Search

Consumer demand for automobiles is changing because of the vehicle's dependability and utility, and the superb design and high comfort make the vehicle a wealthy object class. The creation of object classes necessitates the creation of more sophisticated computer vision models. However, the critical issue is image quality, determined by lighting conditions, viewing angle, and physical vehicle construction. This work focuses on creating and implementing a deep learning-based traffic analysis system. Using a variety of video feeds and vehicle information, the developed model recognizes, categorizes, and counts vehicles in real-time traffic flow. The dynamic skipping method offered in the developed model speeds up the processing of a lengthy video stream while ensuring that the video picture is delivered accurately to the viewer. In real-time traffic, standard vehicle retrieval may assist in determining the make, model, and year of the vehicle. Previous MobileNet and VGG19 models achieved F-values of 0.81 and 0.91, respectively. However, the proposed solution raises MobileNet's frame rate from 71.2 to 89.17 and VGG19's frame rate from 48.2 to 59.14. The method may be applied to a wide range of applications that require a dedicated zone to monitor real-time data analysis and normal multimedia operations. [ABSTRACT FROM AUTHOR]

Sensor data that is often collected in the Internet of Things (IoT) or any smart city environment should be protected against security and privacy concerns. Often, sensor data that is shared by devices in smart cities contains sensitive or private information that can often be shared over different networks and by different smart applications. In the last decade, the area of Privacy-Preserving Data Mining (PPDM) has received a lot of attention as the amount of data received and collected daily is huge. Unfortunately, PPDM mostly applies to binary data. To improve the usefulness of PPDM, we present a more usable version for smart cities called Privacy-Preserving Utility Mining (PPUM), in the form of a Maximal Sensitive Utility-Maximal Sensitive ConflIct (MSU-MSI) algorithm. MSU-MSI finds any conflicting items that may contain sensitive itemsets with high-utility and sanitizes them, stripping them of sensitive and private information while maintaining utility. Any transactions encountered that contain sensitive itemsets are first fed through sanitization processes. This is followed by calculating the total number of items that conflict, and then removing them so sanitization processes can operate more efficiently so as to not redo known sanitization processes. We conduct an in-depth experimental analysis, where our detailed methodology is compared directly with state-of-the-art frameworks such as MSU-MIU, MSU-MAU, HHUIF and MSCIF. Our proposed MSU-MSI shows a higher performance in missing cost, in particular when dealing with highly dense or highly sparse datasets. Moreover, our novel framework is shown to achieve an excellent performance with regards to similarity in database structure and database utility. [ABSTRACT FROM AUTHOR]

The motor movement performed by different body parts affects the synaptic potential at different brain cortices, which can be observed by the electroencephalogram (EEG) signal. The recorded EEG signals can be used to decode the imagined motor task. The EEG signals are non-stationary and transient and contain time, frequency, and space information. Extracting this information and processing them with the latest machine learning and deep learning algorithms can be useful for brain–computer interfacing and other human–machine interaction techniques. EEG signal contains negative values. Hence, nonnegative matrix factorization can be used to provide a meaningful explanation of information within EEG signals. Sparseness in feature vectors is another essential factor to consider while identifying the structures in an input signal. In this work, we propose a novel motor imagery classification model that extracts the weights for predefined motor imagery features from EEG signals and classifies them using a convolution neural network (CNN). Sparse nonnegative matrix factorization is used to extract the fundamental feature vectors for different motor imagery events, which are further used to extract the combined weight matrix of unknown motor imagery events. The designed CNN classifies the extracted weight matrix in the corresponding classes. The acquired EEG signals from all the channels are processed simultaneously using the CNN, which helps extract spatial information from the signals. BCI Competition IV dataset IIa and BCI Competition III dataset IVa are used to validate the proposed method. The proposed method has been compared with existing methods and validates their superiority in terms of average accuracy. The classification accuracy for two types and four types of motor imagery signals is 99.53% and 94.58%, respectively. Empirical results show that EEG signals' sparseness characteristics can be considered an effective feature for motor imagery classification. [ABSTRACT FROM AUTHOR]

Due to global warming and climate change, power generation from renewable resources, such as solar, wind, fuel cells, and others, is becoming increasingly important. The smart grid's incorporation of renewable energy resources makes Peer-to-Peer (P2P) energy trading through the local energy market possible. Due to its distributed nature, Peer-to-Peer (P2P) energy trading faces many challenges regarding security and privacy in energy trading. Most existing works do not consider data privacy among participants. A P2P energy trading model with Decentralized Multi-Criteria Ranked Prosumers called DeMCRP is introduced to address these privacy and security challenges in smart grid energy trading. The proposed DeMCRP trading model uses Corda-distributed ledgers, consensus, and smart contracts for energy trading between energy buyers and sellers, also termed prosumers. In the DeMCRP model, the mapping procedure between prosumers is done based on priority values for such prosumers determined using a multi-criteria decision-making method, namely the Preference Ranking for Organization Method for Enrichment Evaluation II (PROMETHEE II). Furthermore, an energy-trading smart contract performs energy trading between buyers and sellers. The transactions' validation, verification, and uniqueness process is acheived through consensus of the distributed ledger by notaries. The Distributed Service Operator (DSO) selects 51% of sellers as notaries according to the rank of sellers. The rank of sellers is determined using a multi-criteria decision-making method called PROMETHEE II by considering various parameters such as energy surplus, trust factor, and the number of times the seller is selected as notary. Moreover, the performance analysis of the proposed scheme has been carried out in terms of network deployment time and memory utilization. The proposed DeMCRP technique works in polynomial time if the number of participants increase. Furthermore, security analysis has been carried out for various security features like data sharing privacy, users' privacy, non-repudiation, integrity, and preventing double-spending. The proposed method protects the privacy of participants' data and stops double spending, which is not taken into account by many existing methods. [ABSTRACT FROM AUTHOR]

With an emphasis on the role of automation in Industry 4.0, there has been widespread growth in the adoption of industrial Internet of Things (IoT). However, as IoT networks become larger with billions of heterogeneous devices, scalability and efficient data routing become issues, especially in the context of existing blockchain models. Managing network traffic, latency as well as facilitating high throughput is essential for the fluid functioning of real-time systems. This paper aims to deal with such existing issues by discussing newer hierarchical blockchain models over existing SDN and fog-based networking frameworks for large-scale IoT applications. We also prove the model’s feasibility through performance testing through both native and platform-based implementations to support our quest for enhanced scalability and security. [ABSTRACT FROM AUTHOR]

