Search

The concepts of service-oriented computing (SOC) have previously been used in the embedded systems domain, mostly at the device level in ad hoc manners to achieve advantages of device integration. However, SOC has not been used for the development of embedded software systems (ESS), i.e., software controlling the embedded devices. To fill this gap, a process model is proposed in this article that allows the systematic development of ESS based on SOC concepts. The proposed process consists of analysis and design phases of embedded software development. The analysis phase is concerned with the collection of system information and preparation for system design. Based on this, the service-based software architecture is developed in the design phase. The effectiveness of the proposed process model is demonstrated through its application in the Smart Home case study.

Purpose The purpose of this paper is to design an innovative autonomous carrier landing system (ACLS) using novel robust adaptive preview control (RAPC) method, which can assure safe and successful autonomous carrier landing under the influence of airwake disturbance and irregular deck motion. To design a deck motion predictor based on an unscented Kalman filter (UKF), which predicts the touchdown point, very precisely. Design/methodology/approach An ACLS is comprising a UKF based deck motion predictor, a previewable glide path module and a control system. The previewable information is augmented with the system and then latitude and longitudinal controllers are designed based on the preview control scheme, in which the robust adaptive feedback and feedforward gain’s laws are obtained through Lyapunov stability theorem and linear matrix inequality approach, guarantying the closed-loop system’s asymptotic stability. Findings The autonomous carrier landing problem is solved by proposing robust ACLS, which is validated through numerical simulation in presence of sea disturbance and time-varying external disturbances. Practical implications The ACLS is designed considering the practical aspects of the application, presenting superior performance with extended robustness. Originality/value The novel RAPC, relative motion-based guidance system and deck motion compensation mechanism are developed and presented, never been implemented for autonomous carrier landing operations.

In the recent years, cloud computing has become a widely utilized revolution in the field of data modernization due to its favorable circumstances like high processing power, less expense of administrations, elite adaptability, unwavering quality and accessibility. It is an integral tool that improves the cost of equipment, controllability and utility to share the information and so forth numerous organizations are turning their applications and administrations on the cloud. It offers secure and versatile administrations but in every case there exists some cloud security and protection issues when information has sent from a focal stockpiling worker to an alternate cloud, individual and private information augment the danger of information secrecy, respectability, accessibility, and verification before one pick a merchant in the cloud or pick the cloud and move services in the cloud. In this research, paper several articles are reviewed that deals with the security issues and the remedial actions and responses that have been taken by researchers and organizations in the field of cloud computing. This analysis provides insight to future research opportunities to students, researchers, publishers and experts and help them to study current research trend and security issues related to cloud computing.

Asynchronous systems are native to a full custom domain. Their implementation using auto place-and-route tools requires dynamic calibration of interconnects delays in addition to the placement of predefined static delay elements. This paper presents a completion detector for a single-rail bit encoded datapath that, as an adaptive-delay element, eliminates the need to insert any predefined delay element and caters to routing delays dynamically. A programmable pulse-generator is also proposed that empowers the designers to generate clock signals based on the timing report obtained from the CAD tool to drive various synchronous subsystems and embedded resources like BRAMs in FPGAs. Employing these components, we present an asynchronous pipeline model with implicit control to expedite migration from the traditional synchronous pipelines to their asynchronous counterparts. A single-rail bit encoded datapath has been used to utilize chip area effectively instead of a delay-insensitive dual-rail datapath, and a two-phase handshake protocol has been adopted as opposed to a four-phase handshake protocol to lower handshaking overhead. A RISC processor validates the proposed asynchronous pipeline model, exhibiting a smooth functionality and power-delay parameter comparable to that of a synchronous pipeline, in addition to ease of routing and avoiding clock skews in a complex system-on-chip.

Automatic defect classification in photovoltaic (PV) modules is gaining significant attention due to the limited application of manual/visual inspection. However, the automatic classification of defects in crystalline silicon solar cells is a challenging task due to the inhomogeneous intensity of cell cracks and complex background. The present study is carried out for automatic defects classification of PV cells in electroluminescence images. Two machine learning approaches, features extraction-based support vector machine (SVM) and convolutional neural network (CNN) are used for the solar cell defect classifications. Suitable hyperparameters, algorithm optimisers, and loss functions are used to achieve the best performance. Solar cell defects are divided into seven classes such as one non-defective and six defective classes. Feature extraction algorithms such as histograms of oriented gradients (HOG), KAZE, Scale-Invariant Feature Transform (SIFT) and speeded-up-robust features (SURF) are used to train the SVM classifier. Finally, the performance results are compared. It is concluded that CNN's accuracy for solar cell defect classification is 91.58% which outperforms the state-of-the-art methods. With features extraction-based SVM, accuracies of 69.95, 71.04, 68.90, and 72.74% are obtained for HOG, KAZE, SIFT, and SURF, respectively. The present study may contribute to making a PV system more efficient for classifying defects to improve the power system efficiency.

