Search

LoRaWAN (Long Range WAN) is one of the well-known emerging technologies for the Internet of Things (IoT). Many IoT applications involve simple devices that transmit their data toward network gateways or access points that, in their turn, redirect data to application servers. While several security issues have been addressed in the LoRaWAN specification v1.1, there are still some aspects that may undermine privacy and security of the interconnected IoT devices. In this paper, we tackle a privacy aspect related to LoRaWAN device identity. The proposed approach, by monitoring the network traffic in LoRaWAN, is able to derive, in a probabilistic way, the unique identifier of the IoT device from the temporal address assigned by the network. In other words, the method identifies the relationship between the LoRaWAN DevAddress and the device manufacturer DevEUI. The proposed approach, named DEVIL (DEVice Identification and privacy Leakage), is based on temporal patterns arising in the packets transmissions. The paper presents also a detailed study of two real datasets: i) one derived by IoT devices interconnected to a prominent network operator in Italy; ii) one taken from the literature (the LoED dataset in Bhatia et al. (2020)). DEVIL is evaluated on the first dataset while the second is analyzed to support the hypothesis under the DEVIL operation. The results of our analysis, compared with other literature approaches, show how device identification through DEVIL can expose IoT devices to privacy leakage. Finally, the paper also provides some guidelines to mitigate the user re-identification threats.

Data quality is considered to be among the greatest challenges in research on covert networks. This study identifies six aspects of network data collection, namely nodes, ties, attributes, levels, dynamics, and context. Addressing these aspects presents challenges, but also opens theoretical and methodological opportunities. Furthermore, specific issues arise in this research context, stemming from the use of secondary data and the problem of missing data. While each of the issues and challenges has some specific solution in the literature on organized crime and social networks, the main argument of this paper is to try and follow a more systematic and general solution to deal with these issues. To this end, three potentially synergistic and combinable techniques for data collection are proposed for each stage of data collection – biographies for data extraction, graph databases for data storage, and checklists for data reporting. The paper concludes with discussing the use of statistical models to analyse covert networks and the cultivation of relations within the research community and between researchers and practitioners.

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify demand flexibility using an efficient tool called time-varying elasticity, whose value may change depending on the prices and decision dynamics. This tool is particularly useful for evaluating the demand response potential and system reliability. Recent empirical evidences have highlighted some abnormal features when studying demand flexibility, such as delayed responses and vanishing elasticities after price spikes. Existing methods fail to capture these complicated features because they heavily rely on some predefined (often over-simplified) regression expressions. Instead, this paper proposes a model-free methodology to automatically and accurately derive the optimal estimation pattern. We further develop a two-stage estimation process with Siamese long short-term memory (LSTM) networks. Here, a LSTM network encodes the price response, while the other network estimates the time-varying elasticities. In the case study, the proposed framework and models are validated to achieve higher overall estimation accuracy and better description for various abnormal features when compared with the state-of-the-art methods., Comment: Author copy of the manuscript submitted to IEEE Trans on Power Systems

In the era of big data, an important weapon in a machine learning researcher’s arsenal is a scalable support vector machine (SVM) algorithm. Traditional algorithms for learning SVMs scale superlinearly with the training set size, which becomes infeasible quickly for large data sets. In recent years, scalable algorithms have been designed which study the primal or dual formulations of the problem. These often suggest a way to decompose the problem and facilitate development of distributed algorithms. In this paper, we present a distributed algorithm for learning linear SVMs in the primal form for binary classification called the gossip-based subgradient (GADGET) SVM. The algorithm is designed such that it can be executed locally on sites of a distributed system. Each site processes its local homogeneously partitioned data and learns a primal SVM model; it then gossips with random neighbors about the classifier learnt and uses this information to update the model. To learn the model, the SVM optimization problem is solved using several techniques, including a gradient estimation procedure, stochastic gradient descent method, and several variants including minibatches of varying sizes. Our theoretical results indicate that the rate at which the GADGET SVM algorithm converges to the global optimum at each site is dominated by an [Formula: see text] term, where λ measures the degree of convexity of the function at the site. Empirical results suggest that this anytime algorithm—where the quality of results improve gradually as computation time increases—has performance comparable to its centralized, pseudodistributed, and other state-of-the-art gossip-based SVM solvers. It is at least 1.5 times (often several orders of magnitude) faster than other gossip-based SVM solvers known in literature and has a message complexity of O(d) per iteration, where d represents the number of features of the data set. Finally, a large-scale case study is presented wherein the consensus-based SVM algorithm is used to predict failures of advanced mechanical components in a chocolate manufacturing process using more than one million data points. This paper was accepted by J. George Shanthikumar, big data analytics.