Drug Supply Chain Management (DSCM) can be one of the most affected streams in healthcare due to pandemics. The delivery of medicine to patients through DSCM is a complex process. Also, DSCM has several challenges, including counterfeiting, fraud, and the availability of medicine. Therefore, there is a need for security and intelligence strategies to remove pharmaceutical fraud, which remains a significant challenge since ensuring fair and secure access to medicine, services, and assistance is essential in Cyber-Physical Systems (CPS)-based DSCM. The existing CPS-based DSCM systems do, however, have some limitations in security, intelligence, planning, scheduling, quality, and logistics. This paper proposes a secure drug supply chain management framework that can acheive more security and intelligence via machine learning models. The proposed framework utilizes Bidirectional Encoder Representations from Transformers (BERT)-based and machine learning-based attack detection modules to provide more intelligence and security in blockchain-based DSCM. Evaluation results show that BERT-based recommender systems ideally suggest appropriate alternative drugs that are close to 99 % similar to the prescribed medication based on public datasets. Moreover, attack detection in the proposed framework provides significant accuracy, precision, recall, and F-measure results in threat detection (phishing, scamming, and abnormal transactions) in the blockchain layer. [ABSTRACT FROM AUTHOR]

Adaptive interactive systems can be divided into two categories: Semantic adaptations affect the system's function, and syntactic adaptations affect the presentation of information through the operator interface without modifying the system behavior. Although automation is becoming more and more important, in many situations, human operators still play an irreplaceable role, making the development of syntactic adaptations indispensable. However, existing syntactic adaptations usually do not relate to the task context, which is a critical factor to achieve syntactic adaptations. Besides, existing studies do not fully consider the operator's information perception state under highly dynamic scenarios, thus cannot dynamically prompt accurate information to the operators. Aiming at the problems above, a syntactic adaptive interactive system architecture based on perception state estimation and context segmentation is proposed in this paper. To address the real-time context segmentation, a time series segmentation algorithm is proposed, which achieves real-time estimation of the scene and produces highly interpretable results. To address the problem of dynamic perception state estimation, for the first time, the concept of a perception stack is proposed, which can be used to estimate the perception bias in the operator's working memory based on the eye movement data and generate proper prompt information according to the current context. The proposed design method of an adaptive syntactic interactive system was verified in a flight simulator. The system improves information prompts accuracy and reduces redundancy through these innovative mechanisms mentioned above. Comparative experiments confirm significant improvements in the operator's control accuracy and control stability according to our evaluation criteria. [ABSTRACT FROM AUTHOR]

To improve the average remaining energy of the network, reduce the routing overhead, extend the network lifecycle and reduce the average end-to-end delay, a new multi-frequency communication routing protocol for mobile Internet of things device terminal wireless network is proposed. Construct the topology of a multi-frequency wireless communication network and measure and analyze its routing; According to the routing measurement results, the communication routing cluster head is elected; The RPBUC algorithm is used to establish the wireless communication energy consumption model, and the greedy algorithm is used to establish the wireless network communication data transmission mechanism. Based on the wireless network communication energy consumption model and the wireless network communication data transmission mechanism, the ant colony algorithm is used to select the optimal wireless network multi-frequency communication routing protocol. The experimental results show that the average network residual energy of the protocol is greater than 0.01 J, the routing overhead is kept within 0.2, the network life cycle is prolonged, and the average end-to-end delay is effectively reduced. [ABSTRACT FROM AUTHOR]

In the process of engineering project construction, the balanced allocation of resources has an important impact on the purchase of actual materials, the progress of the site construction and the arrangement of temporary facilities. Although there have been many studies on the use of evolutionary computation (EC) to solve the fixed duration of the resource-leveling problem, the optimization effect of standard EC to solve the resource-balancing problem in large-scale network design planning is reduced due to the phenomenon of premature convergence of PSO and the complexity of large-scale network planning. Therefore, in this paper, an adaptive dissipative particle swarm optimization (ADPSO) algorithm is used to solve the resource balancing optimization problem for different network-plans scales, and the feasibility of the developed model is verified using four different scaled network plans (databases). At the same time, a solution to the dynamic resource-leveling problem with optimization for a fixed duration is proposed. The results show that the proposed models are suitable for solving the problem of resource-leveling with a fixed duration of optimization of different scale network plans, and their accuracy and stability are significantly improved compared to the state-of-the-art approaches. Moreover, the proposed models are accurate and suitable for combining the calculation method of network planning time parameters with the ADPSO algorithm to realize dynamic resource balancing optimization. [ABSTRACT FROM AUTHOR]

This paper introduces a novel and complete framework for solving different Internet of Things (IoT) applications, which explores eXplainable AI (XAI), deep learning, and evolutionary computation. The IoT data coming from different sensors is first converted into an image database using the Gamian angular field. The images are trained using VGG16, where XAI technology and hyper-parameter optimization are introduced. Thus, analyzing the impact of the different input values in the output and understanding the different weights of a deep learning model used in the learning process helps us to increase interpretation of the overall process of IoT systems. Extensive testing was conducted to demonstrate the performance of our developed model on two separate IoT datasets. Results show the efficiency of the proposed approach compared to the baseline approaches in terms of both runtime and accuracy. [ABSTRACT FROM AUTHOR]

The growth of media services, multimedia conferencing, interactive distance learning, and distributed interactive simulations is becoming more dependent on the security of multicast communication over 5 G and 6 G networks. In order to ensure the security and efficacy of multicast communication, our research came up with the idea of combining multicast public-key encryption with digital signatures known as "Multi-Receiver Signcryption (MRSC)." As compared to multicast encryption and signature primitives, MRSC significantly improves the effectiveness of secure information delivery through multicast communication over 5 G and 6 G networks. In this paper, we first provide the formal model of MRSC schemes used in Public Key Infrastructure, Identity-based Cryptography, and Certificateless Cryptography. Secondly, we present a typology of MRSC, as well as a summary of an in-depth investigation of the qualities of security, the cost of computing, and the overhead of communication over the networks. [ABSTRACT FROM AUTHOR]

