Search results for: automatic incident detection

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 78

Authors: Lubabatu Sada Sodangi

Abstract:

The rapid growth in exchange and accessibility of information via the internet makes many organisations acquire data on their own operation. The aim of data mining is to analyse the different behaviour of a dataset using observation. Although, the subset of the dataset being analysed may not display all the behaviours and relationships of the entire data and, therefore, may not represent other parts that exist in the dataset. There is a range of techniques used in data mining to determine the hidden or unknown information in datasets. In this paper, the performance of two algorithms Chi-Square Automatic Interaction Detection (CHAID) and multilayer perceptron (MLP) would be matched using an Adult dataset to find out the percentage of an/the adults that earn > 50k and those that earn <= 50k per year. The two algorithms were studied and compared using IBM SPSS statistics software. The result for CHAID shows that the most important predictors are relationship and education. The algorithm shows that those are married (husband) and have qualification: Bachelor, Masters, Doctorate or Prof-school whose their age is > 41<57 earn > 50k. Also, multilayer perceptron displays marital status and capital gain as the most important predictors of the income. It also shows that individuals that their capital gain is less than 6,849 and are single, separated or widow, earn <= 50K, whereas individuals with their capital gain is > 6,849, work > 35 hrs/wk, and > 27yrs their income will be > 50k. By comparing the two algorithms, it is observed that both algorithms are reliable but there is strong reliability in CHAID which clearly shows that relation and education contribute to the prediction as displayed in the data visualisation.

Keywords: data mining, CHAID, multi-layer perceptron, SPSS, Adult dataset

Procedia PDF Downloads 378

Authors: Khouloud Safa Azoud, Süleyman Baştürk

Abstract:

In the pursuit of cleaner and more sustainable urban environments, advanced technologies play a critical role in evolving sanitation systems. This paper presents two distinct advancements in automated cleaning machines designed to improve urban sanitation. The first advancement is a semi-automatic road surface cleaning machine that integrates human labor with solar energy to enhance environmental sustainability and adaptability, especially in regions with limited access to electricity. By reducing carbon emissions and increasing operational efficiency, this approach offers significant potential for urban sanitation enhancement. The second advancement is a multifunctional semi-automatic street cleaning machine equipped with a camera, Arduino programming, and GPS for an autonomous operation aimed at addressing cost barriers in developing countries. Prioritizing low energy consumption and cost-effectiveness, this machine provides versatile cleaning solutions adaptable to various environmental conditions. By integrating solar energy with autonomous operating systems and careful design, these developments represent substantial progress in sustainable urban sanitation, particularly in developing regions.

Keywords: automated cleaning machines, solar energy integration, operational efficiency, urban sanitation systems

Procedia PDF Downloads 35

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 118

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 93

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 308

Authors: Constant Akama, Frank Kulor, Frederick Agyemang

Abstract:

All over the world, due to increasing population, electric power distribution companies are looking for more efficient ways of reading electricity meters. In Ghana, the prepaid metering system was introduced in 2007 to replace the manual system of reading which was fraught with inefficiencies. However, the prepaid system in Ghana is not capable of integration with online systems such as e-commerce platforms and remote monitoring systems. In this paper, we present a design framework for an automatic metering system that can be integrated with e-commerce platforms and remote monitoring systems. The meter was designed using ADE 7755 which reads the energy consumption and the reading is processed by a microcontroller connected to Sim900 General Packet Radio Service module containing a GSM chip provisioned with an Access Point Name. The system also has a billing server and a management server located at the premises of the utility company which communicate with the meter over a Virtual Private Network and GPRS. With this system, customers can buy credit online and the credit will be transferred securely to the meter. Also, when a fault is reported, the utility company can log into the meter remotely through the management server to troubleshoot the problem.

