Search results for: Hybrid Algorithms.

Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li

Abstract:

The widespread popularity of mobile devices and the development of artificial intelligence (AI) have led to the widespread adoption of deep learning (DL) in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace, a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Additionally, we propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. Using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We conduct an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace outperformed FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.

Keywords: Mobile computing, deep learning apps, sensitive information, static analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 596

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: Deep learning, field programmable gate array, FPGA, hardware acceleration, convolutional neural networks, CNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 895

Authors: Victor Krebss

Abstract:

Task of object localization is one of the major challenges in creating intelligent transportation. Unfortunately, in densely built-up urban areas, localization based on GPS only produces a large error, or simply becomes impossible. New opportunities arise for the localization due to the rapidly emerging concept of a wireless ad-hoc network. Such network, allows estimating potential distance between these objects measuring received signal level and construct a graph of distances in which nodes are the localization objects, and edges - estimates of the distances between pairs of nodes. Due to the known coordinates of individual nodes (anchors), it is possible to determine the location of all (or part) of the remaining nodes of the graph. Moreover, road map, available in digital format can provide localization routines with valuable additional information to narrow node location search. However, despite abundance of well-known algorithms for solving the problem of localization and significant research efforts, there are still many issues that currently are addressed only partially. In this paper, we propose localization approach based on the graph mapped distances on the digital road map data basis. In fact, problem is reduced to distance graph embedding into the graph representing area geo location data. It makes possible to localize objects, in some cases even if only one reference point is available. We propose simple embedding algorithm and sample implementation as spatial queries over sensor network data stored in spatial database, allowing employing effectively spatial indexing, optimized spatial search routines and geometry functions.

Keywords: Intelligent Transportation System, Sensor Network, Localization, Spatial Query, GIS, Graph Embedding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1535

Authors: S. Rao Rayapudi

Abstract:

Economic Load Dispatch (ELD) is a method of determining the most efficient, low-cost and reliable operation of a power system by dispatching available electricity generation resources to supply load on the system. The primary objective of economic dispatch is to minimize total cost of generation while honoring operational constraints of available generation resources. In this paper an intelligent water drop (IWD) algorithm has been proposed to solve ELD problem with an objective of minimizing the total cost of generation. Intelligent water drop algorithm is a swarm-based natureinspired optimization algorithm, which has been inspired from natural rivers. A natural river often finds good paths among lots of possible paths in its ways from source to destination and finally find almost optimal path to their destination. These ideas are embedded into the proposed algorithm for solving economic load dispatch problem. The main advantage of the proposed technique is easy is implement and capable of finding feasible near global optimal solution with less computational effort. In order to illustrate the effectiveness of the proposed method, it has been tested on 6-unit and 20-unit test systems with incremental fuel cost functions taking into account the valve point-point loading effects. Numerical results shows that the proposed method has good convergence property and better in quality of solution than other algorithms reported in recent literature.

Keywords: Economic load dispatch, Transmission loss, Optimization, Valve point loading, Intelligent Water Drop Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3629

Authors: V Krishnaveni, S Jayaraman, A Gunasekaran, K Ramadoss

Abstract:

The ElectroEncephaloGram (EEG) is useful for clinical diagnosis and biomedical research. EEG signals often contain strong ElectroOculoGram (EOG) artifacts produced by eye movements and eye blinks especially in EEG recorded from frontal channels. These artifacts obscure the underlying brain activity, making its visual or automated inspection difficult. The goal of ocular artifact removal is to remove ocular artifacts from the recorded EEG, leaving the underlying background signals due to brain activity. In recent times, Independent Component Analysis (ICA) algorithms have demonstrated superior potential in obtaining the least dependent source components. In this paper, the independent components are obtained by using the JADE algorithm (best separating algorithm) and are classified into either artifact component or neural component. Neural Network is used for the classification of the obtained independent components. Neural Network requires input features that exactly represent the true character of the input signals so that the neural network could classify the signals based on those key characters that differentiate between various signals. In this work, Auto Regressive (AR) coefficients are used as the input features for classification. Two neural network approaches are used to learn classification rules from EEG data. First, a Polynomial Neural Network (PNN) trained by GMDH (Group Method of Data Handling) algorithm is used and secondly, feed-forward neural network classifier trained by a standard back-propagation algorithm is used for classification and the results show that JADE-FNN performs better than JADEPNN.