Cyberbullying is disturbing and troubling online misconduct. It appears in various forms and is usually in a textual format in most social networks. Intelligent systems are necessary for automated detection of these incidents. Some of the recent experiments have tackled this issue with traditional machine learning models. Most of the models have been applied to one social network at a time. The latest research has seen different models based on deep learning algorithms make an impact on the detection of cyberbullying. These detection mechanisms have resulted in efficient identification of incidences while others have limitations of standard identification versions. This paper performs an empirical analysis to determine the effectiveness and performance of deep learning algorithms in detecting insults in Social Commentary. The following four deep learning models were used for experimental results, namely: Bidirectional Long Short-Term Memory (BLSTM), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Recurrent Neural Network (RNN). Data pre-processing steps were followed that included text cleaning, tokenization, stemming, Lemmatization, and removal of stop words. After performing data pre-processing, clean textual data is passed to deep learning algorithms for prediction. The results show that the BLSTM model achieved high accuracy and F1-measure scores in comparison to RNN, LSTM, and GRU. Our in-depth results shown which deep learning models can be most effective against cyberbullying when directly compared with others and paves the way for future hybrid technologies that may be employed to combat this serious online issue. [ABSTRACT FROM AUTHOR]

With the development of information technology, the high-speed private data stream encryption transmission system is more and more widely used in the field of education. The high-speed private data stream encryption transmission system can realize high-speed and safe data transmission and protect the privacy and security of user data. To protect the security of private data in the online education of specialty "traffic engineering", an encryption transmission system for high-speed private data stream is designed. After the online education system and core modules of traffic engineering are analyzed, the system framework is designed through the codec module and the high-speed privacy data stream processing control and transmission module. The sliding window segmentation method is used to extract the privacy data in the education system and send it to the coding sub-module. Based on a homomorphic encryption algorithm, a private data stream encryption and decryption model is established. The key encoding is designed by the vector quantization coding method. The private data is authenticated according to the characteristics of the key, and the data encryption transmission is completed through the microcontroller. The experimental results show that the encrypted data of the designed system has only 0.01 Gbit loss, and the encryption time is only 93ms. The data dimension displayed after encryption is relatively scattered, and the distribution probability of encrypted data is between 1500–2000, which can effectively encrypt the private data in the online education system of transportation engineering specialty, and improve the security of high-speed private data flow in the online education system of transportation engineering specialty. [ABSTRACT FROM AUTHOR]

There are some problems in the quality evaluation of network distance education, such as the large error in the quantitative results of the evaluation indicators, the low accuracy of the quality evaluation and the large error in the indicator's weight distribution. Therefore, a quantitative evaluation method of NDE reliability based on Back Propagation (BP) neural networks and fuzzy comprehensive evaluation is proposed. From the perspective of students, teachers and schools, the primary and secondary indicators of teaching evaluation are constructed, and the reliability evaluation indicators system of teaching quality is established. The fuzzy comprehensive evaluation method is used to calculate the membership degree of the evaluation indicators, the consistency verification method is used to determine the consistency of the indicator's attributes, and the quantitative research of the indicators data is completed by the weight calculation method to improve the accuracy of the quantitative results. BP neural network is used to construct the input layer, hidden layer and output layer of network distance education quality reliability evaluation indicators, calculate the weight of evaluation indicators, transform the input evaluation indicators data through linear conversion function, construct the indicators evaluation model, and correct the evaluation results with the help of loss function to improve the accuracy of quality evaluation results. The experimental results show that the evaluation result error of the proposed method is relatively small, with an error of less than 0.3%, and the highest evaluation accuracy reaches 96.3%, which can effectively improve the quantitative evaluation effect of the reliability of network remote teaching quality. [ABSTRACT FROM AUTHOR]

Simultaneously, the application of resilient distributed datasets (RDD) in cloud computing provides a good environment for data analysis of big data. In addition, the combination of Machine Learning (ML) algorithms of the edge computing paradigm and the SFUP-SP algorithm may be able to also be used to improve local computing capabilities and speed up data analysis and user decision-making. [ABSTRACT FROM AUTHOR]

Federated learning is becoming a practical solution for machine learning (ML) in industry. This is due to the possibility of implementing artificial intelligence (AI) systems and training its models on private data sets. However, this is not an ideal solution as it is possible to manipulate or even intercept the model during its transmission between the server and workers. In this paper, we propose a solution to ensure the security of the model transmitted between units in FL. The given model is encrypted with AES, DES, RSA algorithms, then a checksum is determined. This checksum with a private key is stored as a transaction on a blockchain. In the case of sending the model and its modification, the recipient can easily verify whether it is correct. The proposed solution has been described, tested, and compared to indicate its advantages and disadvantages. Conducted experiments were based on analyzing the communication time between participants, the accuracy of machine learning models, and attack detection. In terms of attack detection on the blockchain, we reached 81% thanks to the checksum mechanism. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is a prominent cause of blindness among elderly people and has become a global medical problem over the last few decades. There are several scientific and medical approaches to screen and detect this disease, but most of the detection is done using retinal fungal imaging. The present study uses principal component analysis based deep neural network model using Grey Wolf Optimization (GWO) algorithm to classify the extracted features of diabetic retinopathy dataset. The use of GWO enables to choose optimal parameters for training the DNN model. The steps involved in this paper include standardization of the diabetic retinopathy dataset using a standardscaler normalization method, followed by dimensionality reduction using PCA, then choosing of optimal hyper parameters by GWO and finally training of the dataset using a DNN model. The proposed model is evaluated based on the performance measures namely accuracy, recall, sensitivity and specificity. The model is further compared with the traditional machine learning algorithms—support vector machine (SVM), Naive Bayes Classifier, Decision Tree and XGBoost. The results show that the proposed model offers better performance compared to the aforementioned algorithms. [ABSTRACT FROM AUTHOR]

