Search results for: small target detection

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 248

Authors: Nomfundo Ngombane, Topside E. Mathonsi

Abstract:

Remote sensing and satellite imaging have been widely used to detect wildfires; nevertheless, the technologies present some limitations in terms of early wildfire detection as the technologies are greatly influenced by weather conditions and can miss small fires. The fires need to have spread a few kilometers for the technologies to provide accurate detection. The South African Advanced Fire Information System uses MODIS (Moderate Resolution Imaging Spectroradiometer) as satellite imaging. MODIS has limitations as it can exclude small fires and can fall short in validating fire vulnerability. Thus in the future, a Machine Learning algorithm will be designed and implemented for the early detection of wildfires. A simulator will be used to evaluate the effectiveness of the proposed solution, and the results of the simulation will be presented.

Keywords: moderate resolution imaging spectroradiometer, advanced fire information system, machine learning algorithm, detection of wildfires

Procedia PDF Downloads 58

Authors: Lorico D. S. Lapitan Jr., Yihan Xu, Yuan Guo, Dejian Zhou

Abstract:

The ability of ultrasensitive detection of specific genes and discrimination of single nucleotide polymorphisms is important for clinical diagnosis and biomedical research. Herein, we report the development of a new ultrasensitive approach for label-free DNA detection using magnetic nanoparticle (MNP) assisted rapid target capture/separation in combination with signal amplification using poly-enzyme tagged polymer nanobead. The sensor uses an MNP linked capture DNA and a biotin modified signal DNA to sandwich bind the target followed by ligation to provide high single-nucleotide polymorphism discrimination. Only the presence of a perfect match target DNA yields a covalent linkage between the capture and signal DNAs for subsequent conjugation of a neutravidin-modified horseradish peroxidase (HRP) enzyme through the strong biotin-nuetravidin interaction. This converts each captured DNA target into an HRP which can convert millions of copies of a non-fluorescent substrate (amplex red) to a highly fluorescent product (resorufin), for great signal amplification. The use of polymer nanobead each tagged with thousands of copies of HRPs as the signal amplifier greatly improves the signal amplification power, leading to greatly improved sensitivity. We show our biosensing approach can specifically detect an unlabeled DNA target down to 10 aM with a wide dynamic range of 5 orders of magnitude (from 0.001 fM to 100.0 fM). Furthermore, our approach has a high discrimination between a perfectly matched gene and its cancer-related single-base mismatch targets (SNPs): It can positively detect the perfect match DNA target even in the presence of 100 fold excess of co-existing SNPs. This sensing approach also works robustly in clinical relevant media (e.g. 10% human serum) and gives almost the same SNP discrimination ratio as that in clean buffers. Therefore, this ultrasensitive SNP biosensor appears to be well-suited for potential diagnostic applications of genetic diseases.

Keywords: DNA detection, polymer beads, signal amplification, single nucleotide polymorphisms

Procedia PDF Downloads 229

Authors: Olomon Wu, Hung Lu, Nick Wilkins, Daniel Kerr, Zekeriya Aliyazicioglu, H. K. Hwang

Abstract:

Multiple Input Multiple Output (MIMO) radar has received increasing attention in recent years. MIMO radar has many advantages over conventional phased array radar such as target detection, resolution enhancement, and interference suppression. In this paper, the results are presented from a simulation study of MIMO Uniformly-Spaced Linear Array (ULA) antennas. The performance is investigated under varied parameters, including varied array size, Pseudo Random (PN) sequence length, number of snapshots, and Signal to Noise Ratio (SNR). The results of MIMO are compared to a traditional array antenna.

Keywords: MIMO radar, phased array antenna, target detection, radar signal processing

Procedia PDF Downloads 509

Authors: Jagannath Singh, Durga Prasad Mohapatra

Abstract:

Software refactoring is very essential for maintaining the software quality. It is an usual practice that we first design the software and then go for coding. But after coding is completed, if the requirement changes slightly or our expected output is not achieved, then we change the codes. For each small code change, we cannot change the design. In course of time, due to these small changes made to the code, the software design decays. Software refactoring is used to restructure the code in order to improve the design and quality of the software. In this paper, we propose an approach for performing code refactoring. We use slice-based cohesion metrics to identify the target methods which requires refactoring. After identifying the target methods, we use program slicing to divide the target method into two parts. Finally, we have used the concepts of Aspects to adjust the code structure so that the external behaviour of the original module does not change.