Reduction in power loss while maintaining the acceptable voltage profile has become a challenge for distribution system operators due to expanded living standards. Properly sized shunt capacitors (SCs) allocated at suitable locations of the distribution system can enhance its performance by tackling the power quality issues and foster multiple technical and economic benefits. Most of the existing research work in this domain is accomplished at fixed loading conditions without incorporating purchasing, installation, operation and degradation costs of the SCs. In this work, an intelligent metaheuristic polar bear optimization algorithm (PBOA) is applied to solve the optimal capacitor placement and sizing problem in the radial distribution system (RDS) at various loading conditions. By formulating multiple objective functions for the annual operating cost (AOC), this work incorporates the cost of real power loss ( $$ P_{\text{loss}} $$ ) and various costs associated with SCs. The proposed technique is tested on various IEEE standard bus systems under different loading conditions. The proposed PBOA reduces AOC and $$ P_{\text{loss}} $$ of RDS while maintaining tolerable voltages at systems’ buses. The reductions of 51%, 35%, 26% and 53% in $$ P_{\text{loss}} $$ are observed for IEEE standard 15-, 33-, 34- and 85-bus systems, respectively, at 100% loading from their uncompensated cases. Similarly, reductions in AOCs for the same systems at 100% loading are 32%, 25%, 16% and 45%, respectively. These results prove superiority of proposed method over recent state-of-the-art algorithmic approaches. The results of this work can be useful for distribution system operators in achieving reliable and efficient operation of the power grid.

Many transient-based defect detection methods are based on matching the transient model to the measured data to localize the defects. Despite the high degree of success in laboratory system...

Fault diagnosis in rolling bearings is an indispensable part of maintaining the normal operation of modern machinery, especially under the varying operating conditions. In this paper, an end-to-end adaptive anti-noise neural network framework (AAnNet) is proposed to solve the bearing fault diagnosis problem under heavy noise and varying load conditions, which takes the raw signal as input without requiring manual feature selection or denoising procedures. The proposed AAnNet employs the random sampling strategy and enhanced convolutional neural networks with the exponential linear unit as the activation function to increase the adaptability of the neural network. Moreover, the gated recurrent neural networks with attention mechanism improvement are further adopted to learn and classify the features processed by the convolutional neural networks part. Besides, we try to explain how the network works by visualizing the intrinsic features of the proposed framework. And we explore the effect of the attention mechanism in the proposed framework. Experiments show that the proposed framework achieves state-of-the-art results on two datasets under varying operating conditions.

Pakistan is one of the growing nations, specifically in the field of Information and Communication Technology (ICT). During the last decade, an intense rise in the adaptation of ICT has been observed in all the major cities of Pakistan. This includes, but not limited to, e-commerce, mobile technology, computer communication networks, embedded systems, software engineering, etc. Due to the resource constraints, Pakistan is not the producer of any technology; however, it is a potential consumer of numerous technologies and their products. It therefore, attracts most of the producers around the globe to invest in the technology business in Pakistan. According to the Board of Investment (BOI) Pakistan, the country has received more than US$5.7 billion during the last decade as the foreign investment in IT and Telecommunication sectors only. Moreover, it has more than 140 million cellular subscribers, around 45 million 3G/4G subscribers, more than 3 million fixed local line subscribers and approximately 48 million broadband subscribers [1]. Likewise, Pakistan is also one of the biggest buyers of Consumer Electronics (CE). Very few of the local companies are producing CE products, however, a major share of the CE market has been captured by the international brands of China, Japan, Korea, USA, Germany, etc. In the light of the facts, it can be inferred that the application of ICT such as the Internet of Things (IoT) and Internet of Underwater Things (IoUT) in consumer electronics has the strong potential in shaping a new dimension of CE business in Pakistan. Moreover, the recent literature has strongly advocated for the scope of 5G IoT/IoUT. This is due to the fact that existing communication infrastructure will not be sufficient to handle modern day IoT/IoUT need. In this article, a comprehensive study on the scope of IoT/IoUT enabled consumer electronics business is presented. In addition, the rationale of 5G IoT/IoUT integration in the developing countries like Pakistan is discussed. Moreover, the threats and opportunities in the business of IoT/IoUT enabled CE devices are also been presented. Finally, this study submits the recommendations to establish IoT/IoUT enabled CE business in Pakistan.

Recommender systems use machine-learning techniques to make predictions about resources. The medical field is one where much research is currently being conducted on recommender system utility. In ...

Recently, research on vehicular ad hoc networks (VANETs) has gained momentum all over the world. These emerging networks promise to make our driving experience more efficient, safer, comfortable, and enjoyable. VANETs have the potential to support a wide range of interesting applications. One such promising application area is the discovery of roadside services on the highways. Drivers need an efficient way to find these services during their journeys. However, due to the unique features of VANETs, the design and implementation of such applications is a challenging task. In this paper, we propose an application layer beaconing-based roadside services discovery protocol (RSDP). The RSDP is a lightweight, beacon-based protocol, which uses store-carry-and-response technique and opportunistic vehicle-to-vehicle communication. Our solution is efficient for business owners, as the vehicles move from one place to another to carry service advertisements and opportunistically forward them to other vehicles upon request. Our system architecture is fully based on the VANET standard protocols stack. We performed extensive simulations to evaluate the performance of RSDP in a multilane highway scenario. The results demonstrate the effectiveness of our solution in terms of services discovery.

