Narrow Results

This paper presents a computer-assisted diagnostic system for mass detection and classification, which performs mass detection on regions of interest followed by the benign-malignant classification on detected masses. In order for mass detection to be effective, a sequence of preprocessing steps are designed to enhance the intensity of a region of interest, remove the noise effects and locate suspicious masses using five texture features generated from the spatial gray level difference matrix (SGLDM) and fractal dimension. Finally, a probabilistic neural network (PNN) coupled with entropic thresholding techniques is developed for mass extraction. Since the shapes of masses are crucial in classification between benignancy and malignancy, four shape features are further generated and joined with the five features previously used in mass detection to be implemented in another PNN for mass classification. To evaluate our designed system a data set collected in the Taichung Veteran General Hospital, Taiwan, R.O.C. was used for performance evaluation. The results are encouraging and have shown promise of our system.

An essential component of the immune system that aids in the fight against pathogens is white blood cells. One of the most prevalent blood diseases, leukemia can be fatal if not properly diagnosed. Diagnosing this disease at an early stage may reduce the severity of the disease. This research intends to propose an ensemble model with improved U-net for leukemia detection (EMIULD) with the following four phases: preprocessing, segmentation, feature extraction and detection. The preprocessing step involves preprocessing the blood smear image, which includes filtering and scaling the image. The segmentation phase is applied to the preprocessed image, and U-Net-based segmentation is used to segment the image. As a result, features for the segmented images are extracted, including better Local Gabor XOR Pattern (LGXP), area, and grid-based form features. The extracted features are fed into the suggested ensemble model, which consists of Deep Convolutional Neural Network (DCNN), Support Vector Machine (SVM) and Random Forest (RF) classifiers, with the purpose of detecting leukemia. Finally, the proposed Bidirectional Long Short-Term Memory (Bi-LSTM) network to predict whether the given blood smear image is leukemia or not. The suggested model attained the best outcome when evaluated over the extant approaches.

Every year there are as many as 20,000 scientific papers and reports published about the science of climate and climate change, and the resulting impacts and policy implications. The vast majority of these publications are rigorously done and are peer reviewed before publication, Since about 1990, on a time scale of roughly every 4–6 years, top experts are being asked to assess the state of the science and the implications of the changes occurring in the climate. Internationally, this occurs through the Intergovernmental Panel on Climate Change (IPCC), and for the United States, through the US National Climate Assessments (NCAs). These assessments provide important input to policy considerations, at international, national, and local levels…

Classification of travel patterns including wandering is important for early recognition of cognitive deterioration and other health conditions in people with dementia (PWD). In this chapter, we develop machine learning (ML) and deep learning (DL) models to recognize dementia-related wandering patterns based on the orientation data available in mobile devices. In particular, we use DL with long short-term memory networks (LSTM) and bi-directional LSTM to detect direct, pacing, lapping and random travel patterns. Experimental results on a real dataset collected from 14 subjects show that deep LSTM classifiers improve the classification accuracy by 2% compared to traditional ML classifiers. The results and proposed methodology can be further improved so as to develop useful healthcare applications for dementia-related wandering monitoring and management.

The synthesis of the porphyrin-calix[4]arene conjugates was carried out using the Pd(0)-catalyzed amination of Zn(II) meso-(3-bromophenyl)porphyrinate with bis(3-aminopropoxy)substituted calix[4]arenes (in cone and 1,3-alternate conformations). One of the conjugates was demetalated to give free porphyrin base derivative. The investigation of the fluorescence of the conjugates was studied in the presence of 18 metal perchlorates. The zinc porphyrinate derivatives were found to quench fluorescence in the presence of Cu(II), Al(III) and Cr(III) cations as well as on protonation. Metal-free conjugate was shown to act as a molecular probe for Zn(II), Cu(II) and Cd(II) cations due to strong and different changes of the emission caused by these metals.

As medical countermeasures are usually not immediately available during pandemics, non-pharmaceutical measures are important and often the only options available to governments before the arrival of pharmaceutical interventions. This chapter provides an overview of containment measures historically and typically used in pandemic outbreak of respiratory diseases and in the context of Coronavirus disease 2019 (COVID-19) up until August 2021, summarizes the evidence on their effectiveness and efficiency, and considerations and impact from their deployment.

Measuring the proportions of sunlit areas of crop and weed leaves in field is very important to digital agriculture. In this paper, one way was studied to detect onions (crop) and weeds with using multi-spectral images. A system for acquiring multi-spectral images was built up with four filter: red(r), green (g), blue (b) and infrared (IR). L*a*b* space is used to discard the soil and non-plant (residues) in images. An algorithm of classifying onions from weeds in images was constructed. The distinguishing relatively error rate (DRER) is defined. The best representations of four components (r, g, b and IR) was suggested and used to distinguish onions from weeds.