Keywords: software refactoring, program slicing, AOP, cohesion metrics, code restructure, AspectJ

Procedia PDF Downloads 476

Authors: Gregory Sullivan

Abstract:

The evolution of global warming has escalated the number and complexity of forest fires around the world. As an example, the United States and Brazil combined generated more than 30,000 forest fires last year. The impact to our environment, structures and individuals is incalculable. The world has learned to try to take this in stride, trying multiple ways to contain fires. Some countries are trying to use cameras in limited areas. There are discussions of using hundreds of low earth orbit satellites and linking them together, and, interfacing them through ground networks. These are all truly noble attempts to defeat the forest fire phenomenon. But there is a better, simpler answer. A bigger piece of the solutions puzzle is to see the fires while they are small, soon after initiation. The approach is to see the fires while they are very small and report their location (latitude and longitude) to local first responders. This is done by placing a sensor at geostationary orbit (GEO: 26,000 miles above the earth). By placing this small satellite in GEO, we can “stare” at the earth, and sense temperature changes. We do not “see” fires, but “measure” temperature changes. This has already been demonstrated on an experimental scale. Fires were seen at close to initiation, and info forwarded to first responders. it were the first to identify the fires 7 out of 8 times. The goal is to have a small independent satellite at GEO orbit focused only on forest fire initiation. Thus, with one small satellite, focused only on forest fire initiation, we hope to greatly decrease the impact to persons, property and the environment.

Keywords: space detection, wildfire early warning, demonstration wildfire detection and action from space, space detection to first responders

Procedia PDF Downloads 35

Authors: Shilpa Khobragade, Carlos Da Silva Granja, Niklas Sandström, Igor Efimov, Victor P. Ostanin, Wouter van der Wijngaart, David Klenerman, Sourav K. Ghosh

Abstract:

Rapid, label-free and direct detection of pathogenic bacteria is critical for the prevention of disease outbreaks. This paper for the first time attempts to probe the nonlinear acoustic response of quartz crystal resonator (QCR) functionalized with specific DNA aptamers for direct detection and quantification of viable E. coli KCTC 2571 bacteria. DNA aptamers were immobilized through biotin and streptavidin conjugation, onto the gold surface of QCR to capture the target bacteria and the detection was accomplished by shift in amplitude of the peak 3f signal (3 times the drive frequency) upon binding, when driven near fundamental resonance frequency. The developed nonlinear acoustic aptasensor system demonstrated better reliability than conventional resonance frequency shift and energy dissipation monitoring that were recorded simultaneously. This sensing system could directly detect 10⁽⁵⁾ cells/mL target bacteria within 30 min or less and had high specificity towards E. coli KCTC 2571 bacteria as compared to the same concentration of S.typhi bacteria. Aptasensor response was observed for the bacterial suspensions ranging from 10⁽⁵⁾-10⁽⁸⁾ cells/mL. Conclusively, this nonlinear acoustic aptasensor is simple to use, gives real-time output, cost-effective and has the potential for rapid, specific, label-free direction detection of bacteria.

Keywords: acoustic, aptasensor, detection, nonlinear

Procedia PDF Downloads 535

Authors: Pavel Chmelar, Martin Dobrovolny

Abstract:

Laser projection or laser footprint detection is today widely used in many fields of robotics, measurement, or electronics. The system accuracy strictly depends on precise laser footprint detection on target objects. This article deals with the laser line detection based on the RGB segmentation and the component labeling. As a measurement device was used the developed optical rangefinder. The optical rangefinder is equipped with vertical sweeping of the laser beam and high quality camera. This system was developed mainly for automatic exploration and mapping of unknown spaces. In the first section is presented a new detection algorithm. In the second section are presented measurements results. The measurements were performed in variable light conditions in interiors. The last part of the article present achieved results and their differences between day and night measurements.