Keywords: access point name, general packet radio service, GSM, virtual private network

Procedia PDF Downloads 300

Authors: Lauren Dhugga, Meena Parameswaran, David Blundell, Abbas Khushnood

Abstract:

Context: A multidisciplinary weekly safety briefing was implemented at the Paediatric Cardiothoracic Unit at the Freeman Hospital in Newcastle-upon-Tyne. It is a tertiary referral centre with a quarternary cardiac paediatric intensive care unit and provides complexed care including heart and lung transplants, mechanical support and advanced heart failure assessment. Aim: The aim of this briefing is to provide a structured platform of communication, in an effort to improve efficiency, safety, and patient care. Problem: The paediatric cardiothoracic unit is made up of a vast multidisciplinary team including doctors, intensivists, anaesthetists, surgeons, specialist nurses, echocardiogram technicians, physiotherapists, psychologists, dentists, and dietitians. It provides care for children with congenital and acquired cardiac disease and is one of only two units in the UK to offer paediatric heart transplant. The complexity of cases means that there can be many teams involved in providing care to each patient, and frequent movement of children between ward, high dependency, and intensive care areas. Currently, there is no structured forum for communicating important information across the department, for example, staffing shortages, prescribing errors and significant events. Strategy: An initial survey questioning the need for better communication found 90% of respondents agreed that they could think of an incident that had occurred due to ineffective communication, and 85% felt that incident could have been avoided had there been a better form of communication. Lastly, 80% of respondents felt that a weekly 60 second safety briefing would be beneficial to improve communication within our multidisciplinary team. Based on those promising results, a weekly 60 second safety briefing was implemented to be conducted on a Monday morning. The safety briefing covered four key areas (SAFE): staffing, awareness, fix and events. This was to highlight any staffing gaps, any incident reports to be learned from, any issues that required fixing and any events including teachings for the week ahead. The teams were encouraged to email suggestions or issues to be raised for the week or to approach in person with information to add. The safety briefing was implemented using change theory. Effect: The safety briefing has been trialled over 6 weeks and has received a good buy in from staff across specialties. The aim is to embed this safety briefing into a weekly meeting using the PDSA cycle. There will be a second survey in one month to assess the efficacy of the safety briefing and to continue to improve the delivery of information. The project will be presented at the next clinical governance briefing to attract wider feedback and input from across the trust. Lessons: The briefing displays promise as a tool to improve vigilance and communication in a busy multi-disciplinary unit. We have learned about how to implement quality improvement and about the culture of our hospital - how hierarchy influences change. We demonstrate how to implement change through a grassroots process, using a junior led briefing to improve the efficiency, safety, and communication in the workplace.

Keywords: briefing, communication, safety, team

Procedia PDF Downloads 144

Authors: Tapan Upadhyay, Aqib Siddiqui, Sameer Khan

Abstract:

Railway crossing system in India is a manually operated level crossing system, either manned or unmanned. The main aim is to protect pedestrians and vehicles from colliding with trains, which pass at regular intervals, as India has the largest and busiest railway network. But because of human error and negligence, every year thousands of lives are lost due to accidents at railway crossings. To avoid this, we suggest a solution, by using Programmable Logical Controller (PLC) based automatic system, which will automatically control the barrier as well as roadblocks to stop people from crossing while security warning is given. Often people avoid security warning, and pass two-wheelers from beneath the barrier, while the train is at a distance away. This paper aims at reducing the fatality and accident rate by controlling barrier and roadblocks using sensors which sense the incoming train and vehicles and sends a signal to PLC. The PLC in return sends a signal to barrier and roadblocks. Once the train passes, the barrier and roadblocks retrieve back, and the passage is clear for vehicles and pedestrians to cross. PLC’s are used because they are very flexible, cost effective, space efficient, reduces complexity and minimises errors. Supervisory Control And Data Acquisition (SCADA) is used to monitor the functioning.

Keywords: level crossing, PLC, sensors, SCADA

Procedia PDF Downloads 427

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 9

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 141

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 365

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 329

Authors: Buse T. Aydin, Enver Ozdemir

Abstract:

An automatic dependent surveillance-broadcast (ADS-B) system has serious security problems. In this study, a double layer authentication scheme between the aircraft and ground station, aircraft to aircraft, ground station to ATC tower is designed to prevent any unauthorized aircrafts from introducing themselves as friends. This method can be used as a solution to the problem of authentication. The method is a combination of classical cryptographic methods and new generation physical layers. The first layer has employed the embedded key of the aircraft. The embedded key is assumed to installed during the construction of the utility. The other layer is a physical attribute (flight path, distance, etc.) between the aircraft and the ATC tower. We create a mathematical model so that two layers’ information is employed and an aircraft is authenticated as a friend or unknown according to the accuracy of the results of the model. The results of the aircraft are compared with the results of the ATC tower and if the values found by the aircraft and ATC tower match within a certain error margin, we mark the aircraft as friend. As a result, the ADS-B messages coming from this authenticated friendly aircraft will be processed. In this method, even if the embedded key is captured by the unknown aircraft, without the information of the second layer, the unknown aircraft can easily be determined. Overall, in this work, we present a reliable system by adding physical layer in the authentication process.

