Table of contents

Preface

It is our great pleasure to welcome you to 2017 10th International Conference on Computer and Electrical Engineering which will take place in University of Alberta, Edmonton, Canada during October 11-13, 2017. ICCEE2017 is dedicated to issues related to Computer and Electrical Engineering.

The major goal and feature of the conference is to bring academic scientists, engineers, industry researchers together to exchange and share their experiences and research results, and discuss the practical challenges encountered and the solutions adopted. Professors from Canada and Luxembourg are invited to deliver plenary speeches regarding latest information in their respective expertise areas. It will be a golden opportunity for the students, researchers and engineers to interact with the experts and specialists to get their advice or consultation on technical matters, sales and marketing strategies.

These proceedings present a selection from papers submitted to the conference from universities, research institutes and industries. All of the papers were subjected to peer-review by conference committee members and international reviewers. The papers selected depended on their quality and their relevancy to the conference. The volume tends to present to the readers the recent advances in the field of Computer and Electrical Engineering and various related areas, such as Computer Vision, Graphics and Intelligence, Computational and Artificial Intelligence, Advanced Power Semiconductors, Analogue and Digital Signal Processing, Algorithm, etc.

We would like to thank all the authors who have contributed to this volume and also to the reviewers, speakers, chair persons and all the conference participants for their support to ICCEE 2017.

Best Regards!

Yours sincerely,

Conference Organizing Committee

October 20, 2017

List of Conference Chairs, Local Chair, Program Chairs, Publicity Chairs, Technical Committee are available in this PDF.

All papers published in this volume of Journal of Physics: Conference Series have been peer reviewed through processes administered by the proceedings Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.

In this paper, we propose a novel image retrieval algorithm for mobile visual search. At first, a short visual codebook is generated based on the descriptor database to represent the statistical information of the dataset. Then, an accurate local descriptor similarity score is computed by merging the tf-idf weighted histogram matching and the weighting strategy in compact descriptors for visual search (CDVS). At last, both the global descriptor matching score and the local descriptor similarity score are summed up to rerank the retrieval results according to the learned zone weights. The results show that the proposed approach outperforms the state-of-the-art image retrieval method in CDVS.

Optical character recognition is concerned with the recognition of optically processed characters. The recognition is done offline after the writing or printing has been completed, unlike online recognition where the computer has to recognize the characters instantly as they are drawn. The performance of character recognition depends upon the quality of scanned documents. The preprocessing steps are used for removing low-frequency background noise and normalizing the intensity of individual scanned documents. Several filters are used for reducing certain image details and enabling an easier or faster evaluation. The primary aim of the research work is to recognize handwritten and machine written characters and differentiate them. The language opted for the research work is Punjabi Gurmukhi and tool utilized is Matlab.

An efficient wavelet-based algorithm to reconstruct non-square/non-cubic signals from gradient data is proposed. This algorithm is motivated by applications such as image or video processing in the gradient domain. In some earlier approaches, the non-square/non-cubic gradients were extended to enable a square/cubic Haar wavelet decomposition and the coarsest resolution subband was derived from the mean value of the signal. In this paper, a non-square/non-cubic wavelet decomposition is obtained directly without extending the gradient data. The challenge comes from finding the coarsest resolution subband of the wavelet decomposition and an algorithm to compute this is proposed. The performance of the algorithm is evaluated in terms of accuracy and computation time, and is shown to outperform the considered earlier approaches in a number of cases. Further, a closer look on the role of the coarsest resolution subband coefficients reveals a trade-off between errors in reconstruction and visual quality which has interesting implications in image and video processing applications.

Bone age assessment (BAA) is a task performed on radiographs by the pediatricians in hospitals to predict the final adult height, to diagnose growth disorders by monitoring skeletal development. For building an automatic bone age assessment system the step in routine is to do image pre-processing of the bone X-rays so that features row can be constructed. In this research paper, an enhanced point distribution algorithm using contours has been implemented for segmenting bone parts as per well-established procedure of bone age assessment that would be helpful in building feature row and later on; it would be helpful in construction of automatic bone age assessment system. Implementation of the segmentation algorithm shows high degree of accuracy in terms of recall and precision in segmenting bone parts from left hand X-Rays.

