Hybrid-based Method Research Articles

Comparative post-therapeutic dosimetry between 2D planar-based and hybrid-based methods for personalized Lu-177 treatment.

This study aims to compare the calculated absorbed dose in target organs and tumors obtained using the different imaging protocols and the calculation methodologies implemented by HERMES HybridViewer dosimetry software for 177Lu-PSMA I&T and 177Lu-DOTATATE therapy. Multiple time-point whole-body planar images and one SPECT/CT image were acquired from 18 patients including 177Lu-PSMA I&T (13 patients) and 177Lu-DOTATATE treatment (5 patients) after administration of 3.80-8.58GBq injected activity. The regions of interest were drawn in the whole body, kidneys, liver, urinary bladder, salivary glands, and tumors to determine the time-integrated activity (TIA) in source organs. Absorbed doses in target organs were calculated according to the Medical Internal Radiation Dose (MIRD) scheme using the HERMES HybridViewer dosimetry integrated with OLINDA/EXM V.2.1 that utilizes the non-uniform rational B-splines (NURBS) for computational digital phantom. The planar-based dosimetry showed a higher dose per injected activity compared to the hybrid-based dosimetry, primarily due to organ overlap. The highest difference in absorbed dose between the imaging scenarios was observed in the spleen with a variation of up to 51.6%, while the difference for other target organs and tumors was less than 40%. The dosimetry calculation derived from the 2D planar-based method consistently demonstrates a significantly higher absorbed dose in organs and tumors compared with the hybrid-based method. However, the hybrid method outperforms the planar method in terms of tumor visualization and overlap-free organ delineation.

A graph-based method for identifying critical pipe failure combinations in water distribution networks

ABSTRACT Water distribution networks (WDNs) are critical infrastructures prone to vulnerabilities which lead to failures. Identifying vulnerable components, especially multiple pipe failure combinations, is crucial for effective management and ensuring high reliability. Hydraulic simulations are commonly used for analysing the criticality of WDN, but are time-consuming and highly data-reliant, limiting the number of testable combinations. To address these limitations and constraints, a graph-based method is proposed to quantify the impact magnitude of multiple pipe failure scenarios on performance, enabling the identification of critical combinations. The proposed graph-based approach utilizes structural and topological characteristics of WDNs as well as spatial demand distribution to replicate hydraulic behaviour. The accuracy of the approach is assessed by testing it on three case studies with various pipe failure combinations, and the results are compared with hydraulic analyses. The results demonstrate a strong correlation (Spearman coefficient > 0.75) between graph-based ranking and state-of-the-art hydraulic-based ranking. Additionally, the method exhibits a significant computational gain factor of greater than 30 compared with the hydraulic-based method, rendering it valuable for actively exploring a wide range of critical pipe failure combinations and devising countermeasures. Furthermore, a hybrid-based method that integrates both the graph and hydraulic-based methods is proposed for enhanced accuracy and robust assessments.

Fake News Detection using Machine Learning

Abstract: In recent years, the proliferation of fake news has precipitated numerous social and political quandaries. As the predominant source of information shifts towards digital platforms, discerning accountability for disseminated opinions becomes increasingly challenging, hindering authentication of received information. Given the pervasive nature of ecological and societal dilemmas, the role of machine learning in combating fake messages on social media is paramount. The virality of messages, whether genuine or fabricated, underscores the necessity for an automated, resilient, dependable, and efficient detection mechanism amidst multifarious challenges. This review delves into the contemporary landscape of fake news detection mechanisms within social media. By examining the contextual backdrop of fake news and its ramifications on users, we explore various methodological approaches categorized as content-based, social context-based, and hybrid-based methods. Culminating with an elucidation of four pivotal research challenges, this paper aims to steer future endeavors towards advancing the field.