The field of cryptography has endeavored to solve numerous security problems. However, a common premise of many of those problems is that the encryptor always generates the ciphertext correctly. Around 10 years ago, this premise was not a problem. However, due to the rapid development and the use of the cloud, which has introduced various access policies and functionalities to provide higher security, it is not correct to assume that this premise is always applied. A "Fake Policy Attack", which we introduce in this paper, is an attack that incorrectly sets the access policy of the ciphertext against the system rules so that users who do not meet the rules can decrypt the ciphertext. In other words, it is an attack that ignores the rules of the system and eventually breaks the security and leaks information. This attack can be more critical for the application environments that require strong security not to leak any related information about ciphertext. In this paper, we demonstrate the possible threat of the Fake Policy Attack by providing two relevant examples. Then, we propose a scheme called Policy Authenticable ABE (PA-ABE) to resolve this issue. We provide a formal security analysis of the proposed scheme and performance evaluation results based on our implementation.

The full potential of IoT data is often unrealized because data are restricted to single-purpose use-cases or accessible to a few, siloed users. The opportunities are significantly greater when data can be shared using a marketplace concept. This provides a framework where many suppliers of data can interact with consumers of data, such as AI developers and IoT service providers. Their marketplace interactions provide a means to identify demand for specific types of data and, to incentivize suppliers to offer high quality and dependable data. Standardization is a pre-requisite for an effective marketplace in terms of setting the rules for interactions and in establishing a technical baseline for data supply and consumption. This paper introduces an IoT data marketplace framework and illustrates its application through a set of smart city and intelligent transport system deployments. It highlights use of oneM2M, which is an open standard for the middleware layer in the IoT technology stack. oneM2M’s middleware capabilities reside between IoT devices and communications networks and, the AI/ML and IoT applications that consume IoT data. The proposed IoT data marketplace also includes licensing, usage tracking and secured data sharing features. These provide marketplace users with the tools to control data sharing and monetization. Through reference to multiple deployments of the IoT data marketplace, the paper highlights the benefits of standardization for replicable solutions in multiple IoT segments, interoperability, and business model innovation involving multi-stakeholder ecosystems.

This paper intends to provide an analysis of sound and voice technologies for speech-impaired people regarded as sites of knowledge production about disability. The study will focus on the case of Google’s project to reunite speech-impaired users with their voices using voice cloning technology, an evolution of speech synthesis that allows the reconstruction of the sonic and timbral characteristics of a person’s voice. Addressing both the narratives and representations – which reveal a medical model of disability as an external flaw to be cured through technology – and the material practices and operations enacted by those technologies – which highlight epistemologies of human variation, embodiment and accessibility built into the software –, the paper shows that disability as a social construct is co-constituted in the interaction of these levels. In this regard, the following research proposes a socio-technical model of disability theorisation that combines techno-scientific knowledge, cultural values, images of the user, material operations and organisational practices. From this perspective, the paper argues that the study of disabilities would benefit from the contribution of organisation studies and media studies in order to reveal the ‘constructedness’ of disability and able-bodiedness, and the role of media technologies, institutions, and representations in producing and upholding – as well as potentially challenging – such constructions.

With the advent of advanced technology, the IoT has made possible the connection of numerous devices that can collect vast volumes of data. Hence, the demands of IoT security is paramount. Cryptography is being used to secure the authentication, confidentiality, data integrity and access control of networks. However, due to the many constraints of IoT devices, traditional cryptographic protocols are no longer suited to all IoT environments, such as the smart city. As a result, researchers have been proposing various lightweight cryptographic algorithms and protocols to secure data on IoT networks. This paper discusses state-of-the-art lightweight cryptographic protocols for IoT networks and presents a comparative analysis of popular contemporary ciphers. In doing so, it has classified the most current algorithms into two parts: symmetric and asymmetric lightweight cryptography. Additionally, we evaluate several recently developed block cipher and stream cipher algorithms in terms of their security. In the final section of this paper, we address the changes that need to be made and suggest future research topics.

