Soft Classification Research Articles

Extended Object Tracking with Embedded Classification.

This paper proposes a novel extended object tracking (EOT) approach with embedded classification. Traditionally, for extended objects, only tracking is addressed without considering classification. This has serious defects: On the one hand, some practical EOT problems require classification as an embedded subproblem; on the other hand, with the assistance of classification, the tracking performance can be improved. Therefore, we propose a systematic EOT method with embedded classification, which is desired to satisfy the practical demands and also enjoys superior tracking performance. Specifically, we first formulate the EOT problem with embedded classification by kinematic models and attribute models. Then, we explore a random-matrix-based, multiple model EOT method with embedded classification. Two strategies are creatively provided in which soft classification and hard classification are embedded, respectively. Especially for the EOT with hard classification, a sequential probability ratio-test-based classification scheme is explored due to its nice properties and adaptability to our problem. In both methods, classification assist tracking is used. The simulation results demonstrate the superiority of the proposed EOT method with embedded classification, which can not only satisfy the practical requirements for classification but can also improve the tracking performance by utilizing the assistant of classification.

A new classification method using soft decision-making based on an aggregation operator of fuzzy parameterized fuzzy soft matrices

Recently, a precise and stable machine learning algorithm, i.e. eigenvalue classification method (EigenClass), has been developed by using the concept of generalised eigenvalues in contrast to common approaches, such as k-nearest neighbours, support vector machines, and decision trees. In this paper, we offer a new classification algorithm called fuzzy parameterized fuzzy soft aggregation classifier (FPFS-AC) to combine the modelling ability of soft decision-making (SDM) and classification success of generalised eigenvalues. FPFS-AC constructs a decision matrix by employing the similarity measures of fuzzy parameterized fuzzy soft matrices fpfs -matrices) and a generalised eigenvalue-based similarity measure. Then, it applies an SDM method based on the aggregation operator of fpfs -matrices to a decision matrix and classifies the given test sample. Afterwards, we perform an experimental study using 15 UCI datasets to manifest the success of our approach and compare FPFS-AC with the well-known and state-of-the-art classifiers (kNN, SVM, fuzzy kNN, EigenClass, and BM-fuzzy kNN) in terms of accuracy, precision, recall, macro F-score, micro F-score, and running time. Moreover, we statistically analyse the experimentally obtained data. Experimental and statistical results show that FPFS-AC outperforms the state-of-the-art classifiers in all the datasets concerning the five performance metrics.

Local non‐intrusive reduced order modeling based on soft clustering and classification algorithm

AbstractThe use of non‐intrusive reduced order modeling (NIROM) to approximate high‐fidelity computer models has been steadily increased over the past decade. Recently, local NIROM has been proposed to improve the model accuracy in highly nonlinear problems in which distinct characteristic regimes coexist. The core concept of local NIROM is the decomposition of the parameter domains into a subregime to create multiple models. However, the existing local NIROM not only partitions the individual models in a mutually exclusive manner, but also uses a single model for prediction. This results in the extrapolation of surrogate models and the generation of artificial discontinuities. To mitigate these problems, a local NIROM that allows flexible overlapping of individual NIROMs is developed. This method softly partitions and combines individual NIROMs using machine learning techniques, such as fuzzy c‐means and multinomial logistic regression. Furthermore, a variance‐based adaptive sampling technique that can consider both local exploitation and global exploration is applied to improve model accuracy. The proposed method is validated against the transonic flow and in‐flight icing problem, and demonstrates superior performance relative to its local counterpart by up to 16.5% and 33.9% in terms of normalized root‐mean‐square error and exclusive OR error, respectively.

