Search

With the implementation of sensors technology, the existence of a Wireless Sensors Network (WSN) of great benefit in the agricultural field. Numerous sensor nodes can be deployed to cover large monitoring fields with enough density at low cost. However, the WSN has strict constraints in weight, size and energy. This paper introduces a clustering algorithm that reduces energy dissipation from sensors during data transmission, based on a Low Energy Adaptive Clustering Hierarchy (LEACH) protocol. LEACH protocol has been modified to increase lifetime of the sensor network. This modified LEACH algorithm reduces the consumption of energy at every step in WSN. Comparatively, the modified LEACH protocol balances the energy in the network and decreases energy consumption by 10% when compared with other protocols.

Image processing techniques are now commonly used in the medical field for early detection of diseases. This research aims to improve accuracy, sensitivity and specificity of early detection of lung cancer through a combination of image processing techniques and data mining. The Computed Tomography (CT) scan image of the lungs is pre-processed and the Region of Interest (ROI) segmented, retained and compressed using a DWT (Discrete Waveform Transform) technique. The resulting ROI image is decomposed into four sub frequencies, bands LL, HL, LH, and HH. Again, the LL sub frequency is decomposed into four sub-bands, applying a 2-level DWT to the ROI based image. Further, features such as entropy, co-relation, energy, variance and homogeneity are extracted from the 2-level DWT images using a GLCM (Gray level Co-occurrence Matrix) with classification effected by means of an SVM (Support Vector Machine). Classification identifies whether the CT image is normal or cancerous. The Lung Image Database Consortium dataset (LIDC) has been used for training and testing purpose for this study. A Receiver Operating Characteristics (ROC) curve is used to analyze the performance of the system. Overall the system has accuracy of 95.16%, sensitivity of 98.21% and specificity of 78.69%.

This paper presents a learning based approach to Bangla Sign Language(BdSL) recognition using the convolutional neural network. In our proposed method, a virtual reality-based hand tracking controller known as Leap motion controller (LMC) has introduced to track the continuous motion of the hands. LMC provides a skeletal model of the hand with appropriate data of hand position, orientation, rotation, fingertips, grabbing and more non-linear features. This controller preprocessed all the motion features and provides error free data. This machine calibrates with the environment and builds a virtual hand in a space. LMC also calculates the rotation, orientation, and textures from hands to determine and to extract hand gesture. In the next process, an efficient method is established to proceed a sequence of frames for positional hand gestures and summarize them to a shorter and more generalized sequence of lines and curves which are added to a Hidden Markov Model. For each sign of expression, we considered a start and an end point of state and segmented the state transitions into segmented HMM. In the segmentation, we assumed the state scope of the hidden variables is discrete. The transition probabilities controlled the way of hidden state at a distinct time. If there is a histogram difference in any state, the transition state moved to new frame to achieve a new sign expression. If there is no hand gesture in the frame, the state has ended by moving to the end point of the model. In the end point, we evaluated the desired hand gesture for recognition. After evaluation, hand gesture data set are proceeded over the convolutional neural network (CNN) and built a decision network. Each neuron is built up by calculating the dot product of extracted features in the dataset. In CNN, a single vector of hand gesture data is received and connected through a series of hidden layers and in the end point computed as a single vector loss function. Each feature is considered as a hidden layer. Determining the least loss function, the network recognizes the expected sign expression. In our experiment, we considered training data first to create the neurons in our network as a supervised way. We achieved significant results from our basic sign expressions in a 3% rate of error where without distortion the rate reduced to 2%. This is an enormous achievement in the Bangla sign language recognition method.

For long, online learning has received criticism on not being able to provide helpful insight on students' learning, for a lack of necessary and appropriate interaction between instructor and students. Despite the fact that learning analytics (LA) are on the rise in terms of their popularity in academic institutions, the usefulness of LA come into question, especially the elements intended to provide effective feedbacks on students' learning process. The main problem for this seems to be a lack of analysis of the characteristics of individuals. Therefore, more needs to be done to actually help students' learning process. The study aims to produce a significant body data by analyzing the content available in online learning environments using Bloom's Taxonomy. Initial results show that most content found in online learning environments consist of offline learning material that was transferred to online learning platforms by taking very limited advantage of the resources of the Internet. It is hypothesized that in this study learning content in online environments do not support learners efficiently transfer to higher cognitive levels described in Bloom's taxonomy.

The increasing prevalence of Autism Spectrum Disorder (ASD) has made this as one of the largest disability groups. Autism Spectrum Disorder (ASD) is considered as a lifelong developmental disability impacting on three main areas; communication skills, behavioural patterns and health. The main focus of this research is on the use of Augmentative and Alternative Communication (AAC) solutions as part of assistive and wearable technologies for children with ASD. Specifically, the present study will identify benefits and limitations of the use of these technologies. Of major concern in terms of the use of both technologies, is their limited ability to improve the communication skills and health monitoring of children diagnosed with ASD. This research presents a framework for wearable technology that assists children with ASD through enhancing their communication skills, improving behaviour and facilitating health monitoring.

This paper proposes a hybrid solution of spam email classifier using context based email classification model as main algorithm complimented by information gain calculation to increase spam classification accuracy. Proposed solution consists of three stages email pre-processing, feature extraction and email classification. Research has found that LingerIG spam filter is highly effective at separating spam emails from cluster of homogenous work emails. Also experiment result proved the accuracy of spam filtering is 100% as recorded by the team of developers at University of Sydney. The study has shown that implementing the spam filter in the context -based email classification model is feasible. Experiment of the study has confirmed that spam filtering aspect of context-based classification model can be improved.

Object tracking is one of the most important applications of wireless sensor networks. Energy conservation is the primary issue of most of the tracking algorithms. This paper depicts a comparative study of different prediction methods for object tracking in wireless sensor networks. There are some noted areas of object tracking in which prediction is used for target detection or forecasting, querying to sensor data, deployment of nodes, clustering etc. In this survey paper, various prediction techniques are discussed which associates advantages of accuracy of tracking, reduction of missing rate and energy conservation. Moreover other factors like clustering and data mining techniques that affect the prediction are also discussed.

In this paper, we explore the different approaches of non-parametric models to predict the software reliability. Software reliability is an important part of software quality assessment. Even though many conventional statistical models are successfully used to predict software reliability, no single model can apply in all situations. Software reliability prediction is hard to achieve. In order to improve the accuracy of software reliability prediction, non-parametric methods are suggested. Recently many research works are going on with the combination of Artificial Neural Networks, Fuzzy Logic and Genetic Algorithm. This survey paper explains the different approaches of the non-parametric ANN method to improve the reliability prediction.