This paper introduces a novel framework for identifying a group of intrusions in the context of the Internet of Things (IoT). It combines both deep learning and decomposition. A set of data is first collected and a recurrent neural network is used to estimate the different individual intrusions. These individual intrusions are then used to identify a group of outliers based on a decomposition strategy. As case studies, the proposed solutions have been experimentally evaluated using two computer network intrusion datasets, namely (1) IDS 2018, and (2) LUFlow. The results show the benefits of the proposed framework and clear superiority in comparison to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Edge service computing is an emerging paradigm for computing, storage, and communication services to optimize edge framework latency and cost based on mobile edge computing (MEC) devices. The devices are battery-enabled and have limited communication and computation resources. X consolidation is a major issue in distributed heterogeneous MEC orchestrations, where X represents the task scheduling/device selection/channel selection/offloading strategy. The network entities need to enhance network performance under uncertain circumstances for such orchestrations. Haphazard X consolidation leads to abnormal resource and energy usage, quality of service (QoS) and latency of the edge framework. However, this study concentrates on analysing the impact of reinforcement learning-based edge resource consolidation models. The models are classified according to functionality, including device resource management, service request allocation, device selection, and offloading types. Finally, the article discusses and highlights some unresolved challenges for further study on MEC orchestration to enhance offloading strategy and resource management, as well as device and channel selection efficiency. [ABSTRACT FROM AUTHOR]

A machine learning algorithm that can solve complex tasks by leveraging information through transfer learning while avoiding catastrophic forgetting of previously learned data. This clearly is a principal milestone to achieving human-level intelligence. The exponential growth of the Industrial Internet of Things (IIoT) has warranted an urgent need for reliable security solutions. In this paper, a novel deep progressive algorithm leveraging, both, progressive learning and deep neural networks has been proposed to achieve this. The numerous threats faced by IIoT devices are accurately classified by the proposed Deep Progressive Neural Network (DPNN), and new classes are efficiently added to the previously trained network by employing prior knowledge via lateral connections to the previously learned network. Through robust experimentation, it is shown that the DPNN model improves the efficiency and reliability of the classification of attacks and that the proposed architecture provides an accuracy of 94% compared to the 69.7% accuracy of the contemporary KNN model. [ABSTRACT FROM AUTHOR]

To achieve substrate specificity, protein phosphate 1 (PP1) forms holoenzymes with hundreds of regulatory and inhibitory proteins. Inhibitor-3 (I3) is an ancient inhibitor of PP1 with putative roles in PP1 maturation and the regulation of PP1 activity. Here, we show that I3 residues 27–68 are necessary and sufficient for PP1 binding and inhibition. In addition to a canonical RVxF motif, which is shared by nearly all PP1 regulators and inhibitors, and a non-canonical SILK motif, I3 also binds PP1 via multiple basic residues that bind directly in the PP1 acidic substrate binding groove, an interaction that provides a blueprint for how substrates bind this groove for dephosphorylation. Unexpectedly, this interaction positions a CCC (cys-cys-cys) motif to bind directly across the PP1 active site. Using biophysical and inhibition assays, we show that the I3 CCC motif binds and inhibits PP1 in an unexpected dynamic, fuzzy manner, via transient engagement of the PP1 active site metals. Together, these data not only provide fundamental insights into the mechanisms by which IDP protein regulators of PP1 achieve inhibition, but also shows that fuzzy interactions between IDPs and their folded binding partners, in addition to enhancing binding affinity, can also directly regulate enzyme activity. Protein phosphatase 1 (PP1) is regulated by intrinsically disordered proteins like inhibitor-3, I3. The authors show that I3 does not inhibit PP1 by forming a rigid complex but instead by binding dynamically with its active site metals, showing how flexibility is used in biology. [ABSTRACT FROM AUTHOR]

The Industrial Internet of Things (IIoT) promises to deliver innovative business models across multiple domains by providing ubiquitous connectivity, intelligent data, predictive analytics, and decision-making systems for improved market performance. However, traditional IIoT architectures are highly susceptible to many security vulnerabilities and network intrusions, which bring challenges such as lack of privacy, integrity, trust, and centralization. This research aims to implement an Artificial Intelligence-based Lightweight Blockchain Security Model (AILBSM) to ensure privacy and security of IIoT systems. This novel model is meant to address issues that can occur with security and privacy when dealing with Cloud-based IIoT systems that handle data in the Cloud or on the Edge of Networks (on-device). The novel contribution of this paper is that it combines the advantages of both lightweight blockchain and Convivial Optimized Sprinter Neural Network (COSNN) based AI mechanisms with simplified and improved security operations. Here, the significant impact of attacks is reduced by transforming features into encoded data using an Authentic Intrinsic Analysis (AIA) model. Extensive experiments are conducted to validate this system using various attack datasets. In addition, the results of privacy protection and AI mechanisms are evaluated separately and compared using various indicators. By using the proposed AILBSM framework, the execution time is minimized to 0.6 seconds, the overall classification accuracy is improved to 99.8%, and detection performance is increased to 99.7%. Due to the inclusion of auto-encoder based transformation and blockchain authentication, the anomaly detection performance of the proposed model is highly improved, when compared to other techniques. [ABSTRACT FROM AUTHOR]

Vehicular delay-tolerant networks follow a store–carry–forward mechanism to overcome the state of broken links between source and destination, which is crucial for autonomous vehicle networks. These networks depend upon the mobility of vehicular-relay nodes, which can adopt the store–carry–forward arrangement and provide consent to utilize their resources for packet forwarding. In reality, vehicular-relay nodes drop packets because of a lack of resources and selfish behavior, leading to potential failures in networks. The reason for this failure in performance is the absence of an efficient relay node selection strategy. Typically, vehicular delay networks can provide communication solutions in challenging conditions when other traditional networks fail to perform due to disconnection. However, if the routing strategy does not consider nodes' selfish nature and relay nodes' inefficiency, packet drops continue, and the approach will fail to perform. This paper proposes a routing strategy, known as the best-choice vehicular-relay selection strategy for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) transmission, to overcome this breakdown situation. The proposed strategy selects the best-performing vehicular-relay nodes and restricts the packet replication to low-performing vehicular nodes. The proposed routing strategy selects the best-choice relay nodes based on their past performance. Numerical analysis and our simulation results show that the proposed approach outperforms some of the leading routing strategies in its class by increasing the delivery probability, decreasing the overhead ratio, average latency, and the number of dropped packets in the vehicular network. [ABSTRACT FROM AUTHOR]