YinYang-Net: Complementing Face and Body Information for Wild Gender Recognition

Soft biometrics inference in surveillance scenarios is a topic of interest for various applications, particularly in security-related areas. However, soft biometric analysis is not extensively reported in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">wild conditions</i> . In particular, previous works on gender recognition report their results in face datasets, with relatively good image quality and frontal poses. Given the uncertainty of the availability of the facial region in wild conditions, we consider that these methods are not adequate for surveillance settings. To overcome these limitations, we: 1) present frontal and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">wild</i> face versions of three well-known surveillance datasets; and 2) propose YinYang-Net (YY-Net), a model that effectively and dynamically complements facial and body information, which makes it suitable for gender recognition in wild conditions. The frontal and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">wild</i> face datasets derive from widely used Pedestrian Attribute Recognition (PAR) sets (PETA, PA-100K, and RAP), using a pose-based approach to filter the frontal samples and facial regions. This approach retrieves the facial region of images with varying image/subject conditions, where the state-of-the-art face detectors often fail. YY-Net combines facial and body information through a learnable fusion matrix and a channel-attention sub-network, focusing on the most influential body parts according to the specific image/subject features. We compare it with five PAR methods, consistently obtaining state-of-the-art results on gender recognition, and reducing the prediction errors by up to 24% in frontal samples. The announced PAR datasets versions and YY-Net serve as the basis for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">wild</i> soft biometrics classification and are available in here.

A Comprehensive Flexible Spatiotemporal DAta Fusion Method (CFSDAF) for Generating High Spatiotemporal Resolution Land Surface Temperature in Urban Area

Spatiotemporal fusion of land surface temperature (LST) has a vital significance in studying the temporal and spatial variation of urban heat islands. But most existing LST fusion methods don't consider the high heterogenous urban surface and complexity of spatial layout. In this study, a Comprehensive Flexible Spatiotemporal DAta Fusion (CFSDAF) method was proposed to generate high spatiotemporal resolution urban LST image which was improvements of the Flexible Spatiotemporal DAta Fusion (FSDAF). The CFSDAF first adjusted the differences between coarse resolution LST and fine resolution LST. Then, the visible and near-infrared image of fine resolution was introduced to execute spectral unmixing and to conduct soft classification, which considered the mixed pixel of fine resolution LST. The inverse distance weighting (IDW) interpolation was used in improving the computational efficiency, and the constrained least squares (CLS) was selected to better distribute the residual. The performance of CFSDAF was compared with the temporal adaptive reflectance fusion model (STARFM) and FSDAF. The results indicate that the predicted images by CFSDAF are better than STARFM and FSDAF from both visual comparison and quantitative assessment in two experiments, and CFSDAF can reserve more spatial details and accurately restore the spatial continuity of urban LST than others. Moreover, CFSDAF has high computational efficiency, and can monitor land cover changes same as FSDAF. Due to the above advantages, the CFSDAF has great potential for studying spatiotemporal changes of LST and UHI in urban area.

Kernel-Based Constrained Energy Minimization for Hyperspectral Mixed Pixel Classification

One fundamental task of hyperspectral imaging is spectral unmixing. In this case, the conventional pure pixel-based hyperspectral image classification (HSIC) may not work effectively for mixed pixels. This article presents a kernel-based approach to hyperspectral mixed pixel classification (HMPC) which includes two nonlinear mixed pixel classifiers, kernel constrained energy minimization (KCEM) and kernel linearly constrained minimum variance (KLCMV) to replace the widely used pure pixel-based support vector machine (SVM) classifier. Interestingly, what the binary-class and multiclass SVM classifiers are to pure pixel-based HSIC can be similarly derived for what a single-class KCEM detector and a multiclass KLCMV detector are to HMPC. In particular, the commonly used discrete classification map-based hard classification measures, average accuracy (AA) and overall accuracy (OA) for performance evaluation can be further generalized to real-valued mixed class abundance fractional map-based soft classification measures via 3-D receiver operating characteristic (3-D ROC) analysis-derived detection measures. Extensive experiments are conducted to demonstrate the utility of HMPC where KCEM/KLCMV not only significantly improve the classification performance of CEM/LCMV-based classifiers but also outperform many existing spectral-spatial classification methods.

