Search results for: preposition error detection

Authors: Z. Zerdoumi, D. Benatia, , D. Chicouche

Abstract:

This paper investigates the application of artificial neural network to the problem of nonlinear channel equalization. The difficulties caused by channel distortions such as inter symbol interference (ISI) and nonlinearity can overcome by nonlinear equalizers employing neural networks. It has been shown that multilayer perceptron based equalizer outperform significantly linear equalizers. We present a multilayer perceptron based equalizer with decision feedback (MLP-DFE) trained with the back propagation algorithm. The capacity of the MLP-DFE to deal with nonlinear channels is evaluated. From simulation results it can be noted that the MLP based DFE improves significantly the restored signal quality, the steady state mean square error (MSE), and minimum Bit Error Rate (BER), when comparing with its conventional counterpart.

Keywords: Artificial Neural Network, signal restoration, Nonlinear Channel equalization, equalization

Procedia PDF Downloads 499

Authors: Po-Chun Wang, Yan-Ru Lai, Sophia I. C. Lin, Alvin W. Y. Su

Abstract:

The Generative Theory of Tonal Music (GTTM) provides systematic approaches to recognizing local boundaries of music. The rules have been implemented in some automated melody segmentation algorithms. Besides, there are also deep learning methods with GTTM features applied to boundary detection tasks. However, these studies might face constraints such as a lack of or inconsistent label data. The GTTM database is currently the most widely used GTTM database, which includes manually labeled GTTM rules and local boundaries. Even so, we found some problems with these labels. They are sometimes discrepancies with GTTM rules. In addition, since it is labeled at different times by multiple musicians, they are not within the same scope in some cases. Therefore, in this paper, we examine this database with musicians from the aspect of classical music and relabel the scores. The relabeled database - GTTM Database v2.0 - will be released for academic research usage. Despite the experimental and statistical results showing that the relabeled database is more consistent, the improvement in boundary detection is not substantial. It seems that we need more clues than GTTM rules for boundary detection in the future.

Keywords: dataset, GTTM, local boundary, neural network

Procedia PDF Downloads 152

Authors: Sofia G. Meirinho, Luis G. Dias, António M. Peres, Lígia R. Rodrigues

Abstract:

The emerging development of electrochemical aptasen sors has enabled the easy and fast detection of protein biomarkers in standard and real samples. Biomarkers are produced by body organs or tumours and provide a measure of antigens on cell surfaces. When detected in high amounts in blood, they can be suggestive of tumour activity. These biomarkers are more often used to evaluate treatment effects or to assess the potential for metastatic disease in patients with established disease. Osteopontin (OPN) is a protein found in all body fluids and constitutes a possible biomarker because its overexpression has been related with breast cancer evolution and metastasis. Currently, biomarkers are commonly used for the development of diagnostic methods, allowing the detection of the disease in its initial stages. A previously described RNA aptamer was used in the current work to develop a simple and sensitive electrochemical aptasensor with high affinity for human OPN. The RNA aptamer was biotinylated and immobilized on a gold electrode by avidin-biotin interaction. The electrochemical signal generated from the aptamer–target molecule interaction was monitored electrochemically using cyclic voltammetry in the presence of [Fe (CN) 6]−3/− as a redox probe. The signal observed showed a current decrease due to the binding of OPN. The preliminary results showed that this aptasensor enables the detection of OPN in standard solutions, showing good selectivity towards the target in the presence of others interfering proteins such as bovine OPN and bovine serum albumin. The results gathered in the current work suggest that the proposed electrochemical aptasensor is a simple and sensitive detection tool for human OPN and so, may have future applications in cancer disease monitoring.

Keywords: osteopontin, aptamer, aptasensor, screen-printed electrode, cyclic voltammetry

Procedia PDF Downloads 436

Authors: Farzad Razavi, Behrooz Taheri, Mohammad Parpaei, Mehdi Mohammadi Ghalesefidi, Siamak Zarei

Abstract:

As one of the major problems in protecting large-dimension power systems, power swing and its effect on distance have caused a lot of damages to energy transfer systems in many parts of the world. Therefore, power swing has gained attentions of many researchers, which has led to invention of different methods for power swing detection. Power swing detection algorithm is highly important in distance relay, but protection relays should have general requirements such as correct fault detection, response rate, and minimization of disturbances in a power system. To ensure meeting the requirements, protection relays need different tests during development, setup, maintenance, configuration, and troubleshooting steps. This paper covers power swing scheme of the modern numerical relay protection, 7sa522 to address the effect of the different fault types on the function of the power swing blocking. In this study, it was shown that the different fault types during power swing cause different time for unblocking distance relay.