This paper proposes a new evaluation parameter of image super-resolution reconstruction quality, which is used to determine the influence of super-resolution reconstruction on motion measuring precision. Based on this new evaluation parameter, we respectively employ different algorithms of super-resolution reconstruction with different reconstruction scales, then calculate the motion measuring precision using the corresponding super-resolution image, analyze the impact of image super-resolution technology on the precision of image motion measuring. The experimental results show that only part of the super-resolution algorithms can improve the measuring precision slightly, and prove that under the background of image motion measurement, image super-resolution reconstruction method has the potential to apply to the actual measurement.

In this paper, we propose an automatic detection schema including three stages for weld defects in x-ray images. Firstly, the preprocessing procedure for the image is implemented to locate the weld region; Then a classification model which is trained and tested by the patches cropped from x-ray images is constructed based on deep neural network. And this model can learn the intrinsic feature of images without extra calculation; Finally, the sliding-window approach is utilized to detect the whole images based on the trained model. In order to evaluate the performance of the model, we carry out several experiments. The results demonstrate that the classification model we proposed is effective in the detection of welded joints quality.

ARM-Android is a widespread mobile platform with multi-layer access control mechanisms, security-critical in the system. Many access control vulnerabilities still exist due to the course-grained policy and numerous engineering defects, which have been widely studied. However, few researches focus on the mechanism formalization, including the Android permission framework, kernel process management and hardware isolation. This paper first develops a comprehensive formal access control model on the ARM-Android platform using the B method, from the Android middleware to hardware layer. All the model specifications are type checked and proved to be well-defined, with 75%of proof obligations demonstrated automatically. The results show that the proposed B model is feasible to specify and verify access control schemes in the ARM-Android system, and capable of implementing a practical control module.

OCL is the most prevalent language to document system constraints that are annotated in UML. Writing OCL specifications is not an easy task due to the complexity of the OCL syntax. Therefore, an approach to help and assist developers to write OCL specifications is needed. There are two approaches to do so: First, creating an OCL specifications by a tool called COPACABANA. Second, an MDA-based approach to help developers in writing OCL specification by another tool called NL2OCLviaSBVR that generates OCL specification automatically. This study presents another MDA-based approach called En2OCL, and its objective is twofold. 1- to improve the precison of the existing works. 2- to present a benchmark of these approaches. The benchmark shows that the accuracy of COPACABANA, NL2OCLviaSBVR, and En2OCL are 69.23, 84.64, and 88.40 respectively.

At present, the common information extraction method cannot extract the structured emergency event information accurately; the general information retrieval tool cannot completely identify the emergency geographic information; these ways also do not have an accurate assessment of these results of distilling. So, this paper proposes an emergency information collection technology based on event framework. This technique is to solve the problem of emergency information picking. It mainly includes emergency information extraction model (EIEM), complete address recognition method (CARM) and the accuracy evaluation model of emergency information (AEMEI). EIEM can be structured to extract emergency information and complements the lack of network data acquisition in emergency mapping. CARM uses a hierarchical model and the shortest path algorithm and allows the toponomy pieces to be joined as a full address. AEMEI analyzes the results of the emergency event and summarizes the advantages and disadvantages of the event framework. Experiments show that event frame technology can solve the problem of emergency information drawing and provides reference cases for other applications. When the emergency disaster is about to occur, the relevant departments query emergency's data that has occurred in the past. They can make arrangements ahead of schedule which defense and reducing disaster. The technology decreases the number of casualties and property damage in the country and world. This is of great significance to the state and society.