In recent years, social media has become a ubiquitous and integral part of social discourse. Homophily is a fundamental topic in network science and can provide insights into the flow of information and behaviours within society. Homophily mainly refers to the tendency of similar-minded people to interact with one another in social groups than with dissimilar-minded people. The study of homophily has been very useful in analyzing the formations of online communities. In this paper, we review and survey the effects of homophily in social networks and summarize the state-of-art methods that have been proposed in the past recent years to identify and measure those effects in multiple types of social networks. We conclude with a critical discussion of open challenges and directions for future research. [ABSTRACT FROM AUTHOR]

Massive urbanization and resource scarcity are global phenomena for which researchers around the world see urban transformation into a smart city as the most viable solution. Yet urban planners face many hurdles in transforming cities. These include economic factors such as the high cost of infrastructure development and maintenance, social paradigms, governance, and environmental issues that limit government ambitions. To design an optimal strategy for creating a smart city, the various barriers must be identified and prioritized. The various barriers to the successful implementation of the smart city mission were identified using an extensive literature review and expert opinions. To understand the complex interdependencies among these barriers, the interpretive structural modeling method (ISM) was used. MICMAC analyzed the ISM model to classify the barriers. Indian cities vary greatly in terms of infrastructure, size, population, and available facilities. Therefore, the impact of the barriers and their interdependencies also vary. The author has extended the study and used the fuzzy approach MICMAC to improve the model by incorporating the variations observed when the city category changes. This study will help urban developers and planners to identify the relationship between barriers and design strategic planning to make the city smarter. [ABSTRACT FROM AUTHOR]

Cloud computing provides a service-oriented computing model to cloud users on a metered basis. Most of the cloud data centers are running on fossil fuels. It elevates the carbon emissions to the environment. Green cloud computing is the fusion of greenness in cloud computing to address the issues related to energy consumption and environmental sustainability. Virtual machine (VM) consolidation and live migration can provide standard solutions to energy consumption. The selection of VM for migration is a vital task. It should be performed effectively to trade-off between energy consumption and service level agreement violation (SLAV). The research activity in this article focuses on a new VM selection policy that chooses VM with high energy consumption and small size. Real-world workload traces were used to evaluate the performance of the proposed MECpVmS VM selection policy. Using CloudSim simulation, the MECpVmS VM selection policy has been implemented and assessed with existing VM selection policies. The results show an overall improvement in energy efficiency, energy consumption, SLAV. [ABSTRACT FROM AUTHOR]

Emerging technologies such as network function virtualization and software-defined networking (SDN) have made a phenomenal breakthrough in network management by introducing softwarization. The provision of assets to each virtualized network functions autonomously as well as efficiently and searching for an optimal pattern for traffic routing challenges are still under consideration. Unfortunately, the traditional methods for estimating the desired performance indicators are insufficient for a self-driven SDN. In the last decade, a combination of machine learning and cognitive techniques construct a knowledge plane (KP) for the Internet which introduces numerous benefits to networking, like automation and recommendation. Furthermore, the inclusion of KP to the conventional three planes SDN architectures recently has added another knowledge defined networking (KDN) architecture to drive an SDN autonomously. In this article, a self-driving system has been proposed based on KDN to achieve the selection of an optimal path for the deployment of service function chaining (SFC) and reactive traffic routing among the edge clouds. Considering the limited resource of edge clouds, the proposed system also maintains a balance among edge cloud resources while orchestrating SFC resources. The graph neural network has been also applied in the proposed system to recognize the composite relationship concerning topology, traffic features, and routing patterns for accurate estimation of key performance indicators. The proposed system improves resource utilization efficiency for SFC deployment by 20%, maximum network throughput by 5%, and CPU load by 13%. [ABSTRACT FROM AUTHOR]

Big Data applications require extensive resources and environments to store, process and analyze this colossal collection of data in a distributed manner. Containerization with cloud computing provides a pertinent remedy to accommodate big data requirements, however requires a precise and appropriate load-balancing mechanism. The load on servers increases exponentially with increased resource usage thus making load balancing an essential requirement. Moreover, the adjustment of containers accurately and rapidly according to load as per services is one of the crucial aspects in big data applications. This study provides a review relating to containerized environments like Docker for big data applications with load balancing. A novel scheduling mechanism of containers for big data applications established on Docker Swarm and Microservice architecture is proposed. The concept of Docker Swarm is utilized to effectively handle big data applications' workload and service discovery. Results shows that increasing workloads with respect to big data applications can be effectively managed by utilizing microservices in containerized environments and load balancing is efficiently achieved using Docker Swarm. The implementation is done using a case study deployed on a single server and then scaled to four instances. Applications developed using containerized microservices reduces average deployment time and continuous integration. [ABSTRACT FROM AUTHOR]

Tropical cyclones that originate from the Indian Ocean affect the Indian Sub-Continent. Heavy rainfall and flooding occur because of these cyclones. South Odisha was affected by Cyclonic Storm Daye in September 2018 and Cyclonic Storm Titli was occurred in August affecting Andhra Pradesh and Odisha as well. The Eastern portion of India was affected by the Cyclonic Storm Fani in April 2019. In May 2020, West Bengal was affected by the Amphan which is a Super Cyclonic Storm and in the same year Tamil Nadu was affected by the very severe Cyclonic Storm Nivar in November 2020. These are just a few of the notable cyclonic events in the Indian Sub-Continent. These cyclonic events cause a dramatic change in a very short time from dry soil to exceptional flooding. In this proposed work, we are attempting to create an observations-driven prediction model to quantify the soil moisture variations daily, predict county-based meteorology and evaluate the cause of cyclones and heavy rainfall in certain areas of India. In our work, we applied a deep learning-based methodology to predict soil moisture. For the prediction model, we fused Feed Forward Neural Networks with the Gated Recurrent Unit (GRU) model and present the prediction results. We have used climatic as well as environmental data published by the Indian Meteorological Department (IMD) Warning from 2011. The collected data is time-series data. Comparisons and the relationship that exists between soil moisture and meteorological data are made and analyzed. The soil moisture of the South Indian states Karnataka, Andhra Pradesh and Tamil Nadu are predicted from weather data using a hybrid deep learning model. The evaluations of the proposed work using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and R-squared (R2) against Non-hybrid Neural Network models such as Artificial Neural Networks (ANN), Convolutional Neural Networks, and Gated Recurrent Unit (GRU) models is analyzes where our model has given better results. [ABSTRACT FROM AUTHOR]