Keywords: color segmentation, component labelling, laser line detection, automatic mapping, distance measurement, vector map

Procedia PDF Downloads 396

Authors: McClain Thiel

Abstract:

Object detection and localization has historically required two or more sensors due to the loss of information from 3D to 2D space, however, most surveillance systems currently in use in the real world only have one sensor per location. Generally, this consists of a single low-resolution camera positioned above the area under observation (mall, jewelry store, traffic camera). This is not sufficient for robust 3D tracking for applications such as security or more recent relevance, contract tracing. This paper proposes a lightweight system for 3D person tracking that requires no additional hardware, based on compressed object detection convolutional-nets, facial landmark detection, and projective geometry. This approach involves classifying the target into a demographic category and then making assumptions about the relative locations of facial landmarks from the demographic information, and from there using simple projective geometry and known constants to find the target's location in 3D space. Preliminary testing, although severely lacking, suggests reasonable success in 3D tracking under ideal conditions.

Keywords: monocular distancing, computer vision, facial analysis, 3D localization

Procedia PDF Downloads 106

Authors: Bhekisipho Twala, Mantepu Masetshaba, Ramapulana Nkoana

Abstract:

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. However, an increasingly controversial question is whether such systems can outperform the single best classifier, and if so, what form of multiple classifiers system yields the most significant benefit. Also, multi-target tracking detection using multiple sensors is an important research field in mobile techniques and military applications. In this paper, several multiple classifiers systems are evaluated in terms of their ability to predict a system’s failure or success for multi-sensor target tracking tasks. The Bristol Eden project dataset is utilised for this task. Experimental and simulation results show that the human activity identification system can fulfill requirements of target tracking due to improved sensors classification performances with multiple classifier systems constructed using boosting achieving higher accuracy rates.

Keywords: single classifier, ensemble learning, multi-target tracking, multiple classifiers

Procedia PDF Downloads 230

Authors: Nilubon Kurubanjerdjit, Nattakarn Iam-On, Ka-Lok Ng

Abstract:

MicroRNAs are small non-coding RNA found in many different species. They play crucial roles in cancer such as biological processes of apoptosis and proliferation. The identification of microRNA-target genes can be an essential first step towards to reveal the role of microRNA in various cancer types. In this paper, we predict miRNA-target genes for lung cancer by integrating prediction scores from miRanda and PITA algorithms used as a feature vector of miRNA-target interaction. Then, machine-learning algorithms were implemented for making a final prediction. The approach developed in this study should be of value for future studies into understanding the role of miRNAs in molecular mechanisms enabling lung cancer formation.

Keywords: microRNA, miRNAs, lung cancer, machine learning, Naïve Bayes, SVM

Procedia PDF Downloads 366

Authors: Yusuf Ulaş Kabukçu, Si̇nan Çeli̇k, Onur Salan, Mai̇de Altuntaş, Mert Can Dalkiran, Gökseni̇n Bozdağ, Metehan Bulut, Fati̇h Yaman

Abstract:

This study presents a more compact implementation of the 2.4GHz MIT Coffee Can Doppler Radar for 2.6GHz operating frequency. The main difference of our prototype depends on the use of microstrip antennas which makes it possible to transport with a small robotic vehicle. We have designed our radar system with two different channels: Tx and Rx. The system mainly consists of Voltage Controlled Oscillator (VCO) source, low noise amplifiers, microstrip antennas, splitter, mixer, low pass filter, and necessary RF connectors with cables. The two microstrip antennas, one is element for transmitter and the other one is array for receiver channel, was designed, fabricated and verified by experiments. The system has two operation modes: speed detection and range detection. If the switch of the operation mode is ‘Off’, only CW signal transmitted for speed measurement. When the switch is ‘On’, CW is frequency-modulated and range detection is possible. In speed detection mode, high frequency (2.6 GHz) is generated by a VCO, and then amplified to reach a reasonable level of transmit power. Before transmitting the amplified signal through a microstrip patch antenna, a splitter used in order to compare the frequencies of transmitted and received signals. Half of amplified signal (LO) is forwarded to a mixer, which helps us to compare the frequencies of transmitted and received (RF) and has the IF output, or in other words information of Doppler frequency. Then, IF output is filtered and amplified to process the signal digitally. Filtered and amplified signal showing Doppler frequency is used as an input of audio input of a computer. After getting this data Doppler frequency is shown as a speed change on a figure via Matlab script. According to experimental field measurements the accuracy of speed measurement is approximately %90. In range detection mode, a chirp signal is used to form a FM chirp. This FM chirp helps to determine the range of the target since only Doppler frequency measured with CW is not enough for range detection. Such a FMCW Doppler radar may be used in border security of the countries since it is capable of both speed and range detection.