Keywords: Auto Regressive (AR) Coefficients, Feed Forward Neural Network (FNN), Joint Approximation Diagonalisation of Eigen matrices (JADE) Algorithm, Polynomial Neural Network (PNN).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1889

Authors: Vijaya K. Srivastava, Davide Spinello

Abstract:

This paper presents performance of two robust gradient-based heuristic optimization procedures based on 3ⁿ enumeration and tunneling approach to seek global optimum of constrained integer problems. Both these procedures consist of two distinct phases for locating the global optimum of integer problems with a linear or non-linear objective function subject to linear or non-linear constraints. In both procedures, in the first phase, a local minimum of the function is found using the gradient approach coupled with hemstitching moves when a constraint is violated in order to return the search to the feasible region. In the second phase, in one optimization procedure, the second sub-procedure examines 3ⁿ integer combinations on the boundary and within hypercube volume encompassing the result neighboring the result from the first phase and in the second optimization procedure a tunneling function is constructed at the local minimum of the first phase so as to find another point on the other side of the barrier where the function value is approximately the same. In the next cycle, the search for the global optimum commences in both optimization procedures again using this new-found point as the starting vector. The search continues and repeated for various step sizes along the function gradient as well as that along the vector normal to the violated constraints until no improvement in optimum value is found. The results from both these proposed optimization methods are presented and compared with one provided by popular MS Excel solver that is provided within MS Office suite and other published results.

Keywords: Constrained integer problems, enumerative search algorithm, Heuristic algorithm, tunneling algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 800

Authors: First G.M. Karthik, Second Ramachandra.V.Pujeri, Dr.

Abstract:

Generalized Center String (GCS) problem are generalized from Common Approximate Substring problem and Common substring problems. GCS are known to be NP-hard allowing the problems lies in the explosion of potential candidates. Finding longest center string without concerning the sequence that may not contain any motifs is not known in advance in any particular biological gene process. GCS solved by frequent pattern-mining techniques and known to be fixed parameter tractable based on the fixed input sequence length and symbol set size. Efficient method known as Bpriori algorithms can solve GCS with reasonable time/space complexities. Bpriori 2 and Bpriori 3-2 algorithm are been proposed of any length and any positions of all their instances in input sequences. In this paper, we reduced the time/space complexity of Bpriori algorithm by Constrained Based Frequent Pattern mining (CBFP) technique which integrates the idea of Constraint Based Mining and FP-tree mining. CBFP mining technique solves the GCS problem works for all center string of any length, but also for the positions of all their mutated copies of input sequence. CBFP mining technique construct TRIE like with FP tree to represent the mutated copies of center string of any length, along with constraints to restraint growth of the consensus tree. The complexity analysis for Constrained Based FP mining technique and Bpriori algorithm is done based on the worst case and average case approach. Algorithm's correctness compared with the Bpriori algorithm using artificial data is shown.

Keywords: Constraint Based Mining, FP tree, Data mining, GCS problem, CBFP mining technique.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1702

Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride

Abstract:

In this work, we use machine learning and data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. Our work applies modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.

Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 449

Authors: Satyanadh Gundimada, Vijayan K Asari

Abstract:

A novel feature selection strategy to improve the recognition accuracy on the faces that are affected due to nonuniform illumination, partial occlusions and varying expressions is proposed in this paper. This technique is applicable especially in scenarios where the possibility of obtaining a reliable intra-class probability distribution is minimal due to fewer numbers of training samples. Phase congruency features in an image are defined as the points where the Fourier components of that image are maximally inphase. These features are invariant to brightness and contrast of the image under consideration. This property allows to achieve the goal of lighting invariant face recognition. Phase congruency maps of the training samples are generated and a novel modular feature selection strategy is implemented. Smaller sub regions from a predefined neighborhood within the phase congruency images of the training samples are merged to obtain a large set of features. These features are arranged in the order of increasing distance between the sub regions involved in merging. The assumption behind the proposed implementation of the region merging and arrangement strategy is that, local dependencies among the pixels are more important than global dependencies. The obtained feature sets are then arranged in the decreasing order of discriminating capability using a criterion function, which is the ratio of the between class variance to the within class variance of the sample set, in the PCA domain. The results indicate high improvement in the classification performance compared to baseline algorithms.

Keywords: Discriminant analysis, intra-class probability distribution, principal component analysis, phase congruency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1850

Authors: Ahmed El Azab, Amira M. Idrees, Mahmoud A. Mahmoud, Hesham Hefny

Abstract:

Social networking sites such as Twitter and Facebook attracts over 500 million users across the world, for those users, their social life, even their practical life, has become interrelated. Their interaction with social networking has affected their life forever. Accordingly, social networking sites have become among the main channels that are responsible for vast dissemination of different kinds of information during real time events. This popularity in Social networking has led to different problems including the possibility of exposing incorrect information to their users through fake accounts which results to the spread of malicious content during life events. This situation can result to a huge damage in the real world to the society in general including citizens, business entities, and others. In this paper, we present a classification method for detecting the fake accounts on Twitter. The study determines the minimized set of the main factors that influence the detection of the fake accounts on Twitter, and then the determined factors are applied using different classification techniques. A comparison of the results of these techniques has been performed and the most accurate algorithm is selected according to the accuracy of the results. The study has been compared with different recent researches in the same area; this comparison has proved the accuracy of the proposed study. We claim that this study can be continuously applied on Twitter social network to automatically detect the fake accounts; moreover, the study can be applied on different social network sites such as Facebook with minor changes according to the nature of the social network which are discussed in this paper.