Keywords: ADS-B, authentication, communication with physical layer security, cryptography, identification friend or foe

Procedia PDF Downloads 179

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 118

Authors: Lubna Eljabu, Mohammad Etemad, Stan Matwin

Abstract:

Port authorities have many challenges in congested ports to allocate their resources to provide a safe and secure loading/ unloading procedure for cargo vessels. Selecting a destination port is the decision of a vessel master based on many factors such as weather, wavelength and changes of priorities. Having access to a tool which leverages AIS messages to monitor vessel’s movements and accurately predict their next destination port promotes an effective resource allocation process for port authorities. In this research, we propose a method, namely, Reference Route of Trajectory (RRoT) to assist port authorities in predicting inflow and outflow traffic in their local environment by monitoring Automatic Identification System (AIS) messages. Our RRoT method creates a reference route based on historical AIS messages. It utilizes some of the best trajectory similarity measure to identify the destination of a vessel using their recent movement. We evaluated five different similarity measures such as Discrete Fr´echet Distance (DFD), Dynamic Time Warping (DTW), Partial Curve Mapping (PCM), Area between two curves (Area) and Curve length (CL). Our experiments show that our method identifies the destination port with an accuracy of 98.97% and an fmeasure of 99.08% using Dynamic Time Warping (DTW) similarity measure.

Keywords: spatial temporal data mining, trajectory mining, trajectory similarity, resource optimization

Procedia PDF Downloads 122

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 442

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 275

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 305

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 286

Authors: Ladislav Ptacek, Jan Vanek, Jan Eisner, Alexandra Pruchova, Pavel Linhart, Ludek Muller, Dana Jirotkova

Abstract:

One of the essential steps of avian song processing is signal filtering. Currently, the standard methods of filtering are the Mel Bank Filter or linear filter distribution. In this article, a new type of bank filter called the Bird-Adapted Filter is introduced; whereby the signal filtering is modifiable, based upon a new mathematical description of audiograms for particular bird species or order, which was named the Avian Audiogram Unified Equation. According to the method, filters may be deliberately distributed by frequency. The filters are more concentrated in bands of higher sensitivity where there is expected to be more information transmitted and vice versa. Further, it is demonstrated a comparison of various filters for automatic individual recognition of chiffchaff (Phylloscopus collybita). The average Equal Error Rate (EER) value for Linear bank filter was 16.23%, for Mel Bank Filter 18.71%, the Bird-Adapted Filter gave 14.29%, and Bird-Adapted Filter with 1/3 modification was 12.95%. This approach would be useful for practical use in automatic systems for avian species and individual identification. Since the Bird-Adapted Filter filtration is based on the measured audiograms of particular species or orders, selecting the distribution according to the avian vocalization provides the most precise filter distribution to date.

Keywords: avian audiogram, bird individual identification, bird song processing, bird species recognition, filter bank

Procedia PDF Downloads 387

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 357

Authors: Bipasha Sen, Aditya Agarwal

Abstract:

Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4x and 7.4x respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean's multilingual low resource dataset.