Keywords: power swing, distance relay, power system protection, relay test, transient in power system

Procedia PDF Downloads 387

Authors: Djamil Guettiche, Ahmed Mekki, Tighilt Fatma-Zohra, Rachid Mahmoud

Abstract:

The aim of this study was to synthesize and characterize conducting polymer composites of polypyrrole and graphene, including pristine and surface-treated graphene (PPy/GO, PPy/rGO, and PPy/rGO-ArCOOH), for use as sensitive elements in a homemade chemiresistive module for on-line detection of nitrogen oxides vapors. The chemiresistive module was prepared, characterized, and evaluated for performance. Structural and morphological characterizations of the composite were carried out using FTIR, Raman spectroscopy, and XRD analyses. After exposure to NO and NO₂ gases in both static and dynamic modes, the sensitivity, selectivity, limit of detection, and response time of the sensor were determined at ambient temperature. The resulting sensor showed high sensitivity, selectivity, and reversibility, with a low limit of detection of 1 ppm. A composite of polypyrrole and graphene functionalized with aryl 4-carboxy benzene diazonium salt was synthesized and characterized using FTIR, scanning electron microscopy, transmission electron microscopy, UV-visible, and X-ray diffraction. The PPy-rGOArCOOH composite exhibited a good electrical resistance response to NO₂ at room temperature and showed enhanced NO₂-sensing properties compared to PPy-rGO thin films. The selectivity and stability of the NO₂ sensor based on the PPy/rGO-ArCOOH nanocomposite were also investigated.

Keywords: conducting polymers, surface treated graphene, diazonium salt, polypyrrole, Nitrogen oxide sensing

Procedia PDF Downloads 82

Authors: Muhammad Ali Sarwar, Muhammad Farooq, Nayab Hassan, Hammad Hassan

Abstract:

Pakistan is highly recognized for its agriculture and is well known for producing substantial amounts of wheat, cotton, and sugarcane. However, some factors contribute to a decline in crop quality and a reduction in overall output. One of the main factors contributing to this decline is the presence of weed and its late detection. This process of detection is manual and demands a detailed inspection to be done by the farmer itself. But by the time detection of weed, the farmer will be able to save its cost and can increase the overall production. The focus of this research is to identify and classify the four main types of weeds (Small-Flowered Cranesbill, Chick Weed, Prickly Acacia, and Black-Grass) that are prevalent in our region’s major crops. In this work, we implemented three different deep learning techniques: YOLO-v5, Inception-v3, and Deep CNN on the same Dataset, and have concluded that deep convolutions neural network performed better with an accuracy of 97.45% for such classification. In relative to the state of the art, our proposed approach yields 2% better results. We devised the architecture in an efficient way such that it can be used in real-time.

Keywords: deep convolution networks, Yolo, machine learning, agriculture

Procedia PDF Downloads 123

Authors: Naydelis Brito Suárez, Deni Librado Torres Román, Fernando Hermosillo Reynoso

Abstract:

Automatic detection and generation of a dynamic ROI (Region of Interest) in vehicle traffic surveillance videos based on a static camera in Intelligent Transportation Systems is challenging for computer vision-based systems. The dynamic ROI, being a changing ROI, should capture any other moving object located outside of a static ROI. In this work, the video is represented by a Tensor model composed of a Background and a Foreground Tensor, which contains all moving vehicles or objects. The values of each pixel over a time interval are represented by time series, and some pixel rows were selected. This paper proposes a pixel entropy-based algorithm for automatic detection and generation of a dynamic ROI in traffic videos under the assumption of two types of theoretical pixel entropy behaviors: (1) a pixel located at the road shows a high entropy value due to disturbances in this zone by vehicle traffic, (2) a pixel located outside the road shows a relatively low entropy value. To study the statistical behavior of the selected pixels, detecting the entropy changes and consequently moving objects, Shannon, Tsallis, and Approximate entropies were employed. Although Tsallis entropy achieved very high results in real-time, Approximate entropy showed results slightly better but in greater time.

