Aasia Khanum

Fuzzy case-based reasoning for facial expression recognition

Fuzzy logic (FL) and case-based reasoning (CBR) are two well-known techniques for the implementation of intelligent classification systems. Each technique has its own advantages and drawbacks. FL, for example, provides an intuitive user interface, simplifies the process of knowledge representation, and minimizes the systems computational complexity in terms of time and memory usage. On the other hand, FL has problems in knowledge elicitation which render it difficult to adopt for intelligent system implementation. CBR avoids these problems by making use of past input-output data to decide the system output for the present input. The accuracy of CBR system grows as the number of cases increase. However, more cases can mean added computational complexity in terms of space and time. In this paper we make the proposition that a hybrid system comprising a blend of FL and CBR can lead to a solution where the two approaches cover each others weaknesses and benefit from each others strengths. We support our claim by taking the problem of facial expression recognition from an input image. The facial expression recognition system presented in this paper uses a case base populated with fuzzy rules for recognizing each expression. Experimental results demonstrate that the system inherits the strengths of both methods.

Retinal images: Blood vessel segmentation by threshold probing

An automated system for screening and diagnosis of diabetic retinopathy should segment blood vessels from colored retinal image to assist the ophthalmologists. We present a method for blood vessel enhancement and segmentation. This paper proposes a wavelet based method for vessel enhancement, piecewise threshold probing and adaptive thresholding for vessel localization and segmentation respectively. The method is tested on publicly available DRIVE and STARE databases of manually labeled images which has been established to facilitate comparative studies on segmentation of blood vessels in retinal images. The proposed method achieves an accuracy of 0.9469 on DRIVE database and of 0.9502 on STARE database.

Automated Plant Disease Analysis (APDA): Performance Comparison of Machine Learning Techniques

Plant disease analysis is one of the critical tasks in the field of agriculture. Automatic identification and classification of plant diseases can be supportive to agriculture yield maximization. In this paper we compare performance of several Machine Learning techniques for identifying and classifying plant disease patterns from leaf images. A three-phase framework has been implemented for this purpose. First, image segmentation is performed to identify the diseased regions. Then, features are extracted from segmented regions using standard feature extraction techniques. These features are then used for classification into disease type. Experimental results indicate that our proposed technique is significantly better than other techniques used for Plant Disease Identification and Support Vector Machines outperforms other techniques for classification of diseases.

Discovering Core Architecture Classes to Assist Initial Program Comprehension

Before making modifications to an unfamiliar software system, the new programmer needs to gain some knowledge about that system. The core classes that constitute the system architecture can reveal important structural properties of the system. Hence these core classes can be used to catch an initial glimpse of the system during initial stages of program comprehension. We propose an efficient technique that pinpoints the core architecture classes of the system with the help of our own conceived variant of a dynamic coupling metric. The results are compared with the already performed experiments of similar nature on the same software system. There is a noticeable improvement in the performance with our approach while the precision and recall contest with the best results obtained in other analogous experiments.

A Nonparametric Approach for Mild Cognitive Impairment to AD Conversion Prediction: Results on Longitudinal Data

The goal of this study is to introduce a nonparametric technique for predicting conversion from Mild Cognitive impairment (MCI)-to-Alzheimers disease (AD). Progression of a slowly progressing disease such as AD benefits from the use of longitudinal data; however, research till now is limited due to the insufficient patient data and short follow-up time. A small dataset size invalidates the estimation of underlying disease progression model; hence, a supervised nonparametric method is proposed. While depicting a real-world setting, longitudinal data of three years are employed for training, whereas only the baseline visits data is used for validation. The train set is preprocessed for extraction of two dense clusters representing the subjects who remain stable at MCI or progress to AD after three years of the baseline visit. Similarity between these clusters and the test point is calculated in Euclidean space. Multiple features from two modalities of biomarkers, i.e., neuropsychological measures (NM) and structural magnetic resonance imaging (MRI) morphometry are also analyzed. Due to the limited MCI dataset size (NM: 145, MRI: 52, NM+MRI: 29), leave-one-out cross validation setup is employed for performance evaluation. The algorithm performance is noted for both unimodal case and bimodal cases. Superior performance (accuracy: 89.66%, sensitivity: 87.50%, specificity: 92.31%, precision: 93.33%) is delivered by multivariate predictors. Three notable conclusions of this study are: 1) Longitudinal data are more powerful than the temporal data, 2) MRI is a better predictor of MCI-to-AD conversion than NM, and 3) multivariate predictors outperform single predictor models