To improve the ability of natural language information processing in mobile communication networks, a system based on recurrent neural networks (RNN) is designed. The feedback connection is transformed into a hidden layer pointing to the input layer. According to the physiological process of human speech and the acoustic characteristics of a speech signal, a model is designed using an excitation model, channel model, and radiation model, respectively. The experimental results show that the information processing accuracy of the designed system is high and the processing time is short. [ABSTRACT FROM AUTHOR]

In the Internet of Medical Things (IoMT), collaboration among institutes can help complex medical and clinical analysis of disease. Deep neural networks (DNN) require training models on large, diverse patients to achieve expert clinician-level performance. Clinical studies do not contain diverse patient populations for analysis due to limited availability and scale. DNN models trained on limited datasets are thereby constraining their clinical performance upon deployment at a new hospital. Therefore, there is significant value in increasing the availability of diverse training data. This research proposes institutional data collaboration alongside an adversarial evasion method to keep the data secure. The model uses a federated learning approach to share model weights and gradients. The local model first studies the unlabeled samples classifying them as adversarial or normal. The method then uses a centroid-based clustering technique to cluster the sample images. After that, the model predicts the output of the selected images, and active learning methods are implemented to choose the sub-sample of the human annotation task. The expert within the domain takes the input and confidence score and validates the samples for the model's training. The model re-trains on the new samples and sends the updated weights across the network for collaboration purposes. We use the InceptionV3 and VGG16 model under fabricated inputs for simulating Fast Gradient Signed Method (FGSM) attacks. The model was able to evade attacks and achieve a high accuracy rating of 95%. [ABSTRACT FROM AUTHOR]

Android is the most widely used mobile platform, making it a prime target for malicious attacks. Therefore, it is imperative to effectively circumvent these attacks. Recently, machine learning has been a promising solution for malware detection, which relies on distinguishing features. While machine learning-based malware scanners have a large number of features, adversaries can avoid detection by using feature-related expertise. Therefore, one of the main tasks of the Android security industry is to consistently propose cutting-edge features that can detect suspicious activity. This study presents a novel feature representation approach for malware detection that combines API-Call Graphs (ACGs) with byte-level image representation. First, the reverse engineering procedure is used to obtain the Java programming codes and Dalvik Executable (DEX) file from Android Package Kit (APK). Second, to depict Android apps with high-level features, we develop ACGs by mining API-Calls and API sequences from Control Flow Graph (CFG). The ACGs can act as a digital fingerprint of the actions taken by Android apps. Next, the multi-head attention-based transfer learning method is used to extract trained features vector from ACGs. Third, the DEX file is converted to a malware image, and the texture features are extracted and highlighted using a combination of FAST (Features from Accelerated Segment Test) and BRIEF (Binary Robust Independent Elementary Features). Finally, the ACGs and texture features are combined for effective malware detection and classification. The proposed method uses a customized dataset prepared from the CIC-InvesAndMal2019 dataset and outperforms state-of-the-art methods with 99.27% accuracy. [ABSTRACT FROM AUTHOR]

This research work introduces a new intelligent framework for infectious disease detection by exploring various emerging and intelligent paradigms. We propose new deep learning architectures such as entity embedding networks, long-short term memory, and convolution neural networks, for accurately learning heterogeneous medical data in identifying disease infection. The multi-agent system is also consolidated for increasing the autonomy behaviours of the proposed framework, where each agent can easily share the derived learning outputs with the other agents in the system. Furthermore, evolutionary computation algorithms, such as memetic algorithms, and bee swarm optimization controlled the exploration of the hyper-optimization parameter space of the proposed framework. Intensive experimentation has been established on medical data. Strong results obtained confirm the superiority of our framework against the solutions that are state of the art, in both detection rate, and runtime performance, where the detection rate reaches 98% for handling real use cases. [ABSTRACT FROM AUTHOR]

Large annotated datasets are needed for successful Deep Learning methodologies to achieve human-level performance. These needs restrict the impact of Deep Learning and build the necessity to create smaller and richer representative datasets that can offer a potential solution to this problem. In this paper, we propose task-specific image corpus summarization using semantic information and self-supervision. Our methodology makes use of GAN for the generation of features and leverages rotational invariance for employing self-supervision. All these objectives are facilitated on features from Resnet34. A summary can be obtained efficiently by using k-means clustering on the semantic embedding space and then selecting examples nearest to centroids. In comparison to end-to-end trained models, the proposed model does not require retraining to obtain summaries of different lengths. We also test our model by extensive qualitative and quantitative experiments. [ABSTRACT FROM AUTHOR]

Autonomous Driving Vehicle (ADV) services have become a prominent motif in intelligent vehicle technology by adapting deep learning features. Automated driverless services are a hercules task due to the dynamic driving environment and the performance is deliberately reliant on the quality of data fusion from sensors. Therefore, considering advanced 3D LiDAR sensors is essential to measure the surrounding with 360 ∘ coverage. However, accomplishing maximum autonomy is the main challenge because of debilitated and complex driving environmenst. Deep Learning (DL) based models potentially impact surrounding measures for object detection, classification, and tracking. This study describes the importance of DL-LiDAR strategies to formulate ADV research challenges followed by a comprehensive analysis of Semantic Segmentation, Data Fusion, Data Representation, Feature Extraction, Dynamic Object Detection, and Autonomous Driving-Multi-Objective Tracking mechanisms. Unlike existing review papers, we examine various deep learning influenced approaches and describe their precarious measurements. Also, we analyze the impact of systematic methods based on open-source data sets for object-x (x=classification, localization, tracking) consolidation. Most of the summaries confine scalability, and feasibility of DL techniques in ADV to accomplish an intelligent driving system without human interference. Open research problems are discussed in the last section of the article. [ABSTRACT FROM AUTHOR]