Keywords: convex hull, dynamic ROI detection, pixel entropy, time series, moving objects

Procedia PDF Downloads 78

Authors: Wanwisa Deenin, Abdulhadee Yakoh, Chahya Kreangkaiwal, Orawon Chailapakul, Kanitha Patarakul, Sudkate Chaiyo

Abstract:

LipL32 is an outer membrane protein present only on pathogenic Leptospira species, which are the causative agent of leptospirosis. Leptospirosis symptoms are often misdiagnosed with other febrile illnesses as the clinical manifestations are non-specific. Therefore, an accurate diagnostic tool for leptospirosis is indeed critical for proper and prompt treatment. Typical diagnosis via serological assays is generally performed to assess the antibodies produced against Leptospira. However, their delayed antibody response and complicated procedure are undoubtedly limited the practical utilization especially in primary care setting. Here, we demonstrate for the first time an early-stage detection of LipL32 by an integrated lateral-flow immunoassay with electrochemical readout (eLFIA). A ferrocene trace tag was monitored via differential pulse voltammetry operated on a smartphone-based device, thus allowing for on-field testing. Superior performance in terms of the lowest detectable limit of detection (LOD) of 8.53 pg/mL and broad linear dynamic range (5 orders of magnitude) among other sensors available thus far was established. Additionally, the developed test strip provided a straightforward yet sensitive approach for diagnosis of leptospirosis using the collected human sera from patients, in which the results were comparable to the real-time polymerase chain reaction technique.

Keywords: leptospirosis, electrochemical detection, lateral flow immunosensor, point-of-care testing, early-stage detection

Procedia PDF Downloads 101

Authors: Kyung Jin Kim, Jiwon Kwak, Jae-Hoon Lee, Soo Suk Lee

Abstract:

We describe an innovative method for highly specific detection of miRNAs using a specially modified method of poly(A) adaptor RT-qPCR. We use uniquely designed specific extension sequence, which plays important role in providing an opportunity to affect high specificity of miRNA detection. This method involves two steps of reactions as like previously reported and which are poly(A) tailing and reverse-transcription followed by real-time PCR. Firstly, miRNAs are extended by a poly(A) tailing reaction and then converted into cDNA. Here, we remarkably reduced the reaction time by the application of short length of poly(T) adaptor. Next, cDNA is hybridized to the 3’-end of a specific extension sequence which contains miRNA sequence and results in producing a novel PCR template. Thereafter, the SYBR Green-based RT-qPCR progresses with a universal poly(T) adaptor forward primer and a universal reverse primer. The target miRNA, miR-106b in human brain total RNA, could be detected quantitatively in the range of seven orders of magnitude, which demonstrate that the assay displays a dynamic range of at least 7 logs. In addition, the better specificity of this novel extension-based assay against well known poly(A) tailing method for miRNA detection was confirmed by melt curve analysis of real-time PCR product, clear gel electrophoresis and sequence chromatogram images of amplified DNAs.

Keywords: microRNA(miRNA), specific extension sequence, RT-qPCR, poly(A) tailing assay, reverse transcription

Procedia PDF Downloads 310

Authors: Jing Li Hong

Abstract:

This study compared Michel Foucault’s thoughts and the Chan School’s thoughts on the idea of healing. Healing is not an unfamiliar idea in Buddhist thoughts. The paired concepts of illness and medicine are often used as a metaphor to describe the relationship between people and truth. Foucault investigated the topic of care of self in his later studies and dedicated a large portion of his final semester course at the Collège de France in 1984 to discuss the meaning of Socrates’s offering of a sacrifice to the god of medicine in Phaedo. Foucault indicated a key preposition in ancient philosophy, namely healing. His idea of healing also addressed the relationship between subject and truth. From this relationship, Foucault unraveled his novel study on truth, namely the technologies of the self, with an emphasis on the care of self. Whereas numerous philosophers ask obvious questions such as ‘what is truth’ and ‘how to learn about truth,’ Foucault proposed distinct questions such as ‘what is our relationship to truth’ and ‘how does our relationship with truth turn us into who we are now?’ Thus, healing in both Buddhist and Foucault’s thoughts is related to the relationship between being and truth. This study first reviews Buddhist and Foucault’s ideas of healing to explicate what is illness and what is medicine. Because Buddhist thoughts cover an extensive scope, this study focuses on the thoughts of the Chan School. The second part is a discussion on medicine (treatment), specifically what is used as the medicine for the illness in both thoughts, and how can this medicine treat the illness. This part includes a description and comparison of the use of concepts of negation in these two thought groups. Finally, the subjects that practice the technologies of the self in both groups are compared from the idea of care of self; in other words, the differences between the subjects formed by the different relationships between being and truth are analyzed.

