Recent Advances in Computer Science and Communications - Volume 14, Issue 7, 2021

Background: With today’s emerging world of technology, fusion is the key factor in every field, especially in the field of medical and remote sensing. By fusing two or more images, we get necessary useful data in a particular fused image. So it is the best technique to remove noise data from those images. Methods: Noise or Blurring are those unwanted data that affects the quality of an image in terms of clarity. There are numerous methods for image fusion that can be used to eliminate noise or blurring that gives best results in the form of the fused image. Conclusion: In this paper, diverse techniques have been reviewed, studied and compared to discover the limitations of multiple image fusion techniques.

Background: The data is one of the prime assets in today’s world. The continuous data generation ultimately creates a huge volume of data that cannot be processed or stored by a normal relational database management system. This problem is addressed by a new concept: Big Data. Apart from the size of data, security and privacy of data are the more challenging issues in Big data technology. Objective: The primary objective of the research is to identify the potential security threats of different big data computing technologies and provide a defense mechanism to mitigate the issues. Methods: To identify the security issues, different existing big data systems are thoroughly analysed and observed. Security systems are completely dependent on the system architecture. This can be a single architecture (dependent on one computing technology) or multi architecture type (dependent on multiple computing technologies). The internal mechanism of different technologies is observed and how the attacks change the behavioural pattern of the systems is the main backbone of the research. Based on the behaviour of dissimilar attacks, a comprehensive defense mechanism is identified. Security and privacy challenges of mobile healthcare are also considered as a case study. Results: The complete lists of big data computing security threats in different layers of the systems are identified. Through this research, the remedial measures of the different attacks are found. The security challenges of mobile healthcare technology and its predictive measurements are sorted out. The changes of big data security systems behaviour based on its architecture are of the major findings of this research. Conclusion: The integration of mobile healthcare along with Internet of Things (IoT) and blockchain computing can enhance the system level and hence security threats can be minimized.

The existing studies have already revealed that the information on the web is increasing rapidly. Ambiguous queries and users’ ability to express their intention through queries have been one of the key challenges in retrieving accurate search results from the search engine. This paper in response explored different methodologies proposed during 2005-2019 by the eminent researchers for obtaining better search results. Some of these methodologies are based on the users’ geographical location while others rely on re-ranking the web results and refinement of the users’ queries. Fellow researchers can use this literature to define the fundamental literature of their work. Furthermore, a brief case study of major search engines like Google, Yahoo, Bing, etc. along with the techniques used by these search engines for personalization is also discussed. Finally, the paper discusses some current issues and challenges related to personalization which further defines the future research directions.

Background: Remote authentication in current networks such as IoT that connects many end-devices of low capacity must be light, accurate and scalable without threatening security. In general, biometrics is the most reliable way to authenticate users because of its efficient results in many applications. Objective: The biometric data is expressed by a feature vector that should be extracted and secured by reliable techniques. This paper proposes a suitable extraction and encryption scheme with the aim to make the authentication light, accurate, scalable and secure. Methods: As extraction technique, principal component analysis with a nonlinear block average quantization is used to reduce the feature vector length with the aim to increase the rapidity and the scalability. As encryption technique, the fuzzy commitment and the fuzzy vault with Hamming and Reed-Solomon codes are used to increase security. These cryptosystems are tested with multibiometric modalities to make the validation more credible. Results: Experimental results are analyzed, validated and compared to other works according to several conventional and new recognition rates. Analysis is also done in terms of computation time to validate the lightness of our findings. It is shown that the proposed scheme finds a compromise between the coveted features. Conclusion: Our biometric cryptosystems ensure a secure, light, precise and scalable remote authentication. These properties can be achieved by using the PCA technique with nonlinear coefficient quantization and fuzzy schemes with the appropriate correcting-code.