Keywords: doppler radar, FMCW, range detection, speed detection

Procedia PDF Downloads 362

Authors: Jaime Martín-de-Nicolás, David Mata-Moya, Nerea del-Rey-Maestre, Pedro Gómez-del-Hoyo, María-Pilar Jarabo-Amores

Abstract:

Ship detection is nowadays quite an important issue in tasks related to sea traffic control, fishery management and ship search and rescue. Although it has traditionally been carried out by patrol ships or aircrafts, coverage and weather conditions and sea state can become a problem. Synthetic aperture radars can surpass these coverage limitations and work under any climatological condition. A fast CFAR ship detector based on a robust statistical modeling of sea clutter with respect to sea states in SAR images is used. In this paper, the minimum SNR required to obtain a given detection probability with a given false alarm rate for any sea state is determined. A Gaussian target model using real SAR data is considered. Results show that SNR does not depend heavily on the class considered. Provided there is some variation in the backscattering of targets in SAR imagery, the detection probability is limited and a post-processing stage based on morphology would be suitable.

Keywords: SAR, generalized gamma distribution, detection curves, radar detection

Procedia PDF Downloads 429

Authors: Vijaya Yuvaram Singh V M, Kameshwar Rao J V

Abstract:

The challenge with development of neural network based methods for medical is the availability of data. Anatomical landmark detection in the medical domain is a process to find points on the x-ray scan report of the patient. Most of the time this task is done manually by trained professionals as it requires precision and domain knowledge. Traditionally object detection based methods are used for landmark detection. Here, we utilize reinforcement learning and query based method to train a single agent capable of detecting multiple landmarks. A deep Q network agent is trained to detect single and multiple landmarks present on hip and shoulder from x-ray scan of a patient. Here a single agent is trained to find multiple landmark making it superior to having individual agents per landmark. For the initial study, five images of different patients are used as the environment and tested the agents performance on two unseen images.

Keywords: reinforcement learning, medical landmark detection, multi target detection, deep neural network

Procedia PDF Downloads 118

Authors: Sungsoo Na, Chanho Park

Abstract:

Lung cancer is one of the most common severe diseases driving to the death of a human. Lung cancer can be divided into two cases of small-cell lung cancer (SCLC) and non-SCLC (NSCLC), and about 80% of lung cancers belong to the case of NSCLC. From several studies, the correlation between epidermal growth factor receptor (EGFR) and NSCLCs has been investigated. Therefore, EGFR inhibitor drugs such as gefitinib and erlotinib have been used as lung cancer treatments. However, the treatments result showed low response (10~20%) in clinical trials due to EGFR mutations that cause the drug resistance. Patients with resistance to EGFR inhibitor drugs usually are positive to KRAS mutation. Therefore, assessment of EGFR and KRAS mutation is essential for target therapies of NSCLC patient. In order to overcome the limitation of conventional therapies, overall EGFR and KRAS mutations have to be monitored. In this work, the only detection of EGFR will be presented. A variety of techniques has been presented for the detection of EGFR mutations. The standard detection method of EGFR mutation in ctDNA relies on real-time polymerase chain reaction (PCR). Real-time PCR method provides high sensitive detection performance. However, as the amplification step increases cost effect and complexity increase as well. Other types of technology such as BEAMing, next generation sequencing (NGS), an electrochemical sensor and silicon nanowire field-effect transistor have been presented. However, those technologies have limitations of low sensitivity, high cost and complexity of data analyzation. In this report, we propose a label-free and high-sensitive detection method of lung cancer using quartz crystal microbalance based platform. The proposed platform is able to sense lung cancer mutant DNA with a limit of detection of 1nM.