The conception and realization of scale transformation stochastic resonance (STSR) are proposed, which are used to deal with problem of weak signal detection with large parameters that can not be resolved by traditional bistable system based on stochastic resonance. Magnetic flux leakage (MFL) signals inspection for oil well tubing defects is easily destroyed by noise. In order to detect weak MFL signals effectively, the proposed STSR technology is applied to the inspection. The result shows that the STSR technology has the potential application in engineering practice.

Flight security is directly influenced by flight plan conflicts. In this paper, various factors which cause conflicts in flight plan are discussed. Then, an optimization math model and the algorithm for detecting these conflicts are established. This algorithm is proved to be highly efficient in practice.

The various detection methods using distributed Bragg reflector porous silicon (DBR PSi) for sensing G-type nerve agent mimics have been developed. The versatile PSi has been prepared by an electrochemical etching through applied square current waveform for DBR. The manufactured DBR PSi exhibits unique optical properties providing the reflection of a specific wavelength in the optical reflectivity spectrum. The detection methods involve the shift of DBR peaks in reflectivity spectra under the exposure of vapors of nerve agent mimics. Rapid detections have been achieved in few seconds, in situ, when a laser is used as a light source. The red-shift of reflection peak resulted from the increase of refractive indices in PSi. Real-time detection for the nerve gases indicates that the measurement is reversible. The detection efficiency for nerve agent mimics is also increased, when LED (λ=520 nm) or laser (λ=530 nm) is used as an incident light source instead of tungsten-halogen lamp.

This paper discusses detection and matching of arbitrary image features or patterns. The common characteristics of feature extraction and matching are summarized which show that they can be considered as special cases of a more general problem—signal detection. However, the existing signal detection theories do not solve feature extraction and matching problems readily. Therefore, a general formulation of feature extraction and matching as a problem of signal detection is presented. This formulation unifies feature extraction and matching into a more general framework so that the two can be better integrated to form an automatic system for image matching or object recognition. Following this formulation, guidelines for designing algorithms for detection or matching of arbitrary image features or patterns which can be easily implemented or reconfigurated for many practical applications are derived. Sample algorithms resulting from this formulation and the associated experimental results with real image data are provided which demonstrate the performance and robustness of the methods.

Along with the fast increase of P2P users, P2P worm has become a severe threat to the P2P network and Internet. The P2P worm detection based on Information Correlation-PWDIC is presented in this paper. According to the information correlation, this paper establishes a series of filter rules to realize the detection and containment for P2P worm. Finally, a simulation experiment is given. The result shows that this P2P worm detection method has a good effect on P2P worm detection and also shows the distribution of resources has a great influence on the effect of containment for P2P worm spread.

A detection approach based on the principles of Fourier Transform Infrared Spectroscopy (FTIR) is presented for the trace level detection of toxic compounds in water. The main advantages of this approach are that it operates in heterogeneous aqueous environments, provides fast detection (< 10 min), and exhibits high sensitivity/selectivity to nonvolatile toxic materials with minimal false alarms. The key enablers to using FTIR for aqueous-based detection is the development of a selective and robust sampling protocol coupled to a miniaturized portable FTIR unit. The sampling approaches involve synthesizing and tailoring microporous, mesoporous, and nonporous metal oxide powders/films that are amenable for in situ FTIR measurements. In this paper we provide an overview of the material synthesis and surface modification strategies, and present results obtained using these materials for the low level detection of the organophosphate pesticide phosmet. Phosmet is used as a surrogate for the nerve agent VX.

Currently there exists a critical need within the military and homeland defense for highly sophisticated yet, small, lightweight portable sensors and detection systems for identifying and quantifying biological and biowarfare agents (BWA) in both liquid and aerosolized form. Our proposed BWA detection system is based upon Fourier Transform Infrared Spectroscopy (FTIR), where the main advantages of this approach are that it is reagentless, operates in heterogeneous aqueous environments, and provides fast detection and high sensitivity/selectivity to bacterial spores with minimal false alarms.

The key enabler to using FTIR for BWA detection is to develop selective and robust sampling protocols coupled to a miniaturized, portable FTIR unit. To that end, we have developed front-end liquid flow cells which incorporate electric field (E-Field) concentration methods for spores onto the surface of an Attenuated Total Reflection (ATR) IR crystal. IR spectra are presented which show collection and detection results with BG spores in water. The approaches we have developed take advantage of the fact that all spores are negatively charged in neutral pH solutions. Therefore, E-Field concentration of spores directly onto an ATR sampling element enables low level concentration measurements to be possible.