Neural networks-based soft sensors are wildly employed in the industrial process. Such models have great significance to smart manufacturing. Considering the strict requirements of industrial production, it is vital to ensure the safety and robustness of these models in their actual deployment. However, recent researches have shown that neural networks are quite vulnerable to adversarial attacks. By imposing tiny perturbation to original sample, the fabricated adversarial sample can cheat these models to make wrong decisions. Such phenomenon may bring serious trouble to the practical application of soft sensors. This paper focuses on the adversarial attacks on industrial soft sensors. For the first time, we verify and analyze the effectiveness and deficiencies of existing attack methods in the industrial soft sensor scenario. Based on solving these defects, this paper proposed a novel perspective for attacking soft sensors. We analyzed the optimization mechanism behind this new idea, then designed two algorithms to perform attacks. The proposed methods more conform to the actual situation. Besides, compared with existing approaches, the proposed methods have potentials to cause severer damages since their attacks are not only more concealed but also more likely to cheat the technicians to execute wrong operations. The researches and analyses of the proposed methods lay a solid foundation for more thorough defenses against various attacks, which is quite necessary for making the deployed soft sensors more robust and secure.

Cloud Computing is an alternative to conventional IT Outsourcing. As a result, cloud computing migration between organizations is rapidly growing. The adoption of this technology brings many positive aspects but prescribes various risks and concerns. An organization that officially provides its cloud computing services to external providers and implies that its IT functions and process are outsourced to third-party providers of BPO services. For privacy-making public audit processes in dynamic cloud data storage, a modified Boneh-Lynn-Shachame Dynamic Auditing (MBLSDA) algorithm is suggested in this paper. The proposed algorithm executes an audit process for multiple users based on a batch audit simultaneously and effectively to enable Third Party Auditing (TPA). This paper integrates the homomorphic authenticator in an algorithm of dynamic signing audit by random marking in terms of the privacy conserving public auditing process. When the user of cloud service, store or update the data, it encrypts using Rijndal algorithm, and Boneh-Lynn-Shacham signature generation is used for key generation. Finally, a hybrid of these a proposed Modified Boneh-Lynn-Shacham Signing Dynamic audit the data to provide the security.

With today's rapidly-evolving cloud landscape embracing continuous integration and delivery, users of cloud systems must monitor software running on their containers and virtual machines (VMs) to ensure compliance, security, and efficiency. Traditional solutions to this problem rely on manually-created rules that identify software installations and modifications, but these require expert authors and are often unmaintainable. Recently, automated techniques for software discovery have emerged. Some techniques use examples of software to train machine learning models to predict which software has been installed on a system. Others leverage knowledge of packaging practices to aid in discovery without requiring any pre-training, but these practice-based methods cannot provide precise-enough information to perform discovery by themselves. This paper introduces Praxi, a new software discovery method that builds upon the strengths of prior approaches by combining the accuracy of learning-based methods with the efficiency of practice-based methods. In tests using samples collected on real-world cloud systems, Praxi correctly classifies installations at least 97.6% of the time, while running 14.8 times faster and using 87% less disk space than a similar learning-based method. Using a diverse software dataset, this paper quantitatively compares Praxi to systematic rule-, learning-, and practice-based methods, and discusses the best uses for each.

Warhead power assessment of the anti-ship missile plays a vital role in determining the optimal design of missile, thus having important strategic research significance. However, in the assessment process, expert’s judgement will directly affect the assessment accuracy. In addition, there are many criteria involved in the missile design alternatives. Some criteria with poor performance may be compensated by other criteria with excellent performance, and then it is impossible to find the truly optimal alternative. Aimed at solving these problems, this paper proposes a synthetical assessment process based on fuzzy hesitant linguistic term set and the Gained and Lost Dominance Score (GLDS) method. In order to improve the assessment accuracy of experts and solve the problem that experts generate different opinions, combined with the advantages of fuzzy hesitant sets and linguistic term sets, the double hierarchy hesitant fuzzy linguistic term sets are used in this paper to improve the accuracy of expert’s judgement. In order to effectively combine expert’s experience with the data of criteria, the evidence theory and entropy weight method are used to transfer the expert’s judgement to the weight. In order to avoid selecting defective alternative of missile design, the GLDS is used to fuse expert information and criteria information. Sensitivity analysis shows that the assessment process has sensitivity to some extent. However, when the fluctuation of expert’s assessment makes the fluctuation of θ in the range of −5% to 5%, the impact on the results is not quite conspicuous. The analysis of calculation result and comparative analysis show that the assessment process proposed in this paper is accurate enough, has great advantage in selecting the current and potential optimal alternative of missile design, and avoids the alternatives with low criteria performance that cannot be compensated by other criteria being selected.