Keywords: cancer DNA, resonance frequency, quartz crystal microbalance, lung cancer

Procedia PDF Downloads 205

Authors: Nicholas V. Scott, Jack McCarthy

Abstract:

Military, law enforcement, and counter terrorism organizations are often tasked with target detection and image characterization of scenes containing explosive materials in various types of environments where light scattering intensity is high. Mitigation of this photonic noise using classical digital filtration and signal processing can be difficult. This is partially due to the lack of robust image processing methods for photonic noise removal, which strongly influence high resolution target detection and machine learning-based pattern recognition. Such analysis is crucial to the delivery of reliable intelligence. Polarization filters are a possible method for ambient glare reduction by allowing only certain modes of the electromagnetic field to be captured, providing strong scene contrast. An experiment was carried out utilizing a polarization lens attached to a hyperspectral imagery camera for the purpose of exploring the degree to which an imaged polarized scene of potassium, phosphorus, and nitrogen mixture allows for improved target detection and image segmentation. Preliminary imagery results based on the application of machine learning algorithms, including competitive leaky learning and distance metric analysis, to polarized hyperspectral imagery, suggest that polarization filters provide a slight advantage in image segmentation. The results of this work have implications for understanding the presence of explosive material in dry, desert areas where reflective glare is a significant impediment to scene characterization.

Keywords: explosive material, hyperspectral imagery, image segmentation, machine learning, polarization

Procedia PDF Downloads 112

Authors: Youngsun Moon, Yeong-Ju Go, Jong-Soo Choi

Abstract:

Most drones that currently have surveillance/reconnaissance missions are basically equipped with optical equipment, but we also need to use a microphone array to estimate the location of the acoustic source. This can provide additional information in the absence of optical equipment. The purpose of this study is to estimate Direction of Arrival (DOA) based on Time Difference of Arrival (TDOA) estimation of the acoustic source in the drone. The problem is that it is impossible to measure the clear target acoustic source because of the drone noise. To overcome this problem is to separate the drone noise and the target acoustic source using Blind Source Separation(BSS) based on Independent Component Analysis(ICA). ICA can be performed assuming that the drone noise and target acoustic source are independent and each signal has non-gaussianity. For maximized non-gaussianity each signal, we use Negentropy and Kurtosis based on probability theory. As a result, we can improve TDOA estimation and DOA estimation of the target source in the noisy environment. We simulated the performance of the DOA algorithm applying BSS algorithm, and demonstrated the simulation through experiment at the anechoic wind tunnel.

Keywords: aeroacoustics, acoustic source detection, time difference of arrival, direction of arrival, blind source separation, independent component analysis, drone

Procedia PDF Downloads 132

Authors: Dilip K. Prasad, C. Krishna Prasath, Deepu Rajan, Lily Rachmawati, Eshan Rajabally, Chai Quek

Abstract:

This paper discusses the technical challenges in maritime image processing and machine vision problems for video streams generated by cameras. Even well documented problems of horizon detection and registration of frames in a video are very challenging in maritime scenarios. More advanced problems of background subtraction and object detection in video streams are very challenging. Challenges arising from the dynamic nature of the background, unavailability of static cues, presence of small objects at distant backgrounds, illumination effects, all contribute to the challenges as discussed here.

Keywords: autonomous maritime vehicle, object detection, situation awareness, tracking

Procedia PDF Downloads 420

Authors: Tegan H. Emerson, Colin C. Olson, George Stantchev, Jason A. Edelberg, Michael Wilson

Abstract:

Detecting small targets at range is difficult because there is not enough spatial information present in an image sub-region containing the target to use correlation-based methods to differentiate it from dynamic confusers present in the scene. Moreover, this lack of spatial information also disqualifies the use of most state-of-the-art deep learning image-based classifiers. Here, we use characteristics of target tracks extracted from video sequences as data from which to derive distinguishing topological features that help robustly differentiate targets of interest from confusers. In particular, we calculate persistent homology from time-delayed embeddings of dynamic statistics calculated from motion tracks extracted from a wide field-of-view video stream. In short, we use topological methods to extract features related to target motion dynamics that are useful for classification and disambiguation and show that small targets can be detected at range with high probability.