Background: One of the most prevalent diseases these days is breast cancer which is common amongst women. This sickness has been increasing to an alarming rate due to the lack of accurate diagnoses. Early and accurate detection is one of the safest ways to cure a breast cancer patient. Objectives: The objective of this study was to provide a more effective way to accurately classify a cancer sample; whether is benign or malignant. Methods: The classification model is based on the data collected from the UCI machine learning repository acquired from the Wisconsin hospital called Wisconsin Breast Cancer Data (WBCD). In this study, we preprocessed the dataset using Discrete Wavelet Transform (DWT) and then tested the efficiency of Deep Learning (DL) for breast cancer classification. The model was developed using a feed-forward neural network and the result was compared with the observed values. Results: The result of the experiment proved the effectiveness of the proposed classification technique. The new technique accomplished 98.90% accuracy for classifying breast cancer. Conclusions: The result from the experiment shows the importance of data preprocessing and the efficiency of the neural network over other classification algorithms.

Background: Emergency vehicles required a quick clearance so as to reach the destination with minimum delay and the human life could be saved. Emergency vehicle required a dedicated path for clearance. The dedicated path creates a chaos by blocking the entire route for others vehicles and it is not always possible to create a dedicated path. So there is an imperative need for a smart road navigation system which adapts to the traffic congestion in real-time velocity of vehicle, count of vehicle, number of lanes and distance from source to destination. Objective: The objective of this paper is to find an optimal route for providing a least congested optimal route for emergency vehicle with least delay considering various issues such as congestion, numbers of vehicles, average traffic flow on the roads and width of the lane between source and destination. Methods: Real-time traffic data like number of vehicles, velocity of the vehicles, and the width of the road and distance of the route are used to determine the congestion factor on all possible route. Congestion factor is used for finding the shortest route to requesting emergency vehicle. Results: Experimental results establish that the travel time of a vehicle is reduced by approximately 26%, when the vehicle uses the optimized route. This is beneficial for any emergency vehicle as the optimal path is provided on a real-time basis. Conclusion: This research work proposes an analytical approach that provides the least congested optimal route on-demand based on real-time traffic.

Background: Cloud computing is an emerging technology today and playing an important role in providing the services through the internet. Users get enormous benefits like high accessibility of available application resources, faster time to market, fast development, deployment, lower startup, operations cost and much more. Cloud offers utilizing the benefits through the web services. Objective: The degrading factors such as low Quality of Service, security factors, and less resource management in cloud lead to service suitability issue. In service-oriented computing, finding an efficient QoS based web service on the web is a very challenging task. Methods: A quality of service metric approach is proposed to identify the suitability of web services and ensuring the deployability in the cloud era. The suitability of web service is examined for its suitability cases (simple suitable, average suitable and best suitable) with respect to the quality of service attribute. Results: In the experimental setup, the suitability scores calculated with the essential non-functional quality of service attribute information are identified from the set of services. However, the verification process is expressed using the state transition diagram. Conclusion: The proposed system is simulated using JFLAP-a java package tool and the result shows the service suitability for the cloud. In this context, the efficiency of identifying service suitability for deploying in the cloud gets verified using automated theory without affecting the performance of the cloud service.

Objectives: The main objectives of this manuscript are to investigate and diagnose rolling element bearing defects in its incipient stage. Methods: Vibration signal generated by the induction motor contains a series of frequency components that have rich and viable information about bearing health conditions. Recently, the Maximum Energy Concentration (MEC), measure of time-frequency spectrum has been employed to investigate the small variations in low frequency biomedical signal spectrum. In this paper, the above technique has been modified and applied to study the bearing defects of induction motor using vibration signal and it is termed as Adaptive Modified Morlet Wavelet (AMMW) transform. Initially, this proposed method was validated on two medium frequency synthetic time series signals in terms of MEC measurement at different Signal to Noise Ratio (SNR). Results: The simulated results have depicted that the AMMW method provides excellent timefrequency localization capability over other time-frequency methods like Morlet wavelet transform, modified Morlet wavelet transform, adaptive S-transform and adaptive modified S-transform. Then, this method has been applied to the standard database of vibration signal to determine interquartile power for fault detection purpose and also fault index parameter termed as IFI has been analyzed to detect small variation in vibration signals.

