An efficient computerized decision support system for the analysis and 3D visualization of brain tumor

The quality of health services provided by medical centers varies widely, and there is often a large gap between the optimal standard of services when judged based on the locality of patients (rural or urban environments). This quality gap can have serious health consequences and major implications for patient’s timely and correct treatment. These deficiencies can manifest, for example, as a lack of quality services, misdiagnosis, medication errors, and unavailability of trained professionals. In medical imaging, MRI analysis assists radiologists and surgeons in developing patient treatment plans. Accurate segmentation of anomalous tissues and its correct 3D visualization plays an important role inappropriate treatment. In this context, we aim to develop an intelligent computer-aided diagnostic system focusing on human brain MRI analysis. We present brain tumor detection, segmentation, and its 3D visualization system, providing quality clinical services, regardless of geographical location, and level of expertise of medical specialists. In this research, brain magnetic resonance (MR) images are segmented using a semi-automatic and adaptive threshold selection method. After segmentation, the tumor is classified into malignant and benign based on a bag of words (BoW) driven robust support vector machine (SVM) classification model. The BoW feature extraction method is further amplified via speeded up robust features (SURF) incorporating its procedure of interest point selection. Finally, 3D visualization of the brain and tumor is achieved using volume marching cube algorithm which is used for rendering medical data. The effectiveness of the proposed system is verified over a dataset collected from 30 patients and achieved 99% accuracy. A subjective comparative analysis is also carried out between the proposed method and two state-of-the-art tools ITK-SNAP and 3D-Doctor. Experimental results indicate that the proposed system performed better than existing systems and assists radiologist determining the size, shape, and location of the tumor in the human brain.

     

Human facial expression recognition using curvelet feature extraction and normalized mutual information feature selection

To recognize expressions accurately, facial expression systems require robust feature extraction and feature selection methods. In this paper, a normalized mutual information based feature selection technique is proposed for FER systems. The technique is derived from an existing method, that is, the max-relevance and min-redundancy (mRMR) method. We, however, propose to normalize the mutual information used in this method so that the domination of the relevance or of the redundancy can be eliminated. For feature extraction, curvelet transform is used. After the feature extraction and selection the feature space is reduced by employing linear discriminant analysis (LDA). Finally, hidden Markov model (HMM) is used to recognize the expressions. The proposed FER system (CNF-FER) is validated using four publicly available standard datasets. For each dataset, 10-fold cross validation scheme is utilized. CNF-FER outperformed the existing well-known statistical and state-of-the-art methods by achieving a weighted average recognition rate of 99 % across all the datasets.     

Adaptive fuzzy clustering by fast search and find of density peaks

Clustering by fast search and find of density peaks (CFSFDP) is proposed to cluster the data by finding of density peaks. CFSFDP is based on two assumptions that: a cluster center is a high dense data point as compared to its surrounding neighbors, and it lies at a large distance from other cluster centers. Based on these assumptions, CFSFDP supports a heuristic approach, known as decision graph to manually select cluster centers. Manual selection of cluster centers is a big limitation of CFSFDP in intelligent data analysis. In this paper, we proposed a fuzzy-CFSFDP method for adaptively selecting the cluster centers, effectively. It uses the fuzzy rules, based on aforementioned assumption for the selection of cluster centers. We performed a number of experiments on nine synthetic clustering datasets and compared the resulting clusters with the state-of-the-art methods. Clustering results and the comparisons of synthetic data validate the robustness and effectiveness of proposed fuzzy-CFSFDP method.     

