Progress in Advanced Computing and Intelligent Engineering

Cracks in the concrete structures such as cracks in the inner surface of tunnels are minor fault, however, can cause major damage or loss of lives if not checked frequently. The current method of detecting cracked surface is manual inspection by hand measuring tools and drawing sheets which may not be feasible as the tunnel needs to be blocked for a limited time period, till the inspection is in progress. By image processing, we can analyze the digital images captured from inside the tunnel for localization of cracks. The algorithm proposed in this paper can be applied to an image of the cracked surface of a tunnel for detecting the crack. Moreover, the length of the crack can also be measured in pixels.

Today, many researchers are working on satellite images, to solve resolution problems. Some of the techniques are used to enhance the resolutions that are Stationary Wavelet (SWT), Discrete Wavelet (DWT) and Integer Wavelet Transforms (IWT). These wavelet transforms are considered for improving the quality in terms of resolution enhancement. Low resolution (LR) image is used for processing and decomposed by mentioned transforms. Interpolation techniques are applied to manipulate the output of transform images. Some estimated images determined through the interpolation factor 2 to make equal sizes of images. All the images are integrated with inverse wavelet transform to generate high resolution (HR). In this work, we have compared wavelet transform. LANDSAT5 satellite images are considered for verification of implemented techniques. In this paper, three types of results are presented that are enhanced the image with size 128 × 128 to 512 × 512, 256 × 256 to 512 × 512 and iterative resolution. Some of the quality parameters are applied, i.e. PSNR, RMSE, MAE and MSE for verification for the performance of implemented techniques.

Transportation system (vehicle communication) plays a major role in today’s scenario. Detection of vehicle number plate exactly in blurry conditions was the most challenging issue found in the last three decades. Although many intensive studies were undertaken, none addressed this problem exhaustively. Various methods are introduced by several researchers for detecting the vehicle number from the vehicle number plate images. The purpose of this study was to investigate this current issue by implementing an edge-based approach on the basis of quantitative combination of Canny, Morphological and Sobel methods for the accurate detection of vehicle number in blurry conditions. The experimental results demonstrated that the proposed scheme outperforms its counterparts in terms of Sobel, Prewitt, Roberts, Laplacian of Gaussian (LoG), Morphological and Canny methods in all aspects with higher peak signal to noise ratio (PSNR) and signal to noise ratio (SNR) values. Hence, the proposed hybrid scheme is better and robust and results in accurate estimation of vehicle number from the blurry vehicle number plate (BVNP) images for the given datasets.

It is necessary to monitor the grain size characteristics of particles at production site to control the production equipment, for the assurance of product quality. In this respect, prior research finds that it is critical to evaluate the accuracy of tiny particles since the current practice indicates that the existing methods illustrate multiple shortcomings including large measure error, low accuracy and poor repeatability. Therefore, to improve the accuracy of particles, monitoring this study proposed a calibration method based on SVR algorithm to predict the accurate pixel size of the particles. Results revealed that high-precision pixel mapping of the sensitive area transforms the pixel mapping of the particle image closer to the actual size and improves the measurement precision of the whole system.

Acute myeloid leukemia (AML) is a type of cancer that originates in the bone marrow and moves into the blood quickly. The disease progresses rapidly if not treated. Therefore identification of the disease at an early stage is very important. In the proposed work, different image segmentation techniques like K-medoids and watershed, region growing and active contour have been applied for the segmentation of the nucleus from the blast cells and the results are analyzed.

Speech plays a vital role for human communication. Proper delivery of speech can enable a person to connect with a large number of people. Nowadays, a lot of valuable speeches are being provided by many popular people throughout the world and it will be very helpful if important information can be extracted from those speeches by analyzing them. An automatic speech-to-text converter can facilitate the task of speech analysis. There have been carried out a lot of works for the conversion of speech to text in the last few decades. This paper presents a framework for the acquisition of speech along with the location of the speaker and then conversion of that speech into text. We have worked with speeches containing three different languages. To evaluate our framework, we collected speeches from several locations and the result shows that the framework can be used for efficient collection and analysis of the speeches.

