Search

Classification is a common problem in various fields of life, and the key challenging task in data mining. The primary objective of the classification process is to classify the given dataset in a defined class label for all data. Many research papers widely used classification in the medical sector. Various researches have been carried out to classify medical data using different techniques, such as High Order Neural Network (HONN) combined with Back-Propagation Neural Network (BPNN) as a learning algorithm. Due to the increased data complexity, the back-propagation algorithm faced problems of slow convergence. The Back-Propagation (BP) using the gradient descent technique has the possibility of getting stuck in local minima. So, the BP algorithm may cause difficulties in finding the global minima of the error function. This paper proposed a high-order Functional Link Neural Network (FLNN). The proposed FLNN model is integrated with a metaheuristic-based searching algorithm called Accelerated Particle Swarm Optimization (APSO). The performance of the proposed Accelerated Particle Swarm Optimization Functional Link Neural Network (APSOFLNN) model is validated with various medical datasets and compared to traditional techniques such as Accelerated Particle Swarm Optimization Functional Link Back-Propagation (APSOFLBP), and Artificial Bee Colony Functional Link Neural Network (ABCFLNN). The simulation results showed that the proposed APSOFLNN algorithm for the used benchmarked datasets shows good results in terms of the mean square error (MSE) and accuracy in comparison to the traditional techniques.

Image denoising is a vital pre-processing phase, used to refine the image quality and make it more informative. Many image-denoising algorithms have been proposed with their own pros and cons. This paper presents a comprehensive study of the median filter and its different variants to reduce or remove the impulse noise from gray scale images. These filters are compared with respect to their functionality, time complexity and relative performance. For performance evaluation of the existing algorithms, extensive MATLAB based simulations have been carried out on a set of images. For benchmarking the relative performance, we have used Peak Signal to Noise Ratio (PSNR), Root Mean Square Error (RMSE), Universal Image Quality Index (UQI), Structural Similarity Index (SSIM) and Edge-strength Similarity (ESSIM) as quality assessment metrics. The Extended median filter (EMF) and Modified BDND are best in terms of relative statistical ratios and pleasant visual results where IAMF is having the best time complexity among existing algorithms.

In the area of machine learning, different techniques are used to train machines and perform different tasks like computer vision, data analysis, natural language processing, and speech recognition. Computer vision is one of the main branches where machine learning and deep learning techniques are being applied. Optical character recognition (OCR) is the ability of a machine to recognize the character of a language. Pashto is one of the most ancient and historical languages of the world, spoken in Afghanistan and Pakistan. OCR application has been developed for various cursive languages like Urdu, Chinese, and Japanese, but very little work is done for the recognition of the Pashto language. When it comes to handwritten character recognition, it becomes more difficult for OCR to recognize the characters as every handwritten character’s shape is influenced by the writer’s hand motion dynamics. The reason for the lack of research in Pashto handwritten character data as compared to other languages is because there is no benchmark dataset available for experimental purposes. This study focuses on the creation of such a dataset, and then for the evaluation purpose, a machine is trained to correctly recognize unseen Pashto handwritten characters. To achieve this objective, a dataset of 43000 images was created. Three Feed Forward Neural Network models with backpropagation algorithm using different Rectified Linear Unit (ReLU) layer configurations (Model 1 with 1-ReLU Layer, Model 2 with 2-ReLU layers, and Model 3 with 3-ReLU Layers) were trained and tested with this dataset. The simulation shows that Model 1 achieved accuracy up to 87.6% on unseen data while Model 2 achieved an accuracy of 81.60% and 3% accuracy, respectively. Similarly, loss (cross-entropy) was the lowest for Model 1 with 0.15 and 3.17 for training and testing, followed by Model 2 with 0.7 and 4.2 for training and testing, while Model 3 was the last with loss values of 6.4 and 3.69. The precision, recall, and f-measure values of Model 1 were better than those of both Model 2 and Model 3. Based on results, Model 1 (with 1 ReLU activation layer) is found to be the most efficient as compared to the other two models in terms of accuracy to recognize Pashto handwritten characters.