Classification of Drinking Water Quality Index and Identification of Significant Factors

Water pipes are considered to be one of responsible sources for the water pollution. Among these sources of water supply, the water pipes are the only source of carrying out fresh or processed water into lakes, ponds and streams etc. In Pakistan, knowledge on the condition of water pipes is scarce as deterioration of water pipes are hardly inspected due to high cost. The aim of the current research was to examine the quality of water pipelines of eight districts of South-Punjab, namely, Mianwali, Khushab, Layyah, Bhakkar, Dera Ghazi Khan, Muzaffargarh, Rajanpur and Rahim Yar Khan. Selected sampling stations were analyzed for physio-chemical parameters such as pH, Total Dissolve Solids (TDS), Sulfate (SO₄), Chlorine (Cl), Calcium (Ca), Magnesium (Mg), Hardness, Nitrate (NO₃), Fluoride (F) and Iron (Fe). The data pertaining water monitoring contain different parameters and seem difficult work for the interpretation of water quality by managing different parameters separately. For this purpose, National Sanitation Foundation Water Quality Index (NSF-WQI) was determined to communicate the quality of water in a simple form. Besides this, groups comprising of similar sampling sites based on water quality characteristics were identified using unsupervised technique. Factor Analysis (FA) has been performed for extracting the latent pollution sources that may cause the more variance in large and complex data. The calculated values of WQI from 1600 sampling stations ranging from 20.73 to 223.74 are divided into five groups; Excellent to Unsuitable class of waters with the average value 62.09 described as good limit for drinking water. Further sampling stations are divided into five optimal clusters selected with suitable k value obtained from Silhouette coefficient. Results of k-means clustering are also verified with natural groups made by WQI. Analysis of multivariate techniques showed several factors to be responsible for the water quality deterioration. It is found out from the FA that three latent factors such as organic pollution, agriculture run-off and urban land use caused 83.30 % of the total variation. Hence, water quality management and control of these latent factors are strongly recommended.     

Effects of isomerism on near infrared properties of perylene bisimide derivatives

In this study, five different perylene bisimide derivatives are synthesized, four of which are structural isomers. The pigments are used to prepare corresponding paints and their ultraviolet–visible–near infrared (NIR) reflectance is investigated on two optically different substrates, namely high absorptive and high reflective substrates. These pigments are classified according to their NIR properties. They show substantial differences in NIR reflectance, transmittance, and absorbance despite their structural similarities. This indicates that the NIR properties of perylene bisimide derivatives are dependent on the nature of N-substituent and electronic environment of the molecule. This study shows that the existence of bonds with high-frequency fundamental vibrations and their counts which were introduced as affecting parameters on the NIR properties of the perylene pigments is not the main affecting factor and we should seek it elsewhere such as the crystal structure and intermolecular interactions of the pigments.     

Optimal opportunistic routing and network coding for bidirectional wireless flows

There is growing interest in recent years in routing methods for wireless networks that leverage the broadcast nature of the wireless medium and the ability of nodes to overhear their neighbors’ transmissions. Such methods include opportunistic routing (OR), which generally choose the next hop on a routing path only after the outcome of the previous transmission is known; and wireless network coding (NC), which linearly combines packets from different flows coexisting in the network. In this paper, we study the potential benefits of forwarding schemes that combine elements from both the OR and NC approaches, when traffic on a bidirectional unicast connection between two nodes is relayed by multiple common neighbors. We present a theoretically optimal scheme that provides a lower bound on the expected number of transmissions required to communicate a packet in both directions as a function of link error probabilities, and demonstrate that this bound can be up to 20% lower than with either OR or NC employed alone even in a small network. Using simulation, we further explore the control overhead in a direct implementation of the scheme with a simple coordination mechanism and show that the optimal bound can be closely approached for a wide range of link error rates.     

Microstructure and properties of the Ba<Subscript>0.75−x</Subscript>Ca<Subscript>x</Subscript>La<Subscript>0.25</Subscript>Fe<Subscript>11.6</Subscript>Co<Subscript>0.25</Subscript>Ti<Subscript>0.15</Subscript>O<Subscript>19</Subscript> hexaferrites

In the case of Ti⁴⁺ remain unchanged, the Ca²⁺ substituted Ba_0.75?xCa_xLa_0.25Fe_11.6Co_0.25Ti_0.15O₁₉ (0?≤?x?≤?0.05) were prepared by conventional solid-state reaction method at temperature of 1280 °C. A ball-to-power weight ratio of 10:1. Their crystal structure and magnetic properties were mainly investigated. The results show that the single magnetoplumbite phase structure transformed into the multiphase structure. Meanwhile, the small amount of α-Fe₂O₃ phase existed in M-type phase. The micrographs were observed by a field emission scanning electron microscopy (SEM). Vibrating sample magnetometer (VSM) was used to analyze the magnetic properties. The saturation magnetization (M _s ) first increases then decreases when x from 0 to 0.03. But, when x from 0.03 to 0.05, the saturation magnetization (M _s ) first increases then decreases too. The maximum value is at x?=?0.04 (M _s ?=?70.73 emu/g). The value of coercivity (H _c ) first increases then decreases when x from 0 to 0.04. But, the value increased when x from 0.04 to 0.05. The maximum value is at x?=?0.02 (H _c ?=?1691 Oe).     