In this era where both techniques and technology are going digital, there is a need of designing and developing such a system that automatically identifies the person and also the person’s attributes with the help of the biometric system. The biometric of every person is unique. Therefore, in this context, the use of the biometric system to identify the identity of an individual is a popular approach. Gait is a biometric approach that helps to verify the identity of a person by their walking patterns. Owing to the advantages of gait as a biometric, its popularity among the researchers is amplified in recent years. In this paper, a review is represented, where several papers with different methods, have been mentioned which recognize the person and its attributes such as gender and age based on the gait of the person.

With the advancement in Internet technology, a digital video can be easily modified, copied, and distributed among a large audience. Copyright protection and security become very essential aspects because of the extensive use of digital multimedia applications. Digital watermarking is being used for copyright protection, data authenticity for multimedia contents such as image, audio, and video. In this paper, a DWT-DFT-SVD-based method is opted to improve robustness and overall computational requirements. The computed PSNR between original video signal and watermarked signal is improved up to 60 db. The normalized correlation value of the original and the extracted watermark image have a high level of imperceptibility. The proposed scheme shows strong robustness against several geometric and non-geometric attacks.

Time Series Data mining is a popular field in data science to discover and extract useful information from the time series data. Time Series Motif discovery is one of the tasks in data mining to discover frequent patterns which are unknown previously. Motif discovery has gained a lot of attention since its advent in 2002. Many motif discovery techniques were introduced and applied in various domains like E-commerce, Weather Prediction, Seismology, etc. In this paper, we introduce a technique for anomaly detection and motif discovery in the ECG data using Matrix Profile which has been introduced recently in the literature. Anomaly detection in ECG helps to detect the abnormal heartbeats before the process of diagnosis and motif discovery helps to locate the highly similar beats in the ECG. Using Matrix Profile for the task of anomaly detection and motif discovery in our proposed technique provides our technique with properties that are inherited from Matrix Profile. Thus, the proposed technique in this paper has properties like exactness, simple and parameter-free, space-efficient, anytime, handle missing data, free from the curse of dimensionality.

Security is mandatory and of utmost importance for all organizations. While the legitimate people should be allowed inside enterprises, the illegal ones should be barred from entering and this can be achieved using face recognition techniques. In this work, we have come up with a robust architecture using artificial intelligence and Internet of things that can be used across different enterprises. We have also derived the methodology and solution for implementing a more advanced security system. For proper demonstration, we have also considered one of the business use cases along with proposed processing work flow.

Dental caries is one of the most predominant pathologies in the world. Early detection of dental caries leads to the prevention of tooth decay. According to G.V Black classification model dental caries can be classified into six classes (Class I–Class VI) based on the location of caries. The proposed work classifies caries infected tooth based on G.V black classification using deep convolution network architecture (DCNN). In the proposed approach, feature extraction of the preprocessed images is done using Local Ternary Pattern (LTP) and feature reduction is done using Principal Component Analysis (PCA). The pretrained models used in the study are AlexNet architecture and GoogleNet architecture. AlexNet is 8 layer DCNN and classifies the tooth with an accuracy of 93%, 90% sensitivity and 92% specificity. GoogleNet is a 22 layer DCNN and classifies with an accuracy of 94%, 91% sensitivity and 93% specificity.

Cognitive radio techniques are becoming very popular to overcome the spectrum scarcity. For dynamic channel access, spectrum latency is a major bottleneck to achieve good QoS. In this paper, we have proposed distributed proactive channel scanning for different channel assignment policies of primary users (PUs). From periodic channel scanning, secondary users (SUs) store recent history of channel occupancy, and based on that decide the order of channel selection when demand comes, and switch channels proactively, if any better channel appears. For various channel allocation strategies of primary users, different channel selection algorithms are presented for secondary users to improve the spectrum latency as well as the channel switching overhead per call. Through simulation, the performance of the proposed strategies is compared with that of conventional cognitive radio. Results show that by the proposed scheme, the call drop/block rate decreases by more than $$30\%$$ 30 % with significant reduction in interference, and hence improving the QoS of the system.

