BEASF-Based Image Enhancement for Caries Detection Using Multidimensional Projection and Neural Network

Tooth caries or cavities diagnosing are concerned as the most significant research work, as this is the common oral disease suffered by humans. Many approaches have been proposed under the topics including demineralization and decaying as well. However, the imaging modalities often suffer from various critical or complex aspects that struggles the methods to attain accurate diagnosis. This article turns to introduce a new cavity diagnosis model with three phases: (i) pre-processing (ii) feature extraction (iii) classification. In the first phase, a new bi-histogram equalization with adaptive sigmoid functions (BEASF) is introduced to enhance the image quality followed by other enhancements models like grey thresholding and active contour. Then, the features are extracted using multilinear principal component analysis (MPCA). Further, the classification is done via neural network (NN) classifier. After the implementation, the proposed model compares its performance over other conventional methods like principal component analysis (PCA), linear discriminant analysis (LDA) and independent component analysis (ICA) and the performance of the approach is analyzed in terms of measures such as accuracy, sensitivity, specificity, precision, false positive rate (FPR), false negative rate (FNR), negative predictive value (NPV), false discovery rate (FDR), F1Score and Mathews correlation coefficient (MCC), and proves the superiority of proposed work.

T-Whale

One of the infrastructureless networks built by various independent mobile nodes is mobile ad hoc network (MANET), which is an emerging technology, requiring a secure routing protocol for data transmission. Accordingly, literature presents various secure routing protocols for MANETs by utilizing trust and data encryption. In this article, a whale optimization algorithm (WOA) is utilized for selecting the optimal secured routing path in the MANET. The WOA algorithm utilizes the trust factor and the distance between the nodes for computing the fitness for the routing path. Overall, the steps involved in the proposed routing algorithm are as follows: i) Measuring the trust and the distance-based metrics for every node; ii) Discovering k-disjoint path; and iii) Determining the optimal path based on the trust and the distance-based metrics. The performance of the trust-based WOA (T-Whale) is analyzed using the metrics, energy, throughput, and packet delivery rate. From the simulation results, it is evident that the T-Whale algorithm has the improved energy, throughput, and PDR values of 27.4520, 0.4, and 0.4, at the simulation time of 10 sec over the conventional trust random search algorithm when the node is under attack.

A Comprehensive Analysis on Biodiesel Blend Model

This article addresses the issue regarding the exploitation of conventional fuel diesel. To overcome this issue, the Tamanu oil-diesel oil blend is introduced, where a new neural model is proposed, which is trained by renowned firefly algorithm, termed as FF-NM. In addition, different compression ratios such as 15, 16, 17, 17.5 and blend ratios like 5:95, 6:94, 7:93, 8:92, and 9:91and 10:90 is exploited. The emission analysis and the combustion characteristics of the TO-diesel oil blend are evaluated as well as the MSE analysis is carried out for the proposed FF-NM method. For all the predicted parameters, the MSE of the proposed method is low for varying blend as well as the compression ratios. Moreover, the emission characteristics of the HC, CO2, NOx, CO, as well as O2 at different CR concerning the actual, and FF-NM is computed with the chosen blend ratios. From analysis, it is recognized that the estimation errors are less for the FF-NM approach. Hence, the simulation outcomes demonstrate the better performance of the proposed FF-NM approach under various compression ratios of 15, 16, 17 and 17.5, respectively.

Deployment of Context-Aware Sensor in Wireless Sensor Network Based on the Variants of Genetic Algorithm

Wireless sensor networks (WSNs) are generally a group of spatially scattered and devoted sensors to record and monitor the physical environmental condition, and the collected data is grouped at a central location. In fact, the environmental conditions such as sound, humidity, temperature, wind, pollution levels, etc., can be clearly determined by WSNs. The principal objective of WSNs is to organize the whole sensor nodes in their related positions, thereby developing an effective network. In WSNs, target COVerage (TCOV) and Network CONnectivity (NCON) are the main concern of the sensor deployment problem. Many research works aspire the evolvement of smart context awareness algorithm for sensor deployment issues in WSN. Here the TCOV and NCON process are deployed as the minimization problem. This article makes an analysis of different GA variations in attaining the objective. The GA variations are as follows: self-adaptive genetic algorithm (SAGA), deterministic-adaptive genetic algorithm (DAGA), Individual- Adaptive Genetic Algorithm (IAGA). Finally, the methods are compared to one another in terms of connectivity and coverage performance.