In this paper, we present a multi-region ensemble classifier approach (MRECA) using a cognitive ensemble of classifiers for accurate identification of attention-deficit/hyperactivity disorder (ADHD) subjects. This approach is developed using the features extracted from the structural MRIs of three different developing brain regions, viz., the amygdala, caudate, and hippocampus. For this study, the structural magnetic resonance imaging (sMRI) data provided by the ADHD-200 consortium has been used to identify the following three classes of ADHD, viz., ADHD-combined, ADHD-inattentive, and the TDC (typically developing control). From the sMRIs of the amygdala, caudate, and hippocampus regions of the brain from the ADHD-200 data, multiple feature sets were obtained using a feature-selecting genetic algorithm (FSGA), in a wraparound approach using an extreme learning machine (ELM) basic classifier. An improved crossover operator for the FSGA has been developed for obtaining higher accuracies compared with other existing crossover operators. From the multiple feature sets and the corresponding ELM classifiers, a classifier-selecting genetic algorithm (CSGA) has been developed to identify the top performing feature sets and their ELM classifiers. These classifiers are then combined using a risk-sensitive hinge loss function to form a risk-sensitive cognitive ensemble classifier resulting in a simultaneous multiclass classification of ADHD with higher accuracies. Performance evaluation of the multi-region ensemble classifier is presented under the following three scenarios, viz., region-based individual (best) classifier, region-based ensemble classifier, and finally a multiple-region-based ensemble classifier. The study results clearly indicate that the proposed “multi-region ensemble classification approach” (MRECA) achieves a much higher classification accuracy of ADHD data (normally a difficult problem because of the variations in the data) compared with other existing methods.

A novel unsupervised image classification algorithm which based on the sparse representation theory for polarimetric synthetic aperture radar (PolSAR) image is introduced in this paper. The algorit...

This article presents a brief review of machine learning/classification strategies for the classification of EMG signals in the context of Myoelectric controlled prosthesis. It focuses on certain parameters adopted for machine learning such as selecting the size of windows and frequency range adopted for different filters, the filters of three domains including time domain, frequency domain and time-frequency domain, and the classifiers commonly used and that of different statistical tests performed for evaluating the significant difference between the EMG and performance of features and classifiers. Also, the comparative analysis of different EMG related studies has been done in this article. The paper would contribute to selecting the parameters before evaluating the results using machine learning. The criteria for selection of the papers to present the review is set by looking at the frequently used features and classifiers that have been used by the researchers for EMG signals analysis in the past 2 decades.

In this chapter, we review methods for video-based heart monitoring, from classical signal processing approaches to modern deep learning methods. In addition, we propose a new method for learning an optimal filter that can overcome many of the problems that can affect classical approaches, such as light reflection and subject's movements, at a fraction of the training cost of deep learning approaches. Following the usual procedures for region of interest extraction and tracking, robust skin color estimation and signal pre-processing, we introduce a least-squares error optimal filter, learnt using an established training dataset to estimate the photoplethysmographic (PPG) signal more accurately from the measured color changes over time. This method not only improves the accuracy of heart rate measurement but also resulted in the extraction of a cleaner pulse signal, which could be integrated into many other useful applications such as human biometric recognition or recognition of emotional state. The method was tested on the DEAP dataset and showed improved performance over the best previous classical method on that dataset. The results obtained show that our proposed contact-free heart rate measurement method has significantly improved on existing methods.

Information and Communication Technology (ICT) has a crucial role in creating and implementing support applications for visual impaired users. For instance, most of them face a lot of challenges in carrying out educational activities and collaborating with another sighted individual. Visual impairment entails a lack of confidence and acceptance to be integrated in a collaborative group. The proposed research provides an innovative solution, based on Artificial Intelligence techniques, like a rule-based framework to perform efficient collaborative activities, along with awareness features to notify each other. Furthermore, our application enables speech communication. The developed system is evaluated with experiments through collaborative writing activities performed by blind users. The obtained results are promising because users showed curiosity, being concentrated on constructive tasks, and to have great confidence in them.

Cardiac disease treatments are often being subjected to the acquisition and analysis of vast quantity of digital cardiac data. These data can be utilized for various beneficial purposes. These data’s utilization becomes more important when we are dealing with critical diseases like a heart attack where patient life is often at stake. Machine learning and deep learning are two famous techniques that are helping in making the raw data useful. Some of the biggest problems that arise from the usage of the aforementioned techniques are massive resource utilization, extensive data preprocessing, need for features engineering, and ensuring reliability in classification results. The proposed research work presents a cost-effective solution to predict heart attack with high accuracy and reliability. It uses a UCI dataset to predict the heart attack via various machine learning algorithms without the involvement of any feature engineering. Moreover, the given dataset has an unequal distribution of positive and negative classes which can reduce performance. The proposed work uses a synthetic minority oversampling technique (SMOTE) to handle given imbalance data. The proposed system discarded the need of feature engineering for the classification of the given dataset. This led to an efficient solution as feature engineering often proves to be a costly process. The results show that among all machine learning algorithms, SMOTE-based artificial neural network when tuned properly outperformed all other models and many existing systems. The high reliability of the proposed system ensures that it can be effectively used in the prediction of the heart attack.