AI in Healthcare needed to bring real, actionable insights and Individualized insights in real time for patients and Doctors to support treatment decisions., We need a Patient Centred Platform for integrating EHR Data, Patient Data, Prescriptions, Monitoring, Clinical research and Data. This paper proposes a generic architecture for enabling AI based healthcare analytics Platform by using open sources Technologies Apache beam, Apache Flink Apache Spark, Apache NiFi, Kafka, Tachyon, Gluster FS, NoSQL- Elasticsearch, Cassandra. This paper will show the importance of applying AI based predictive and prescriptive analytics techniques in Health sector. The system will be able to extract useful knowledge that helps in decision making and medical monitoring in real-time through an intelligent process analysis and big data processing.

Almost all public-sector organisations in Bangladesh now offer online services through web applications, along with the existing channels, in their endeavour to realise the dream of a 'Digital Bangladesh'. Nations across the world have joined the online environment thanks to training and awareness initiatives by their government. File sharing and downloading activities using web applications have now become very common, not only ensuring the easy distribution of different types of files and documents but also enormously reducing the time and effort of users. Although the online services that are being used frequently have made users' life easier, it has increased the risk of exploitation of local file disclosure (LFD) vulnerability in the web applications of different public-sector organisations due to unsecure design and careless coding. This paper analyses the root cause of LFD vulnerability, its exploitation techniques, and its impact on 129 public-sector websites in Bangladesh by examining the use of manual black box testing approach.

Illusive comments of product or services are misleading for people in decision making. The current methodologies to predict deceptive comments are concerned for feature designing with single training model. Indigenous features have ability to show some linguistic phenomena but are hard to reveal the latent semantic meaning of the comments. We propose a prediction model on general features of documents using stacking with ensemble learning. Term Frequency/Inverse Document Frequency (TF/IDF) features are inputs to stacking of Random Forest and Gradient Boosted Trees and the outputs of the base learners are encapsulated with decision tree to make final training of the model. The results exhibits that our approach gives the accuracy of 92.19% which outperform the state-of-the-art method.

Protection of digital assets and intellectual property is becoming a challenge for most of the companies. Due to increasing availability of database services on internet, data may be insecure after passing through precarious networks. To protect intellectual property (IP) is a major concern for today's organizations, because a leakage that compromises IP means, sensitive information of a company is in the hands of biggest competitors. Electronic information processing and communication is replacing paper in many applications increasingly. Instead of paper, an email is being used for communication at workplace and from social media logins to bank accounts. Nowadays an email is becoming a mainstream business tool. An email can be misused to leave company's sensitive data open to compromise. So, it may be of little surprise that attacks on emails are common. So, here we need an email protection system (EPS) that will protect information to leave organization via mail. In this paper, we developed an algorithm that will offer email protection via gateway during data transfer. This algorithm matches the patterns with the keywords stored in the database and then takes the actions accordingly to protect the data. This paper describes why email protection is important? How companies can protect their confidential information from being leaked by insiders.

The paper proposes adaptive web recommendation system based on user behavior. The proposed system uses expert system to evaluating and recommending suitable items of content. Relevant items are subsequently evaluated and filtered based on history of visited items and user´s preferred categories of items. Main parts of the proposed system are presented and described. The proposed recommendation system is verified on specific example.

Every company wants to discover what its customers feel about it. But sentiment analysis can get coarser and turn inward to improve employee as well as customers' satisfaction. A term called sentiment analysis, or the mathematical taxonomy of statements' negative or positive connotations, gives companies potent ways to analyse cumulative language data across all sorts of communications. There's real value in measuring sentiment inside and outside your company. Our big data experts analyse the core grounds of the problems raised while handling giant datasets and find solutions to efficiently manage massive datasets with ease. We built a sentiment analysis solution to measure positive and negative sentiments with top rating products for Amazon.com's Electronics products as against competitor products.