Autistic Language Processing by Patterns Detection

The main goal of this article is to present an approach that allows the automatic management of autistic communication patterns by processing audio and video from the therapy session of individuals suffering autistic spectrum disorders (ASD). Such patients usually have social and communication alterations that make it difficult to evaluate the meaning of those expressions. As their communicational skills may have different degrees of variation, it is very hard to understand the semantics behind the verbal behavior. The current work is based on previous work on machine learning for individual performance evaluation. Statistics show that autistic verbal behavior are physically expressed by repetitive sounds and related movements that are evident and stereotyped. The works of Leo Kanner and Ángel Riviere are also considered here. Using machine learning and neural nets with certain set of parameters, it is possible to automatically detect patterns in audio and video recording of patient's performance, which is an interesting opportunity to communicate with ASD patients.

Optimisation of Engineering Systems With the Bees Algorithm

This article describes the Bees Algorithm in standard formulation and presents two applications to real-world continuous optimisation engineering problems. In the first case, the Bees Algorithm is employed to train three artificial neural networks (ANNs) to model the inverse kinematics of the joints of a three-link manipulator. In the second case, the Bees Algorithm is used to optimise the parameters of a linear model used to approximate the torque output for an electro-hydraulic load system. In both cases, the Bees Algorithm outperformed the state-of-the-art in the literature, proving to be an effective optimisation technique for engineering systems.

Hengam a MapReduce-Based Distributed Data Warehouse for Big Data

When working with a high volume of information that follows an exponential pattern, the authors confront big data. This huge amount of information makes big data retrieval and analytics important issues. There have been many attempts to solve data analytic problems using distributed platforms, but the main problem with the proposed methods is not observing the data locality. In this article, a MapReduce-based method called Hengam is proposed. In this method, data format unification helps nodes to have data independence. The unified format leads to an increase in the information retrieval speed and prevents data exchange betoen nodes. The proposed method was evaluated using data items from an ICT company and the information retrieval time was much better than that of other open-source distributed data warehouse software.

Estimation of Dynamic Noise in Mandelbrot Map

Julia and Mandelbrot sets have been studied continuously attracting fractal scientists since their creation. As a result, Julia and Mandelbrot sets have been analyzed intensively. In this article, researchers have studied the effect of noise on these sets and analyzed perturbation. Continuing the trend in this article, they analyze perturbation and find the corresponding amount of dynamic noise in the Mandelbrot map. Further, in order to recover a distorted fractal image, a restoration algorithm is presented.

Generation of UNL Attributes and Resolving Relations for Bangla EnConverter

Conversion of Bangla language to another native language and another language to Bangla language using Universal Networking Language (UNL) is highly demanding due to rapidly increasing the usage of Internet-based applications. UNL has been used by various researchers as an inter-lingual approach for an Automated Machine Translation (AMT) scheme. This article presents a novel work on construction of EnConverter for Bangla language with a special focus on generation of UNL attributes and resolving relations of Bangla text. The architecture of Bangla EnConverter, algorithms for understanding the Bangla input sentence; resolution of UNL relations; and attributes for Bangla text/language are also explained in this article. This article highlights the analysis rules for EnConverter and indicates its usage in generation of UNL expressions. This article presents the results of implementation of Bangla EnConverter and compares these with the system available at Russian and English Language Server.

Performance Evaluation of Feed-Forward Neural Network Models for Handwritten Hindi Characters with Different Feature Extraction Methods

Automatic handwritten character recognition is one of the most critical and interesting research areas in domain of pattern recognition. The problem becomes more challenging if domain is handwritten Hindi character as Hindi characters are cursive in nature and demonstrate a lot of similar features. A number of feature extraction, classification and recognition techniques have been devised and being used in this area; still the efficiency and accuracy is awaited. In this article, performance of various feed-forward neural networks is evaluated for the generalized classification of handwritten Hindi characters using various feature extraction methods. To study and analyze the performance of the selected neural networks, training and test character patterns are presented to each model and their recognition accuracy is measured. It has been analyzed that the Radial basis function network and Exact Radial basis network give highest recognition accuracy while Elman backpropagation neural network gives lowest recognition rate for most of the selected feature extraction methods.