Keywords: Chan, heterogeneous, living style, language of paradox, Michel Foucault, negation, parrhesia, the care of self

Procedia PDF Downloads 190

Authors: Fotis I. Giasemis, Alexandros Sopasakis

Abstract:

This study focuses on detecting traffic anomalies using generative models applied to real-time observations. By integrating a Graph Neural Network with an attention-based mechanism within the Spatiotemporal Generative Adversarial Network framework, we enhance the capture of both spatial and temporal dependencies in traffic data. Leveraging minute-by-minute observations from cameras distributed across Gothenburg, our approach provides a more detailed and precise anomaly detection system, effectively capturing the complex topology and dynamics of urban traffic networks.

Keywords: traffic, anomaly detection, GNN, GAN

Procedia PDF Downloads 14

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: artificial neural networks, fuel consumption, friedman test, machine learning, statistical hypothesis testing

Procedia PDF Downloads 186

Authors: Khadijat T. Bamigbade, Olufade F. W. Onifade

Abstract:

The field of automatic facial expression analysis has been an active research area in the last two decades. Its vast applicability in various domains has drawn so much attention into developing techniques and dataset that mirror real life scenarios. Many techniques such as Local Binary Patterns and its variants (CLBP, LBP-TOP) and lately, deep learning techniques, have been used for facial expression recognition. However, the problem of occlusion has not been sufficiently handled, making their results not applicable in real life situations. This paper develops a simple, yet highly efficient method tagged Local Binary Pattern-Histogram of Gradient (LBP-HOG) with occlusion detection in face image, using a multi-class SVM for Action Unit and in turn expression recognition. Our method was evaluated on three publicly available datasets which are JAFFE, CK, SFEW. Experimental results showed that our approach performed considerably well when compared with state-of-the-art algorithms and gave insight to occlusion detection as a key step to handling expression in wild.

Keywords: automatic facial expression analysis, local binary pattern, LBP-HOG, occlusion detection

Procedia PDF Downloads 174

Authors: Khaldon Lweesy, Feryal Alskafi, Rabaa Hammad, Shaker Khanfar, Yara Alsukhni

Abstract:

Electronic noses are devices designed to emulate the humane sense of smell by characterizing and differentiating odor profiles. In this study, we build a low-cost e-nose using an array module containing four different types of metal oxide semiconductor gas sensors. We used this system to create a profile for a meat specimen over three days. Then using a pattern recognition software, we correlated the odor of the specimen to its age. It is a simple, fast detection method that is both non-expensive and non-destructive. The results support the usage of this technology in food control management.

Keywords: e-nose, low cost, odor detection, food safety

Procedia PDF Downloads 144

Authors: Goutham Kumar Dogiparti, D. R. Seshu

Abstract:

In the present study, wavelet analysis was used for locating damage in simply supported and cantilever beams. Study was carried out varying different levels and locations of damage. In numerical method, ANSYS software was used for modal analysis of damaged and undamaged beams. The mode shapes obtained from numerical analysis is processed using MATLAB wavelet toolbox to locate damage. Effect of several parameters such as (damage level, location) on the natural frequencies and mode shapes were also studied. The results indicated the potential of wavelets in identifying the damage location.