Nowadays due to most of the telecommunication standard development organizations focusing on using device-to-device communication so that they can provide proximity-based services and add-on services on top of the available cellular infrastructure. An Oppnets and wireless sensor network play a prominent role here. Routing in these networks plays a significant role in fields such as traffic management, packet delivery etc. Routing is a prodigious research area with diverse unresolved issues. This paper firstly focuses on the importance of Opportunistic routing and its concept then focus is shifted to prime aspect i.e. on packet reception ratio which is one of the highest QoS Awareness parameters. This paper discusses the two important functions of routing in wireless sensor networks (WSN) namely route selection using least routing time algorithm (LRTA) and data forwarding using clustering technique. Finally, the simulation result reveals that LRTA performs relatively better than the existing system in terms of average packet reception ratio and connectivity.

The simple landslide monitoring system is mainly designed for slope, collapse body and surface crack. In the harsh environment, the dynamic displacement data of the disaster body is transmitted to the terminal acquisition system in real time. The main body of the system adopt is PIC32MX795F512. This chip is to realize low power design, wakes the system up through the clock chip, and turns on the switching power supply at set time, which makes the wireless transmission module running during the interval to ensure the maximum battery consumption, so that the system can be stable long term work.

The volume of data being collected, analyzed, and stored has exploded in recent years, in particular in relation to the activity on the cloud computing. While large-scale data processing, analysis, storage, and platform model such as cloud computing were previously and currently are increasingly. Today, the major challenge is it address how to monitor and control these massive amounts of data and perform analysis in real-time at scale. The traditional methods and model systems are unable to cope with these quantities of data in real-time. Here we present a new methodology for constructing a model for optimizing the performance of real-time monitoring of big datasets, which includes a machine learning algorithms and Apache Spark Streaming to accomplish fine-grained fault diagnosis and repair of big dataset. As a case study, we use the failure of Virtual Machines (VMs) to start-up. The methodology proposition ensures that the most sensible action is carried out during the procedure of fine-grained monitoring and generates the highest efficacy and cost-saving fault repair through three construction control steps: (I) data collection; (II) analysis engine and (III) decision engine. We found that running this novel methodology can save a considerate amount of time compared to the Hadoop model, without sacrificing the classification accuracy or optimization of performance. The accuracy of the proposed method (92.13%) is an improvement on traditional approaches.

This study aimed to explore how much interest do technical colleges students have in vocational guidance E-Systems and to detect the most important E-Systems of vocational guidance that they use. The researcher collected data, through questionnaires, from 311 students in their fourth, fifth, or sixth semesters in the colleges of technology in Saudi Arabia. The data were analysed using the chi square test, factor analysis, and descriptive analysis. This study shows the importance in the integration of the E-Systems to vocational guidance. The model includes: the use of e-vocational consulting programs, e-extracurricular programs, e-vocational activities, informational systems, and e-exams for vocational tendency, which were rarely studied before. The results indicated that the college student is highly motivated by vocational guidance using the E-system, unlike the traditional methods of vocational guidance, and young students are motivated by the E-system when it is used in vocational guidance. The study conclude that the integration of the E-system has significantly contributed to vocational guidance. The study recommends that the e-system be implemented to all areas of decision-making. Practitioners should Interact with students through the E-Systems and arrive at decisions that are good for educational growth.

Nowadays, access control is an indispensable part of the Personal Health Record and supplies for its confidentiality by enforcing policies and rules to ensure that only authorized users gain access to requested resources in the system. In other words, the access control means protecting patient privacy in healthcare systems. Attribute-Based Access Control (ABAC) is a new access control model that can be used instead of other traditional types of access control such as Discretionary Access Control, Mandatory Access Control, and Role-Based Access Control. During last five years ABAC has shown some applications in both recent academic fields and industry purposes. ABAC by using user's attributes and resources, makes a decision according to an access request. In this paper, we propose an ABAC framework for healthcare system. We use the engine of ABAC for rendering and enforcing healthcare policies. Moreover, we handle emergency situations in this framework.