Keywords: Fake accounts detection, classification algorithms, twitter accounts analysis, features based techniques.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5837

Authors: Heiko Weiß, Andreas Meister, Christoph Ament, Nils Dreifke

Abstract:

Linear actuators are deployed in a wide range of applications. This paper presents the modeling and system identification of a variable excited linear direct drive (LDD). The LDD is designed based on linear hybrid stepper technology exhibiting the characteristic tooth structure of mover and stator. A three-phase topology provides the thrust force caused by alternating strengthening and weakening of the flux of the legs. To achieve best possible synchronous operation, the phases are commutated sinusoidal. Despite the fact that these LDDs provide high dynamics and drive forces, noise emission limits their operation in calm workspaces. To overcome this drawback an additional excitation of the magnetic circuit is introduced to LDD using additional enabling coils instead of permanent magnets. The new degree of freedom can be used to reduce force variations and related noise by varying the excitation flux that is usually generated by permanent magnets. Hence, an identified simulation model is necessary to analyze the effects of this modification. Especially the force variations must be modeled well in order to reduce them sufficiently. The model can be divided into three parts: the current dynamics, the mechanics and the force functions. These subsystems are described with differential equations or nonlinear analytic functions, respectively. Ordinary nonlinear differential equations are derived and transformed into state space representation. Experiments have been carried out on a test rig to identify the system parameters of the complete model. Static and dynamic simulation based optimizations are utilized for identification. The results are verified in time and frequency domain. Finally, the identified model provides a basis for later design of control strategies to reduce existing force variations.

Keywords: Force variations, linear direct drive, modeling and system identification, variable excitation flux.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1033

Authors: Makhlouf Mourad, Messabih Sidi Mohamed, Bouchher Omar, Houali Farida, Benrachedi Khaled

Abstract:

Mesoporous materials are very commonly used as adsorbent materials for removing phenolic compounds. However, the adsorption mechanism of these compounds is still poorly controlled. However, understanding the interactions mesoporous materials/adsorbed molecules is very important in order to optimize the processes of liquid phase adsorption. The difficulty of synthesis is to keep an orderly and cubic pore structure and achieve a homogeneous surface modification. The grafting of Si(CH₃)₃ was chosen, to transform hydrophilic surfaces hydrophobic surfaces. The aim of this work is to study the kinetics and thermodynamics of two volatile organic compounds VOC phenol (PhOH) and P hydroxy benzoic acid (4AHB) on a mesoporous material of type MCM-48 grafted with an organosilane of the Trimethylchlorosilane (TMCS) type, the material thus grafted or functionalized (hereinafter referred to as MCM-48-G). In a first step, the kinetic and thermodynamic study of the adsorption isotherms of each of the VOCs in mono-solution was carried out. In a second step, a similar study was carried out on a mixture of these two compounds. Kinetic models (pseudo-first order, pseudo-second order) were used to determine kinetic adsorption parameters. The thermodynamic parameters of the adsorption isotherms were determined by the adsorption models (Langmuir, Freundlich). The comparative study of adsorption of PhOH and 4AHB proved that MCM-48-G had a high adsorption capacity for PhOH and 4AHB; this may be related to the hydrophobicity created by the organic function of TMCS in MCM-48-G. The adsorption results for the two compounds using the Freundlich and Langmuir models show that the adsorption of 4AHB was higher than PhOH. The values ​​obtained by the adsorption thermodynamics show that the adsorption interactions for our sample with the phenol and 4AHB are of a physical nature. The adsorption of our VOCs on the MCM-48 (G) is a spontaneous and exothermic process.

Keywords: Adsorption, kinetics, isotherm, mesoporous materials, TMCS, phenol, P-hydroxy benzoic acid.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 800

Authors: Hamidreza Hoshyarmanesh, Hosein Madieh, Sanju Lama, Yaser Maddahi, Garnette R. Sutherland, Kourosh Zareinia

Abstract:

This paper illustrates the concept of an algorithm to register specified markers on the neuroArm surgical manipulators, an image-guided MR-compatible tele-operated robot for microsurgery and stereotaxy. Two range-finding algorithms, namely time-of-flight and phase-shift, are evaluated for registration and supervisory control. The time-of-flight approach is implemented in a semi-field experiment to determine the precise position of a tiny retro-reflective moving object. The moving object simulates a surgical tool tip. The tool is a target that would be connected to the neuroArm end-effector during surgery inside the magnet bore of the MR imaging system. In order to apply flight approach, a 905-nm pulsed laser diode and an avalanche photodiode are utilized as the transmitter and receiver, respectively. For the experiment, a high frequency time to digital converter was designed using a field-programmable gate arrays. In the phase-shift approach, a continuous green laser beam with a wavelength of 530 nm was used as the transmitter. Results showed that a positioning error of 0.1 mm occurred when the scanner-target point distance was set in the range of 2.5 to 3 meters. The effectiveness of this non-contact approach exhibited that the method could be employed as an alternative for conventional mechanical registration arm. Furthermore, the approach is not limited by physical contact and extension of joint angles.