Smart antenna technology is used for capacity enhancement and generating main beam and null along with user and interferer as desired. This paper presents the design of smart antenna for WiMAX application and the use of array synthesis methods like Tchebycheff distribution to reduce side lobe level in presence of different fading channels. Also, performance evaluation of the least mean square algorithm is done in application to linear and planar smart antenna array. Side lobe-level reduction up to 10 dB is achieved for planar array.

This work presents the performance comparison of different variants of hybrid Functional Linked Artificial Neural Network (FLANN) structures and Differential Evolution (DE) algorithm (FLANN-DE) for intelligent nonlinear dynamic system identification. FLANN is single-layer artificial neural network structure having less computational complexity and preferred for online applications and DE being a derivative-free metaheuristic algorithm is used as a global optimization tool. System identification finds its application in direct modelling, channel identification and estimation, geological exploration, instrumentation and control. Direct modelling is based on adaptive filtering concept and can be developed as an optimization problem. The goal of direct modelling is to estimate a model and a set of system parameters by minimizing the prediction error between the actual system output and the model output. The identification problem involves the construction of an estimated model which generates the output which matches that of desired system output when subjected to the same input signal. In this present work, hybrid FLANN-DE is proposed for direct modelling of nonlinear dynamic systems and comparative analysis is carried out for different variants of FLANN structures such as Chebyshev FLANN (CFLANN), Legendre FLANN (LFLANN) and Trigonometric FLANN (TFLANN) in terms of performance, the speed of computation and accuracy of results.

Human upper extremity has numerous functions in day-to-day life. Strokes lead to weakening in hand muscles because of which the patient is unable to hold an object properly. Stroke related problems are treated by physiotherapy and grip strength recovery is assessed by the devices such as Jamar dynamometer and pinch meter. In this paper, load cell and Force Sensing Resistor sensors are used which mimics the use of Jamar dynamometer and assesses the patient recovery quantitatively. The sensory unit consists of the load cell which is used to sense the data and give it to the Wheatstone bridge. Participant is asked to apply force on the developed hand dynamometer and the values of grip strength forces are recorded in the system. This device transmits the participant data wirelessly using the Bluetooth module. Load cell and Force Sensing Resistors (FSR) sensor data are stored in Rapid Miner and the graphs of grip strength are plotted. Thus, the developed prototype helps to determine the grip strength of a disabled person hand using low-cost devices and possible to compare the present and previous results of the assessment. The field of application of this tool is in physiotherapy and occupational therapy.

This paper deals with power quality profile analysis of distributed generation (DG) system using unified power quality conditioner (UPQC). Despite the several benefits of DG like excellent energy supply, reducing the expansion of power distribution system, environmentally friendly, and so on, there are several challenges existing due to the integration of DG with the grid or operating it in stand-alone mode. Power quality (PQ) issue is one of the main technical challenges in DG power system. In order to provide improved PQ of energy supply, it is necessary to analyze the harmonics distortion of the system as well as the voltage sag and swell. The UPQC has been extensively useful and it is verified to be the best solution to diminish this PQ issue. This paper explores the detail of PQ impacts in a DG (comprising of Solar PV and Fuel cell) system operates in stand-alone mode. The voltage sag compensation with current and voltage harmonics are estimated at varying load conditions with different control scheme like the synchronous reference frame (SRF) and modified SRF technique. The proposed model is developed in MATLAB/SIMULINKR and the result obtained validates the superiority of the proposed technique over others in terms of harmonics elimination and sag compensation.

A hybrid optimization technique is used to improve the stability and voltage profile in multi-machine systems. The hybrid biogeography-based optimization (BBO)-differential evolutionary (DE) algorithm application is to reduce the system loss and the voltage profile and stability increases when the devices are tuned by hybrid BBO-DE technique. It works using the eigen value based objective function to tune the parameters of the static var compensator (SVC) and power system stabilizer (PSS). In this research paper, eigen value grounded objective function is practiced to gain stability. Many optimization techniques are used to attain a solution to tune the parameters or to place the device in a better location. Here, a hybrid optimization technique is used to tune the parameters of the SVC and PSS after clearing three-phase fault.