Task scheduling in parallel multiple sequence alignment (MSA) through improved dynamic programming optimization speeds up alignment processing. The increased importance of multiple matching sequences also needs the utilization of parallel processor systems. This dynamic algorithm proposes improved task scheduling in case of parallel MSA. Specifically, the alignment of several tertiary structured proteins is computationally complex than simple word-based MSA. Parallel task processing is computationally more efficient for protein-structured based superposition. The basic condition for the application of dynamic programming is also fulfilled, because the task scheduling problem has multiple possible solutions or options. Search space reduction for speedy processing of this algorithm is carried out through greedy strategy. Performance in terms of better results is ensured through computationally expensive recursive and iterative greedy approaches. Any optimal scheduling schemes show better performance in heterogeneous resources using CPU or GPU.

The advent of information technology re-innovates all sectors of bio-sciences. Researchers use Semantic Web to improve web searching, mining and integration, which alleviates the time-consuming task of finding relevant and high-quality content. Semantics is improved through ontology engineering in any domain. Amended and developed ontologies will be uploaded to existing standardised and approved biomedical repositories. The establishment of a World Wide Web Consortium (W3C) approved and standardised ontology repository is the most ambitious goal. This work will solely focus on some selected agri-ontologies. The main objective is to promote outcome-based research and transformation styles of relevant expertise sharing. The intended goal is to win project funding to train and equip students with relevant skills and expertise. Need-based and market-oriented training and professional grooming are a tangible asset for students. The majority of traditional Web development freelancers are unaware of ontology or semantic web market demand. Freelancing is another option for expert Ontology developers. However, agriculture students are used to all the research vocabulary and terminologies in their area, but they do not know how to contribute their expertise to improve the efficiency of the Semantic Web in their domain. If the improvement in relevant ontology becomes a part of the Semantic Web, then it is termed ‘Real-time Web semantics enhancement’. In other words, the target ontology becomes a part of the future Web of meaning.

Metaheuristic algorithms are popular techniques used to solve several optimization problems. Among the key algorithms, cuckoo search (CS) is a comparatively novel and promising metaheuristic algorithm. Various researchers have shown that it performs better when compared to other metaheuristic algorithms while searching for optimal value and is being used to solve various real-world problems. However, the basic CS algorithm can be improved by enhancing the probabilities of survival of the eggs. It will decrease the possibility of the eggs getting ruined by the host bird. The cuckoo birds move to a new position looking for more search space to get better solutions. Furthermore, better search space can be obtained by executing levy flight with accelerated particle swarm optimization (APSO). This research proposes a new method known as hybrid accelerated cuckoo particle swarm optimization (HACPSO) algorithm, based on two metaheuristic algorithms. In the proposed HACPSO algorithm, APSO provides communication for looking better place having the best nest with greater survivability for cuckoo birds. Different simulation has been carried using standard dataset and efficiency of the proposed algorithm is compared with CS, artificial bee colony and other similar hybrid variants. The simulation results demonstrate that the HACPSO algorithm performs better as compared to other algorithms in term of accuracy, MSE, SD, and with fast convergence rate to the target space.

The merger of wireless sensor technologies, pervasive computing, and biomedical engineering has resulted in the emergence of wireless body sensor network (WBSN). WBSNs assist human beings in various monitoring applications such as health-care, entertainment, rehabilitation systems, and sports. Life-critical health-care applications of WBSNs consider both reliability and delay as major Quality of Service (QoS) parameters. In addition to the common limitations and challenges of wireless sensor networks (WSNs), WBSNs pose distinct constraints due to the behavior and chemistry of the human body. The biomedical sensor nodes (BMSNs) adopt multihop communication while reporting the heterogeneous natured physiological parameters to the nearby base station also called local coordinator. Routing in WBSNs becomes a challenging job due to the necessary QoS considerations, overheated in-body BMSNs, and high and dynamic path loss. To the best of our knowledge, none of the existing routing protocols integrate the aforementioned issues in their designs. In this research work, a multiconstraint-aware routing mechanism (modular-based) is proposed which considers the QoS parameters, dynamic and high path loss, and the overheated nodes issue. Two types of network frameworks, with and without relay/forwarder nodes, are being used. The data packets containing physiological parameters of the human body are categorized into delay-constrained, reliability-constrained, critical (both delay- and reliability-constrained), and nonconstrained data packets. NS-2 is being used to carry out the simulations of the proposed mechanism. The simulation results reveal that the proposed mechanism has improved the QoS-aware routing for WBSNs by adopting the proposed multiconstraint-aware strategy.