Keywords: 3D laser scanner, intraoperative MR imaging, neuroArm, real time registration, robot-assisted surgery, supervisory control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1061

Authors: Vitomir Struc, Nikola Pavesic

Abstract:

Over the past decades, automatic face recognition has become a highly active research area, mainly due to the countless application possibilities in both the private as well as the public sector. Numerous algorithms have been proposed in the literature to cope with the problem of face recognition, nevertheless, a group of methods commonly referred to as appearance based have emerged as the dominant solution to the face recognition problem. Many comparative studies concerned with the performance of appearance based methods have already been presented in the literature, not rarely with inconclusive and often with contradictory results. No consent has been reached within the scientific community regarding the relative ranking of the efficiency of appearance based methods for the face recognition task, let alone regarding their susceptibility to appearance changes induced by various environmental factors. To tackle these open issues, this paper assess the performance of the three dominant appearance based methods: principal component analysis, linear discriminant analysis and independent component analysis, and compares them on equal footing (i.e., with the same preprocessing procedure, with optimized parameters for the best possible performance, etc.) in face verification experiments on the publicly available XM2VTS database. In addition to the comparative analysis on the XM2VTS database, ten degraded versions of the database are also employed in the experiments to evaluate the susceptibility of the appearance based methods on various image degradations which can occur in "real-life" operating conditions. Our experimental results suggest that linear discriminant analysis ensures the most consistent verification rates across the tested databases.

Keywords: Biometrics, face recognition, appearance based methods, image degradations, the XM2VTS database.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2284

Authors: Roberto Sabatini, Alessandro Gardi, Mark A. Richardson

Abstract:

The availability of powerful eye-safe laser sources and the recent advancements in electro-optical and mechanical beam-steering components have allowed laser-based Light Detection and Ranging (LIDAR) to become a promising technology for obstacle warning and avoidance in a variety of manned and unmanned aircraft applications. LIDAR outstanding angular resolution and accuracy characteristics are coupled to its good detection performance in a wide range of incidence angles and weather conditions, providing an ideal obstacle avoidance solution, which is especially attractive in low-level flying platforms such as helicopters and small-to-medium size Unmanned Aircraft (UA). The Laser Obstacle Avoidance Marconi (LOAM) system is one of such systems, which was jointly developed and tested by SELEX-ES and the Italian Air Force Research and Flight Test Centre. The system was originally conceived for military rotorcraft platforms and, in this paper, we briefly review the previous work and discuss in more details some of the key development activities required for integration of LOAM on UA platforms. The main hardware and software design features of this LOAM variant are presented, including a brief description of the system interfaces and sensor characteristics, together with the system performance models and data processing algorithms for obstacle detection, classification and avoidance. In particular, the paper focuses on the algorithm proposed for optimal avoidance trajectory generation in UA applications.

Keywords: LIDAR, Low-Level Flight, Nap-of-the-Earth Flight, Near Infra-Red, Obstacle Avoidance, Obstacle Detection, Obstacle Warning System, Sense and Avoid, Trajectory Optimisation, Unmanned Aircraft.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 7085

Authors: Mylena McCoggle, Shyra Wilson, Andrea Rivera, Rocio Alba-Flores, Valentin Soloiu

Abstract:

This work describes a system that uses electromyography (EMG) signals obtained from muscle sensors and an Artificial Neural Network (ANN) for signal classification and pattern recognition that is used to control a small unmanned aerial vehicle using specific arm movements. The main objective of this endeavor is the development of an intelligent interface that allows the user to control the flight of a drone beyond direct manual control. The sensor used were the MyoWare Muscle sensor which contains two EMG electrodes used to collect signals from the posterior (extensor) and anterior (flexor) forearm, and the bicep. The collection of the raw signals from each sensor was performed using an Arduino Uno. Data processing algorithms were developed with the purpose of classifying the signals generated by the arm’s muscles when performing specific movements, namely: flexing, resting, and motion of the arm. With these arm motions roll control of the drone was achieved. MATLAB software was utilized to condition the signals and prepare them for the classification. To generate the input vector for the ANN and perform the classification, the root mean square and the standard deviation were processed for the signals from each electrode. The neuromuscular information was trained using an ANN with a single 10 neurons hidden layer to categorize the four targets. The result of the classification shows that an accuracy of 97.5% was obtained. Afterwards, classification results are used to generate the appropriate control signals from the computer to the drone through a Wi-Fi network connection. These procedures were successfully tested, where the drone responded successfully in real time to the commanded inputs.