This paper proposes an algorithm for signal validation using unsupervised methods in emergency situations at nuclear power plants (NPPs) when signals are rapidly changing. The algorithm aims to determine the stuck failures of signals in real time based on a variational auto-encoder (VAE), which employs unsupervised learning, and long short-term memory (LSTM). The application of unsupervised learning enables the algorithm to detect a wide range of stuck failures, even those that are not trained. First, this paper discusses the potential failure modes of signals in NPPs and reviews previous studies conducted on signal validation. Then, an algorithm for detecting signal failures is proposed by applying LSTM and VAE. To overcome the typical problems of unsupervised learning processes, such as trainability and performance issues, several optimizations are carried out to select the inputs, determine the hyper-parameters of the network, and establish the thresholds to identify signal failures. Finally, the proposed algorithm is validated and demonstrated using a compact nuclear simulator.

For the path coverage testing of a Message-Passing Interface (MPI) program, test data generation based on an evolutionary optimization algorithm (EOA) has been widely known. However, during the use of the above technique, it is necessary to evaluate the fitness of each evolutionary individual by executing the program, which is generally computationally expensive. In order to reduce the computational cost, this paper proposes a method of integrating an ensemble surrogate model's estimation into the process of generating test data. The proposed method first produces a number of test inputs using an EOA, and forms a training set together with their real fitness. Then, this paper trains an ensemble surrogate model (ESM) based on the training set, which is employed to estimate the fitness of each individual. Finally, a small number of individuals with good estimations are selected to further execute the program, so as to have their real fitness for the subsequent evolution. This paper applies the proposed method to seven benchmark MPI programs, which is compared with several state-of-the-art approaches. The experimental results show that the proposed method can generate test data with significantly low computational cost.

As a class of randomized learner model, stochastic configuration networks (SCNs) have been successfully applied in a few data analytics tasks. Given the industrial big data modeling tasks, however, the original SCNs potentially lead to excessive training time. To this end, this paper extends SCNs to a hybrid parallel version, termed HPSCNs. In the hybrid parallel learning algorithm, two SCNs are synchronously constructed. The difference between the two of them is that one employs a point-incremental algorithm, and another one adopts a block-incremental algorithm. Moreover, a data parallel method is established based on a dynamic block strategy to accelerate the establishment of candidate node pool for each SCN. Additionally, this paper proposes an adaptive hyperparameter adjustment method, which allows the hyperparameters in the supervisory mechanism to be automatically adjusted along with the learning process. Comparative experiments are first conducted through four large-scale benchmark datasets, followed by the fully discussion on the algorithm parameters. Finally, a practical industrial application case is made, where a grinding particle size soft sensor is developed based on HPSCN, showing the effectiveness of the proposed algorithm.

The extraction of text information from traffic panels is one of the challenging problems in computer vision. Although the past decade has seen a promising shift and important progress in object detection, few works and a limited number of datasets focus specifically on extracting text from traffic signs. To address the lack of data for text detection in traffic panels, especially those with Arabic scripts, this paper introduces a new multilingual and multipurpose dataset named ASAYAR. It consists of three sub-datasets: Arabic-Latin scene text localization, traffic sign detection, and directional symbol detection. The dataset contains 1763 images collected on different Moroccan highways, and annotated manually, using 16 object categories. The fully annotated ASAYAR images contains more than 20000 bounding box objects. The paper also investigates the usability of the dataset, by evaluating the performance of the state-of-the-art algorithms for object and text detection. Experimental results show good detection scores, demonstrating the potential contribution of ASAYAR in the development of methods for text extraction from traffic panels.

The main focus of the paper is to propose an artificial immune systems-based classification model for code-mixed social media data. The artificial immune systems are computational models inspired by the biological immune system. In this paper, artificial immune systems are used to optimize the initial parameters of Long short-term memory (LSTM) model. The proposed artificial immune systems-based LSTM model is then used for the classification of code-mixed data. The classification of Hindi-English code-mixed data into Hindi, English, and ambiguous words is done. Popular word embedding features were used for the representation of each word. The word embedding features and character embedding features have been used. The proposed method helps in identifying the word context by extracting the intent of user for using the ambiguous word in code-mixed sentence. Extensive experiments reveal that the artificial immune systems-based classification model outperforms competitive models especially when there are some ambiguous words in the social media data.

Many applications for the automated diagnosis of plant disease have been developed based on the success of deep learning techniques. However, these applications often suffer from overfitting, and the diagnostic performance is drastically decreased when used on test datasets from new environments. In this paper, we propose LeafGAN, a novel image-to-image translation system with own attention mechanism. LeafGAN generates a wide variety of diseased images via transformation from healthy images, as a data augmentation tool for improving the performance of plant disease diagnosis. Thanks to its own attention mechanism, our model can transform only relevant areas from images with a variety of backgrounds, thus enriching the versatility of the training images. Experiments with five-class cucumber disease classification show that data augmentation with vanilla CycleGAN cannot help to improve the generalization, i.e., disease diagnostic performance increased by only 0.7% from the baseline. In contrast, LeafGAN boosted the diagnostic performance by 7.4%. We also visually confirmed the generated images by our LeafGAN were much better quality and more convincing than those generated by vanilla CycleGAN. The code is available publicly at: https://github.com/IyatomiLab/LeafGAN., Accepted as a regular paper in the IEEE Transactions on Automation Science and Engineering (T-ASE)