Effect of Features Extraction and Selection on the Evaluation of Machine Learning Models

The exponential growth of sophisticated malware attacks against computer systems, has alerted IT security experts on the shortcomings of traditional protection tools because, they became unable to detect new families of malware that are more advanced and use advanced tools such as polymorphism, metamorphism, and obfuscation tools. Nowadays, machine learning is widely used in several IT fields; and also in cybersecurity, and can be an essential tool for malware detection, moreover, it can go beyond the limits of classic malware detection methods, such as the signature-based method, the anomaly-based method and the hybrid-based method, etc. The purpose of this study is to analyze the feature selection and extraction effects on the performance of malware classification model using machine learning. The results show that reducing dimensionality of datasets can help to improve the efficiency of security models in restricted time but with high performance, Random Forest using chi-square achieves an accuracy of 99.51%.

A Hybrid Differential Transforms and Finite Difference Method to Numerical Solution of Convection–Diffusion Equation

In this work, we discuss a hybrid-based method on differential transforms and a finite difference method to numerical solution of convection–diffusion equation with Dirichlet’s type boundary conditions. The developed method is tested on various problems and the numerical results are reported in tabular and figure form. This method can be easily extended to handle non-linear convection–diffusion partial differential equations.

A homogeneous ensemble based dynamic artificial neural network for solving the intrusion detection problem

Network security is a mechanism of protecting the usability and integrity of any given network and its transmitted data. Network security's effectiveness is crucial to the network environment to ensure it is free from any threat, especially in the critical infrastructure (CI). The supervisory control and data acquisition systems in the CI are getting more connected to the internet, putting them in serious security concerns. Any malicious attack against these systems could cause considerable human, economic, and material damages. Thus, it leads to the emergence of the intrusion detection system (IDS). Theoretically, a modern IDS must handle a large amount of data with high accuracy. Ensemble-based, hybrid-based methods and their distinguished applications are a promising way to solve these issues. The efficiency of the IDS is mainly dependent on the selected data features and the used classification method. The artificial neural network (ANN) has been applied in various fields, but it requires adjustment on few parameters to work effectively. This study proposes a homogeneous ensemble based on single-class dynamic ANN (HOE-DANN). Each dynamic ANN (DANN) is optimized by a filter-wrapper method using a modified discrete cuttlefish algorithm based on rough set theory, and a migration-strategy based cuttlefish algorithm. Both algorithms simultaneously optimize the features, ANN structure, weights, and biases for creating the DANN. However, the threshold value of the ensemble model was set using the hill-climbing algorithm. The experiments were applied to well-known benchmark datasets, namely the KDD99, UNSW-NB15, and gas pipeline data logs (GPDL). The results show that the HOE-DANN outperforms the single model based on the DANN. Additionally, a comparison with several state-of-the-art methods has shown that the proposed method offers superior performance in terms of the detection rate (DR), false alarm rate (FAR), and classification accuracy (ACC). The HOE-DANN model was able to achieve DR of 97.47%, FAR of 2.25%, and ACC of 97.52% using the KDD99 dataset, DR of 99.93%, FAR of 13.13%, and ACC of 94.08% using the UNSW-NB15 dataset, and DR of 98.08%, FAR of 2.69%, and ACC of 94.50% using the GPDL dataset.

A review of image fusion techniques for pan-sharpening of high-resolution satellite imagery

Pan-sharpening methods are commonly used to synthesize multispectral and panchromatic images. Selecting an appropriate algorithm that maintains the spectral and spatial information content of input images is a challenging task. This review paper investigates a wide range of algorithms, including 41 methods. For this purpose, the methods were categorized as Component Substitution (CS-based), Multi-Resolution Analysis (MRA), Variational Optimization-based (VO), and Hybrid and were tested on a collection of 21 case studies. These include images from WorldView-2, 3 & 4, GeoEye-1, QuickBird, IKONOS, KompSat-2, KompSat-3A, TripleSat, Pleiades-1, Pleiades with the aerial platform, and Deimos-2. Neural network-based methods were excluded due to their substantial computational requirements for operational mapping purposes. The methods were evaluated based on four Spectral and three Spatial quality metrics. An Analysis Of Variance (ANOVA) was used to statistically compare the pan-sharpening categories. Results indicate that MRA-based methods performed better in terms of spectral quality, whereas most Hybrid-based methods had the highest spatial quality and CS-based methods had the lowest results both spectrally and spatially. The revisited version of the Additive Wavelet Luminance Proportional Pan-sharpening method had the highest spectral quality, whereas Generalized IHS with Best Trade-off Parameter with Additive Weights showed the highest spatial quality. CS-based methods generally had the fastest run-time, whereas the majority of methods belonging to MRA and VO categories had relatively long run times.