Background: With the rapid development of the domestic, independent heating system, the wall-hanging boiler has become the focus of concern for a large number of users. As an independent heat source, it has been widely applied in many places. Objective: Based on many deficiencies emerging from the wall-hanging gas boiler used at present, a novel electrothermal wall-hanging boiler is presented in this paper to realize the central heating system and provide a constant temperature water supply system in the meantime. Methods: 3D solid model of the wall-hanging boiler was firstly designed by using the software Solidworks, and then, based on ARM intelligent microcontroller, the circuit board production was completed with the corresponding control circuit design to conduct the automatic temperature regulation of the wall-hanging boiler, so as to achieve the desired effect of the constant temperature heating and energy conservation. Results: On the basis of the experiments and the test of sample, it was concluded that the trial operation of the prototype can meet the expected requirements. The greatest innovation of the product is to use a new type of nano semiconductor material, and a sort of hydrocyclone mode to enhance the heat exchange in a more full and uniform way, as well as improve the thermal efficiency greatly. Conclusion: Such patent provides an effective theoretical and experimental basis for the diagnosis and fixing of the electrothermal wall-hanging boiler. With the help of the prototyping fabrication and debugging installation, it can be shown that the novel electrothermal wall-hanging boiler will have a very broad application prospect.

Aims: In this paper, we propose an enhanced artificial bee colony (ABC) algorithm for the job shop scheduling problem. Background: Meta-heuristic approaches are widely applied to solve job shop scheduling problem and find the near optimal solutions in polynomial time. Objective: Improving performance of ABC algorithm to solve job shop scheduling problem. Methods: Using local search heuristics in ABC algorithm. Results: The experimental results showed that the proposed algorithm improves the efficiency. Conclusion: Proposed algorithm improves efficiency.

Aims: Presenting a novel approach to identify Persian static symptoms in that the proposed sign language recognition system consists of two segmentation and feature extraction phases. In the segmentation phase, the hand region is separated by an effective segmentation method from the original image. Objective: (1) Introducing an effective framework to solve sensitivity to light conditions in identifying and recognizing letters of the Persian sign language alphabet. (2) Proposing a new feature extraction method to eliminate sensitivity to rotation and scale changes. (3) Creating a new dataset includes 480 images of the sign language alphabet symptoms in order to show the performance of our method. Methods: The proposed sign language recognition system uses two segmentation and feature extraction phases. In the segmentation phase, the hand region is separated by an effective segmentation method from the original image. This method is based on the unique Gaussian model in the YCbCr color space. The Bayes rule is used to precisely identify the hand region too. In the feature extraction phase, the radial model is used to obtain a one-dimensional function to display the hand region boundary and to compute the combined feature vector. In order to normalize this method, the Fourier Transformation method is applied. Results: The system was trained and tested using 480 image samples of Persian sign language characters, 15 images per sign, with the .jpg extension. Extensive experimental evaluations indicate that the proposed recognition system is less susceptible to displacement, scale, and rotation, and can detect symptoms at an accuracy of 95.62%. Conclusion: In this article, a new system was proposed for recognizing the alphabet letters in Persian sign language. This system consists of two main phases: the segmentation phase or the hand region identification and feature extraction phase. In the segmentation phase of the detection system, at first, the hand region is separated by an effective segmentation method from the original image. This method is based on the single Gaussian model in the color space of the YCbCr and the Bayes rule. Applying this method in hand segmentation, enables the system, to recognize the hand region well. In this method, after hand region detection, using the Sobel edge detector, the image edge is extracted. In the feature extraction phase, the radial distance model was used to obtain a one-dimensional function display of the hand region boundary and compute its feature vector. This model is based on the edge and image centroid and computes the centroid distance to the shape boundary as a function of the angle. Since this model by itself is sensitive to the scale variations and tilt, in order to normalize this method to tilt variations, the Fourier transformation was applied to feature vector computed by the radial model. Then the vector elements are divided by the largest vector element, thus, using this method the computed feature vector will be distinct for different images and will show less sensitivity to displacement, scale, and gradient. A database consist of 480 images of Persian sign symptoms was created to the overall accuracy evaluation of the system, the results show that the proposed recognition system can identify 32 letters of the Persian sign language alphabet with a detection rate 95.62%.