Due to the lack of confidence and vision capability, it becomes very difficult for blind individuals to perform group activities with sighted persons. By use of modern technology, we can easily overcome this issue. Google Docs, Microsoft word add-in, and other available tools do not provide voice-based notifications about dynamic actions for the visually impaired in a shared environment. Communication is done through comments which are not helpful for blinds. Our cloud-based collaborative writing platform is designed especially for the visually impaired where they write, manage and share documents. Co-authors communicate and receive voice notifications about the activities along with popups. The basic objective of this research is to encourage blind people to participate in group-based authoring activities with each other and sighted people. For this purpose, a questionnaire was distributed among people of blind institutes. The results of the survey show that blind people highly need a collaborative platform.

Synthetic Aperture Radar (SAR) has the advantage of operating regardless of the cloud cover or a lack of light. This makes SAR a potential substitution for optical sensors in various ways. SAR images have been effectively used for detecting the various terrain changes, particularly in comparing the terrain before and after natural disasters. In this paper, we compare SAR images to measure the forest loss rate before and after the fire. we analyze the Gangwon-do forest fire which occurred in 2019. SNAP (Sentinels Application Platform) is used in this paper to process Sentinel-1. Pre-processing, post-processing, color manipulation, cropping image was used in the program. Based on the calculated loss rate, we expect that it can be used for other researches such as flood or debris flow. It would be more accurate by using SAR images.

In this paper, matrix converter is used as a phase conversion device. It is employed as bidirectional converter, where three-phase to five-phase and five-phase to three-phase conversion is studied. It can be used for connecting 5-phase AC machines to a 3-phase AC supply and connecting 5-phase generation to 3-phase load respectively. Then switching optimization is performed to control matrix converter switching frequency and reduce switching losses and decrease total harmonic distortion. Simulations are performed in MATLAB/ Simulink and results are presented.

With the recent development and application of human–computer interaction systems, facial expression recognition (FER) has become a popular research area. The recognition of facial expression is a difficult problem for existing machine learning and deep learning models because that the images can vary in brightness, background, pose, etc. Deep learning methods also require the support of big data. It does not perform well when the database is small. Feature extraction is very important for FER, even a simple algorithm can be very effective if the extracted features are sufficient to be separable. However, deep learning methods automatically extract features so that some useless features can interfere with useful features. For these reasons, FER is still a challenging problem in computer vision. In this paper, with the aim of coping with few data and extracting only useful features from image, we propose new face cropping and rotation strategies and simplification of the convolutional neural network (CNN) to make data more abundant and only useful facial features can be extracted. Experiments to evaluate the proposed method were performed on the CK+ and JAFFE databases. High average recognition accuracies of 97.38% and 97.18% were obtained for 7-class experiments on the CK+ and JAFFE databases, respectively. A study of the impact of each proposed data processing method and CNN simplification is also presented. The proposed method is competitive with existing methods in terms of training time, testing time, and recognition accuracy.

This research paper aims to investigate Matrix Converter's use for Power Factor Improvement, Reactive Power Compensation, and novel switching optimization. Initially, the introduction of the matrix converter and its different topologies is presented and its various control techniques are analyzed. The Model Predictive Control of current in the direct matrix converter is investigated in three distinct parts. The first part deals with the control of output current through which distortion-free output current is obtained at the load side. The second part deals with the control of reactive power at the input side of the load so that reactive power at the input is minimized for achieving near unity power factor. The third part is related to switching optimization. In this part, Matrix converter’ switching is optimized to a level that unnecessary switching states are eliminated and only the essential switching is allowed. This optimization significantly reduced Total Harmonic Distortion in the waveforms. Finally, in the end, all three parts are combined into one cost function. Each part has its own customizable weighting factor. Filter at the input side of the matrix converter is added to reduce input current distortion. Simulations for this control technique are done in MATLAB/Simulink and its analysis and results are presented in the paper.

The smile is one of the most common human facial expressions encountered in our daily lives. Smile recognition can be used in many scenarios, such as emotion monitoring, human-to-robot games, and camera shutter control, which is why smile recognition has received significant attention of researchers. This topic is a significant but challenging problem, particularly in unconstrained scenarios. The variety of facial sizes, illumination conditions, head poses, occlusions, and other factors increases the difficulty of this problem. To address this problem, we propose a novel multiple convolutional neural network (CNN) fusion approach in which a face-based CNN and a mouth-based CNN are used to perform smile recognition. According to the results obtained using the two CNNs, we fuse the two networks using a specified weight and choose the higher-probability result as the final result. Experimental results indicate that the method is effective on a real-world smile dataset (GENKI-4 K). The smile recognition rate of the proposed method is improved by 1.6% and 3.3% relative to the face-based CNN and mouth-based CNN, respectively, and the proposed method outperforms the most of previous methods.