With the widespread development of green technologies like wind, photovoltaic and other renewable energy sources into the distribution network, voltage stability problem has gained prominence. Electric spring, a new power electronic-based voltage regulating device can effectively maintain voltage constant at the critical loads. This is done by coordinating the load demand to track the power generation source. In account of the voltage fluctuations caused by the renewable power source, this paper deals with optimization of gains of the PI controller using Jaya algorithm proposed. Simulations carried out demonstrate that the adaptive PI-based ES restrains the voltage fluctuations in reduced settling time and less peak overshoot.

Successful delivery of electrical power depends upon the reliability of system such as protection of electrical equipment, delivery media and condition of environment. Unlike overhead transmission lines, an underground cable is not exposed to the variable weather condition, so the reliability of electrical power delivery is more in comparison with overhead lines. An experimental set-up has been developed to conduct switching transient of power cable with induction motor acting as a load, and the current and voltage data are saved in a digital storage oscilloscope during the transient operation and analysed properly. Switching operation mainly creates surges and moves through the cable circuit. R, L and C parameters of the cable have been calculated using traditional method of determination. The aim of this paper is mainly to energise a low-voltage distribution cable and to study the behaviour of switching transient. In addition to switching transient, different types of fault such as line to ground fault and double line to ground fault have been created in an unloaded cable. A MATLAB/Simulink platform has been used to study the cable parameters and its characteristics.

Integration of Distributed Generator (DG) to the distribution network feeder causes its power flow to bidirectional in place of unidirectional influencing the feeder protection. The analysis of chapter presents the influence of Distributed Generator on the over current relay behaviour. The behaviour of the scheme is evaluated for an 8-bus radial distribution feeder in PSCAD/EMTDC software and the characteristics of over current relay are tested on MATLAB software. The simulation result indicates the effects of DG on feeder protection as the current from Distributed Generator reduces relay reach.

The network which is able to accommodate today’s real-time need is growing in a very fast manner. But simultaneously also occurs an increase in the rate of network attacks and threats. Distributed Denial of Service (DDoS) is one of the attacks in which intruder attempts to disrupt normal network traffic by flooding huge traffic into the network and ultimately halt the network services and resources. There are numerous solutions available for the detection and prevention of DDoS attacks in traditional networks but making use of Software-Defined Security (SDS) is a new way of securing the network. The basic principle of separating the intelligence of the network from the infrastructure can be considered as the new hope for securing the network. This chapter aims to provide the need for SDS in networks with related literature survey we have also found out the research gaps from research done till now or going on. A method to prevent a network from DDoS attacks is also proposed using SDS.

The scheduling algorithms for IEEE 802.16 standard are designed with the predominant goals of throughput optimization, ensuring fairness and Quality of Service (QoS) provisioning. In this work, enhancements are proposed to the existing Weighted Fair Queuing (WFQ) and Deficit Weighted Round Robin (DWRR) scheduling algorithms to efficiently utilize the unused units. In WFQ, additional units may be assigned to a queue, thus reducing the service rate. Instead in Enhanced WFQ (EWFQ), multiple queues are served in a round by effectively utilizing the unexploited units. In DWRR, a queue is not serviced if the size of the packet at the front of the queue exceeds the available quantum. Enhanced DWRR (EDWRR) checks for packets with sizes less than the Deficit Counter (DC), sorts the queue and services a smaller packet in the current round. Further, if the queue that is currently served becomes empty, the DC is transferred to the ensuing active queue instead of making it zero. This helps in servicing more number of packets in a round. The proposed scheduling schemes are proficient in servicing specific traffic flows.

This chapter presents the application of an artificial neural network-based monitoring system power grid network. Neural net modules used for this study are of two kinds, a distributed separate artificial neural net (ANN) module to monitor all lines individually from separate points in the network and central common multiple-input, multiple-layer ANN to monitor all lines together. Only the active power flowing on all the lines of the utility network were monitored using the ANN’s. This work elaborates and evaluates the technical repercussions of both the modules. The ANN model employed was a feed-forward net with backpropagation of error. The aspiration of the task is to deliberate on the opportunities and obstacles of the various configurations of ANN models employed.