In basketball videos, the trajectories of a basketball changes rapidly. Since the visual features changes in a more homogeneous region, the frame difference method is a suitable basis for trajectory real-time tracking. However, traditional methods need a huge number of iterative calculations in a random image to find spatial feature differences to segment the basketball from to frame, resulting in tracking lag. Therefore, a real-time tracking method of basketball trajectory is designed based on an associative Markov Chain Monte Carlo (MCMC) model. From pixel illumination differences between two adjacent frames in basketball game videos, the basketball’s movement is determined, and the foreground and background of the basketball frame are separated. Then, coordinates of the basketball are detected by a Convolutional Neural Network (CNN), and the change of coordinates is used to construct a visual 2D mapping model, which calculates both angular and linear acceleration of the basketball. To solve the interaction problem of randomness and spatial variability, an associative MCMC model is designed to segment basketball images with simple conditions, and a Bayesian network is established to input parameters of the segmented basketball movement for the determination of trajectory deviation. Finally, basketball movement trends are calculated to achieve real-time tracking of the trajectory in the basketball video. The experimental results show that compared with the original running path, this method has the smallest difference in tracking trajectory error, and the estimation error does not exceed 0.2 when the false alarm rate is 100. The trajectory tracking time is always less than 2.2 seconds, indicating that it has good trajectory tracking ability. [ABSTRACT FROM AUTHOR]

HUIM has been an important issue in recent years, particularly in basket-market analysis, since it identifies useful information or goods for decision-making. Numerous research focused on extracting high-utility itemsets from datasets, revealing a tremendous amount of pattern information. This approach is incapable of providing correct choices in a short amount of time, e.g., real-time and online decision-making systems since it is difficult to extract relevant and important information in a short period of time from a huge body of found knowledge. Discovering closed patterns with high utilization (or closed pattern mining with high utility) is a market engineering method that discovers fewer but lucrative patterns. However, prior research has been unable to handle huge data, which is incompatible with today's Internet of Things (IoT) environments, where huge volumes of data are collected every second. We begin by introducing the multi-objective model for mining the closed high utility itemsets (called MCUI-Miner), which employs MapReduce frameworks of a Spark structure. To begin, the multi-objective k-means the model is used to categorize transactions based on their significant relationship to the frequency component. The MapReduce model and GA are used to examine potential and probable candidates for mining closed high-utility itemsets in a large-scale database. Experiments have shown that the proposed framework outperforms the conventional CLS-Miner in terms of runtime, memory use, and scalability. [ABSTRACT FROM AUTHOR]

The Internet of Things is made up of a set of embedded devices such as light detection sensors, ranging (LiDAR) sensors, and millimetre-wave sensors. These sensors generate a massive amount of data in which limited communication capacity is available to share a massive amount of data to Fog-based Roadside Units (RSU) for data process and analysis service. Fog-based RSU has become an emerging paradigm in intelligent transportation but needs research attention to design intelligent decision-making methods for data communication and computation at Fog-based RSU. To address these issues, we design a two-level Quantum based D2D Computation, Communication ( Q D C 2 ) approach. First, design a bandwidth allocation strategy based on spatial importance score factors to resolve embedded devices' data transmission issues. Second, design an adaptive equilibrium service offloading strategy based on device-centric measurements to assess the computation capacity and performance rate for resolving Fog-node computation consistency issues. Additionally, Fog-based RSU is interconnected with LAN helps to optimize service latency. Simulation results show that our approach achieved a high service reliability rate (79.56%), low error rate (0.9%), and an execution delay of 22.5 s for 15 devices compared to state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In order to improve the quality of online distance education and students' online learning, an intelligent online distance education decision-making method based on cloud computing is proposed. Using computing, we provide decision-making resources for online education decision-making through the resource layer; adopt the G1 deviation maximization method to calculate the combination weight, and determine the optimal decision-making scheme in combination with bipolar binary semantics and cloud model; moreover, we provide human–computer interaction windows to view the decision-making scheme at the application layer; and complete the optimal decision-making for intelligent online education by providing the management function of cloud computing services. Experimental results show that this method can effectively obtain a decision-making scheme for network education. After the application of this method, the students' learning ability and academic performance have been significantly improved. [ABSTRACT FROM AUTHOR]

When the existing methods are used to encrypt the lightweight infrared image, there is no denoising processing for the lightweight infrared image, which has the problems of low image signal-to-noise ratio, low encryption efficiency and poor encryption effect. A dual chaotic encryption method for lightweight infrared image is proposed. The discrete orthogonal wavelet transform is used to process the lightweight infrared image. The wavelet coefficients of the lightweight infrared image are estimated by improving the block singular value decomposition. The estimated high-frequency image and low-frequency image are transformed by inverse wavelet transform to complete the denoising of the lightweight infrared image. The wavelet coefficients are estimated by threshold method or minimum mean square error method, and then the noise free lightweight infrared image is obtained by inverse wavelet transform. The lightweight infrared image is encrypted by double scrambling of pixel position and bit, and the dual chaotic encryption of lightweight infrared image is realized. The experimental results show that the security coefficient of the image encrypted by this method is more than 0.8. This method has high image signal-to-noise ratio, high encryption efficiency and good encryption effect. [ABSTRACT FROM AUTHOR]

Recently, revealing more valuable information except for quantity value for a database is an essential research field. High utility itemset mining (HAUIM) was suggested to reveal useful patterns by average-utility measure for pattern analytics and evaluations. HAUIM provides a more fair assessment than generic high utility itemset mining and ignores the influence of the length of itemsets. There are several high-performance HAUIM algorithms proposed to gain knowledge from a disorganized database. However, most existing works do not concern the uncertainty factor, which is one of the characteristics of data gathered from IoT equipment. In this work, an efficient algorithm for HAUIM to handle the uncertainty databases in IoTs is presented. Two upper-bound values are estimated to early diminish the search space for discovering meaningful patterns that greatly solve the limitations of pattern mining in IoTs. Experimental results showed several evaluations of the proposed approach compared to the existing algorithms, and the results are acceptable to state that the designed approach efficiently reveals high average utility itemsets from an uncertain situation. [ABSTRACT FROM AUTHOR]