The development of Wireless Sensor Networks (WSNs) has been attained in the past few years due to its important using in wide range of application. The readings of data derived from WSN nodes are not always accurate and may contain abnormal data. This paper proposed an anomaly detection and classification algorithm in WSNs. At first, an integration of Contourlet Transform (CT) algorithm and One Class Support Vector Machine (OCSVM) algorithm (CT-OCSVM) is utilized to detect outliers then Fuzzy Inference System (FIS) is used to identify the source of these outliers. The underlying aim of this paper focuses on treating the collected streams of data as raw datum of an image, which is then passed through some filters using CT to get compressed size of directional subbands coefficients. The coefficients of CT are examined by OCSVM algorithm to detect anomalies. Finally the source of anomalies is identified based on using FIS and by exploiting the spatial temporal correlation existing between the sensed data. The integrated algorithm is tested using different types of filters. Real datasets collected from a small WSN constructed in a local lab are used for testing the integrated algorithms. The simulation results have shown a high rate of accurate classification with high detection rate and low false alarm rate.

The class imbalance problem has a huge impact on the performance of diagnostic models. When it occurs, the minority samples are easily ignored by classification models. Besides, the distribution of class imbalanced data differs from the actual data distribution, which makes it difficult for classifiers to learn an accurate decision boundary. To tackle the above issues, this paper proposes a novel imbalanced data classification method based on weakly supervised learning. Firstly, Bagging algorithm is employed to sample majority data randomly to generate several relatively balanced subsets, which are then used to train several support vector machine (SVM) classifiers. Next, these trained SVM classifiers are adopted to predict the labels of those unlabeled data, and samples that are predicted as minority class are added to the original dataset to reduce the imbalance ratio. The critical idea of this paper is to introduce real-world samples into the imbalanced dataset by virtue of weakly supervised learning. In addition, bi-directional gated recurrent units (BGRU) are used to construct a diagnostic model for fault diagnosis, and a new weighted cross-entropy function is proposed as the loss function to reduce the impact of noise. Besides, it also increases the model's attention to the original minority samples. Furthermore, experimental evaluations of the proposed method are conducted on two datasets, i.e., PHM challenge 2008 and 2010 datasets, and the experimental results demonstrate the effectiveness and superiority of the proposed method.

Developing smart city applications typically faces challenges such as meeting several complex requirements, integrating heterogeneous data sources, and considering geographical information representing the real-world urban space. Smart city platforms have a key role in realizing these applications as they provide high-level services that can be (re)used by developers. Despite the existence of many platforms to support the development of smart city applications, most of them do not associate the offered services with geographical information, do not support performing semantic queries on the available data, and have limitations that may burden development tasks. This paper presents Smart Geo Layers (SGeoL), a platform for developing smart city applications. Besides integrating urban data with geographical information, SGeoL relies on an underlying middleware infrastructure and leverages it by including high-level abstractions for (i) context data management, (ii) integration of heterogeneous data, (iii) semantic support, (iv) data analysis and visualization, and (v) data security and privacy support. This paper also reports experiences on the real use of SGeoL and empirical results on the evaluation of its performance and scalability.

The virtual power plant (VPP) is a cloud-based aggregator that combines heterogeneous distributed generations (DG) to give a reliable and friendly power supply. In this paper, a VPP which consists of natural gas network, P2G equipment, flexible load and other resources is introduced in electricity market and natural gas market considering the uncertainties of renewable energy outputs and demand responses. Moreover, the optimal scheduling strategy of VPP includes power and gas dispatch considering bidirectional flows of power and gas, and the optimization model considering dual energy markets which include electricity market and natural gas market is investigated by developing different scenarios to maximize the VPPs profit. Case studies have been carried out to analyze the economy and scheduling strategy of the VPP. Simulation results show that the VPP studied in this paper can effectively reduce the proportion of renewable curtailment by selling electricity or P2G equipment. Besides, it is beneficial to maintain pressure stability and security operation of natural gas network, and the VPP could decrease unbalanced penalty cost and reduce the impact from uncertainties in dual energy markets.