The visual exploration of retinal blood vessels assists ophthalmologists in the diagnoses of different abnormalities of the eyes such as diabetic retinopathy, glaucoma, cardiovascular ailment, high blood pressure, arteriosclerosis, and age-related macular degeneration. The manual inspection of retinal vasculature is an extremely challenging and tedious task for medical experts due to the complex structure of an eye, tiny blood vessels, and variation in vessels width. Several automatic retinal vessels extraction techniques have been proposed in contemporary literature, which assist ophthalmologists in the timely identification of an eye disorders. However, due to the fast evolution of such techniques, a comprehensive survey is needed. This survey presents a comprehensive review of such techniques, strategies, and algorithms presented to date. The techniques are classified into logical groups based on the underlying methodology employed for retinal vessel extraction. The performance of existing techniques is reported on the publicly accessible datasets in term of various performance measures, providing a valuable comparison among the techniques. Thus, this survey presents a valuable resource for researchers working toward automatic extraction of retinal vessels.

The increasing trend in building sector's energy demand calls for reliable and robust energy consumption forecasting models. This study aims to compare prediction capabilities of five different intelligent system techniques by forecasting electricity consumption of an administration building located in London, United Kingdom. These five techniques are; Multiple Regression (MR), Genetic Programming (GP), Artificial Neural Network (ANN), Deep Neural Network (DNN) and Support Vector Machine (SVM). The prediction models are developed based on five years of observed data of five different parameters such as solar radiation, temperature, wind speed, humidity and weekday index. Weekday index is an important parameter introduced to differentiate between working and non-working days. First four years data is used for training the models and to obtain prediction data for fifth year. Finally, the predicted electricity consumption of all models is compared with actual consumption of fifth year. Results demonstrate that ANN performs better than all other four techniques with a Mean Absolute Percentage Error (MAPE) of 6% whereas MR, GP, SVM and DNN have MAPE of 8.5%, 8.7%, 9% and 11%, respectively. The applicability of this study could span to other building categories and will help energy management teams to forecast energy consumption of various buildings.

Polarimetric synthetic aperture radar (PolSAR) data show good performance in near-real-time earthquake/tsunami damage assessment. In this paper, an improved damage level index for earthquake/tsunami damage level mapping of urban areas based on distance metric learning using full PolSAR data has been proposed. First, urban areas are extracted by our proposed classification method, which conjunctively uses multiresolution segmentation and support vector machine. Then, a double-bounce scattering power-based damage level index is adopted for damage level mapping. To solve the problem that the primary result does not match with the truth damage level in heavily damaged areas, distance metric learning method is introduced to calculate the Mahalanobis metric to compose an improved index. Extensive experimental comparison and analysis on L -band ALOS PALSAR data of Tohoku earthquake demonstrate the effectiveness of the proposed index. Both the analysis about damage level assessment map and sample areas’ linear fitting with truth damage level indicate the improved damage level index achieves high accuracy. The same analysis was applied to evaluate the damage induced in Kumamoto earthquake event. The analysis result verified the robustness of the proposed damage level index.

The ultimate goal of learning algorithms is to find the best solution from a search space without testing each and every solution available in the search space. During the evolution process new solutions (children) are produced from existing solutions (parents), where new solutions are expected to be better than existing solutions. This paper presents a new parent selection method for the crossover operation in genetic programming. The idea is to promote crossover between two behaviourally (phenotype) diverse parents such that the probability of children being better than their parents increases. The relative phenotype strengths and weaknesses of pairs of parents are exploited to find out if their crossover is beneficial or not (diverse partner selection (DPS)). Based on the probable improvement in children compared to their parents, crossover is either allowed or disallowed. The parents qualifying for crossover through this process are expected to produce much better children and are allowed to produce more children than normal parents through brood recombination (BR). BR helps to explore the search space around diverse parents much more efficiently. Experimental results from different benchmarking problems demonstrate that the proposed method (DPS with BR) improves the performance of genetic programming significantly.

Fronthaul networks are leveraging communication links between the remote radio heads and baseband units in cloud radio access networks, and common public radio interface (CPRI) is an interface to carry time-sensitive traffic over the fronthaul. For the fronthaul networks which impose stringent bandwidth, latency, and jitter requirements, Ethernet can be a cost-effective solution to carry the CPRI traffic. However, Ethernet networks have limitations to transport the multiple CPRI streams simultaneously and satisfy the strict service requirements due to the accumulation of unavoidable intrinsic delays at switches. To address these issues, this paper evaluates the impact of intrinsic delay on the performance of CPRI over Ethernet (CoE) networks with experimental results and proposes a virtual local area network-based CoE network architecture along with two transport algorithms to carry the multiple CPRI streams over Ethernet despite the intrinsic delays. We confirmed with computer simulations that with the proposed techniques, the end-to-end delays and jitter for a number of CPRI streams within the acceptable range of fronthaul requirements can be achieved.