Social Opportunistic IoT (Social OppIoT) networks is a subclass of Social Internet of Things (SIoT) networks. In social OppIoT, users perform communication in a distributed manner using smart devices by regularly moving around without any communication infrastructures, making routing a strenuous process due to its highly fragile connection intermittency and device mobility. Moreover, due to the growing heterogeneous devices, problems can exist in searching for the right relay node from a massive number of devices. In this paper, a novel forwarding scheme named "A Local Betweenness Centrality Based Forwarding Technique for Social Opportunistic IoT Networks" (LBCFT) has been proposed, which uses a reduction strategy to discard the inefficient devices. LBCFT introduces a new centrality measurement called local betweenness centrality to form the significant overlapping communities of network devices to boost forwarding. Message dissemination is controlled by handling inefficient devices using a reduction strategy, which includes the node's trajectory and intra-community and inter-community centrality. The performance of LBCFT is evaluated through ONE Simulator against the existing analogous ideologies like Supernode, Geo-Routing with Angle-based Decision (GRAD), and the benchmark protocols BubbleRap, as well as PROPHET. The simulation results show that the proposed LBCFT protocol, on average, outperforms Supernode, GRAD, BubbleRap, and PROPHET by 5.22%, 36.51%, 64.12%, and 57.96% respectively, in terms of the delivery probability. [ABSTRACT FROM AUTHOR]

The world is diving deeper into the digital age, and the sources of first information are moving towards social media and online news portals. The chances of being misinformed increase multifold as our reliance on sources of information are getting ambiguous. Traditional news sources followed strict codes of practice to verify stories, whereas today, users can upload news items on social media and unverified portals without proving their veracity. The absence of any determinants of such news articles' truthfulness on the Internet calls for a novel approach to determine the realness quotient of unverified news items by leveraging technology. This study presents a dynamic model with a secure voting system, where news reviewers can provide feedback on news, and a probabilistic mathematical model is used for predicting the truthfulness of the news item based on the feedback received. A blockchain-based model, ProBlock is proposed; so that correctness of information propagated is ensured. [ABSTRACT FROM AUTHOR]

Researchers working on cancer datasets often encounter two major challenges in their data science tasks. First, the numbers of samples are often low while the numbers of features needed for extraction are high. Secondly, the existence of noise and uncertainties in datasets can cause issues with any data science related tasks. Addressing such issues is of paramount importance to researchers and consequently to society as well. In this paper, making use of Principal Component Analysis (PCA) we remove irrelevant and redundant features from known cancer datasets. We then implement a novel internal structure using a deep neural network, which is based on the radial basis function (RBF) for feature extraction. This task is followed with the selection of the most informative features, which are prepared for an adaptive neuro-fuzzy inference system (ANFIS) based on Takagi-Sugeno-Kang (TSK). The entire process considers different values of thresholds which may cause a deficient number of features for classification. As a result, in the fuzzy classifier, the number of rules will not be substantial. Finally, our proposed approach is evaluated in three cancer datasets which are COLON, ALL-AML, and LEUKEMIA. We also apply two classifiers: 1) neuro-fuzzy inference system with different types of membership functions and 2) multi-layer perceptron to classify those cancer datasets into two groups. Our strong experimental results show that our method leads to a higher accuracy when compared to a multi-layer perceptron classifier. [ABSTRACT FROM AUTHOR]

Effective vector representation has been proven useful for transaction classification and clustering tasks in Cyber-Physical Systems. Traditional methods use heuristic-based approaches and different pruning strategies to discover the required patterns efficiently. With the extensive and high dimensional availability of transactional data in cyber-physical systems, traditional methods that used frequent itemsets (FIs) as features suffer from dimensionality, sparsity, and privacy issues. In this paper, we first propose a federated learning-based embedding model for the transaction classification task. The model takes transaction data as a set of frequent item-sets. Afterward, the model can learn low dimensional continuous vectors by preserving the frequent item-sets contextual relationship. We perform an in-depth experimental analysis on the number of high dimensional transactional data to verify the developed models with attention-based mechanism and federated learning. From the results, it can be seen that the designed model can help and improve the decision boundary by reducing the global loss function while maintaining both security and privacy. [ABSTRACT FROM AUTHOR]

The rapid development of information technology accelerates the modernization of distance education. To realize the unified organization and management of learning resources as well as improve the utilization rate of resources, this paper proposes the design of a mobile online education resource sharing system from the perspective of man-machine cooperation. This paper analyzes the main body and scope of collaboration, constructs a man-machine collaborative resource sharing model with large-scale man-machine cooperation as the main model; defines the system design principle, comprehensively considers the software layering idea and user usage, and determines the overall framework including client, presentation layer and business logic layer; divides resource sharing into three stages: production, registration, audit and release, and uses "centralized management", to protect the intellectual property rights of distance education resources. The role access control mechanism is used to manage user rights, and the settlement incentive algorithm is introduced to protect the intellectual property rights of distance education resources. Our experimental results show that the system can be used as a key technology to promote the development of distance education information, improve the efficiency of resource sharing, and enhance the enthusiasm of users to contribute educational resources. [ABSTRACT FROM AUTHOR]

To observe the earth surface and its atmospheric interaction, various advanced optical and radar sensors are utilized. This observation returns a huge amount of optical multidimensional remote sensing images which may be used in multidisciplinary fields. The processing of these images in real time is a challenging task because of their high spatial resolution and complex data structure. At the same time, these images are quite confidential in various applications such as in the military and intelligence sectors. For secretly transmitting the remote sensing images in real time, a real-time cheating immune secret sharing approach is introduced in this paper. The proposed approach minimizes the time as well as space complexity for the secret sharing effectively. It also generates meaningful shares without the restriction for any fixed number participants. Generated shares by the proposed approach are cheating immune. That means they can authenticate themselves if tampered with. Experimental results show the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Image reconstruction is a mathematical process, where the image is compressed into a small representation and derived from this form. The general use of the reconstruction technique finds a place in noise removal from images obtained in medicine or other areas of life. In this paper, we propose a heuristic validation mechanism for training different types of neural networks in the problem of image reconstruction. The main idea is based on finding some important areas on image by heuristic algorithm and train network until a certain level of entropy of these areas is achieved. The mathematical model of this technique is described and supported by experimental results on different datasets with complex analysis of different heuristics. Proposed approach shows that it can reduce the average time of training process using convolutional neural networks. [ABSTRACT FROM AUTHOR]