Internet of Things (IoT), an emerging technology, is becoming an essential part of today’s world. Machine learning (ML) algorithms play an important role in various applications of IoT. For decades, the location information has been extremely useful for humans to navigate both in outdoor and indoor environments. Wi-Fi access point-based indoor positioning systems get more popularity, as it avoids extra calibration expenses. The fingerprinting technique is preferred in an indoor environment as it does not require a signal’s Line of Sight (LoS). It consists of two phases: offline and online phase. In the offline phase, the Wi-Fi RSSI radio map of the site is stored in a database, and in the online phase, the object is localized using the offline database. To avoid the radio map construction which is expensive in terms of labor, time, and cost, machine learning techniques may be used. In this research work, we proposed a hybrid technique using Cuckoo Search-based Support Vector Machine (CS-SVM) for real-time position estimation. Cuckoo search is a nature-inspired optimization algorithm, which solves the problem of slow convergence rate and local minima of other similar algorithms. Wi-Fi RSSI fingerprint dataset of UCI repository having seven classes is used for simulation purposes. The dataset is preprocessed by min-max normalization to increase accuracy and reduce computational speed. The proposed model is simulated using MATLAB and evaluated in terms of accuracy, precision, and recall with K-nearest neighbor (KNN) and support vector machine (SVM). Moreover, the simulation results show that the proposed model achieves high accuracy of 99.87%.

In this modern era skin cancer is a serious problem around the globe and so it is the age of technology and it is important to solve this problem through intelligence machines which using different algorithms rather than conventional method. Intelligent machine using different algorithms to classify the skin cancer images in a reliable way to save effort, time and ease human life. For this purpose, deep learning (CNN) algorithm is used by intelligent machine to classify the skin cancer images according to its types. In this current research work there are three types of skin cancer types name is Basal cell Carcinoma (BBC), Melanocytic Nevus (NV) and Vascular Lesion (VASC) are used. The study showed that implementing deep learning in the field of cancer diseases may be the most appropriate way to classify and recognize the images of skin cancer according to their type, which can be very useful in the field of medicine for early diagnosis and improve the exact result of the diagnosis. This current work has shown and produced results with 98.89% accuracy.

To reduce healthcare costs and improve human well-being, a promising technology known as wireless body area networks (WBANs) has recently emerged. It is comprised of various on-body as well as implanted sensors which seamlessly monitor the physiological characteristics of the human body. The information is heterogeneous in nature, requires different QoS factors. The information may be classified as delay-sensitive, reliability-sensitive, critical, and routine. On-time delivery and minimum losses are the main QoS-factors required to transmit the captured information. Various researchers have work to provide the required QoS, and some have also considered the other constraints due to the characteristics and texture of the human body. In this research work, we have discussed the communication architecture of WBANS along with the various challenges of WBANS. Furthermore, we have classified and discussed the existing QoS-aware data dissemination mechanisms. In the end, a comparative study of existing QoS-aware data dissemination mechanisms highlights the pros and cons of each mechanism.

IEEE 802.15.4, Low data Rate low power Wireless Personal Area Network (LR-WPAN) standard uses fixed duty cycle of the superframe operation. Fixed duty cycle operation of the stated standard suffers from several network issues like Personal Area Network (PAN) tedious initialization interval, nodes association duration, number of associated nodes, average network delay, throughput and nodes energy etc. Low duty cycle control operation with lower energy consumption of the network is one of the attractive feature of IEEE 802.15.4. Two superframe parameters Beacon Order (BO) and Superframe Order (SO) decide the beacon interval and duty cycle of the standard and has a strong impact on the performance of other network parameters. In this paper we analyze the IEEE 802.15.4 MAC with brief simulations by varying the two superframe parameters BO and SO to accomplish the finest performance of the WBAN network.