Keywords: convolutional neural networks, language compatibility, low resource languages, multilingual automatic speech recognition

Procedia PDF Downloads 123

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 113

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 407

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 41

Authors: Graham Hancox, Saydia Razak, Sue Hignett, Jo Barnes, Jyri Silmari, Florian Kading

Abstract:

In the event of a Chemical, Biological, Radiological and Nuclear (CBRN) incident rapidly gaining, situational awareness is of paramount importance and advanced technologies have an important role to play in improving detection, identification, monitoring (DIM) and patient tracking. Understanding how these advanced technologies can fit into current response systems is essential to ensure they are optimally designed, usable and meet end-users’ needs. For this reason, Human Factors (Ergonomics) methods have been used within an EU Horizon 2020 project (TOXI-Triage) to firstly describe (map) the hierarchical structure in a CBRN response with adapted Accident Map (AcciMap) methodology. Secondly, Hierarchical Task Analysis (HTA) has been used to describe and review the sequence of steps (sub-tasks) in a CBRN scenario response as a task system. HTA methodology was then used to map one advanced technology, ‘Tag and Trace’, which tags an element (people, sample and equipment) with a Near Field Communication (NFC) chip in the Hot Zone to allow tracing of (monitoring), for example casualty progress through the response. This HTA mapping of the Tag and Trace system showed how the provider envisaged the technology being used, allowing for review and fit with the current CBRN response systems. These methodologies have been found to be very effective in promoting and supporting a dialogue between end-users and technology providers. The Human Factors methods have given clear diagrammatic (visual) representations of how providers see their technology being used and how end users would actually use it in the field; allowing for a more user centered approach to the design process. For CBRN events usability is critical as sub-optimum design of technology could add to a responders’ workload in what is already a chaotic, ambiguous and safety critical environment.

Keywords: AcciMap, CBRN, ergonomics, hierarchical task analysis, human factors

Procedia PDF Downloads 222

Authors: Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Abstract:

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.

Keywords: fake news detection, natural language processing, machine learning, classification techniques.

Procedia PDF Downloads 168

Authors: Lae-Jeong Park

Abstract:

The paper presents a method that utilizes figure-ground color segmentation to extract effective global feature in terms of false positive reduction in the head-shoulder detection. Conventional detectors that rely on local features such as HOG due to real-time operation suffer from false positives. Color cue in an input image provides salient information on a global characteristic which is necessary to alleviate the false positives of the local feature based detectors. An effective approach that uses figure-ground color segmentation has been presented in an effort to reduce the false positives in object detection. In this paper, an extended version of the approach is presented that adopts separate multipart foregrounds instead of a single prior foreground and performs the figure-ground color segmentation with each of the foregrounds. The multipart foregrounds include the parts of the head-shoulder shape and additional auxiliary foregrounds being optimized by a search algorithm. A classifier is constructed with the feature that consists of a set of the multiple resulting segmentations. Experimental results show that the presented method can discriminate more false positive than the single prior shape-based classifier as well as detectors with the local features. The improvement is possible because the presented approach can reduce the false positives that have the same colors in the head and shoulder foregrounds.

Keywords: pedestrian detection, color segmentation, false positive, feature extraction

Procedia PDF Downloads 281

Authors: Yagahira E. Castro-Sesquen, Chloe Kim, Robert H. Gilman, David J. Sullivan, Peter C. Searson

Abstract:

Diagnosis of severe malaria is particularly important in highly endemic regions since most patients are positive for parasitemia and treatment differs from non-severe malaria. Diagnosis can be challenging due to the prevalence of diseases with similar symptoms. Accurate diagnosis is increasingly important to avoid overprescribing antimalarial drugs, minimize drug resistance, and minimize costs. A nanoparticle-based assay for detection and quantification of Plasmodium falciparum histidine-rich protein 2 (HRP2) in urine and serum is reported. The assay uses magnetic beads conjugated with anti-HRP2 antibody for protein capture and concentration, and antibody-conjugated quantum dots for optical detection. Western Blot analysis demonstrated that magnetic beads allows the concentration of HRP2 protein in urine by 20-fold. The concentration effect was achieved because large volume of urine can be incubated with beads, and magnetic separation can be easily performed in minutes to isolate beads containing HRP2 protein. Magnetic beads and Quantum Dots 525 conjugated to anti-HRP2 antibodies allows the detection of low concentration of HRP2 protein (0.5 ng mL-1), and quantification in the range of 33 to 2,000 ng mL-1 corresponding to the range associated with non-severe to severe malaria. This assay can be easily adapted to a non-invasive point-of-care test for classification of severe malaria.

Keywords: HRP2 protein, malaria, magnetic beads, Quantum dots

Procedia PDF Downloads 333