A Multi-Stage Approach Combining Very High-Resolution Satellite Image, GIS Database and Post-Classification Modification Rules for Habitat Mapping in Hong Kong

Identification and mapping of various habitats with sufficient spatial details are essential to support environmental planning and management. Considering the complexity of diverse habitat types in a heterogeneous landscape, a context-dependent mapping framework is expected to be superior to traditional classification techniques. With the aim to produce a territory-wide habitat map in Hong Kong, a three-stage mapping procedure was developed to identify 21 habitats by combining very-high-resolution satellite images, geographic information system (GIS) layers and knowledge-based modification rules. In stage 1, several classification methods were tested to produce initial results with 11 classes from a WorldView-2/3 image mosaic using a combination of spectral, textural, topographic and geometric variables. In stage 2, modification rules were applied to refine the classification results based on contextual properties and ancillary data layers. Evaluation of the classified maps showed that the highest overall accuracy was obtained from pixel-based random forest classification (84.0%) and the implementation of modification rules led to an average 8.8% increase in the accuracy. In stage 3, the classification scheme was expanded to all 21 habitats through the adoption of additional rules. The resulting habitat map achieved &gt;80% accuracy for most of the evaluated classes and &gt;70% accuracy for the mixed habitats when validated using field-collected points. The proposed mapping framework was able to utilize different information sources in a systematic and controllable workflow. While transitional mixed habitats were mapped using class membership probabilities and a soft classification method, the identification of other habitats benefited from the hybrid use of remote-sensing classification and ancillary data. Adaptive implementation of classification procedures, development of appropriate rules and combination with spatial data are recommended when producing an integrated and accurate map.

A fault diagnostic method for oil-immersed transformer based on multiple probabilistic output algorithms and improved DS evidence theory

Power transformer is one of the most vital equipment in the electric power systems, which serves as the connection of power networks at different voltage levels. However, the power transformers in service are subjected to various stresses like thermal stress and electrical stress, which may lead to several faults such as arching, partial discharge and overheating. In order to detect these incipient faults and ensure the normal operation of power transformers, the diagnostic methods based on Dissolved Gas Analysis (DGA) have been developed. However, the DGA methods suffer from low diagnostic accuracy. On the other hand, with the development of Artificial Intelligence (AI), a lot of intelligent algorithms have been applied in this area. However, most traditional AI algorithms are hard classification, which may cause the wrong diagnosis of faults. To overcome those disadvantages, a method based on the improved DS evidence theory and multiple probabilistic output algorithms is proposed in this paper to improve the performance of fault diagnosis of oil-immersed transformers. Firstly, the performance of the soft and hard classification algorithms is compared and analyzed. After that, three diagnostic models based on the Multiclass Relevance Vector Machine (MRVM), Multiclass Support Vector Machine (MSVM) and Back Propagation Neural Network (BPNN) are established. In order to improve the accuracy of these models, Particle Swarm Optimization (PSO) is used to optimize their hyper-parameters. Finally, the combination of these three probabilistic output models is achieved based on the improved Dempster-Shafer (DS) evidence theory, which can help to obtain a more accurate fault diagnosis result by fusing multiple algorithm results. The case study results show that the proposed method achieves a probabilistic output for the fault diagnosis of oil-immersed transformers and overcomes the deficiency of traditional DGA methods which are difficult to get accurate diagnosis results and can’t summarize the fault development rule inductively.

Development of distribution maps of spectrally similar degradation products by Raman chemical imaging microscope coupled with a new variable selection technique and SIMCA classifier

The ability to detect degradation products of active pharmaceutical ingredients (API) is an essential performance not only for conducting proper stability studies and subsequently gain regulatory approvals; but as well for detecting degradation products during the manufacturing process (In Process Control). Thus, this study aims to present the ability of using Raman Chemical Imaging (Raman-CI) microscope, with its optimum precision, in combination with appropriate chemometrics algorithms, to detect the spectrally similar Salicylic Acid (SA) in Acetylsalicylic Acid (ASA) powder mixture, and then create a chemical distribution map that reflects the distribution of ASA’s main degradation product. The generated Hyperspectral images were processed where, a supervised chemometrics soft classifier, Soft Independent Modeling of Class Analogy (SIMCA), is applied to classify pixels and construct the subsequent distribution maps. In addition, due to the challenge of the high structural and spectral similarity between both substances, this study presents a new variable selection and dimensionality reduction technique, called Variable Strength Coefficient (VSC) to maximize the spectral differences and enhance the model precision and selectivity. A High-performance liquid chromatographic (HPLC) method was applied as a reference separation method to assess the results obtained by the proposed technique. The proposed technique was validated, where the obtained results confirmed that Raman Chemical Imaging Microscope, when coupled with SIMCA and VSC, is a powerful tool with outstanding accuracy. In addition, this approach could be suitable in applications where constructing accurate distribution maps of spectrally similar API’s is required.