Hybrid Feature Selection and Tumor Identification in Brain MRI Using Swarm Intelligence

Demand for automatic classification of Brain MRI (Magnetic Resonance Imaging) in the field of Diagnostic Medicine is rising. Feature Selection of Brain MRI is critical and it has a great influence on the classification outcomes, however selecting optimal Brain MRI features is difficult. Particle Swarm Optimization (PSO) is an evolutionary meta-heuristic approach that has shown great potential in solving NP-hard optimization problems. In this paper MRI feature selection is achieved using Discrete Binary Particle Swarm Optimization (DBPSO). Classification of normal and abnormal Brain MRI is carried out using two different classifiers i.e. Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Experimental results show that the proposed approach reduces the number of features and at the same time it achieves high accuracy level. PSO-SVM is observed to achieve high accuracy level using minimum number of selected features.

Classification of Brain Tumor Types in MRI Scans Using Normalized Cross-Correlation in Polynomial Domain

Biomedical research in last decade or so has seen the development of highly accurate algorithms focused on the detection and classification of the brain tumor into malignant or benign. As a result of these advancements a new research direction has emerged which focuses on categorizing the brain tumors based on their types, such as Glioma, Metastases, and Meningioma etc. In this paper, we present a novel application of normalized cross-correlation in polynomial domain technique (predominately used in image registration) to classify Magnetic Resonance Image (MRI) of a brain into one of eight (8) different categories with high accuracy. The MRI scan is transformed into polynomial domain by first calculating its central moments and then fitting them to a 2nd order polynomial space. Experimental results show that the proposed approach provides very accurate and stable classification in real time.

Potential Lung Nodules Identification for Characterization by Variable Multistep Threshold and Shape Indices from CT Images

Computed tomography (CT) is an important imaging modality. Physicians, surgeons, and oncologists prefer CT scan for diagnosis of lung cancer. However, some nodules are missed in CT scan. Computer aided diagnosis methods are useful for radiologists for detection of these nodules and early diagnosis of lung cancer. Early detection of malignant nodule is helpful for treatment. Computer aided diagnosis of lung cancer involves lung segmentation, potential nodules identification, features extraction from the potential nodules, and classification of the nodules. In this paper, we are presenting an automatic method for detection and segmentation of lung nodules from CT scan for subsequent features extraction and classification. Contribution of the work is the detection and segmentation of small sized nodules, low and high contrast nodules, nodules attached with vasculature, nodules attached to pleura membrane, and nodules in close vicinity of the diaphragm and lung wall in one-go. The particular techniques of the method are multistep threshold for the nodule detection and shape index threshold for false positive reduction. We used 60 CT scans of “Lung Image Database Consortium-Image Database Resource Initiative” taken by GE medical systems LightSpeed16 scanner as dataset and correctly detected 92% nodules. The results are reproducible.

Ranked neuro fuzzy inference system (RNFIS) for information retrieval

The paper presents a novel approach to informational retrieval based on a synergy of knowledge-based models, set theoretic models, and vector space models of domain within a Fuzzy Logic framework. An input query is expanded to multiple synonym queries based on query semantics. Each document in the collection is divided into different zones with different relative importance assigned to each zone indicating its role in the query. Fuzzy rule bases are applied to each zone with parameters derived from vector space models and semantic query expansion. Fuzzy inference procedure outputs the relevance rank of each zone in satisfying the query. The relevance ranks of different zones are aggregated using the Ordered Weighted Averaging (OWA) operator to get the overall relevance rank of the complete document. The documents are ranked according to their relevance. The system has been tested on a standard dataset and has been demonstrated to show improved performance over typical vector space based approaches.

Lossless image compression using kernel based Global Structure Transform (GST)

Lossless data compression using the variants of Burrows-Wheeler Transform (BWT) with various compression encoders has proven its effectiveness. This research provides a unique method for lossless compression of color images by improving the Global Structure Transform (GST) stage of the Burrows-Wheeler Compression Algorithm (BWCA). The proposed model applies the Move-To-Front (MTF) transform at the GST stage by selecting 2-D block (kernel) of BWT data. This method has resulted in a high occurrence of same gray levels in the kernel. Moreover, the symbol map for the MTF Encoder is generated only for the available gray levels in the kernel. The overall redundancy of the MTF indexes increases at the GST stage of the BWCA which results in increased compression.