In wireless sensor networks, efficient resource management is a major concern for the battery operated sensor nodes. Data collection using mobile sink(s) is considered as a good strategy to prolong network lifetime and improve network coverage. Most of the existing mobile sink based data collection schemes operate in event driven or periodic sensing modes. There are several application environments, which dictate query driven data collection using a mobile sink e.g., a mobile sink might require reinforced data reporting from one particular network segment compared to others. In this regard, the existing query driven data collection schemes either impose too many constraints on network operation or poorly perform when delivering the requested data to a mobile sink with variable speed. In this paper we propose Query-Driven Virtual Grid based Data Dissemination (QDVGDD) scheme that aims to improve data delivery performance to a mobile sink. The proposed scheme makes use of a virtual infrastructure thereby causing minimal network control overheads while delivering the requested data with high quality of service to the mobile sink. We carried out extensive simulation works in NS-2.35 to evaluate the performance of our QDVGDD at different sink’s speeds and network sizes. Simulation results reveal improved performance of QDVGDD in terms of data delivery latency, data delivery ratio, average energy consumption, and estimated network traffic as compared to other state-of-the-art.

Forecasting electricity consumption can help policymakers to properly plan for economic development. This is possible through energy conservation by avoiding excessive consumption of electricity through enhanced operational strategy. Power utilization and financial improvement are in long term relationship with all member nations of the Organization of Petroleum Exporting Countries (OPEC). In order to improve electricity consumption forecasting performance, this paper proposes an alternate machine learning method for forecasting OPEC electricity consumption with improved performance. The modeling of the OPEC electricity utilization forecast depends on the Cuckoo Search Algorithm by means of Levy flights. The proposed method is found to be efficient, operative, consistent, and robust compared to the electricity consumption forecasting methods that have already been discussed by researchers in the literature. In turn, energy conservation can be motivated in the twelve OPEC member countries.

In wireless sensor networks, exploiting the sink mobility has been considered as a good strategy to balance the nodes energy dissipation. Despite its numerous advantages, the data dissemination to the mobile sink is a challenging task for the resource constrained sensor nodes due to the dynamic network topology caused by the sink mobility. For efficient data delivery, nodes need to reconstruct their routes toward the latest location of the mobile sink, which undermines the energy conservation goal. In this paper, we present a virtual grid-based dynamic routes adjustment (VGDRA) scheme that aims to minimize the routes reconstruction cost of the sensor nodes while maintaining nearly optimal routes to the latest location of the mobile sink. We propose a set of communication rules that governs the routes reconstruction process thereby requiring only a limited number of nodes to readjust their data delivery routes toward the mobile sink. Simulation results demonstrate reduced routes reconstruction cost and improved network lifetime of the VGDRA scheme when compared with existing work.

Wireless Body Sensor Networks (WBSNs) constitute a subset of Wireless Sensor Networks (WSNs) responsible for monitoring vital sign-related data of patients and accordingly route this data towards a sink. In routing sensed data towards sinks, WBSNs face some of the same routing challenges as general WSNs, but the unique requirements of WBSNs impose some more constraints that need to be addressed by the routing mechanisms. This paper identifies various issues and challenges in pursuit of effective routing in WBSNs. Furthermore, it provides a detailed literature review of the various existing routing protocols used in the WBSN domain by discussing their strengths and weaknesses.