Cyber attacks may cause significant damage to cyber-physical systems (CPSs). Secure control is an effective measure to resist cyber attacks. While efforts have been made in developing secure control methods, the secure control problem for fast time-varying cyber attacks has not been well investigated. This paper presents a secure control strategy for mitigating fast time-varying actuator attacks in CPSs. For attacked CPSs, a nonlinear disturbance observer (NDO) is firstly constructed to estimate the lumped uncertainty. Then, to ensure the security of attacked CPSs, a L2 gain secure controller is designed to guarantee the stability of the CPSs. It is capable of handling not only constant and slow time-varying attacks but also fast time-varying cyber attacks to a certain extent. Compared with existing secure controllers, the secure controller designed in this paper withstands attacks with a wider range of frequencies, thus enhancing the resilience of the CPSs against unknown attacks. Simulations are conducted to verify the effectiveness of the proposed secure control strategy.

In this paper, we presented a method of minimizing the number of overlapped partial products in the accumulation of four-term Karatsuba multiplication. This method reduced the summation of 13 overlapped partial products to 9 and the summation of 40 overlapped partial products to 24 in the case of four-term Karatsuba multiplication and eight-term Karatsuba multiplication, respectively. Moreover, to deal with the problem of negative multiplicands introduced by the choice in the evaluation of four-term Karatsuba multiplication, we further presented a method of converting negative multiplicands to non-negative multiplicands. In this way, our method would lead to the reduction of summation complexity and not using signed multipliers. Compared to the original Karatsuba multiplication designs, our proposed Karatsuba-like multiplication with optimal interpolation would lead to up to 7.7% reduction in ADP (area-delay-product) in ASIC implementations, and up to 20.2% reduction in ADP compared with built-in designs of Synopsys Design Compiler.

This paper presents an automated design and optimization framework for electric transportation power systems (ETPS), enabled by machine learning (ML). The use of physical models, simulations, and optimization methods can greatly aid the engineering design process. However, when considering the optimal co-design of multiple inter-dependent subsystems that span multiple physical domains, such model-based simulations can be computationally expensive, and traditional metaheuristic optimization methods can be unreliable. Bayesian optimization (BO), a ML framework, paves one feasible pathway to realize an efficient design process practically. However, current state-of-the-art BO algorithms are non-compatible or perform poorly when applied to system-level ETPS design with multiple objectives and constraints. This paper proposes a novel BO algorithm referred to as Max-value Entropy Search for Multi-objective Optimization with Constraints (MESMOC) to solve multi-objective optimization (MOO) problems with black-box constraints that can only be evaluated through design simulations. After full presentation of the algorithm, MESMOC is applied to a realistic ETPS design case using a heavy-duty electric vertical-takeoff-landing (eVTOL) urban aerial vehicle (UAV) power system. Two MOO experimental trials show a drastic reduction in the number of design simulations to discover a high-quality Pareto front. In Trial 1, MESMOC uncovered the entire Pareto front while only requiring to explore ~4% of the design space. With expanded design parameters and a larger design space in Trial 2, a near-complete but high-quality Pareto front was uncovered. Both trials compared MESMOC to the popular genetic algorithm NSGA-II and another BO algorithm PESMOC, showing superior performance.

Anomaly detection for smart contracts can effectively prevent hidden security risks such as financial fraud, illegal financing, and money laundering. Ethereum is currently the largest platform for smart contracts, and anomaly detection is imminent. However, the data related to smart contracts is huge and contains complex objects and relationships. It is impossible to extract high-order attributes and low efficiency using traditional methods. The key to reduce fraud is extracting features from complex smart contracts and effectively identifying abnormal contracts. Therefore, this paper constructs a Heterogeneous Graph Transformer Networks (S_HGTNs) suitable for smart contract anomaly detection to detect financial fraud on the Ethereum platform. To perform feature representation, this paper first extracts the features to construct a Heterogeneous Information Network (HIN) for smart contract, and uses the relationship matrix obtained from the meta-path learned in the transformer network as the input of the convolution network, and finally uses the node embedding for classification tasks. The classification results show that this model performs better than the traditional model and the standard deviation is small, which proves the effectiveness and stability of the model.

In recent years driving violations have increased in big and crowded cities specially in developing countries. This has resulted in escalation of traffic congestions and number of accidents, making them difficult to handle by a central managing authority. New technologies can be used in order to mitigate this problem. Hence, in this paper, we propose a novel concept, called self-fining vehicle, using Blockchain infrastructure on top of the Vehicular Edge Computing, VEC. Self-fining vehicle is a vehicle that detects and records driving violations, issues tickets and pays fines without the need for centralized management system. Violations can be coded into OBU and detected by vehicular communications. The conceptual architecture of secure self-fining vehicle is proposed and discussed in this paper. The proposed architecture improves violation data security, processing speed and communication delay using encryption, authentication, Blockchain and edge computing, enhancing quality of service and consumers‘ quality of experience. The performance analysis of the proposed architecture proves its efficiency in terms of latency in service delivery.