Keywords: damage, detection, beams, wavelets

Procedia PDF Downloads 369

Authors: Xiaoqing Wang, Junfeng Wang, Xiaolan Zhu

Abstract:

Android operating system has been recognized by most application developers because of its good open-source and compatibility, which enriches the categories of applications greatly. However, it has become the target of malware attackers due to the lack of strict security supervision mechanisms, which leads to the rapid growth of malware, thus bringing serious safety hazards to users. Therefore, it is critical to detect Android malware effectively. Generally, the permissions declared in the AndroidManifest.xml can reflect the function and behavior of the application to a large extent. Since current Android system has not any restrictions to the number of permissions that an application can request, developers tend to apply more than actually needed permissions in order to ensure the successful running of the application, which results in the abuse of permissions. However, some traditional detection methods only consider the requested permissions and ignore whether it is actually used, which leads to incorrect identification of some malwares. Therefore, a machine learning detection method based on the actually used permissions combination and API calls was put forward in this paper. Meanwhile, several experiments are conducted to evaluate our methodology. The result shows that it can detect unknown malware effectively with higher true positive rate and accuracy while maintaining a low false positive rate. Consequently, the AdaboostM1 (J48) classification algorithm based on information gain feature selection algorithm has the best detection result, which can achieve an accuracy of 99.8%, a true positive rate of 99.6% and a lowest false positive rate of 0.

Keywords: android, API Calls, machine learning, permissions combination

Procedia PDF Downloads 332

Authors: Mohammad Y. Abualhoul, Edgar Talavera Munoz, Fawzi Nashashibi

Abstract:

The new emerging Visible Light Communication (VLC) technology has been subjected to intensive investigation, evaluation, and lately, deployed in the context of convoy-based applications for Intelligent Transportations Systems (ITS). The technology limitations were defined and supported by different solutions proposals to enhance the crucial alignment and mobility limitations. In this paper, we propose the incorporation of VLC technology and Lane-Centering (LC) technique to assure the VLC-connectivity by keeping the autonomous vehicle aligned to the lane center using vision-based lane detection in a convoy-based formation. Such combination can ensure the optical communication connectivity with a lateral error less than 30 cm. As soon as the road lanes are detectable, the evaluated system showed stable behavior independently from the inter-vehicle distances and without the need for any exchanged information of the remote vehicles. The evaluation of the proposed system is verified using VLC prototype and an empirical result of LC running application over 60 km in Madrid M40 highway.

Keywords: visible light communication, lane-centerin, platooning, intelligent transportation systems, road safety applications

Procedia PDF Downloads 176

Authors: Meltem Agar, Maisem Laabei, Hannah Leese, Pedro Estrela

Abstract:

Pathogenic bacteria and the diseases they cause have become a global problem. Their early detection is vital and can only be possible by detecting the bacteria causing the disease accurately and rapidly. Great progress has been made in this field with the use of biosensors. Molecularly imprinted polymers have gain broad interest because of their excellent properties over natural receptors, such as being stable in a variety of conditions, inexpensive, biocompatible and having long shelf life. These properties make molecularly imprinted polymers an attractive candidate to be used in biosensors. In this study it is aimed to produce an aptamer-molecularly imprinted polymer based electrochemical sensor by utilizing the properties of molecularly imprinted polymers coupled with the enhanced specificity offered by DNA aptamers. These ‘apta-MIP’ sensors were used for the detection of Staphylococcus aureus and Escherichia coli. The experimental parameters for the fabrication of sensor were optimized, and detection of the bacteria was evaluated via Electrochemical Impedance Spectroscopy. Sensitivity and selectivity experiments were conducted. Furthermore, molecularly imprinted polymer only and aptamer only electrochemical sensors were produced separately, and their performance were compared with the electrochemical sensor produced in this study. Aptamer-molecularly imprinted polymer based electrochemical sensor showed good sensitivity and selectivity in terms of detection of Staphylococcus aureus and Escherichia coli. The performance of the sensor was assessed in buffer solution and tap water.

Keywords: aptamer, electrochemical sensor, staphylococcus aureus, molecularly imprinted polymer

Procedia PDF Downloads 121

Authors: Sherif K. El Dyasti, Esam A. Hagras, Adel E. El-Hennawy

Abstract:

This paper addresses the performance of antenna array beam-forming on Chip-Interleaved Code Division Multiple Access (CI_CDMA) system based on Minimum Mean Square Error (MMSE) detector in aeronautical mobile radio channel. Multipath fading, Doppler shifts caused by the speed of the aircraft, and Multiple Access Interference (MAI) are the most important reasons that affect and reduce the performance of aeronautical system. In this paper, we suggested the CI-CDMA with antenna array to combat this fading and improve the bit error rate (BER) performance. We further evaluate the performance of the proposed system in the four standard scenarios in aeronautical mobile radio channel.