Keywords: Biosensors, electromyography, Artificial Neural Network, Arduino, drone flight control, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 555

Authors: Blessing Ojeme, Frederick Quinn, Russell Karls, Shannon Quinn

Abstract:

The detection and segmentation of mitochondria from fluorescence microscopy is crucial for understanding the complex structure of the nervous system. However, the constant fission and fusion of mitochondria and image distortion in the background make the task of detection and segmentation challenging. Although there exists a number of open-source software tools and artificial intelligence (AI) methods designed for analyzing mitochondrial images, the availability of only a few combined expertise in the medical field and AI required to utilize these tools poses a challenge to its full adoption and use in clinical settings. Motivated by the advantages of automated methods in terms of good performance, minimum detection time, ease of implementation, and cross-platform compactibility, this study proposes a fully automated framework for the detection and segmentation of mitochondria using both image shape information and descriptive statistics. Using the low-cost, open-source Python and OpenCV library, the algorithms are implemented in three stages: pre-processing; image binarization; and coarse-to-fine segmentation. The proposed model is validated using the fluorescence mitochondrial dataset. Ground truth labels generated using Labkit were also used to evaluate the performance of our detection and segmentation model using precision, recall and rand index. The study produces good detection and segmentation results and reports the challenges encountered during the image analysis of mitochondrial morphology from the fluorescence mitochondrial dataset. A discussion on the methods and future perspectives of fully automated frameworks concludes the paper.

Keywords: 2D, Binarization, CLAHE, detection, fluorescence microscopy, mitochondria, segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 465

Authors: H. Juma, F. Al-hujaili, R. Kashani

Abstract:

Modern structures such as floor systems, pedestrian bridges and high-rise buildings have become lighter in mass and more flexible with negligible damping and thus prone to vibration. In this paper, a semi-actively controlled pendulum tuned mass dampers (PTMD) is presented that uses air springs as both the restoring (resilient) and energy dissipating (damping) elements; the tuned mass damper (TMD) uses no passive dampers. The proposed PTMD can readily be fine-tuned and re-tuned, via software, without changing any hardware. Almost all existing semi-active systems have the three elements that passive TMDs have, i.e., inertia, resilient, and dissipative elements with some adjustability built into one or two of these elements. The proposed semi-active air suspended TMD, on the other hand, is made up of only inertia and resilience elements. A notable feature of this TMD is the absence of a physical damping element in its make-up. The required viscous damping is introduced into the TMD using a semi-active control scheme residing in a micro-controller which actuates a high-speed proportional valve regulating the flow of air in and out of the air springs. In addition to introducing damping into the TMD, the semi-active control scheme adjusts the stiffness of the TMD. The focus of this work has been the synthesis and analysis of the control algorithms and strategies to vary the tuning accuracy, introduce damping into air suspended PTMD, and enable the PTMD to self-tune itself. The accelerations of the main structure and PTMD as well as the pressure in the air springs are used as the feedback signals in control strategies. Numerical simulation and experimental evaluation of the proposed tuned damping system are presented in this paper.

Keywords: Tuned mass damper, air spring, semi-active, vibration control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 656

Authors: Shilpy Sharma

Abstract:

As the web continues to grow exponentially, the idea of crawling the entire web on a regular basis becomes less and less feasible, so the need to include information on specific domain, domain-specific search engines was proposed. As more information becomes available on the World Wide Web, it becomes more difficult to provide effective search tools for information access. Today, people access web information through two main kinds of search interfaces: Browsers (clicking and following hyperlinks) and Query Engines (queries in the form of a set of keywords showing the topic of interest) [2]. Better support is needed for expressing one's information need and returning high quality search results by web search tools. There appears to be a need for systems that do reasoning under uncertainty and are flexible enough to recover from the contradictions, inconsistencies, and irregularities that such reasoning involves. In a multi-view problem, the features of the domain can be partitioned into disjoint subsets (views) that are sufficient to learn the target concept. Semi-supervised, multi-view algorithms, which reduce the amount of labeled data required for learning, rely on the assumptions that the views are compatible and uncorrelated. This paper describes the use of semi-structured machine learning approach with Active learning for the “Domain Specific Search Engines". A domain-specific search engine is “An information access system that allows access to all the information on the web that is relevant to a particular domain. The proposed work shows that with the help of this approach relevant data can be extracted with the minimum queries fired by the user. It requires small number of labeled data and pool of unlabelled data on which the learning algorithm is applied to extract the required data.

Keywords: Search engines; machine learning, Informationretrieval, Active logic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2083

Authors: Sylvain Amailland, Jean-Hugh Thomas, Charles Pézerat, Romuald Boucheron, Jean-Claude Pascal

Abstract:

The noise requirements for naval and research vessels have seen an increasing demand for quieter ships in order to fulfil current regulations and to reduce the effects on marine life. Hence, new methods dedicated to the characterization of propeller noise, which is the main source of noise in the far-field, are needed. The study of cavitating propellers in closed-section is interesting for analyzing hydrodynamic performance but could involve significant difficulties for hydroacoustic study, especially due to reverberation and boundary layer noise in the tunnel. The aim of this paper is to present a numerical methodology for the identification of hydroacoustic sources on marine propellers using hydrophone arrays in a large hydrodynamic tunnel. The main difficulties are linked to the reverberation of the tunnel and the boundary layer noise that strongly reduce the signal-to-noise ratio. In this paper it is proposed to estimate the reflection coefficients using an inverse method and some reference transfer functions measured in the tunnel. This approach allows to reduce the uncertainties of the propagation model used in the inverse problem. In order to reduce the boundary layer noise, a cleaning algorithm taking advantage of the low rank and sparse structure of the cross-spectrum matrices of the acoustic and the boundary layer noise is presented. This approach allows to recover the acoustic signal even well under the boundary layer noise. The improvement brought by this method is visible on acoustic maps resulting from beamforming and DAMAS algorithms.