The primary goal of any financial investor is to maximize returns and minimize risks.Investment specialists and portfolio managers have to manually analyze assets, determine potential returns and risks, and adhere to client preferences to create optimal portfolios. It is a complex and gruelling process and demands significant skill and relevant experience for success. Like all other sectors in finance, machine learning models have seen tremendous success in the portfolio selection problem as well. In this paper, a thorough review of several machine learning portfolio optimization techniques such as Clustering-based, SVM based, Genetic Algorithm based, and more has been presented. This paper, in its entirety, condenses and interprets the numerous approaches and the merits and limitations corresponding to their implementation. The conclusions presented by this review can be utilized to identify the advantages of these papers. This will help future researchers in their study of the domain and ensure availability of essential data for further analysis in a systematic and comprehensive manner. With the help of this study, researchers will be well placed to identify areas that present scope for improvement and come up with novel or possibly hybrid techniques to achieve near perfection in Portfolio Selection

There has been an increased interest in the creation of AI social agents who possess complex behaviors that allow them to perform social interactions. Behavior trees provide a plan model execution that has been widely used to build complex behaviors for AI social agents. Behavior trees can be represented in the form of a memory structure known as cognitive scripts, which would allow them to evolve through further development over multiple exposure to repeated enactment of a particular behavior or similar ones. Behavior trees that share the same context will then be able to learn from each other resulting in new behavior trees with richer experience. The main challenge appears in the expensive cost of retrieving contextually similar behavior trees (scripts) from a repertoire of scripts to allow for that learning process to occur. This paper introduces a novel application of map-and-reduce technique to retrieve cognitive with low computational time and memory allocation. The paper focuses on the design of a corpus of cognitive scripts, as a knowledge engineering key challenge, and the application of map-and-reduce with semantic information to retrieve contextually similar cognitive scripts. The results are compared to other techniques used to retrieve cognitive scripts in the literature, such as Pharaoh which uses the least common parent (LCP) technique in its core. The results show that the map-and-reduce technique can be successfully used to retrieve cognitive scripts with high retrieval accuracy of 92.6%, in addition to being cost effective.

The chemical production process is a special dynamic and complex system. It has the characteristics of instability and danger, thus making safety management in the production process very difficult. To support the long-term and stable operation of the chemical process, timely and accurate fault diagnosis is very necessary. Aiming at the high-dimensional nonlinearity of chemical process data, this paper proposes a fault diagnosis method in chemical process that is based on multi-scale convolutional neural network (MsCNN) combined with matrix diagram. This model uses software to convert the pre-processed time series signal data of the chemical process into sets of matrix diagrams, and then uses the MsCNN model to accurately diagnose various types of faults in the chemical production process. Taking Tennessee Eastman (TE) process fault data set as an example, verification shows good simulation results in detection accuracy and loss. This method can create high-precision judgments on fault types, which is beneficial to timely elimination of faults and avoidance of safety accidents. The results show that the new model proposed in this paper has good potential in the field of fault diagnosis in chemical processes, and is also reliable, practical and scientific.

With the increase in volume of data and presence of structured and unstructured data in the biomedical filed, there is a need for building models which can handle complex & non-linear relations in the data and also predict and classify outcomes with higher accuracy. Deep learning models are one of such models which can handle complex and nonlinear data and are being increasingly used in the biomedical filed in the recent years. Deep learning methodology evolved from artificial neural networks which process the input data through multiple hidden layers with higher level of abstraction. Deep Learning networks are used in various fields such as image processing, speech recognition, fraud deduction, classification and prediction. Objectives of this paper is to provide an overview of Deep Learning Models and its application in the biomedical domain using R Statistical software Deep Learning concepts are illustrated by using the R statistical software package. X-ray Images from NIH datasets used to explain the prediction accuracy of the deep learning models. Deep Learning models helped to classify the outcomes under study with 91% accuracy. The paper provided an overview of Deep Learning Models, its types, its application in biomedical domain. - is paper has shown the effect of deep learning network in classifying images into normal and disease with 91% accuracy with help of the R statistical package.