Cartoons are an informative way for creating awareness; children take keen interest in watching cartoons and spend leisure time in front of television. Unfortunately there is an inclination towards violence and other objectionable scenes in cartoon videos that have very bad impact on the developing personality of children. Extensive use of such violent scenes is one of the factors of increase of violence in society. Parents rely on cartoons as a mean of amusement for their children without analyzing its content which can pose serious negative impacts on child behavior. To protect children from violent content means are require for automatic detection of violence content in cartoon videos. In this paper different low-level visual features are evaluated for violence detection in cartoon videos using indigenously developed dataset that is categorized as violent and non-violent. From our results it has been observed that low-level visual features could not be used efficiently for the detection of violence. However these features are very helpful in identifying the character and situation that if combined with a knowledgebase capability can be used for detection of violence and other objectionable elements in the cartoon videos.

With the promise of cost effective, unobtrusive, and unsupervised continuous monitoring, wireless body sensor networks (WBSNs) have attracted a wide range of monitoring applications such as medical and healthcare, sport activity, and rehabilitation systems. Most WBSN's medical and healthcare applications are real-time and life-critical, which require strict guarantee of quality of service (QoS), in terms of latency, and reliability. Reliability in routing plays key role in providing the overall reliability in WBSNs. This paper presents reliability aware routing (RAR) for intra-WBSNs that aims to provide high reliability for reliability constraint data packets. It considers the high and dynamic path loss due to body postural movements and temperature rise of the implanted biomedical sensor nodes. We have used two network models in this paper: RAR without Relays (RAR) and RAR with Relays (RARR). The simulation results reveal that RARR outperforms the other state-of-the-art schemes while RAR has slightly low reliability at low data rates as compared to RARR but significantly higher than other state-of-the-art schemes.

A novel technique for electronic fetal monitoring is presented. It is based on training a Volterra based neural network to classify the fetal states based on a recorded cardiotocography (CTG) data base. The dataset consists of measurements of fetal heart rate and uterine contraction. The CTG signals have 21 attributes and three fetal states, normal, suspect and Pathologic. The Volterra based neural networks (VNN) employ Volterra series expansion for the input vectors and can produce explicit equations describing any multi-input multi-output (MIMO) system. Moreover, VNN has fast and uniform convergence. Simulations have demonstrated the efficiency of the proposed technique in electronic fetal monitoring. The VNN was able to classify the fetal states in a very low number of iterations with negligible error (practically zero). The conventional neural networks, on the other hand, have failed to achieve a reliable convergence.

Recently, Wireless Body Sensor Network (WBSN) has been emerged as a promising technology to provide medical and healthcare monitoring. It can significantly reduce the health-care cost by providing continuous health monitoring facility to the elderly people suffering from chronic diseases. The life critical and real time medical application of WBSNs requires the assurance of the demanded Quality of Service (QoS) both in terms delay and reliability. This paper proposes Critical Data Routing (CDR) that categorizes the sensory data packets as critical and non-critical data packets. Along with the heterogeneous natured data, it also addresses the high and dynamic path loss and the temperature rise issues caused by postural movement of the human body and electromagnetic waves absorption respectively. The simulation results show that the proposed CDR scheme achieves its designed objective of forwarding the critical data packets within certain time limits and with highest reliability while reducing the temperature rise of the in-body sensor nodes.

Wireless sensor network (WSN) is considered as the enabling technology to bridge the gap between the physical and digital world. Some of the applications environments of WSN require a mobile sink to operate in the sensor field where delayed and/or partial data delivery might lead to inappropriate conclusions and thus require high quality of service in terms of latency and packets delivery ratio. Majority of existing mobile sink based data dissemination schemes aim to prolong network lifetime whereas few schemes improve the data delivery performance by employing multiple mobile sinks which add to the hardware and operating cost. In this paper we propose a virtual grid based data dissemination (VGDD) scheme that aims to optimize the tradeoff between network lifetime and data delivery performance while adhering to the low cost theme of WSN. Using the virtual structure, the proposed VGDD scheme follows a set of rules to disseminate sink's mobility updates in an energy efficient manner thereby maintaining nearly optimal routes. Furthermore, to cope with speed's variation of mobile sink, VGDD makes use of appropriate forwarder nodes for guaranteed data delivery. Simulation results reveal improved data delivery performance in terms of latency and data delivery ratio compared to existing work.