Keywords: Acoustic imaging, boundary layer noise denoising, inverse problems, model adaptation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 974

Authors: Rashima Mahajan, Dipali Bansal, Shweta Singh

Abstract:

Real time non-invasive Brain Computer Interfaces have a significant progressive role in restoring or maintaining a quality life for medically challenged people. This manuscript provides a comprehensive review of emerging research in the field of cognitive/affective computing in context of human neural responses. The perspectives of different emotion assessment modalities like face expressions, speech, text, gestures, and human physiological responses have also been discussed. Focus has been paid to explore the ability of EEG (Electroencephalogram) signals to portray thoughts, feelings, and unspoken words. An automated workflow-based protocol to design an EEG-based real time Brain Computer Interface system for analysis and classification of human emotions elicited by external audio/visual stimuli has been proposed. The front end hardware includes a cost effective and portable Emotiv EEG Neuroheadset unit, a personal computer and a set of external stimulators. Primary signal analysis and processing of real time acquired EEG shall be performed using MATLAB based advanced brain mapping toolbox EEGLab/BCILab. This shall be followed by the development of MATLAB based self-defined algorithm to capture and characterize temporal and spectral variations in EEG under emotional stimulations. The extracted hybrid feature set shall be used to classify emotional states using artificial intelligence tools like Artificial Neural Network. The final system would result in an inexpensive, portable and more intuitive Brain Computer Interface in real time scenario to control prosthetic devices by translating different brain states into operative control signals.

Keywords: Brain Computer Interface (BCI), Electroencephalogram (EEG), EEGLab, BCILab, Emotiv, Emotions, Interval features, Spectral features, Artificial Neural Network, Control applications.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5297

Authors: Theerawat Songyot, Tham Manjing, Bunyarit Uyyanonvara, Chanjira Sinthanayothin

Abstract:

Corner detection and optical flow are common techniques for feature-based video stabilization. However, these algorithms are computationally expensive and should be performed at a reasonable rate. This paper presents an algorithm for discarding irrelevant feature points and maintaining them for future use so as to improve the computational cost. The algorithm starts by initializing a maintained set. The feature points in the maintained set are examined against its accuracy for modeling. Corner detection is required only when the feature points are insufficiently accurate for future modeling. Then, optical flows are computed from the maintained feature points toward the consecutive frame. After that, a motion model is estimated based on the simplified affine motion model and least square method, with outliers belonging to moving objects presented. Studentized residuals are used to eliminate such outliers. The model estimation and elimination processes repeat until no more outliers are identified. Finally, the entire algorithm repeats along the video sequence with the points remaining from the previous iteration used as the maintained set. As a practical application, an efficient video stabilization can be achieved by exploiting the computed motion models. Our study shows that the number of times corner detection needs to perform is greatly reduced, thus significantly improving the computational cost. Moreover, optical flow vectors are computed for only the maintained feature points, not for outliers, thus also reducing the computational cost. In addition, the feature points after reduction can sufficiently be used for background objects tracking as demonstrated in the simple video stabilizer based on our proposed algorithm.

Keywords: background object tracking, feature point reduction, low cost tracking, video stabilization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1767

Authors: Sanghoon Kim, Sun-Tae Chung, Souhwan Jung, Dusik Oh, Jaemin Kim, Seongwon Cho

Abstract:

Eye localization is necessary for face recognition and related application areas. Most of eye localization algorithms reported so far still need to be improved about precision and computational time for successful applications. In this paper, we propose an eye location method based on multi-scale Gabor feature vectors, which is more robust with respect to initial points. The eye localization based on Gabor feature vectors first needs to constructs an Eye Model Bunch for each eye (left or right eye) which consists of n Gabor jets and average eye coordinates of each eyes obtained from n model face images, and then tries to localize eyes in an incoming face image by utilizing the fact that the true eye coordinates is most likely to be very close to the position where the Gabor jet will have the best Gabor jet similarity matching with a Gabor jet in the Eye Model Bunch. Similar ideas have been already proposed in such as EBGM (Elastic Bunch Graph Matching). However, the method used in EBGM is known to be not robust with respect to initial values and may need extensive search range for achieving the required performance, but extensive search ranges will cause much more computational burden. In this paper, we propose a multi-scale approach with a little increased computational burden where one first tries to localize eyes based on Gabor feature vectors in a coarse face image obtained from down sampling of the original face image, and then localize eyes based on Gabor feature vectors in the original resolution face image by using the eye coordinates localized in the coarse scaled image as initial points. Several experiments and comparisons with other eye localization methods reported in the other papers show the efficiency of our proposed method.