Background: Identification of key processes and key paths plays an important role in project management and control. Therefore, in order to reduce the expected time of the project, some analysis methods other than engineering technology must be adopted. The Graphical Evaluation and Review Technique (GERT) is a useful tool in system analysis and design. The GERT can process the relationships in network diagrams, which is a network with feedback function and has been applied in many fields. Methods: In this paper, based on Bayesian network model and GERT network, a new method for analyzing project process has been studied. Firstly, all the variable nodes of the GERT network are determined. Secondly, the variable nodes in the GERT network are divided into tandem nodes, aggregation nodes, distributed nodes, and self-loop nodes in the Bayesian network. Third, the GERT network parsing method is used to calculate the expected time of the partial variable node. Then the network structure of the Bayesian network is constructed by connecting the nodes with the directed edges. Results: Thus, a GERT Bayesian model is established. Based on the probability of Bayesian network, we determined the key process, made improvements in the key process and shortened the processing time. Conclusion: Finally, this method is used to analyze an ERP project activity flow chart with selfloop structure, identify the key processes and key paths, and determine the time period. Based on this, the validity and reliability of the method in project process management are verified.

Background: Crop yield is affected by several agronomic factors such as soil type and date of sowing, and meteorological factors such as temperature and rainfall. While the agronomic factors are responsible for inter-region variations in yield, the year-wise yield variation in a particular region may be attributed to meteorological factors. Various Data Mining Techniques can be applied to analyse the effect of these factors on crop yield. Objective: To develop a model for prediction of Block-wise average wheat yield in the Patiala district of Punjab, India. Methods: Sampling is used for the collection of the yield data, and the data concerning temperature and rainfall is obtained from the Indian Meteorological Department, Pune. The data is then preprocessed and analysed to study the effect of phase-wise average temperature and total rainfall on the wheat yield. The factors that are found to significantly affect yield are used for building a model for yield prediction. Results: It has been found that the average temperature and the total rainfall for the whole wheat growing season are not much of help in explaining the variations in yearly wheat yield. The temperature and rainfall have different effects at different stages of plant growth and the yield is affected accordingly. It is inferred that the average temperature and the total rainfall during the vegetative phase and the grain development and ripening phase are the most important parameters for the prediction of wheat yield. Conclusion: The stepwise selection mechanism is used to choose the variables whose inclusion explains the maximum variance in yield. The model is evaluated based on different parameters and is found to explain 95.6% of the yearly variations in yield.

Background: Automatic human emotion recognition system is an active area of research due to its wide applications in the field of Human Computer Interaction(HCI) systems, driver fatigue monitoring systems, surveillance systems, human assistance systems, smile detectors etc. Objective: The study presents a fuzzy based approach to extract facial features from input image and builds different classification models to classify the image into two emotion classes i.e. happy and neutral. The system has potential implications in the field of smile detection systems, customer experience analysis and patient monitoring systems. Methods: The proposed system determines the dimensional attributes (l-attribute and w-attribute) of mouth region extracted from the facial image using viola-jones algortithm. The feature set is generated by using a total of 136 images from JAFFE, NimStim and MUG dataset. The differentiating power of the attribures is then evaluated using five different classification models. Results: The accuracy, precision and recall is determined for each classification model. The results show good accuracy of 70% for the grayscale JAFFE and NimStim databases and 95% for the coloured MUG database. Conclusion: The mouth features calculated in the study are based on the geometric coordinates which eliminates the possibility of false distance measurements due to presence of noise or shadows.