A lot of research works have been reported so far for event area localization and estimation in self-organized wireless sensor networks deployed to monitor a region round the clock. In most of the works, it has been assumed that a node is affected whenever it lies within the event region. But in reality, each node does not sense just its point of location but covers a region defined by its sensing range and extracts an aggregated view of the sensed region. Unfortunately, so far no sensing model takes into account this fact. In this paper, a new realistic model of sensing is proposed for continuous event region, and based on that a lightweight localized algorithm is developed to identify a minimal set of boundary nodes based on 0/1 decision predicates to locate and estimate the event area in real time with high precision. Extensive simulation studies and testbed results validate our proposed model and also show that using only elementary integer operations and limited communication, the proposed scheme outperforms existing techniques achieving a 5–10% precision in area estimation with 75–80% reduction in network traffic even for sparse networks.

Cyber-physical system (CPS) is an evolving technology, and as usual, security is a vital issue in its adaptation. Privacy is a primary security requirement in CPS and can cause havoc if unresolved. Much work is done in the area of privacy preservation in CPS, but they are domain-specific. There is no generic mechanism for privacy preservation in CPS. Here, we design a framework for privacy preservation in CPS. The proposed study aims to integrate separate privacy protection mechanisms in different levels of the CPS architecture, addressing different kinds of privacy as information contents, locations, identities, dates and times, addresses, etc., within a common structure.

VANET is an essential key technology for building up an intelligent transportation system (ITS) that combines current wireless technologies to vehicles. Real-time information sent to driver or vehicle ensures smooth traffic flow in order to ensure safe driving and traffic management while avoiding accidents. To maintain smooth functioning and protection of real-time information from alteration, data must be secured and authenticated. In this paper, a novel anonymous authentication scheme for VANET has been presented which tries to provide strong non-repudiation, anti-forgery, and anonymity properties. Additionally, to avoid vehicles from abusing VANET as well as to provide strong privacy protection, a conditional tracking mechanism for vehicle tracing is developed which revokes certificates of misbehaving vehicles in an efficacious manner. Moreover, the proposed protocol protects the network from attacks such as masquerading, identity theft, and certificate replication.

The next generation of wireless network consists of many overlaying integrated networks which know as heterogenous network in which mobile node will be on mobility between/within these networks. During mobility of node, the ongoing call of mobile node should be transferred between/within these seamless networks. The transfer of mobile node between/within network can be done using handover algorithms. Most of the handover algorithms designed for heterogeneous wireless network are mainly based on parameters such as signal strength, SIR, distance, velocity, direction, and power consumption. For an effective handover, different approaches have been proposed. These approaches have their own advantages and disadvantages, and each of them performs better than the others under certain circumstances. The chapter classifies and discuss the different approaches for designing of vertical handoff mechanism.

A complex issue in handling systems with continually changing processing demands is an intractable task. A more current example of these systems can be observed in wireless sensor networks and traffic-intensive IoT networks. Thus, an adaptive framework is desired which can handle the load and can also assist in enhancing the performance of the system. In this paper, our objective is to provide the non-stationary solution of Erlang loss queueing model where s servers can serve at most s jobs at a time. We have employed time-dependent perturbation theory to obtain the probability distribution of M/M/s/s queueing model. The time-dependent arrival and service rates are assumed to be in sinusoidal form. The opted theory gives approximation for probability distribution correct up to first and second order. The result shows that first- and second-order approximations provide better approximation than the existing ones.

Increasing crossover of information and wireless network technologies in the medical field embarks a major revolution. Wire body area network (WBAN) is one such result of crossover. Low-cost, lightweight, multipurpose sensors can be easily integrated into a wireless communication network for health monitoring. It is a wireless networking technology based on radio frequency, consisting of small sensors, transmitting the data which could be further used for medical or safeguarding measures, and thus, there is a need to introduce better safety measures in WBAN schemes. In this paper, we proposed a novel authentication scheme for WBAN with anonymity and provided a formal security proof through BAN logic.