Keywords: motion tracks, persistence images, time-delay embedding, topological data analysis

Procedia PDF Downloads 83

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 82

Authors: Junichiro Kawaguchi

Abstract:

Space debris problems have emerged and threatened the use of low earth orbit around the Earth owing to a large number of spacecraft. In debris removal, a number of research and patents have been proposed and published so far. They assume servicing spacecraft, robots to be built for accessing the target debris objects. The robots should be sophisticated enough automatically to access the debris articulating the attitude and the translation motion with respect to the debris. This paper presents the idea of using the torpedo-like third unsophisticated and disposable body, in addition to the first body of the servicing robot and the second body of the target debris. The third body is launched from the first body from a distance farer than the size of the second body. This paper presents the method and the system, so that the third body is launched from the first body. The third body carries both a net and an inflatable or extendible drag deceleration device and is built small and light. This method enables even a micro to nano satellite to perform contactless and multiple debris removal even via a single flight.

Keywords: ballute, debris removal, echo satellite, gossamer, gun-net, inflatable space structure, small satellite, un-cooperated target

Procedia PDF Downloads 90

Authors: Aika Umemuro, Mitsuru Sato, Mizuki Narita, Saya Hori, Saya Sakurai, Tomomi Nakayama, Ayano Nakazawa, Toshihiro Ogura

Abstract:

Mammography requires the detection of very small calcifications, and physicians search for microcalcifications by magnifying the images as they read them. The mouse is necessary to zoom in on the images, but this can be tiring and distracting when many images are read in a single day. Therefore, an image magnification system combining an eye-detector and a simple electroencephalograph (EEG) scanner was devised, and its operability was evaluated. Two experiments were conducted in this study: the measurement of eye-detection error using an eye-detector and the measurement of the time required for image magnification using a simple EEG scanner. Eye-detector validation showed that the mean distance of eye-detection error ranged from 0.64 cm to 2.17 cm, with an overall mean of 1.24 ± 0.81 cm for the observers. The results showed that the eye detection error was small enough for the magnified area of the mammographic image. The average time required for point magnification in the verification of the simple EEG scanner ranged from 5.85 to 16.73 seconds, and individual differences were observed. The reason for this may be that the size of the simple EEG scanner used was not adjustable, so it did not fit well for some subjects. The use of a simple EEG scanner with size adjustment would solve this problem. Therefore, the image magnification system using the eye-detector and the simple EEG scanner is useful.

Keywords: EEG scanner, eye-detector, mammography, observers

Procedia PDF Downloads 195

Authors: Fouzi Harrou, Ying Sun, Sofiane Khadraoui

Abstract:

Anomaly detection based on Principal Component Analysis (PCA) was studied intensively and largely applied to multivariate processes with highly cross-correlated process variables. Monitoring metrics such as the Hotelling's T2 and the Q statistics are usually used in PCA-based monitoring to elucidate the pattern variations in the principal and residual subspaces, respectively. However, these metrics are ill suited to detect small faults. In this paper, the Exponentially Weighted Moving Average (EWMA) based on the Q and T statistics, T2-EWMA and Q-EWMA, were developed for detecting faults in the process mean. The performance of the proposed methods was compared with that of the conventional PCA-based fault detection method using synthetic data. The results clearly show the benefit and the effectiveness of the proposed methods over the conventional PCA method, especially for detecting small faults in highly correlated multivariate data.

Keywords: data-driven method, process control, anomaly detection, dimensionality reduction

Procedia PDF Downloads 268

Authors: Deepanjali Gurav, Kun Qian

Abstract:

In-vitro metabolic diagnosis relies on designed materials-based analytical platforms for detection of selected metabolites in biological samples, which has a key role in disease detection and therapeutic evaluation in clinics. However, the basic challenge deals with developing a simple approach for metabolic analysis in bio-samples with high sample complexity and low molecular abundance. In this work, we report a designer plasmonic nanoshells based platform for direct detection of small metabolites in clinical samples for in-vitro metabolic diagnostics. We first synthesized a series of plasmonic core-shell particles with tunable nanoshell structures. The optimized plasmonic nanoshells as new matrices allowed fast, multiplex, sensitive, and selective LDI MS (Laser desorption/ionization mass spectrometry) detection of small metabolites in 0.5 μL of bio-fluids without enrichment or purification. Furthermore, coupling with isotopic quantification of selected metabolites, we demonstrated the use of these plasmonic nanoshells for disease detection and therapeutic evaluation in clinics. For disease detection, we identified patients with postoperative brain infection through glucose quantitation and daily monitoring by cerebrospinal fluid (CSF) analysis. For therapeutic evaluation, we investigated drug distribution in blood and CSF systems and validated the function and permeability of blood-brain/CSF-barriers, during therapeutic treatment of patients with cerebral edema for pharmacokinetic study. Our work sheds light on the design of materials for high-performance metabolic analysis and precision diagnostics in real cases.

Keywords: plasmonic nanoparticles, metabolites, fingerprinting, mass spectrometry, in-vitro diagnostics

Procedia PDF Downloads 109

Authors: Andrii Shalaginov, Katrin Franke, Xiongwei Huang

Abstract:

One of the leading problems in Cyber Security today is the emergence of targeted attacks conducted by adversaries with access to sophisticated tools. These attacks usually steal senior level employee system privileges, in order to gain unauthorized access to confidential knowledge and valuable intellectual property. Malware used for initial compromise of the systems are sophisticated and may target zero-day vulnerabilities. In this work we utilize common behaviour of malware called ”beacon”, which implies that infected hosts communicate to Command and Control servers at regular intervals that have relatively small time variations. By analysing such beacon activity through passive network monitoring, it is possible to detect potential malware infections. So, we focus on time gaps as indicators of possible C2 activity in targeted enterprise networks. We represent DNS log files as a graph, whose vertices are destination domains and edges are timestamps. Then by using four periodicity detection algorithms for each pair of internal-external communications, we check timestamp sequences to identify the beacon activities. Finally, based on the graph structure, we infer the existence of other infected hosts and malicious domains enrolled in the attack activities.

Keywords: malware detection, network security, targeted attack, computational intelligence

Procedia PDF Downloads 228

Authors: Tao Song, Hao Cheng, Guangfeng Tian, Chuang Xu

Abstract:

An autonomous emergency braking system is an advanced driving assistance system that enables vehicle collision avoidance and pedestrian collision avoidance to improve vehicle safety. At present, because the pedestrian target is small, and the mobility is large, the pedestrian AEB system is faced with more technical difficulties and higher functional requirements. In this paper, a method of pedestrian target selection based on a variable width funnel is proposed. Based on the current position and predicted position of pedestrians, the relative position of vehicle and pedestrian at the time of collision is calculated, and different braking strategies are adopted according to the hazard level of pedestrian collisions. In the CNCAP standard operating conditions, comparing the method of considering only the current position of pedestrians and the method of considering pedestrian prediction position, as well as the method based on fixed width funnel and variable width funnel, the results show that, based on variable width funnel, the choice of pedestrian target will be more accurate and the opportunity of the intervention of AEB system will be more reasonable by considering the predicted position of the pedestrian target and vehicle's lateral motion.

Keywords: automatic emergency braking system, pedestrian target selection, TTC, variable width funnel

Procedia PDF Downloads 131

Authors: Ma Lei-Lei, Zhou You

Abstract:

Aiming at the problems of low detection accuracy of deep learning algorithm in traffic sign detection, this paper proposes improved EfficientDet based traffic sign detection algorithm. Multi-head self-attention is introduced in the minimum resolution layer of the backbone of EfficientDet to achieve effective aggregation of local and global depth information, and this study proposes an improved feature fusion pyramid with increased vertical cross-layer connections, which improves the performance of the model while introducing a small amount of complexity, the Balanced L1 Loss is introduced to replace the original regression loss function Smooth L1 Loss, which solves the problem of balance in the loss function. Experimental results show, the algorithm proposed in this study is suitable for the task of traffic sign detection. Compared with other models, the improved EfficientDet has the best detection accuracy. Although the test speed is not completely dominant, it still meets the real-time requirement.