Aims: The paper is concerned with the problem of robust H∞ output feedback control for photovoltaic nonlinear system. Background: The PV systems are built to transform sun irradiance into electrical power. The dc-dc converters, such as buck type, boost type, and buck-boost type, have been widely implemented in the PV systems. Linear controllers for dc-dc converters are often designed based on mathematical models. To get a desired performance objective, an accurate model is essential. Objective: There has been increasing interest in the scheme of digital controller design for dc-dc converters. However, most of the research efforts are focused on the representation based on the standard forward-shift operator approach, which are of inherently ill-conditioned when datum are taken at high sampling rates. Compared with the forward-shift operator, the delta operator has many virtues which can be applied as a better representation of the underlying physical model under high sampling rates. Despite the delta operator possessing the superior high sample rate performance has been recognized in the past two decades, there exists little literature discussing the analysis and synthesis of photovoltaic nonlinear systems by using delta operator fuzzy control method, which motivates us to make an effort in this topic. Methods: We propose a Fuzzy Dynamic Output Feedback (FDOF) controller, and introduce a novel Lyapunov-Krasovskii Functional (LKF) in delta domain, the framework of robust H∞ output feedback control is investigated. Results: Sufficient conditions are derived for the existence of the desired FDOF controllers in terms of Linear-Matrix Inequalities (LMIs). A numerical example is used to illustrate the design procedure of the present method. Conclusion: This paper has studied the problems of robust H∞ output feedback control for photovoltaic nonlinear system with interval time-varying delay and parametric uncertainties. Based on the formulated fuzzy system and the FDOF controller, we introduced a Lyapunov-Krasovskii function in delta domain, the scheme of FDOF was proposed. Sufficient conditions for the existence of the FDOF controller were derived in terms of LMIs. A numerical example was used to demonstrate the effectiveness of our proposed methods.

Background: In the era of Internet of Things (IoT), automation of home and security systems is becoming remarkably easy. Many research works have also been conducted to bring the most convenient way of automating home appliances and security systems. But little research has been carried out in providing the most comprehensive or autonomous or self-controlled home automation. This paper aims to provide a comprehensive solution to mitigate the existing need. End users can interact with household appliances in a variety of means irrespective of platforms used and their geographical location through a smartphone application. Using their speech as input, users can also operate the electrical appliances via voice commands. In addition to the mobile application and voice command by integrating some cloud services, an attractive web interface could be provided as another alternative for better data presentation and analysis. The autonomous feature would allow the home to monitor and control its environment by itself through installed sensors, sharing data and taking a relevant measurement without a need for human intervention. Methods: In order to achieve these performances, the work will deploy MQTT (Message Queuing Telemetry Transport), a messaging protocol to enable the modules to easily communicate with one another. Results: Multiple alternative means of controlling and interacting with home appliances were provided. Both autonomous mode and safe mode features would make the system to behave and run autonomously. Conclusion: The paper also highlights the presentation for an application of multiway, crossplatform and user-oriented home automation and security system as well as convenient means of controlling and monitoring household electrical appliances.