Distributed systems like cloud platforms are being used widely in recent times. However, such platforms face a major issue of data storage on cloud in terms of security. If data on the cloud is not encrypted, it can be accessed by unauthorized members. This violates the confidentiality of the data. If data is stored in an encrypted format, every authorized party member will have to decrypt the data first in order to perform operations on it and then encrypt it back to upload it on the distributed platform. This has to be done every time, and every member performs operations on data. Needles to say, it complicates the entire procedure of sharing data and a lot of time is wasted in encrypting and decrypting data even for small operations like searching and sorting. To avoid these complications, this paper suggests a way to store data on cloud by homomorphically encrypting it. Homomorphic encryption allows user to compute on encrypted data without the need of decrypting it. In this paper, elliptic curve cryptography (ECC) is used for homomorphic encryption of data. The size of the ciphertext generated by ECC is smaller than the ciphertext generated by other encryption schemes. As cloud is mostly used for storing databases, this paper further employs searching and sorting techniques on the encrypted data.

In wireless communication systems, the received signal is superimposed by the contemporaneous effects of both shadowing and multipath fading. The conventional composite models fail to capture the outliers in the fading channels. In this context, we portray the significance of the Tsallis’ non-extensive parameter ‘q’ in modeling various fading environments. This paper exploits the well-known q-Weibull probability density function (pdf) in characterizing the composite fading channels. The q-Weibull pdf yields a tight agreement over the generated fading signals. Furthermore, the different performance metrics, viz. amount of fading, average channel capacity, and outage probability, are obtained in closed form. The derived results are validated using rigorous Monte Carlo simulation procedure.

Over the past few years, erasure coding has been widely used as an efficient fault tolerance mechanism in distributed storage systems. There are various implementations of erasure coding available in the research community. Jerasure is one of the widely used open-source library in erasure coding. In this paper, we compared various implementations of Jerasure library in encoding and decoding scenario. Our goal is to compare codes with different filesystems data to understand its impact on code performance. The number of failure scenarios is evaluated to understand performance characteristics of Jerasure code implementation.

Large-scale cover song retrieval systems frameworks can figure tune-to-tune likeness and suit contrasts in timing, key, and beat. Straightforward vector separation measure is not enough incredible to perform spread melody acknowledgment and high arrangements, for example, dynamic time-traveling does not scale to a large number of cases, making spread tune recovery erroneous for business-scale applications. In this work, the substance-based music highlights of tunes are utilized as information and changed them into vectors by utilizing the 2D Fourier change approach. By anticipating the tunes into a combination vector of PCA and LDA, the effective KD-tree and R-tree indexing calculation is utilized to look at the comparability of melodies and recover the most comparable tunes from the enormous scale database. The proposed framework is not just effective enough to perform adaptable substance-based music recovery, yet can likewise build up the capability of making comparative music acknowledgment applications quicker and increasingly exact.

Materialized view selection is a major challenge in data warehouse management, and prioritized cube selection is further approach to find an optimal set of prioritized cubes under resource constraints. In this paper, we introduce a hybrid approach combining particle swarm optimization (PSO) algorithm with tabu search (TS) to solve the prioritized cube selection problem. Our proposed hybrid algorithm deals with PSO’s premature convergence problem through integration of TS local neighbourhood search, and thus significantly improves the solution quality. We also present a neighbourhood reduction strategy based on cube information obtained during PSO search to intensify the search of TS for better solutions. Finally, we prove the effectiveness of our proposed hybrid algorithm for high-dimensional prioritized cube selection problem by comparing the results with PSO algorithm results.

Nature-inspired metaheuristic algorithms along with their improved and hybrid versions have been gaining intrinsic popularity in solving nonlinear constrained complex real-world problems. On this presentation, a new hybrid butterfly optimization algorithm (BOA), viz. BOSCA combined with sine cosine algorithm (SCA) is suggested to develop a balanced yet powerful optimization technique through enhancing and stabalizing the global exploration and local exploitation ability. In this, metaheuristic hybridization is done in such a way to get both the exploration and exploitation phases for each of the butterfly with sufficient chance to improvise each solution. To prove the efficiency and robustness of the developed BOSCA, it has been applied to solve twenty-five classical benchmark functions. A comparative study has been done by taking some of the popular algorithms in available in literature and this developed algorithm is found to be superior to the compared algorithms. Again to validate its efficiency in real-world problems, it has been applied to two real-world problems; One is gas transmission compressor design problem and another is optimal capacity of gas production facilities. Results of these real-world problems have been compared to that of some other algorithms and the proposed method found to be superior in real-world optimization problems also.