A hybrid-based method for Chinese domain lightweight ontology construction

This paper proposes a framework to automatically construct lightweight ontology from a corpus of Chinese domain Web documents. A hybrid-based method was used for domain lightweight ontology learning. Rule-based method, statistics-based method and cluster-based method were combined to complete two sub-tasks: concept extraction and taxonomic relationships extraction. Firstly, multiword terms were identified based on a set of rules as well as a Named Entity Module. Three statistic methods were employed jointly to rank the order of domain concepts. Secondly, clustering and subsumption methods were joined to construct taxonomy. Concepts were clustered into several groups through clustering method. Three similarity measures were defined to compute similarities between concepts, which aims at capturing semantic, spatial, and co-occurrence information. Subsumption method was adopted to construct taxonomic structure for each concept group, since taxonomic relations only existed between similar concepts. Thirdly, the definitions of the concepts extracted in the first step are collected from online Chinese Encyclopedia. On this collection of concept definitions, the rule-based method and a set of lexico-syntactic patterns were applied to extract taxonomic relationships and refine the taxonomy. Finally, we evaluate our method using gold-standard evaluation on domain of football games. In our evaluation, we compare our method with several classical algorithms. The experimental results show the effectiveness of our method.

HYBRID-BASED DENSE STEREO MATCHING

Stereo matching generating accurate and dense disparity maps is an indispensable technique for 3D exploitation of imagery in the fields of Computer vision and Photogrammetry. Although numerous solutions and advances have been proposed in the literature, occlusions, disparity discontinuities, sparse texture, image distortion, and illumination changes still lead to problematic issues and await better treatment. In this paper, a hybrid-based method based on semi-global matching is presented to tackle the challenges on dense stereo matching. To ease the sensitiveness of SGM cost aggregation towards penalty parameters, a formal way to provide proper penalty estimates is proposed. To this end, the study manipulates a shape-adaptive cross-based matching with an edge constraint to generate an initial disparity map for penalty estimation. Image edges, indicating the potential locations of occlusions as well as disparity discontinuities, are approved by the edge drawing algorithm to ensure the local support regions not to cover significant disparity changes. Besides, an additional penalty parameter 𝑃𝑒 is imposed onto the energy function of SGM cost aggregation to specifically handle edge pixels. Furthermore, the final disparities of edge pixels are found by weighting both values derived from the SGM cost aggregation and the U-SURF matching, providing more reliable estimates at disparity discontinuity areas. Evaluations on Middlebury stereo benchmarks demonstrate satisfactory performance and reveal the potency of the hybrid-based dense stereo matching method.

HYBRID-BASED DENSE STEREO MATCHING

Abstract. Stereo matching generating accurate and dense disparity maps is an indispensable technique for 3D exploitation of imagery in the fields of Computer vision and Photogrammetry. Although numerous solutions and advances have been proposed in the literature, occlusions, disparity discontinuities, sparse texture, image distortion, and illumination changes still lead to problematic issues and await better treatment. In this paper, a hybrid-based method based on semi-global matching is presented to tackle the challenges on dense stereo matching. To ease the sensitiveness of SGM cost aggregation towards penalty parameters, a formal way to provide proper penalty estimates is proposed. To this end, the study manipulates a shape-adaptive cross-based matching with an edge constraint to generate an initial disparity map for penalty estimation. Image edges, indicating the potential locations of occlusions as well as disparity discontinuities, are approved by the edge drawing algorithm to ensure the local support regions not to cover significant disparity changes. Besides, an additional penalty parameter 𝑃𝑒 is imposed onto the energy function of SGM cost aggregation to specifically handle edge pixels. Furthermore, the final disparities of edge pixels are found by weighting both values derived from the SGM cost aggregation and the U-SURF matching, providing more reliable estimates at disparity discontinuity areas. Evaluations on Middlebury stereo benchmarks demonstrate satisfactory performance and reveal the potency of the hybrid-based dense stereo matching method.