Non-Model-Based Monocular Pose Estimation Network for Uncooperative Spacecraft Using Convolutional Neural Network

The pose estimation of uncooperative target spacecraft is a key technique in on-orbit servicing missions, among which the method based on monocular camera with low mass and power requirements has attracted widespread attention. However, monocular pose estimation methods mostly rely on the known 3D model of the target spacecraft, and non-model-based methods have low accuracy and even output the results when there is no target spacecraft in the image. In this paper, a non-model-based monocular pose estimation network for uncooperative spacecraft based on the convolutional neural network is proposed. This network uses three sub-networks to solve the problems of pose estimation and object detection. The first sub-network, called the attitude prediction sub-network, is used to predict the relative attitude of the target spacecraft by soft classification and error quaternion regression. The second sub-network, called the position regression sub-network, is used to predict the relative position of the target spacecraft by regression. The third sub-network called the object detection sub-network is used to detect the target spacecraft to determine whether the predicted pose needs to be output. The experimental results of the pose estimation of two public spacecraft demonstrate that the proposed method can effectively detect the target spacecraft and achieve better pose estimation accuracy than previous non-model-based methods.

A 50.7-dB-DR Finger-Resistance Extracting Multi-Touch Sensor IC for Soft Classification of Fingers Contacted on 6.7-in Capacitive Touch Screen Panel

This article presents multi-touch readout IC embedding finger-resistance extraction (FRE) on a capacitive touch screen panel (TSP). The proposed FRE mode is aimed to have the ability to tell users apart while sensing touch input by utilizing a unique finger’s resistance due to different bio-electrical properties. The resonance-driven FRE technique and a clamped zoom-in integrator are exploited to obtain a wide dynamic range (DR). A switched-capacitor current-controlled oscillator-based 14-bit analog-to-digital converter (ADC) was also designed, which has the benefits of low noise, compact size, and high flexibility of its resolution. The prototype chip fabricated in 0.18- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu \text{m}$ </tex-math></inline-formula> CMOS achieved the measured signal-to-noise ratio (SNR) of 37.5 dB and DR of 50.7 dB in touch sensing and FRE modes, respectively, in a real-6.7-in capacitive TSP. By applying support vector machine learning to the FRE data, five different user-fingers were successfully classified with 97.7% accuracy after 500 learning cycles and thus demonstrating the feasibility of reliable user-differentiation on multi-user collaborative touch interfaces.

Exploring Fuzzy Local Spatial Information Algorithms for Remote Sensing Image Classification

Fuzzy c-means (FCM) and possibilistic c-means (PCM) are two commonly used fuzzy clustering algorithms for extracting land use land cover (LULC) information from satellite images. However, these algorithms use only spectral or grey-level information of pixels for clustering and ignore their spatial correlation. Different variants of the FCM algorithm have emerged recently that utilize local spatial information in addition to spectral information for clustering. Such algorithms are seen to generate clustering outputs that are more enhanced than the classical spectral-based FCM algorithm. Nonetheless, the scope of integrating spatial contextual information with the conventional PCM algorithm, which has several advantages over the FCM algorithm for supervised classification, has not been explored much. This study proposed integrating local spatial information with the PCM algorithm using simpler but proven approaches from available FCM-based local spatial information algorithms. The three new PCM-based local spatial information algorithms: Possibilistic c-means with spatial constraints (PCM-S), possibilistic local information c-means (PLICM), and adaptive possibilistic local information c-means (ADPLICM) algorithms, were developed corresponding to the available fuzzy c-means with spatial constraints (FCM-S), fuzzy local information c-means (FLICM), and adaptive fuzzy local information c-means (ADFLICM) algorithms. Experiments were conducted to analyze and compare the FCM and PCM classifier variants for supervised LULC classifications in soft (fuzzy) mode. The quantitative assessment of the soft classification results from fuzzy error matrix (FERM) and root mean square error (RMSE) suggested that the new PCM-based local spatial information classifiers produced higher accuracies than the PCM, FCM, or its local spatial variants, in the presence of untrained classes and noise. The promising results from PCM-based local spatial information classifiers suggest that the PCM algorithm, which is known to be naturally robust to noise, when integrated with local spatial information, has the potential to result in more efficient classifiers capable of better handling ambiguities caused by spectral confusions in landscapes.