Keywords: Eye Localization, Gabor features, Multi-scale, Gabor wavelets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1821

Authors: A. K. Prajapati

Abstract:

In this paper, the periodic surveillance scheme has been proposed for any convex region using mobile wireless sensor nodes. A sensor network typically consists of fixed number of sensor nodes which report the measurements of sensed data such as temperature, pressure, humidity, etc., of its immediate proximity (the area within its sensing range). For the purpose of sensing an area of interest, there are adequate number of fixed sensor nodes required to cover the entire region of interest. It implies that the number of fixed sensor nodes required to cover a given area will depend on the sensing range of the sensor as well as deployment strategies employed. It is assumed that the sensors to be mobile within the region of surveillance, can be mounted on moving bodies like robots or vehicle. Therefore, in our scheme, the surveillance time period determines the number of sensor nodes required to be deployed in the region of interest. The proposed scheme comprises of three algorithms namely: Hexagonalization, Clustering, and Scheduling, The first algorithm partitions the coverage area into fixed sized hexagons that approximate the sensing range (cell) of individual sensor node. The clustering algorithm groups the cells into clusters, each of which will be covered by a single sensor node. The later determines a schedule for each sensor to serve its respective cluster. Each sensor node traverses all the cells belonging to the cluster assigned to it by oscillating between the first and the last cell for the duration of its life time. Simulation results show that our scheme provides full coverage within a given period of time using few sensors with minimum movement, less power consumption, and relatively less infrastructure cost.

Keywords: Sensor Network, Graph Theory, MSN, Communication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1464

Authors: F. M. Pisano, M. Ciminello

Abstract:

Aerospace, mechanical, and civil engineering infrastructures can take advantages from damage detection and identification strategies in terms of maintenance cost reduction and operational life improvements, as well for safety scopes. The challenge is to detect so called “barely visible impact damage” (BVID), due to low/medium energy impacts, that can progressively compromise the structure integrity. The occurrence of any local change in material properties, that can degrade the structure performance, is to be monitored using so called Structural Health Monitoring (SHM) systems, in charge of comparing the structure states before and after damage occurs. SHM seeks for any "anomalous" response collected by means of sensor networks and then analyzed using appropriate algorithms. Independently of the specific analysis approach adopted for structural damage detection and localization, textual reports, tables and graphs describing possible outlier coordinates and damage severity are usually provided as artifacts to be elaborated for information extraction about the current health conditions of the structure under investigation. Visual Analytics can support the processing of monitored measurements offering data navigation and exploration tools leveraging the native human capabilities of understanding images faster than texts and tables. Herein, a SHM system enrichment by integration of a Visual Analytics component is investigated. Analytical dashboards have been created by combining worksheets, so that a useful Visual Analytics tool is provided to structural analysts for exploring the structure health conditions examined by a Principal Component Analysis based algorithm.

Keywords: Interactive dashboards, optical fibers, structural health monitoring, visual analytics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 829

Authors: Ashly Joseph, Jithu Paulose

Abstract:

Large language models (LLMs) have revolutionized natural language processing capabilities, enabling applications such as chatbots, dialogue agents, image, and video generators. Nevertheless, their trainings on extensive datasets comprising personal information poses notable privacy and safety hazards. This study examines methods for addressing these challenges, specifically focusing on approaches to enhance the security of LLM outputs, safeguard user privacy, and adhere to data protection rules. We explore several methods including post-processing detection algorithms, content filtering, reinforcement learning from human and AI inputs, and the difficulties in maintaining a balance between model safety and performance. The study also emphasizes the dangers of unintentional data leakage, privacy issues related to user prompts, and the possibility of data breaches. We highlight the significance of corporate data governance rules and optimal methods for engaging with chatbots. In addition, we analyze the development of data protection frameworks, evaluate the adherence of LLMs to General Data Protection Regulation (GDPR), and examine privacy legislation in academic and business policies. We demonstrate the difficulties and remedies involved in preserving data privacy and security in the age of sophisticated artificial intelligence by employing case studies and real-life instances. This article seeks to educate stakeholders on practical strategies for improving the security and privacy of LLMs, while also assuring their responsible and ethical implementation.

Keywords: Data privacy, large language models, artificial intelligence, machine learning, cybersecurity, general data protection regulation, data safety.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 104

Authors: D. Zare, H. Naderi, A. A. Jafari

Abstract:

Drying characteristics of rough rice (variety of lenjan) with an initial moisture content of 25% dry basis (db) was studied in a hot air dryer assisted by infrared heating. Three arrival air temperatures (30, 40 and 500C) and four infrared radiation intensities (0, 0.2 , 0.4 and 0.6 W/cm2) and three arrival air speeds (0.1, 0.15 and 0.2 m.s-1) were studied. Bending strength of brown rice kernel, percentage of cracked kernels and time of drying were measured and evaluated. The results showed that increasing the drying arrival air temperature and radiation intensity of infrared resulted decrease in drying time. High bending strength and low percentage of cracked kernel was obtained when paddy was dried by hot air assisted infrared dryer. Between this factors and their interactive effect were a significant difference (p<0.01). An intensity level of 0.2 W/cm2 was found to be optimum for radiation drying. Furthermore, in the present study, the application of Artificial Neural Network (ANN) for predicting the moisture content during drying (output parameter for ANN modeling) was investigated. Infrared Radiation intensity, drying air temperature, arrival air speed and drying time were considered as input parameters for the model. An ANN model with two hidden layers with 8 and 14 neurons were selected for studying the influence of transfer functions and training algorithms. The results revealed that a network with the Tansig (hyperbolic tangent sigmoid) transfer function and trainlm (Levenberg-Marquardt) back propagation algorithm made the most accurate predictions for the paddy drying system. Mean square error (MSE) was calculated and found that the random errors were within and acceptable range of ±5% with coefficient of determination (R2) of 99%.