Keywords: aeronautical channel, CI-CDMA, beamforming, communication, information

Procedia PDF Downloads 422

Authors: Arabi Abderrazak, Bourouba Nacerdine, Ayad Mouloud, Belaout Abdeslam

Abstract:

In this paper, a new test technique of analog circuits using time mode simulation is proposed for the single catastrophic faults detection in analog circuits. This test process is performed to overcome the problem of catastrophic faults being escaped in a DC mode test applied to the inverter amplifier in previous research works. The circuit under test is a second-order low pass filter constructed around this type of amplifier but performing a function that differs from that of the previous test. The test approach performed in this work is based on two key- elements where the first one concerns the unique square pulse signal selected as an input vector test signal to stimulate the fault effect at the circuit output response. The second element is the filter response conversion to a square pulses sequence obtained from an analog comparator. This signal conversion is achieved through a fixed reference threshold voltage of this comparison circuit. The measurement of the three first response signal pulses durations is regarded as fault effect detection parameter on one hand, and as a fault signature helping to hence fully establish an analog circuit fault diagnosis on another hand. The results obtained so far are very promising since the approach has lifted up the fault coverage ratio in both modes to over 90% and has revealed the harmful side of faults that has been masked in a DC mode test.

Keywords: analog circuits, analog faults diagnosis, catastrophic faults, fault detection

Procedia PDF Downloads 445

Authors: Aaditya U. Jhamb

Abstract:

Due to the current energy crisis that many countries are battling, energy-efficient buildings are the subject of extensive research in the modern technological era because of growing worries about energy consumption and its effects on the environment. The paper explores 8 factors that help determine energy efficiency for a building: (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution), with Tsanas and Xifara providing a dataset. The data set employed 768 different residential building models to anticipate heating and cooling loads with a low mean squared error. By optimizing these characteristics, machine learning algorithms may assess and properly forecast a building's heating and cooling loads, lowering energy usage while increasing the quality of people's lives. As a result, the paper studied the magnitude of the correlation between these input factors and the two output variables using various statistical methods of analysis after determining which input variable was most closely associated with the output loads. The most conclusive model was the Decision Tree Regressor, which had a mean squared error of 0.258, whilst the least definitive model was the Isotonic Regressor, which had a mean squared error of 21.68. This paper also investigated the KNN Regressor and the Linear Regression, which had to mean squared errors of 3.349 and 18.141, respectively. In conclusion, the model, given the 8 input variables, was able to predict the heating and cooling loads of a residential building accurately and precisely.

Keywords: energy efficient buildings, heating load, cooling load, machine learning models

Procedia PDF Downloads 102

Authors: Tae-Uk Yun, Pullip Chung, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection using machine learning techniques over the past years. But, there have been no prior studies proposed an automated fake news detection method for Korean news to our best knowledge. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (topic modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as logistic regression, backpropagation network, support vector machine, and deep neural network can be applied. To validate the effectiveness of the proposed method, we collected about 200 short Korean news from Seoul National University’s FactCheck. which provides with detailed analysis reports from 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

Keywords: fake news detection, Korean news, machine learning, text mining

Procedia PDF Downloads 278

Authors: Bhuyain Mobarok Hossain

Abstract:

Image classification and localization research is currently an important strategy in the field of computer vision. The evolution and advancement of deep learning and convolutional neural networks (CNN) have greatly improved the capabilities of object detection and image-based classification. Target detection is important to research in the field of computer vision, especially in video surveillance systems. To solve this problem, we will be applying a convolutional neural network of multiple scales at multiple locations in the image in one sliding window. Most translation networks move away from the bounding box around the area of interest. In contrast to this architecture, we consider the problem to be a classification problem where each pixel of the image is a separate section. Image classification is the method of predicting an individual category or specifying by a shoal of data points. Image classification is a part of the classification problem, including any labels throughout the image. The image can be classified as a day or night shot. Or, likewise, images of cars and motorbikes will be automatically placed in their collection. The deep learning of image classification generally includes convolutional layers; the invention of it is referred to as a convolutional neural network (CNN).