A Functional Radiological and Soft Tissue Classification to Predict Outcomes in Orbital Fracture Surgery in a Multidisciplinary "Real-World" Setting.

Purpose: The decision for open reduction and internal fixation (ORIF) of orbital fractures is usually based on clinical severity and soft tissue and bony findings. This study aimed to identify prognostic factors for a successful surgical outcome.Materials and Methods: We included all orbital fractures treated by ORIF referred to the Ophthalmology clinic for assessment over a 12-year period. A successful outcome was defined as (i) a single operation, (ii) improved diplopia and globe position at 6 months, (iii) no surgical complications, and (iv) patient satisfaction. Data was collected on presenting symptoms, orthoptic measurements, time interval from injury to surgery, fracture geometry and involvement of internal, and external bony landmarks. Univariate and multivariate regression was used to identify predictive factors for success.Results: There were 143 cases with median age 35.4 years and 81.8% (117/143) male. 51% (73/143) were complex fractures involving multiple orbital walls. 63.6% (91/143) achieved significant improvement in both enophthalmos and diplopia at 6 months. 15.3% (22/143) had significant preoperative soft tissue or neurogenic injury. 11.8% (17/143) required orbital plate repositioning or removal. 1.4% (2/143) developed orbital haematoma and 4.2% (6/143) had cicatricial entropion. Pre-operative nerve or muscle damage (OR 0.05, p = 0.01) and infraorbital fissure fracture (OR 0.38, p = 0.04) were associated with poor outcomes, whereas an intact posterior ledge was associated with successful outcomes (OR 3.03, p = 0.02).Conclusion: Careful ocular motility evaluation to ascertain neurogenic injury and muscle compartment syndrome, and radiological analysis of the integrity of the posterior ledge and the inferior orbital fissure can facilitate management and expectations of ORIF surgery.

Ways to build text collections for training classifiers

We report on solving the problem of forming a Russian-language text collection (dataset) consisting of bibliographic descriptions of scientific articles for training classifiers. Various approaches to creating such collections are considered. The expediency of using expert estimates for assigning class labels is assessed. The known datasets are analyzed, the requirements for the generated text array are formulated, and the choice of the subject area (Computer Science) is justified. We propose a technology of forming collection in conditions of the shortage of Russian-language articles. To do this we use automated translation of publications (bibliographic descriptions) from available English-language electronic libraries (ACM digital library, IEEE Xplore digital library, CiteSeerX) with additional expert quality control of the translation. The bibliographic collection thus formed was studied using methods of clustering (Latent Semantic Analysis) and visualization (Principal Component Analysis). Training and test samples were compiled and «standard» classifiers (K-Nearest Neighbor Method, Logistic Regression, Random Forest) were used. Then we calculated standard quality measures (accuracy, precision, recall). The rigid and soft classification were carried out. For rigid and soft classification all calculated measures (for the studied classifiers) ranged within [0.79; 0.87], and [0.91; 0.95], respectively. The experiments showed almost identical results for Russian and English bibliographic descriptions (the difference did not exceed 2%). The proposed method of forming text collections reduces the complexity of the labeling process compared to the expert approach, solves the problem of the lack of Russian-language documents, allows formation of sufficiently large balanced bibliographic datasets for training and testing classifiers.

Deep learning based bi-level approach for proactive loan prospecting

A fundamental component to managing a marketing campaign is identifying prospects and selection of leads. Current lead generation models focus on predicting the intention of a customer to purchase a product, however with financial products, particularly loans, this can be insufficient as there are many factors to consider, such as risk, utility, and financial maturity. Developing a marketing campaign for loan prospecting should consider not only customers who need a loan, but rather clients who need a loan and will also be approved. Otherwise, the marketing effort is deemed ineffective, if the lead cannot be converted into a sale. Although, a low response rate is expected for a marketing campaign for loans, we highlight a better approach in managing resources while maintaining a shortlist of high-quality leads. This manuscript introduces a bi-level approach to handle the complex nature of loan products. Two classifiers are built, one modelling loan intention and the other one modelling loan eligibility. We adopt convex combination to control weights of both problems, which in most cases results in an improved performance for identifying future successful loan applicants when compared to baseline models. Rank-based evaluation measures are also adopted to explore the performance of customer rankings. We find that soft classifiers, such as deep learning techniques, are ideal for ranking customers, achieving a superior performance when compared to other machine learning techniques. In addition, we conclude that an ideal cut-off for K customers is estimated to be between 20 to 25 customers, however our best model can maintain an Average Precision of greater than 0.85 when K approaches 50.