The crowd phenomenon frequently occurs in dense urban living environments. Crowd counting or estimation helps to develop management strategies such as designing safe public places and evacuation plan for emergencies. These strategies are different depending upon the type of event such as political and public demonstrations, sports, and religious events. However, estimating the number of people in crowds at closed or open environments is quite challenging because of the dynamics involved in the process. In addition, crowd estimation itself poses challenges due to randomness in crowd behavior, motion, and an area’s geometric specifications. Crowd behavior as well as the area parameters is studied before suggesting any possible technological solution for managing a crowd. This article presents a theoretical understanding of the major crowd size estimation approaches that cannot be achieved through the study of existing survey papers in this area, because the existing survey papers focus on particular technologies/specific areas with no or brief description of the involved steps. Besides, this article also highlights the strength and weakness of crowd size estimation solutions and their possible applications. It is, therefore, believed that the provided information would assist in developing an intelligent system for crowd management.

To date, the use of matched-field processing (MFP) for leak detection in pipes has been limited to cases where the mismatch between data and model is assumed to be random and Gaussian distributed. This paper extends the MFP to the more realistic case where the mismatch involves both random and modeling errors. Experimental results show that the modeling error for cases with and without a leak remains similar in shape and magnitude. As a result, modeling errors can potentially be estimated from a baseline signal which ideally can be obtained before major defects emerge. This attribute is exploited to formulate a novel MFP technique that uses both past baseline and current signals to detect leaks. The novel MFP remains optimal in the sense of achieving maximum signal-to-noise ratio. The gain of the proposed leak detection method is assessed via three experimental scenarios in which the modeling errors range from simple to complex.

This work was supported by the Deanship of Scientific Research at Majmaah University, Saudi Arabia. Energy-efficient and reliable data gathering using highly stable links in underwater wireless sensor networks (UWSNs) is challenging because of time and location-dependent communication characteristics of the acoustic channel. In this paper, we propose a novel dynamic firefly mating optimization inspired routing scheme called FFRP for the internet of UWSNs-based events monitoring applications. The proposed FFRP scheme during the events data gathering employs a self-learning based dynamic firefly mating optimization intelligence to find the highly stable and reliable routing paths to route packets around connectivity voids and shadow zones in UWSNs. The proposed scheme during conveying information minimizes the high energy consumption and latency issues by balancing the data traffic load evenly in a large-scale network. In additions, the data transmission over highly stable links between acoustic nodes increases the overall packets delivery ratio and network throughput in UWSNs. Several simulation experiments are carried out to verify the effectiveness of the proposed scheme against the existing schemes through NS2 and AquaSim 2.0 in UWSNs. The experimental outcomes show the better performance of the developed protocol in terms of high packets delivery ratio (PDR) and network throughput (NT) with low latency and energy consumption (EC) compared to existing routing protocols in UWSNs. Deanship of Scientific Research at Majmaah University, Saudi Arabia

The current method of meter reading is manual and error-prone in developing countries. A meter reader logs the reading to calculate the cost of electricity. In recent years, there have been multiple efforts to provide automated solutions to read the meter digits. However, the existing systems extract reading based on a specific meter topology. In this paper, we propose an approach based on Faster R-CNN to extract and recognize digits in an electric meter. We compared our method against several state-of-the-art object detection methods. The proposed approach is robust against different lightening conditions, severe perspective distortions and blurred images. In addition, it is scaleinvariant. Furthermore, we created a new dataset consisting of 10310 images taken from electricity companies in Pakistan to benchmark meter digit recognition task. Experimental results shows the high accuracy of the proposed approach on the created electricity meter dataset.

Cloud radio access networks (C-RANs) are emerging architectural solutions to anticipate the increased capacity and quality demands of future 5G cellular networks at a reduced cost. In C-RANs, a transport segment referred to as fronthaul has been defined, which become a major constraint in practical implementations due to its high cost. A transport protocol referred to as eCPRI (enhanced common public radio interface), which was specifically designed for the fronthaul networks, imposes stringent end-to-end (E2E) latency and capacity requirements, which can be satisfied through the extortionate optical links. The high implementation cost of optical fronthaul networks significantly increased the system cost and made the fronthaul a hurdle to accomplish the cost&ndash, benefits of the C-RANs&rsquo, architecture. The globally deployed Ethernet networks could be leveraging solutions, but are inadequate to comply with the eCPRI requirements in fronthaul bridged networks and result in intolerable latencies due to ineffectual traditional quality of service aware forwarding schemes. Therefore, to realize the cost&ndash, benefits of ubiquitously deployed Ethernet infrastructure, this paper proposes the E2E latency aware path computation and packet forwarding schemes, which ameliorate the performance of Ethernet-based fronthaul bridged networks to transport the eCPRI traffic at tolerable latencies. The simulation results verify the feasibility of low-cost Ethernet to carry the eCPRI traffic streams up to 100 Gbps with the proposed schemes in fronthaul bridged networks.

This article presents four stage interleaved boost converter using self-lift technique. The proposed converter uses self-lift cells in four stages for high output voltage gain, low input ripples current, high efficiency. The input inductor is connected in series with battery to reduce ripples in the input current and one input parallel capacitor was used to reduce the stress and maintain constant current on battery. Initially the converter work on four PWM signals after that proposed converter work on two PWM signals with 50% duty cycle and 100 kHz frequency. The voltage is boosted in every stage of the interleaved topology to produce high output voltage gain up to 230V from 15V battery. The efficiency of the proposed converter is 96.7 % with 2.3A outputs current.