Keywords: image classification, object detection, localization, particle filter

Procedia PDF Downloads 313

Authors: Koichi Kurita

Abstract:

In this study, an effective non-contact technique for the detection of human physical activity is proposed. The technique is based on detecting the electrostatic induction current generated by the walking motion under non-contact and non-attached conditions. A theoretical model for the electrostatic induction current generated because of a change in the electric potential of the human body is proposed. By comparing the obtained electrostatic induction current with the theoretical model, it becomes obvious that this model effectively explains the behavior of the waveform of the electrostatic induction current. The normal walking motions are recorded using a portable sensor measurement located in a passageway　of office building. The obtained results show that detailed information regarding physical activity such as a walking cycle can be estimated using our proposed technique. This suggests that the proposed technique which is based on the detection of the walking signal, can be successfully applied to the detection of human walking motion in a secured building.

Keywords: human walking motion, access control, electrostatic induction, alarm monitoring

Procedia PDF Downloads 360

Authors: Adel Salem Bahakeem, Ahmad Jamal, Mir Md. Maruf Morshed, Elwaleed Awad Khidir

Abstract:

Direct Current (DC) servo motors, or simply DC motors, play an important role in many industrial applications such as manufacturing of plastics, precise positioning of the equipment, and operating computer-controlled systems where speed of feed control, maintaining the position, and ensuring to have a constantly desired output is very critical. These parameters can be controlled with the help of control systems such as the Proportional Integral Derivative (PID) controller. The aim of the current work is to investigate the effects of Proportional (P) and Integral (I) controllers on the steady state and transient response of the DC motor. The controller gains are varied to observe their effects on the error, damping, and stability of the steady and transient motor response. The current investigation is conducted experimentally on a servo trainer CE 110 using analog PI controller CE 120 and theoretically using Simulink in MATLAB. Both experimental and theoretical work involves varying integral controller gain to obtain the response to a steady-state input, varying, individually, the proportional and integral controller gains to obtain the response to a step input function at a certain frequency, and theoretically obtaining the proportional and integral controller gains for desired values of damping ratio and response frequency. Results reveal that a proportional controller helps reduce the steady-state and transient error between the input signal and output response and makes the system more stable. In addition, it also speeds up the response of the system. On the other hand, the integral controller eliminates the error but tends to make the system unstable with induced oscillations and slow response to eliminate the error. From the current work, it is desired to achieve a stable response of the servo motor in terms of its angular velocity subjected to steady-state and transient input signals by utilizing the strengths of both P and I controllers.

Keywords: DC servo motor, proportional controller, integral controller, controller gain optimization, Simulink

Procedia PDF Downloads 113

Authors: Kouorsh Zarea, Fatemeh Hassani, Samira Beiranvand, Akram Mohamadi

Abstract:

Background and Objectives: Medication error in hospitals is a major cause of the errors which disrupt the health care system. The aim of this study was to assess the nurses’ medication errors and related factors. Material and methods: This was a descriptive study on 225 nurses in various hospitals, selected through multistage random sampling. Data was collected by three researcher made tools; demographic, medication error and related factors questionnaires. Data was analyzed by descriptive statistics, Chi-square, Kruskal-Wallis, One-way analysis of variance. Results: Based on the results obtained, the type of medication errors giving drugs to patients later or earlier (55.6%), multiple oral medication together regardless of their interactions (36%) and the postoperative analgesic without a prescription (34.2%), respectively. In addition, factors such as the shortage of nurses to patients’ ratio (57.3%), high load functions (51.1%) and fatigue caused by the extra work (40.4%), were the most important factors affecting the incidence of medication errors. The fear of legal issues (40%) are the most important factor is the lack of reported medication errors. Conclusions: Based on the results, effective management and promotion motivate nurses. Therefore, increasing scientific and clinical expertise in the field of nursing medication orders is recommended to prevent medication errors in various states of nursing intervention. Employing experienced staff in areas with high risk of medication errors and also supervising less-experienced staff through competent personnel are also suggested.