Ni(II) biosorption by Cassia fistula (Golden Shower) biomass

Cassia fistula is a fast-growing, medium-sized, deciduous tree which is now widely cultivated worldwide as an ornamental tree for its beautiful showy yellow flowers. Methods are required to reuse fallen leaves, branches, stem bark and pods when they start getting all over lawn. This investigation studies the use of these non-useful parts of C. fistula as naturally occurring biosorbent for the batch removal of Ni(II) in a well stirred system under different experimental conditions. The data showed that the maximum pH (pHmax) for efficient sorption of Ni(II) was 6 at which evaluated biosorbent dosage, biosorbent particle size, initial concentrations of Ni(II) and sorption time were 0.1 g/100 mL, <0.255 mm, up to 200 mg/L and 720 min, respectively. The experimental results were analyzed in terms of Langmuir and Freundlich isotherms. The Langmuir isotherm model fitted well to data of Ni(II) biosorption by C. fistula biomass as compared to the model of Freundlich. The kinetic studies showed that the sorption rates could be described better by a second order expression than by a more commonly applied Lagergren equation. The magnitude of the Gibbs free energy values indicates spontaneous nature of the sorption process. The sorption ability of C. fistula biomass for Ni(II) removal tends to be in the order: leaves相似文献   

Prospects of reusable endogenous hydrolyzing enzymes in bioethanol production by simultaneous saccharification and fermentation

This study was conducted to evaluate the presence, origination and classification of various hydrolyzing enzymes from malt and their specified hydrolyzing effects on various substrates for bioethanol production and to link these characteristics with the future prospects of bioethanol production. These enzymes are categorized as cell wall, starch, protein, lipid, polyphenol and thiol hydrolyzing enzymes based on their substrate specificity. Waste from beer fermentation broth (WBFB) has been evaluated as a rich source of malt derived hydrolyzing enzymes with significant self potential for bioethanol production. However, yeast cells cannot survive at the high temperature required for the saccharification activities of hydrolyzing enzymes during simultaneous saccharification and fermentation (SSF). This dilemma might be resolved by bioethanol production at elevated temperatures via cell-free fermentation systems in the presence of malt hydrolyzing enzymes. Moreover, emerging technologies such as genetic engineering in biomass and biotransformation in cell-free enzymatic systems will likely hasten bioethanol production in the near future. The present study adds new dimensions to eco-friendly bioethanol production from renewable and waste energy resources based on the specific hydrolyzing activities of malt enzymes.     

Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture

Brain tumor is one of the most dreadful natures of cancer and caused a huge number of deaths among kids and adults from the past few years. According to WHO standard, the 700,000 humans are being with a brain tumor and around 86,000 are diagnosed since 2019. While the total number of deaths due to brain tumors is 16,830 since 2019 and the average survival rate is 35%. Therefore, automated techniques are needed to grade brain tumors precisely from MRI scans. In this work, a new deep learning‐based method is proposed for microscopic brain tumor detection and tumor type classification. A 3D convolutional neural network (CNN) architecture is designed at the first step to extract brain tumor and extracted tumors are passed to a pretrained CNN model for feature extraction. The extracted features are transferred to the correlation‐based selection method and as the output, the best features are selected. These selected features are validated through feed‐forward neural network for final classification. Three BraTS datasets 2015, 2017, and 2018 are utilized for experiments, validation, and accomplished an accuracy of 98.32, 96.97, and 92.67%, respectively. A comparison with existing techniques shows the proposed design yields comparable accuracy.