Fast Markerless Tracking for Augmented Reality in Planar Environment

Markerless tracking for augmented reality should not only be accurate but also fast enough to provide a seamless synchronization between real and virtual beings. Current reported methods showed that a vision-based tracking is accurate but requires high computational power. This paper proposes a real-time hybrid-based method for tracking unknown environments in markerless augmented reality. The proposed method provides collaboration of vision-based approach with accelerometers and gyroscopes sensors as camera pose predictor. To align the augmentation relative to camera motion, the tracking method is done by substituting feature-based camera estimation with combination of inertial sensors with complementary filter to provide more dynamic response. The proposed method managed to track unknown environment with faster processing time compared to available feature-based approaches. Moreover, the proposed method can sustain its estimation in a situation where feature-based tracking loses its track. The collaboration of sensor tracking managed to perform the task for about 22.97 FPS, up to five times faster than feature-based tracking method used as comparison. Therefore, the proposed method can be used to track unknown environments without depending on amount of features on scene, while requiring lower computational cost.

Korean anaphora recognition system to develop healthcare dialogue-type agent.

ObjectivesAnaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current study, all the merits of rule-based, machine learning-based, semantic-based anaphora recognition systems were combined to design and realize a new hybrid-type anaphora recognition system with an optimum capacity.MethodsAnaphora recognition rules were encoded on the basis of the internal traits of referred expressions and adjacent contexts to realize a rule-based system and to serve as a baseline. A semantic database, related to predicate instances of sentences including referred expressions, was constructed to identify semantic co-relationships between the referent candidates (to which semantic tags were attached) and the semantic information of predicates. This approach would upgrade the anaphora recognition system by reducing the number of referent candidates. Additionally, to realize a machine learning-based system, an anaphora recognition model was developed on the basis of training data, which indicated referred expressions and referents. The three methods were further combined to develop a new single hybrid-based anaphora recognition system.ResultsThe precision rate of the rule-based systems was 54.9%. However, the precision rate of the hybrid-based system was 63.7%, proving it to be the most efficient method.ConclusionsThe hybrid-based method, developed by the combination of rule-based and machine learning-based methods, represents a new system with enhanced functional capabilities as compared to other pre-existing individual methods.

Robust bronchoscope motion tracking using sequential Monte Carlo methods in navigated bronchoscopy: dynamic phantom and patient validation

Accurate and robust estimates of camera position and orientation in a bronchoscope are required for navigation. Fusion of pre-interventional information (e.g., CT, MRI, or US) and intra-interventional information (e.g., bronchoscopic video) were incorporated into a navigation system to provide physicians with an augmented reality environment for bronchoscopic interventions. Two approaches were used to predict bronchoscope movements by incorporating sequential Monte Carlo (SMC) simulation including (1) image-based tracking techniques and (2) electromagnetic tracking (EMT) methods. SMC simulation was introduced to model ambiguities or uncertainties that occurred in image- and EMT-based bronchoscope tracking. Scale invariant feature transform (SIFT) features were employed to overcome the limitations of image-based motion tracking methods. Validation was performed on five phantom and ten human case datasets acquired in the supine position. For dynamic phantom validation, the EMT-SMC simulation method improved the tracking performance of the successfully registered bronchoscopic video frames by 12.7% compared with a hybrid-based method. In comparisons between tracking results and ground truth, the accuracy of the EMT-SMC simulation method was 1.51 mm (positional error) and 5.44° (orientation error). During patient assessment, the SIFT-SMC simulation scheme was more stable or robust than a previous image-based approach for bronchoscope motion estimation, showing 23.6% improvement of successfully tracked frames. Comparing the estimates of our method to ground truth, the position and orientation errors are 3.72 mm and 10.2°, while those of our previous image-based method were at least 7.77 mm and 19.3°. The computational times of our EMT- and SIFT-SMC simulation methods were 0.9 and 1.2 s per frame, respectively. The SMC simulation method was developed to model ambiguities that occur in bronchoscope tracking. This method more stably and accurately predicts the bronchoscope camera position and orientation parameters, reducing uncertainties due to problematic bronchoscopic video frames and airway deformation during intra-bronchoscopy navigation.