The probability distribution of a system can be adaptively derived using the maximum entropy principle subject to its information set in terms of probabilistic moments. The obtained probability distribution characterizes the wide range of exponential family of distributions when one maximizes Shannon entropy. On maximizing Tsallis entropy with non-extensive parameter q, power law distributions are obtained which portrays the well-known Shannon family of exponential distribution as, $$q \to 1$$ q → 1 . The maximization of Shannon entropy subject to the shifted geometric mean constraints leads to a probability distribution in terms of Hurwitz zeta function. This density characterizes the equilibrium state of broadband network traffic. Moreover, maximization of Shannon entropy in Laplace domain subject to specific constraints provides a transient probability distribution which characterizes the behavior of M/M/1/1 queueing system.

Industry 4.0 holds tremendous potential to transform the operational productivity of industries. Construction sector of India has fallen behind to embrace Industry 4.0 framework. Delay in project completion and lack of coordination within departments due to unavailability of real-time information hampers the effectiveness of the operations on a daily basis. The investigation of impediments in the adoption of Industry 4.0 in the construction industry of India is an urgent requirement to restore the efficiency of the sector. Based on the extant literature review and discussions with the experts, 25 key challenges were identified. Using multi-criteria decision-making (MCDM) tool, fuzzy TOPSIS, which operates with uncertain and vague inputs, the ranking of the challenges was established. Huge costs incurred in the implementation and maintenance emerged as the biggest obstacle followed closely by problems in hiring skilled people with the required expertise. Heavy lay-offs, disruptions in compensation and legal barriers are some other serious issues that hinder adoption of Industry 4.0. Through this paper, key obstacles in the adoption of digital technology are expected to surface up that can inform management and assist in the timely decision making.

The activities of human can be classified into human actions, interactions, object–human interactions and group actions. The recognition of actions in the input video is very much useful in computer vision technology. This system gives application to develop a model that can detect and recognize the actions. The variety of HAR applications are surveillance environment systems, healthcare systems, military, patient monitoring system (PMS), etc., that involve interactions between electronic devices such as human–computer interfaces with persons. Initially, collecting the videos containing actions or interactions was performed by the humans. The given input videos were converted into number of frames, and then these frames were undergone preprocessing stage using by applying median filter. The noise of the given input frame is reduced by applying the median filter of the neighboring pixels. Through frames, desired features were extracted. The actions of the person which is recognised from the system is going to extract further. There are three spatial–temporal interest point (STIP) techniques such as Harris SPIT, Gabor SPIT and HOG SPIT used for feature extraction from video frames. SVM algorithm is applied for classifying the extracted feature. The action recognition is based on the colored label identified by classifier. The system performance is measured by calculating the classifier performance which is the accuracy, sensitivity and specificity. The accuracy represents the classifier reliability. The specificity and sensitivity represent how exactly the classifier categorizes its features to each correct category and how the classifier rejects the features that are not belonging to the particular correct category.

One of the most elemental operations concerning the analysis of properties of a network is community detection. It is the process of decomposition of a given network into groups of densely connected nodes that tend to share some similar properties. A wide variety of algorithms to identify the communities in complex networks exists. In this paper, an intelligent genetic algorithm (GA)-based approach to identify communities has been proposed. The efficiency of the solution that resulted from the genetic algorithm depends on the setting appropriate values for the various parameters involved. As a means to reduce the convergence time of the genetic algorithm, a fuzzy cognitive map (FCM) is used. The knowledge derived from the FCM is used to populate the initial population reducing the randomness of the algorithm. The potency of the algorithm is evaluated on various weighted and unweighted benchmark networks.

Wide usage of online applications has increased the risk of misuse of data by affecting privacy and security policies. Digital forensics is a process of solving criminal cases related to digital devices. Technical growth in this area is the expansion of forensic tools to collect the pieces of evidence. Database forensics is one of the categories of digital forensics. Database forensics covers the scanning of various parts of it for data recovery or finding data tampering. Forensic tools are available for most of the relational databases. Very few tools are available in the market for NoSQL databases. This paper is an attempt to present available digital forensic tools and to experiment with relevant free tools on the MongoDB database to check the usefulness.