System-wide seismic vulnerability of aging multiple-span multiple-girder bridges in low-to-moderate seismic hazard regions

This article describes the approach, methods, and findings of a quantitative analysis of the seismic vulnerability in low-to-moderate seismic hazard regions of the Central and Eastern United States for system-wide assessment of typical multiple span bridges built in the 1950s through the 1960s. There is no national database on the status of seismic vulnerability of bridges, and thus no means to estimate the system-wide damage and retrofit costs for bridges. The study involved 380 nonlinear analyses using actual time-history records matched to four representative low-to-medium hazard target spectra corresponding with peak ground accelerations from approximately 0.06 to 0.3 g. Ground motions were obtained from soft and stiff site seismic classification locations and applied to models of four typical multiple-girder with concrete bent bridges. Multiple-girder bridges are the largest single category, comprising 55% of all multiple span bridges in the United States. Aging and deterioration effects were accounted for using reduced cross-sections representing fully spalled conditions and compared with pristine condition results. The research results indicate that there is an overall low likelihood of significant seismic damage to these typical bridges in such regions, with the caveat that certain bridge features such as more extensive deterioration, large skews, and varied bent heights require bridge-specific analysis. The analysis also excludes potential damage resulting from liquefaction, flow-spreading, or abutment slumping due to weak foundation or abutment soils.

Feasibility of using a single MRI acquisition for fiducial marker localization and synthetic CT generation towards MRI-only prostate radiation therapy treatment planning

Purpose. To investigate the feasibility of using a single MRI acquisition for fiducial marker identification and synthetic CT (sCT) generation towards MRI-only treatment planning for prostate external beam radiation therapy (EBRT). Methods. Seven prostate cancer patients undergoing EBRT, each with three implanted gold fiducial markers, participated in this study. In addition to the planning CT scan, all patients were scanned on a 3 T MR scanner with a 3D double-echo gradient echo (GRE) sequence. Quantitative susceptibility mapping (QSM) was performed for marker localization. QSM-derived marker positions were compared to those from CT. The bulk density assignment technique for sCT generation was adopted. The magnitude GRE images were segmented into muscle, bone, fat, and air using a combination of unsupervised intensity-based classification of soft tissue and convolutional neural networks (CNN) for bone segmentation. Results. All implanted markers were visualized and accurately identified (average error: 0.7 ± 0.5 mm). QSM generated distinctive contrast for hemorrhage, calcifications, and gold fiducial markers. The estimated susceptibility/HU values on QSM/CT for gold and calcifications were 31.5 ± 2.9 ppm/1220 ± 100 HU and 14.6 ± 0.9 ppm/440 ± 100 HU, respectively. The intensity-based soft tissue classification resulted in an average Dice score of 0.97 ± 0.02; bone segmentation using CNN resulted in an average Dice score of 0.93 ± 0.03. Conclusion. This work indicates the feasibility of simultaneous fiducial marker identification and sCT generation using a single MRI acquisition. Future works includes evaluation of the proposed method in a large cohort of patients with optimized acquisition parameters as well as dosimetric evaluations.