Keywords: convolutional neural network, transformer, feature pyramid networks, loss function

Procedia PDF Downloads 73

Authors: V. S. S. Kumar, V. Ramya

Abstract:

In the modern electronic warfare, the signal scenario is changing at a rapid pace with the introduction of Low Probability of Intercept (LPI) radars. In the modern battlefield, radar system faces serious threats from passive intercept receivers such as Electronic Attack (EA) and Anti-Radiation Missiles (ARMs). To perform necessary target detection and tracking and simultaneously hide themselves from enemy attack, radar systems should be LPI. These LPI radars use a variety of complex signal modulation schemes together with pulse compression with the aid of advancement in signal processing capabilities of the radar such that the radar performs target detection and tracking while simultaneously hiding enemy from attack such as EA etc., thus posing a major challenge to the ES/ELINT receivers. Today an increasing number of LPI radars are being introduced into the modern platforms and weapon systems so these LPI radars created a requirement for the armed forces to develop new techniques, strategies and equipment to counter them. This paper presents various modulation techniques used in generation of LPI signals and development of Time Frequency Algorithms to analyse those signals.

Keywords: anti-radiation missiles, cross terms, electronic attack, electronic intelligence, electronic warfare, intercept receiver, low probability of intercept

Procedia PDF Downloads 409

Authors: Neeraj Neeraj, Soumen Basu, Banibrata Maity

Abstract:

Glutathione (GSH) is one of the most important biomolecules having small molecular weight, which helps in various cellular functions like regulation of gene, xenobiotic metabolism, preservation of intracellular redox activities, signal transduction, etc. Therefore, the detection of GSH requires huge attention by using extremely selective and sensitive techniques. Herein, a rapid fluorometric nanosensor is designed by combining carbon dots (Cdots) and MnO₂ nanoparticles of different sizes for the detection of GSH. The bottom-up approach, i.e., microwave method, was used for the preparation of the water soluble and greatly fluorescent Cdots by using ascorbic acid as a precursor. MnO₂ nanospheres of different sizes (large, medium, and small) were prepared by varying the ratio of concentration of methionine and KMnO₄ at room temperature, which was confirmed by HRTEM analysis. The successive addition of MnO₂ nanospheres in Cdots results fluorescence quenching. From the fluorescence intensity data, Stern-Volmer quenching constant values (KS-V) were evaluated. From the fluorescence intensity and lifetime analysis, it was found that the degree of fluorescence quenching of Cdots followed the order: large > medium > small. Moreover, fluorescence recovery studies were also performed in the presence of GSH. Fluorescence restoration studies also show the order of turn on follows the same order, i.e., large > medium > small, which was also confirmed by quantum yield and lifetime studies. The limits of detection (LOD) of GSH in presence of Cdots@different sized MnO₂ nanospheres were also evaluated. It was observed thatLOD values were in μM region and lowest in case of large MnO₂ nanospheres. The separation distance (d) between Cdots and the surface of different MnO₂ nanospheres was determined. The d values increase with increase in the size of the MnO₂ nanospheres. In summary, the synthesized Cdots@MnO₂ nanocomposites acted as a rapid, simple, economical as well as environmental-friendly nanosensor for the detection of GSH.

Keywords: carbon dots, fluorescence, glutathione, MnO₂ nanospheres, turn off-on

Procedia PDF Downloads 119

Authors: N. Ghatwary, A. Ahmed, H. Jalab

Abstract:

In this paper, an approach for the liver tumor detection in computed tomography (CT) images is represented. The detection process is based on classifying the features of target liver cell to either tumor or non-tumor. Fractional differential (FD) is applied for enhancement of Liver CT images, with the aim of enhancing texture and edge features. Later on, a fusion method is applied to merge between the various enhanced images and produce a variety of feature improvement, which will increase the accuracy of classification. Each image is divided into NxN non-overlapping blocks, to extract the desired features. Support vector machines (SVM) classifier is trained later on a supplied dataset different from the tested one. Finally, the block cells are identified whether they are classified as tumor or not. Our approach is validated on a group of patients’ CT liver tumor datasets. The experiment results demonstrated the efficiency of detection in the proposed technique.

Keywords: fractional differential (FD), computed tomography (CT), fusion, aplha, texture features.

Procedia PDF Downloads 330