A hybrid strategy to integrate surface-based and mutual-information-based methods for co-registering brain SPECT and MR images

Co-registration of brain SPECT and MR images has been used extensively in clinical applications. The complementary features of two major co-registration methods--surface- and mutual-information-based (MI-based)--motivated us to study a hybrid-based scheme that uses the surface-based method to achieve a quick alignment, followed by the MI-based method for fine tuning. Computer simulations were conducted to evaluate the accuracy and robustness of surface-, MI-, and hybrid-based registration methods by designing different levels of noise and mismatch in the registration experiments. Results demonstrated that the hybrid surface-MI-based scheme outperforms both the surface- and MI-based methods in providing superior accuracy and success rates. Specifically, the translational and rotational errors were no more than 1 mm and 2°, respectively, with consistent success rates over 98%. Besides, the hybrid-based method saved 12-53% of the computation efforts, compared with using the MI-based method alone. We recommend the use of hybrid-based method when the orientational differences between the floating and reference images exceed 10°.

Development of auto defect classification system on porosity powder metallurgy products

Automatic optical inspection (AOI) has been applied to many manufacturing fields for defect inspection of mass production parts, such as PCB and TFT-LCD, but it has never been applied to the production line of porous powder metallurgy. By its nature, the powder-formed part has inherent non-uniform porosity pattern on the metal substrate. The defect’s images are not easily separated from the substrate surface using the conventional binarization technique. This study develops a new image processing methodology and employs optical system design to build up an on-line surface defect inspection system for powder metallurgy parts. An analysis algorithm is also developed for the auto defect classification technique. It removes the noise signals from the porous image, detects the object edge and uses the hybrid-based method to sort out defects on the surface, such as crevice, scratch, broken corner and dent. Experimental tests show the maximum miss rate can be controlled to less than 5.65%.

IDEAL-Q, an Automated Tool for Label-free Quantitation Analysis Using an Efficient Peptide Alignment Approach and Spectral Data Validation

In this study, we present a fully automated tool, called IDEAL-Q, for label-free quantitation analysis. It accepts raw data in the standard mzXML format as well as search results from major search engines, including Mascot, SEQUEST, and X!Tandem, as input data. To quantify as many identified peptides as possible, IDEAL-Q uses an efficient algorithm to predict the elution time of a peptide unidentified in a specific LC-MS/MS run but identified in other runs. Then, the predicted elution time is used to detect peak clusters of the assigned peptide. Detected peptide peaks are processed by statistical and computational methods and further validated by signal-to-noise ratio, charge state, and isotopic distribution criteria (SCI validation) to filter out noisy data. The performance of IDEAL-Q has been evaluated by several experiments. First, a serially diluted protein mixed with Escherichia coli lysate showed a high correlation with expected ratios and demonstrated good linearity (R2 = 0.996). Second, in a biological replicate experiment on the THP-1 cell lysate, IDEAL-Q quantified 87% (1,672 peptides) of all identified peptides, surpassing the 45.7% (909 peptides) achieved by the conventional identity-based approach, which only quantifies peptides identified in all LC-MS/MS runs. Manual validation on all 11,940 peptide ions in six replicate LC-MS/MS runs revealed that 97.8% of the peptide ions were correctly aligned, and 93.3% were correctly validated by SCI. Thus, the mean of the protein ratio, 1.00 ± 0.05, demonstrates the high accuracy of IDEAL-Q without human intervention. Finally, IDEAL-Q was applied again to the biological replicate experiment but with an additional SDS-PAGE step to show its compatibility for label-free experiments with fractionation. For flexible workflow design, IDEAL-Q supports different fractionation strategies and various normalization schemes, including multiple spiked internal standards. User-friendly interfaces are provided to facilitate convenient inspection, validation, and modification of quantitation results. In summary, IDEAL-Q is an efficient, user-friendly, and robust quantitation tool. It is available for download.