An Interpretable Experimental Data Augmentation Method to Improve Knee Health Classification Using Joint Acoustic Emissions

The characteristics of joint acoustic emissions (JAEs) measured from the knee have been shown to contain information regarding underlying joint health. Researchers have developed methods to process JAE measurements and combined them with machine learning algorithms for knee injury diagnosis. While these methods are based on JAEs measured in controlled settings, we anticipate that JAE measurements could enable accessible and affordable diagnosis of acute knee injuries also in field-deployable settings. However, in such settings, the noise and interference would be greater than in sterile, laboratory environments, which could decrease the performance of existing knee health classification methods using JAEs. To address the need for an objective noise and interference detection method for JAE measurements as a step towards field-deployable settings, we propose a novel experimental data augmentation method to locate and then, remove the corrupted parts of JAEs measured in clinical settings. In the clinic, we recruited 30 participants, and collected data from both knees, totaling 60 knees (36 healthy and 24 injured knees) to be used subsequently for knee health classification. We also recruited 10 healthy participants to collect artifact and joint sounds (JS) click templates, which are audible, short duration and high amplitude JAEs from the knee. Spectral and temporal features were extracted, and clinical data was augmented in five-dimensional subspace by fusing the existing clinical dataset into experimentally collected templates. Then knee scores were calculated by training and testing a linear soft classifier utilizing leave-one-subject-out cross-validation (LOSO-CV). The area under the curve (AUC) was 0.76 for baseline performance without any window removal with a logistic regression classifier (sensitivity = 0.75, specificity = 0.78). We obtained an AUC of 0.86 with the proposed algorithm (sensitivity = 0.80, specificity = 0.89), and on average, 95% of all clinical data was used to achieve this performance. The proposed algorithm improved knee health classification performance by the added information through identification and collection of common artifact sources in JAE measurements. This method when combined with wearable systems could provide clinically relevant supplementary information for both underserved populations and individuals requiring point-of-injury diagnosis in field-deployable settings.

Detection of Architectural Distorted Region in Mammogram Images Using Hybrid Classification Approaches

The architectural distorted regions in mammogram images are detected and segmented using computer aided hybrid classification approach in this paper. The main importance of this research work is to provide a computer aided methodology for screening the distorted regions in mammogram images. In present approach, the classification accuracy of the conventional methods is not suitable for further diagnosis process such as malignant and benign. Hence, the main objective of this paper is to develop an efficient architectural region detection method using soft computing method with high classification accuracy for further diagnosis purpose. This proposed method has two stages of the proposed flow as architectural distorted detected mammogram image and segmentation of architectural distorted regions in mammogram images. The first stage of this proposed method uses Random Forest (RF) classification method which classifies the source mammogram image into either normal or abnormal. In second stage of the proposed method, the abnormal image is further classified into either Benign or Malignant using Adaptive Neuro Fuzzy Inference System (ANFIS) classification approach. The proposed methodology for architectural distorted region detection is tested on the publicly available mammogram datasets Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) respectively. In this paper, the mammogram images from MIAS dataset are grouped into normal case (156 images), benign case (122 images) and malignant case (98 images). The mammogram images from DDSM dataset are grouped into normal case (144 images), benign case (112 images) and malignant case (145 images). The overall average detection rate of the proposed system on the mammogram images in MIAS dataset is about 98.7%. The overall average detection rate of the proposed system on the mammogram images in DDSM dataset is about 98.3%. The extensive simulations are carried out on the mammogram images which are obtained from these dataset and the results are compared with stated of art methods.

Feature Extraction and Classification of Heart Murmurs Based on Acoustic Qualities

Background and objectiveHeart murmur characterization is a crucial part of cardiac auscultation for determining the potential etiology and severity of heart diseases. One such helpful murmur characterization is the sonic qualities, which reflect both structural and hemodynamical states of the heart. Therefore, the objective is to develop a machine learning based solution for classifying murmur qualities. MethodsFour medically defined murmur qualities, namely the musical quality, blowing-like quality, coarse quality, and soft quality were examined. Feature was extracted from heart murmurs signals in their time domain, frequency domain, time-frequency domain, and phase space domain. Sequential forward floating selection (SFFS) was implemented along with three classifiers, including k-nearest neighbor (KNN), Naïve-Bayes (NB), and linear support vector machine (SVM). ResultsIt was found that multi-domain features are suited for better classification results and linear SVM was able to achieve a better balance between performance and the size of feature subsets among tested classifiers. Using the derived features, classification accuracies of 86%, 91%, 90%, and 84% were achieved for musical quality, blowing-like quality, coarse quality, and soft quality classifications respectively. ConclusionsThe study demonstrated that it is possible to effectively characterize heart murmur through its diagnostic characteristics instead of drawing direct conclusions, which is helpful for retaining versatility and generality found in the conventional cardiac auscultation.