Keywords: Rough rice, Infrared-hot air, Artificial Neural Network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1826

Authors: Florin Pop

Abstract:

Simulation is a very powerful method used for highperformance and high-quality design in distributed system, and now maybe the only one, considering the heterogeneity, complexity and cost of distributed systems. In Grid environments, foe example, it is hard and even impossible to perform scheduler performance evaluation in a repeatable and controllable manner as resources and users are distributed across multiple organizations with their own policies. In addition, Grid test-beds are limited and creating an adequately-sized test-bed is expensive and time consuming. Scalability, reliability and fault-tolerance become important requirements for distributed systems in order to support distributed computation. A distributed system with such characteristics is called dependable. Large environments, like Cloud, offer unique advantages, such as low cost, dependability and satisfy QoS for all users. Resource management in large environments address performant scheduling algorithm guided by QoS constrains. This paper presents the performance evaluation of scheduling heuristics guided by different optimization criteria. The algorithms for distributed scheduling are analyzed in order to satisfy users constrains considering in the same time independent capabilities of resources. This analysis acts like a profiling step for algorithm calibration. The performance evaluation is based on simulation. The simulator is MONARC, a powerful tool for large scale distributed systems simulation. The novelty of this paper consists in synthetic analysis results that offer guidelines for scheduler service configuration and sustain the empirical-based decision. The results could be used in decisions regarding optimizations to existing Grid DAG Scheduling and for selecting the proper algorithm for DAG scheduling in various actual situations.

Keywords: Scheduling, Simulation, Performance Evaluation, QoS, Distributed Systems, MONARC

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1752

Authors: B. Golchin, N. Riahi

Abstract:

One of the most significant issues as attended a lot in recent years is that of recognizing the sentiments and emotions in social media texts. The analysis of sentiments and emotions is intended to recognize the conceptual information such as the opinions, feelings, attitudes and emotions of people towards the products, services, organizations, people, topics, events and features in the written text. These indicate the greatness of the problem space. In the real world, businesses and organizations are always looking for tools to gather ideas, emotions, and directions of people about their products, services, or events related to their own. This article uses the Twitter social network, one of the most popular social networks with about 420 million active users, to extract data. Using this social network, users can share their information and opinions about personal issues, policies, products, events, etc. It can be used with appropriate classification of emotional states due to the availability of its data. In this study, supervised learning and deep neural network algorithms are used to classify the emotional states of Twitter users. The use of deep learning methods to increase the learning capacity of the model is an advantage due to the large amount of available data. Tweets collected on various topics are classified into four classes using a combination of two Bidirectional Long Short Term Memory network and a Convolutional network. The results obtained from this study with an average accuracy of 93%, show good results extracted from the proposed framework and improved accuracy compared to previous work.

Keywords: emotion classification, sentiment analysis, social networks, deep neural networks

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 665

Authors: Roya Morad, W. Eirik Heintz

Abstract:

The identity of a neighborhood is inevitably shaped by the architecture and the people of that place. Conventionally the streets within each neighborhood served as a semi-public-private extension of the private living spaces. The street as a design element formed a hybrid condition that was neither totally public nor private, and it encouraged social interactions. Thus through creating a sense of community, one of the most basic human needs of belonging was achieved. Similar to major global cities, Tehran has undergone serious urbanization. Developing into a capital city of high rises has resulted in an increase in urban density. Although allocating more residential units in each neighborhood was a critical response to the population boom and the limited land area of the city, it also created a crisis in terms of social communication and place attachment. District 10 in Tehran is a neighborhood that has undergone the most urban transformation among the other 22 districts in the capital and currently has the highest population density. This paper will explore how the active streets in district 10 have changed into their current condition of high rises with a lack of meaningful social interactions amongst its inhabitants. A residential building can be thought of as a large group of people. One would think that as the number of people increases, the opportunities for social communications would increase as well. However, according to the survey, there is an indirect relationship between the two. As the number of people of a residential building increases, the quality of each acquaintance reduces, and the depth of relationships between people tends to decrease. This comes from the anonymity of being part of a crowd and the lack of social spaces characterized by most high-rise apartment buildings. Without a sense of community, the attachment to a neighborhood is decreased. This paper further explores how the neighborhood participates to fulfill ones need for social interaction and focuses on the qualitative aspects of alternative spaces that can redevelop the sense of place attachment within the community.

Keywords: High density, place attachment, social communication, street life, urban transformation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 514