuroevolutionary Algorithm
Authors: Min Shi
Abstract:
State of the art research with Artificial Neural Networks for the downscaling of General Circulation Models (GCMs) mainly uses back-propagation algorithm as a training approach. This paper introduces another training approach of ANNs, Evolutionary Algorithm. The combined algorithm names neuroevolutionary (NE) algorithm. We investigate and evaluate the use of the NE algorithms in statistical downscaling by generating temperature estimates at interior points given information from a lattice of surrounding locations. The results of our experiments indicate that NE algorithms can be efficient alternative downscaling methods for daily temperatures.Keywords: temperature, downscaling, artificial neural networks, evolutionary algorithms
Procedia PDF Downloads 3435746 Impacts of Present and Future Climate Variability on Forest Ecosystem in Mediterranean Region
Authors: Orkan Ozcan, Nebiye Musaoglu, Murat Turkes
Abstract:
Climate change is largely recognized as one of the real, pressing and significant global problems. The concept of ‘climate change vulnerability’ helps us to better comprehend the cause/effect relationships behind climate change and its impact on human societies, socioeconomic sectors, physiographical and ecological systems. In this study, multifactorial spatial modeling was applied to evaluate the vulnerability of a Mediterranean forest ecosystem to climate change. As a result, the geographical distribution of the final Environmental Vulnerability Areas (EVAs) of the forest ecosystem is based on the estimated final Environmental Vulnerability Index (EVI) values. This revealed that at current levels of environmental degradation, physical, geographical, policy enforcement and socioeconomic conditions, the area with a ‘very low’ vulnerability degree covered mainly the town, its surrounding settlements and the agricultural lands found mainly over the low and flat travertine plateau and the plains at the east and southeast of the district. The spatial magnitude of the EVAs over the forest ecosystem under the current environmental degradation was also determined. This revealed that the EVAs classed as ‘very low’ account for 21% of the total area of the forest ecosystem, those classed as ‘low’ account for 36%, those classed as ‘medium’ account for 20%, and those classed as ‘high’ account for 24%. Based on regionally averaged future climate assessments and projected future climate indicators, both the study site and the western Mediterranean sub-region of Turkey will probably become associated with a drier, hotter, more continental and more water-deficient climate. This analysis holds true for all future scenarios, with the exception of RCP4.5 for the period from 2015 to 2030. However, the present dry-sub humid climate dominating this sub-region and the study area shows a potential for change towards more dry climatology and for it to become a semiarid climate in the period between 2031 and 2050 according to the RCP8.5 high emission scenario. All the observed and estimated results and assessments summarized in the study show clearly that the densest forest ecosystem in the southern part of the study site, which is characterized by mainly Mediterranean coniferous and some mixed forest and the maquis vegetation, will very likely be influenced by medium and high degrees of vulnerability to future environmental degradation, climate change and variability.Keywords: forest ecosystem, Mediterranean climate, RCP scenarios, vulnerability analysis
Procedia PDF Downloads 3485745 Comparative Evaluation of Equity Indicators in the Matikiw Community-Based Forest Management Project in Pakil, Laguna and the Minayutan and Bacong Sigsigan Community-Based Forest Management Project in Famy, Laguna
Authors: Katherine Arquio
Abstract:
Community-based Forest Management (CBFM) is one of the integrative programs that slowly turned the course of forest management from traditional corporate to community-based practice resulting to people empowerment. As such, one of its goals is to promote socio-economic welfare among the people in the community in which social equity is included. This study aims to look at the equity aspect of the program, particularly if there are equity differences between two CBFM sites- Matikiw in Pakil, Laguna and Minayutan and Bacong Sigsigan in Famy, Laguna. Equity indicators were identified first, since these will be the basis of the questions that will be asked on the survey, after this, the survey proper was conducted, and finally, the analysis. Two tailed t-test was used as statistical tool since the difference between the two sites is the focus of the study. Statistical analysis was done through the use of STATA program, a statistical software. There were 32 indicators identified and results showed that, out of these indicators, only 13 were found significantly different between the two. The 13 indicators were significantly observed only in Matikiw; the other 19 indicators were commonly observed in both areas and are conducive as equity indicators for the CBFM program.Keywords: social equity, CBFM, social forestry, equity indicators
Procedia PDF Downloads 3715744 An Optimization Algorithm Based on Dynamic Schema with Dissimilarities and Similarities of Chromosomes
Authors: Radhwan Yousif Sedik Al-Jawadi
Abstract:
Optimization is necessary for finding appropriate solutions to a range of real-life problems. In particular, genetic (or more generally, evolutionary) algorithms have proved very useful in solving many problems for which analytical solutions are not available. In this paper, we present an optimization algorithm called Dynamic Schema with Dissimilarity and Similarity of Chromosomes (DSDSC) which is a variant of the classical genetic algorithm. This approach constructs new chromosomes from a schema and pairs of existing ones by exploring their dissimilarities and similarities. To show the effectiveness of the algorithm, it is tested and compared with the classical GA, on 15 two-dimensional optimization problems taken from literature. We have found that, in most cases, our method is better than the classical genetic algorithm.Keywords: chromosome injection, dynamic schema, genetic algorithm, similarity and dissimilarity
Procedia PDF Downloads 3345743 Simulation Approach for a Comparison of Linked Cluster Algorithm and Clusterhead Size Algorithm in Ad Hoc Networks
Authors: Ameen Jameel Alawneh
Abstract:
A Mobile ad-hoc network (MANET) is a collection of wireless mobile hosts that dynamically form a temporary network without the aid of a system administrator. It has neither fixed infrastructure nor wireless ad hoc sessions. It inherently reaches several nodes with a single transmission, and each node functions as both a host and a router. The network maybe represented as a set of clusters each managed by clusterhead. The cluster size is not fixed and it depends on the movement of nodes. We proposed a clusterhead size algorithm (CHSize). This clustering algorithm can be used by several routing algorithms for ad hoc networks. An elected clusterhead is assigned for communication with all other clusters. Analysis and simulation of the algorithm has been implemented using GloMoSim networks simulator, MATLAB and MAPL11 proved that the proposed algorithm achieves the goals.Keywords: simulation, MANET, Ad-hoc, cluster head size, linked cluster algorithm, loss and dropped packets
Procedia PDF Downloads 387