Background: The notion of fuzzy set was introduced by Zadeh. After that, many researchers extended the concept of fuzzy sets in different ways. Atanassov introduced the concept of intuitionistic fuzzy sets as an extension of fuzzy sets. This concept is applied in many fields such as bio-informatics, image processing, decision making, feature selection, pattern recognition, etc. Objectives: The prime objective of this paper is to introduce a new generalized intuitionistic fuzzy divergence measure with proof of its validity and discussions on its elegant properties. Applications of the proposed divergence measure in multi-attribute decision making and pattern recognition are also discussed with some numerical illustrations. Furthermore, the proposed divergence measure is compared with other methods for solving MADM and pattern recognition problems, which exist in the literature. Methods: The divergence measure method is used to measure the divergence between two given sets. In addition, the results of the other existing measures are also given to compare with the proposed measure. Results: It was observed that the proposed divergence measure found much better results in comparison with the other existing methods. Conclusion: A new divergence measure for intuitionistic fuzzy sets is introduced with some of its properties. Applications of the proposed divergence measure to pattern recognition and MADM are illustrated through examples. The comparison of the proposed method with the existing methods shows the legacy of the results of the proposed method. It is concluded that the proposed divergence measure is effective for solving real-world problems related to MADM and pattern recognition.

Background: Gender recognition is one of the most challenging perceptible tasks, which is gaining attention in the increasing digital data era as the requirement of a personalized, reliable and ethical system inevitable. A problem that we address in this paper greatly deals with the gender based identification system. We are motivated by this problem as many recent social interactions and existing services rely on the gender of an individual, and also in forensic identification, the gender information provides the feasibility for easy and quick investigation. Objective: The paper primarily focused on the gender based identification problem and culminated a robust gender based recognition system with a higher accuracy rate. We attempted to perceive the gender of an individual through the multimodal biometric system by integrating the three prominent biometric traits namely: fingerprint, palm-print and hand in a specific manner. The proposed multimodal biometric for gender recognition system provides a better accuracy rate improvement with the optimal feature set which is generated from available high dimensional features set. Methods: Aiming for the objective to reduce the search space, a hybrid meta-heuristic approach GSA-Firefly (GFF) is introduced in this paper. The optimization approach GFF is proposed to retrieve the optimal number of features from the high dimensional features generated by fusing the texture features of all the three considered biometric traits along with the fingerprint minutiae features. Furthermore, the decision tree classifier is used to classify the gender of an individual. Results: The feasibility of the proposed approach is measured with different qualitative performance parameters. In light of achieving the accuracy rate of 99.2%, it shows that its performance is comparatively better against other techniques reported in the literature with the different sets of the classifier. Conclusion: The hybridization technique that effectively integrates meta-heuristic approaches, GSA and firefly, outperforms other similar approaches with respect to obtaining the optimal features of multimodal biometric for the gender based identification system. Furthermore, the novel technique enhances the overall performance of the system by reducing the search space over time and space.

Background: Hub Location Problem (HLP) deals with long-term strategic decision planning in various application domains with the aim of reducing overall transportation cost. It deals with identifying hubs and allocating spokes to hubs in order to route the flow of goods between origin-destination locations. Due to the complex nature of the problem, meta-heuristic algorithms are best suited to solve HLPs. The existing algorithms face the accuracy and consistency related issues for solving the HLPs. Objective: This paper attempts to solve a variant of HLP, which is known as Uncapacitated Single Allocation p-Hub Location Problem with Fixed Cost (USApHLP-FC), using Anti-Predatory Nature- Inspired Algorithm (APNIA) to improve accuracy and consistency in results. Methods: APNIA is a recently proposed meta-heuristic nature-inspired algorithm, which is based on the anti-predatory behavior of frogs. For solving the HLP, APNIA is used for both identifying the hubs and allocating the spokes to hubs in order to reduce the total cost of goods transportation. Results: A numerical problem with 10 locations is used for empirical study. The experimental result shows that APNIA outperforms other leading proposals in terms of total cost and gap value. The obtained results of APNIA are compared with the genetic algorithm, particle swarm optimization, artificial bee colony, firefly algorithm, teacher learning based optimization and Jaya algorithm. The comparative study indicates at least 0.86% improvement in accuracy and at least a 10% gain in consistency by APNIA for the different number of generations. Conclusion: The experimental evaluation and performance comparison signify that APNIA based approach has improved accuracy and consistency in solutions than other compared algorithms. It establishes the robustness of anti-predatory NIA for solving the hub location problems.