Cloud-radio access networks (C-RANs) are the evolving mobile communication architectures to support high data rates and low latencies in 5G networks. Fronthaul link is an obstacle in C-RANs implementation, due to its high cost and stringent requirements. The optical links are the most appropriate option to realize the fronthaul networks, but it increases the cost, and stringent performance requirements limit the link length to a few kilometers. To tackle these issues, extensive efforts have been devoted to designing the proficient fronthaul networks by applying the compression algorithms, software-defined techniques, and CPRI over Ethernet based solutions. In this paper, we evaluated the performance of passive optical networks (PON) based links for long-distance communications in fronthaul systems. We also determine the optimized location for adding the amplifiers in long-distance fronthaul links to connect the source and destination nodes without violating the performance requirements which results in the cost reduction. The simulation results showed the improvement in the long-distance PON-based fronthaul networks with the placement of the amplifier at an optimized location.

The increasing usage of smart devices and the penetration of mobile phones in the low-end markets have outpaced the average growth of this wireless mobile communications industry due to which the world is witnessing the demands of burgeoning data traffic, proliferating bandwidth and energy efficient wireless communication technologies. Realizing these increased demands, the research on the Fifth Generation (5G) mobile communication technology has already been initiated by research institutes and industries worldwide. This paper gives a brief overview of some 5G technologies along with their possible challenges and the applications.

A novel electrical model of neuron is proposed in this presentation. The suggested neural network model has linear/nonlinear input-output characteristics. This new deterministic model has joint biological properties in excellent agreement with the earlier deterministic neuron model of Hopfield and Tank and to the stochastic neuron model of McCulloch and Pitts. It is an accurate portrayal of differential equation presented by Hopfield and Tank to mimic neurons. Operational amplifiers, resistances, capacitor, and diodes are used to design this system. The presented biological model of neurons remains to be advantageous for simulations. Impulse response is studied and conferred to certify the stability and strength of this innovative model. A simple illustration is mapped to demonstrate the exactness of the intended system. Precisely mapped illustration exhibits 100 % accurate results.

The newly proposed fronthaul and backhaul (FB) segments in the cloud-radio access networks (C-RANs) could be leveraging solutions to satisfy the 5G demands, but the rigorous one-way delay and packet delay variations (PDVs) requirements of fronthaul networks are the bottleneck. Time division multiplexing (TDM)-based passive optical networks (PONs) can be a promising candidate to carry the fronthaul traffic, but the TDM-PON systems have limitations to meet the fronthaul QoS requirements due to unavoidable delays at the switching nodes. Moreover, the unification of FB traffics over the same segment is vital to fully exploit the cost benefits, but due to the poor performance of the PON systems for the fronthaul traffic, the backhaul traffic could not be forwarded through the same fronthaul segments. Therefore, in this paper, we propose and implemented the strict priority and frame pre-emption-based buffering schemes to transport the FB packet flows simultaneously at tolerable delays and PDVs.

In this piece of research, we have presented an approach to populate Failure Mode and Effect Analysis (FMEA) ontology from existing worksheets prepared by experts. FMEA is a commonly used method for risk assessment in any organization. This method is initiated by domain experts who analyze all the associated risks to a product or process, their causes, severity, effects and mitigation actions. Besides domain experts, time and cost are the other two factors involved in successful completion of FMEA. Reusability of the knowledge produced at the end of this method can bring numerous benefits to an organization. Some ontologies are available for semantic content management of FMEA knowledge but in order to avail their full benefits, it is must that they can acquire the existing knowledge automatically. Major objective of this article is to develop an algorithm, which can populate FMEA ontology from existing worksheets. Major contribution of this work is to identify an existing FMEA ontology and its evaluation for schema and relationship richness, then its automatic population using proposed algorithm without human intervention, and finally making it a part of complete knowledge management system. Our proposed algorithm correctly mapped 1357 instances to FMEA ontology from manually prepared FMEA spreadsheets. This FMEA ontology has been queried by domain experts and it was proved to be very helpful in experts like decision-making.

Software engineering has been an active working area for many decades. It evolved in a bi-folded manner. First research and subsequently development. Since the day of its inception, the massive number of variants and methods of software engineering were proposed. Primarily, these methods are designed to cater the time-varying need of modern approach. In this connection, the Global Software Engineering (GSE) is one of the growing trends in the modern software industry. At the same time, the employment of Agile development methodologies has also gained the significant attention in the literature. This has created a rationale to explore and adopt agile development methodology in GSE. It gained rigorous attention as an alternative to traditional software development methodologies. This paper has presented a comprehensive review on the adaptation of modern agile practices in GSE. In addition, the strength and limitation of each approach have been highlighted. Finally, the open area in the said domain is submitted as one of the deliverables of this work.