Keywords: medication error, nurse, clinical care, drug errors

Procedia PDF Downloads 267

Authors: Delphine Vendryes, Dushyanth Sekhar, Baojia Tong, Matthew Theisen, Chester Curme

Abstract:

Much of the data that inform the decisions of governments, corporations and individuals are harvested from unstructured documents. Data extraction is defined here as a process that turns non-machine-readable information into a machine-readable format that can be stored, for instance, in a database. In financial services, introducing more automation in data extraction pipelines is a major challenge. Information sought by financial data consumers is often buried within vast bodies of unstructured documents, which have historically required thorough manual extraction. Automated solutions provide faster access to non-machine-readable datasets, in a context where untimely information quickly becomes irrelevant. Data quality standards cannot be compromised, so automation requires high data integrity. This multifaceted task is broken down into smaller steps: ingestion, table parsing (detection and structure recognition), text analysis (entity detection and disambiguation), schema-based record extraction, user feedback incorporation. Selected intermediary steps are phrased as machine learning problems. Solutions leveraging cutting-edge approaches from the fields of computer vision (e.g. table detection) and natural language processing (e.g. entity detection and disambiguation) are proposed.

Keywords: computer vision, entity recognition, finance, information retrieval, machine learning, natural language processing

Procedia PDF Downloads 118

Authors: Bilal Saoud

Abstract:

In this paper, we propose a new method to find the community structure in networks. Our method is based on bee colony and the maximization of modularity to find the community structure. We use a bee colony algorithm to find the first community structure that has a good value of modularity. To improve the community structure, that was found, we merge communities until we get a community structure that has a high value of modularity. We provide a general framework for implementing our approach. We tested our method on computer-generated and real-world networks with a comparison to very known community detection methods. The obtained results show the effectiveness of our proposition.

Keywords: bee colony, networks, modularity, normalized mutual information

Procedia PDF Downloads 412

Authors: Arth J. Shah, Madhu R. Kamble

Abstract:

Voice biometric liveness detection is customized to certify an authentication process of the voice data presented is genuine and not a recording or synthetic voice. With the rise of deepfakes and other equivalently sophisticated spoofing generation techniques, it’s becoming challenging to ensure that the person on the other end is a live speaker or not. Voice Liveness Detection (VLD) system is a group of security measures which detect and prevent voice spoofing attacks. Motivated by the recent development of the Kolmogorov-Arnold Network (KAN) based on the Kolmogorov-Arnold theorem, we proposed KAN for the VLD task. To date, multilayer perceptron (MLP) based classifiers have been used for the classification tasks. We aim to capture not only the compositional structure of the model but also to optimize the values of univariate functions. This study explains the mathematical as well as experimental analysis of KAN for VLD tasks, thereby opening a new perspective for scientists to work on speech and signal processing-based tasks. This study emerges as a combination of traditional signal processing tasks and new deep learning models, which further proved to be a better combination for VLD tasks. The experiments are performed on the POCO and ASVSpoof 2017 V2 database. We used Constant Q-transform, Mel, and short-time Fourier transform (STFT) based front-end features and used CNN, BiLSTM, and KAN as back-end classifiers. The best accuracy is 91.26 % on the POCO database using STFT features with the KAN classifier. In the ASVSpoof 2017 V2 database, the lowest EER we obtained was 26.42 %, using CQT features and KAN as a classifier.

Keywords: Kolmogorov Arnold networks, multilayer perceptron, pop noise, voice liveness detection

Procedia PDF Downloads 48

Authors: Jae-Hyun Ro, Jong-Kwang Kim, Chang-Hee Kang, Hyoung-Kyu Song

Abstract:

In multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems, QR decomposition-M algorithm (QRD-M) has suboptimal error performance. However, the QRD-M has still high complexity due to many calculations at each layer in tree structure. To reduce the complexity of the QRD-M, proposed QRD-M modifies existing tree structure by eliminating unnecessary candidates at almost whole layers. The method of the elimination is discarding the candidates which have accumulated squared Euclidean distances larger than calculated threshold. The simulation results show that the proposed QRD-M has same bit error rate (BER) performance with lower complexity than the conventional QRD-M.

Keywords: complexity, MIMO-OFDM, QRD-M, squared Euclidean distance

Procedia PDF Downloads 338