Detection of gaseous effluent plumes from airborne platforms provides a unique challenge to the remote sensing community. The measured signatures are a complicated combination of phenomenology including effects of the atmosphere, spectral characteristics of the background material under the plume, temperature contrast between the gas and the surface, and the concentration of the gas. All of these quantities vary spatially further complicating the detection problem. In complex scenes simple estimation of a “residual” spectrum may not be possible due to the variability in the scene background. A common detection scheme uses a matched filter formalism to compare laboratory-measured gas absorption spectra with measured pixel radiances. This methodology can not account for the variable signature strengths due to concentration path length and temperature contrast, nor does it take into account measured signatures that are observed in both absorption and emission in the same scene. We have developed a physics-based, forward model to predict in-scene signatures covering a wide range in gas / surface properties. This target space is reduced to a set of basis vectors using a geometrical model of the space. Corresponding background basis vectors are derived to describe the non-plume pixels in the image. A Generalized Likelihood Ratio Test is then used to discriminate between plume and non-plume pixels. Several species can be tested for iteratively. The algorithm is applied to airborne LWIR hyperspectral imagery collected by the Airborne Hyperspectral Imager (AHI) over a chemical facility with some ground truth. When compared to results from a clutter matched filter the physics-based signature approach shows significantly improved performance for the data set considered here.

Threats associated with bioaerosol weapons have been around for several decades. However, with the recent political developments that changed the image and dynamics of the international order and security, the visibility and importance of these bioaerosol threats have considerably increased. Over the last few years, Defence Research and Development Canada has investigated the spectrometric LIDAR-based standoff bioaerosol detection technique to address this menace. This technique has the advantages of rapidly monitoring the atmosphere over wide areas without physical intrusions and reporting an approaching threat before it reaches sensitive sites. However, it has the disadvantages of providing a quality of information that degrades as a function of range and bioaerosol concentration. In order to determine the importance of these disadvantages, Canada initiated in 1999 the SINBAHD (Standoff Integrated Bioaerosol Active Hyperspectral Detection) project investigating the standoff detection and characterization of threatening biological clouds by Laser-Induced Fluorescence (LIF) and intensified range-gated spectrometric detection techniques. This article reports an overview of the different lessons learned with this program. Finally, the BioSense project, a Technology Demonstration Program aiming at the next generation of wide area standoff bioaerosol sensing, mapping, tracking and classifying systems, is introduced.

The paper gives out a new method to detect weak known signal based on second order differential equation, the differential equation is listed to eliminate weak known signal through the characteristics of the source signal code and the mixing signals which have been received, then the differential equation only includes addition interference and mixed signal. The waveformcharacteristics of the source signal code te^−αt can be used to eliminate source signal code in the second order differential equation, solving differential equations and obtaining interference, which is subtracted by measured mixed signal, the tested signal can be resumed and detected.

Based on conductive film pull-sensitive effect, infrared image detection method of concrete micro-crack was put forward to solve the problem of long distance nondestructive detection. Firstly, basic principle of infrared detection technology was analyzed. Effect of environment temperature and atmospheric transmission process on target real temperature was considered. Secondly, conductive film electrothermal effect was analyzed. After electrifying, temperature of crack was higher than that of uncrack. Non-uniformity distribution of surface temperature was formed. Heat transfer mechanism of conductive film was discussed. Finally, infrared thermal image of conductive film was obtained by infrared thermal imager. Crack development process could be drawn under the action of external force. Combined with crack magnifier measurement, effect of conductive film emissivity on crack temperature was predicted. The relationship of crack width and temperature difference was discussed. The result indicated that the proposed detection method was feasible.

At construction sites, many pictures are taken for inspection and management of construction. Objects such as construction machinery, signages, signboard, construction workers, etc., are captured, but their existence and locations must be manually detected by humans. Thus, it is desirable to automate the object detection process in order to improve the efficiency. For detection of objects from digital images, machine learning with feature values of images has generally been employed. However, this method requires determination of features and contents, which is learned by humans, taking much labour and making it difficult to achieve satisfactory accuracy. On the other hand, deep learning can automatically determine these features and contents of various objects from digital images so that it can reduce labour and can increase accuracy compared to the conventional machine learning. Therefore, this research aims to automatically detect positions and shapes of objects from digital images by using deep learning. First, a dataset is created and Single Shot Multibox Detector (SSD) is employed for an object detection algorithm to detect positions. Next, re-detection of positions is performed by fine-tuning the weights of SSD. In addition, using detected object information can improve the efficiency of filing images. The shape of an object can be assumed using fully convolutional network (FCN). In this research, construction machinery, workers and signages were detected from digital images taken at construction sites by the proposed method. The proposed method has shown better performance compared to the conventional machine learning method. Finally, object position detection and shape detection are overlapped and the result shows the visually detailed object detection.

Listeria monocytogenes is a foodborne pathogen of great interest due to its unique epidemiological features, its ubiquity and the severity of the diseases it causes The purpose of this work was to study the presence of Listeria monocytogenes in modified-atmosphere-packaged (MAP) vegetables available to consumers in Valencia by normalized cultural method and multiplex PCR technique. L. monocytogenes was detected in a total of 23 among 70 MAP vegetables samples. Cultural method allowed the isolation of three strains of this pathogen while PCR yielded L. monocytogenes positive results in 22 samples.