Over the last few decades, software security has become significant in parallel to general software testing. Previously, the scope of software security was relatively limited as compared to the software functionality. But now, in global software engineering, the scope and budget of software security are far more than its basic functionality. This has created a pressing need to devise the separate set of working boundaries between software quality testing, and software security testing in global software engineering. In the past literature, a massive number of software security testing methods has been devised. In this paper, a comprehensive literature review is presented on the recent global software security testing methods. In addition, the strength and limitation of each framework are discussed and analyzed. Finally, this work submits the open areas in the domain of global software security testing methods as one of the deliverables of this research work.

An unsupervised earthquake/tsunami damage information extraction method using single post-event polarimetric SAR data is proposed in this paper. All urban areas are extracted by an improved classification method which can effectively discriminate urban and foreshortening mountain areas, they are grouped into four kinds of buildings to detect damaged buildings. The proposed unsupervised method can explicitly detect all the damaged buildings, including those with large orientation angle which are easily recognized as undamaged buildings. The technique is validated based on the study about Tohoku earthquake/tsunami event, and is implemented on the L-band ALOS/PALSAR data set. The analysis in this paper verifies that the proposed method can achieve accurate damage information.

The categorization of high dimensional data present a fascinating challenge to machine learning models as frequent number of highly correlated dimensions or attributes can affect the accuracy of classification model. In this paper, the problem of high dimensionality of stock exchange is investigated to predict the market trends by applying the principal component analysis (PCA) with linear regression. PCA can help to improve the predictive performance of machine learning methods while reducing the redundancy among the data. Experiments are carried out on a high dimensional spectral of 3 stock exchanges such as: New York Stock Exchange, London Stock Exchange and Karachi Stock Exchange. The accuracy of linear regression classification model is compared before and after applying PCA. The experiments show that PCA can improve the performance of machine learning in general if and only if relative correlation among input features is investigated and careful selection is done while choosing principal components. Root mean square error (RMSE) is used as an evaluation metric to evaluate the classification model.

The increasing use of software in Embedded Real-Time Systems (ERTS) has allowed the application of software engineering methods and techniques in their development. In this regard, Service-Oriented Computing (SOC) has previously been used to reduce the development complexity of ERTS. However, the concepts of SOC are mostly used at the implementation level without any focus on system design. To fill this gap, the author has previously developed a meta-model for service-oriented development of ERTS. Although the proposed meta-model allows the high-level modeling of ERTS in terms of service-oriented concepts, it covers only the structural requirements. Therefore, the meta-model is further extended in this paper to include the behavior modeling of the system. The effectiveness of the proposed mechanism is demonstrated with the help of Traffic Light Controller and Arbiter case studies. Following the model-based system engineering process, the high-level models can be transformed into the low-level models.

This paper presents an application of a novel approach for detecting and tracking an object with a 2 DOF robotic manipulator which can be equipped with an array of electrically controlled actuators. The said approach utilizes the Image Based Visual Servoing (IBVS) technique. The developed system is able to determine the object pose in real time from features in the image. Object is detected using shaped based approach algorithms of image processing. The position and orientation of the world coordinates of the object being tracked are calculated from the coordinates of the object in image plane using camera's intrinsic and extrinsic parameters. Experimental results demonstrate the effectiveness of this proposed approach.

Cluster analysis of textual documents is a common technique for better ltering, navigation, under-standing and comprehension of the large document collection. Document clustering is an autonomous methodthat separate out large heterogeneous document collection into smaller more homogeneous sub-collections calledclusters. Self-organizing maps (SOM) is a type of arti cial neural network (ANN) that can be used to performautonomous self-organization of high dimension feature space into low-dimensional projections called maps. Itis considered a good method to perform clustering as both requires unsupervised processing. In this paper, weproposed a SOM using multi-layer, multi-feature to cluster documents. The paper implements a SOM usingfour layers containing lexical terms, phrases and sequences in bottom layers respectively and combining all atthe top layers. The documents are processed to extract these features to feed the SOM. The internal weightsand interconnections between these layers features(neurons) automatically settle through iterations with a smalllearning rate to discover the actual clusters. We have performed extensive set of experiments on standard textmining datasets like: NEWS20, Reuters and WebKB with evaluation measures F-Measure and Purity. Theevaluation gives encouraging results and outperforms some of the existing approaches. We conclude that SOMwith multi-features (lexical terms, phrases and sequences) and multi-layers can be very e ective in producinghigh quality clusters on large document collections.

This article describes a new method for the georeferencing of UK-DMC imagery that does not require ground control points (GCPs). The proposed method utilizes satellite ancillary data, and the inter-imager offsets to determine the geolocation of individual pixels. The major step involved is the direct georeferencing of each pixel using satellite GPS and attitude sensor observations. The known separation between the sensors will allow us to determine the geolocations of all pixels that are taken at the same time using the same exterior orientation parameters. Traditional methods for georeferencing use GCPs, which are expensive and time-consuming tasks. Moreover, the traditional method is not suitable for a pushbroom imager because every scan line has a different set of exterior orientation parameters. Therefore, we propose a direct georeferencing approach without GCPs. The major source of error in direct georeferencing is the error in attitude measurements. The reason for this error is considered to be the ...