Implantable internet of things medical devices (IoTMD) has drawn a disruptive transformation in the healthcare domain. It has improved the services of healthcare providers in delivering patient care. Even better, it has supported individuals that are suffering from a chronic condition in self-managing their condition. Patients diagnosed with diabetes are the leading beneficiaries of IoTMD, assisting them in maintaining their sugar level at a normal range. However, the security defense of these systems against potential cyberthreats is currently underdeveloped. Such threats must not be ignored as they can put the lives of the patients in danger. Thus, this paper proposes deep learning (DL)-based anomaly detection system composed of estimation and classification models applied to a subdomain in healthcare systems referred to as Diabetes Management Control System (DMCS). The estimation model was used to forecast the glucose level of patients at each evaluation time step, whereas the classification model is intended to detect anomalous data points. This paper implements convolutional neural network (CNN) and multilayer perceptron (MLP) algorithms for comparison purposes. Moreover, considering that the dataset contains sensitive physiological information of the patients, this paper implements the independent learning (IL) and federated learning (FL) methods to maintain user data privacy. Furthermore, the post-quantization compression technique was also applied to convert models into their lightweight version, overcoming the computationally demanding processes of DL. Based on the experiment results, the FL method showed a higher recall rate ( > = 98.69%) than the IL method ( = 97.87%). Additionally, the FL-aided CNN-based anomaly detection system performs better than the MLP-based approach. The former achieved an average recall rate of 99.24%, whereas the latter only attained 98.69%. Without loss of recall value, the inference latency of the models was tremendously reduced from more than 300 ms to less than two milliseconds when the original models were converted to their lightweight version.

With the advancement of technology and innovation in the oil and gas industry, the production of liquid and gaseous hydrocarbon from conventional and unconventional resources has seen exponential growth. Recently, the USA and other oil giants have shifted their paradigm from conventional to unconventional resources of exploration and production of hydrocarbon. However, there is still a perpetual force that exists to develop and devise new innovative approaches and methodologies for the exploration, extraction efficiencies, and production performance of hydrocarbons. To better evaluate the impact of well attributes, reservoir characteristics and production behavior of well machine learning and artificial intelligence-based models have been developed by researchers that with the help of simulation and modeling provide us the true picture of reservoir performance without exploring and investing billions of dollars. This review paper encompasses the literature published in the recent years and narrated the recent development made by researchers especially in the field of production performance estimation of shale gas by developing machine learning-based models. More specifically, this paper deals with the major shale gas reservoir of North America including Marcellus shale, Eagle Ford shale, and Bakken Shale. Additionally, equations, input parameters, and formations that are considered key parameters for the development of the smart shale gas models are also discussed in this manuscript. In addition, the methodology comparison of different machine learning algorithms including their limitations and advantages are also presented.

The concept of the fifth generation (5G) mobile network system has emerged in recent years as telecommunication operators and service providers look to upgrade their infrastructure and delivery modes to meet the growing demand. Concepts such as softwarization, virtualization, and machine learning will be key components as innovative and flexible enablers of such networks. In particular, paradigms such as software-defined networks, software-defined perimeter, cloud & edge computing, and network function virtualization will play a major role in addressing several 5G networks' challenges, especially in terms of flexibility, programmability, scalability, and security. In this work, the role and potential of these paradigms in the context of V2X communication is discussed. To do so, the paper starts off by providing an overview and background of V2X communications. Then, the paper discusses in more details the various challenges facing V2X communications and some of the previous literature work done to tackle them. Furthermore, the paper describes how softwarization, virtualization, and machine learning can be adapted to tackle the challenges of such networks.

The diversity and complexity of the parameters involved in the modeling of proton exchange membrane fuel cells (PEMFCs) have restricted further research and applications of such cells, and the similarity theory is a promising solution to this problem. The similarity theory is an effective tool to obtain compact and generalized results with the same precision as that of the basic mathematical model. This paper presents a comprehensive review of the application of the similarity theory to most aspects of PEMFCs. The advantages of using the similarity theory, such as generality, reduction in the test effort, convenient comparisons and guidance to scale up the experiment, are discussed and analyzed. Although a number of similarity criteria have been proposed in recent years, the similarity theory is not as widely applied or well accepted in PEMFC research as in the heat transfer and fluid flow domain. The objective of this paper is to demonstrate the feasibility of performing a similarity analysis for such complex systems and encouraging researchers to present a dimensionless expression of their results in the follow up PEMFC research. A key challenge is to use the similarity analysis for a complete gas-water-electricity-heat-mechanics coupled PEMFC system and obtain the correlation between the dimensionless output voltage/current and input similarity criteria. This review indicates that none of the existing models can achieve this objective, and further research pertaining to this aspect must be performed. Several recommendations to achieve this aim, including a hierarchical classification of the criteria, are provided.

Fine-grained vehicle categorization has evolved into a significant subject of study due to its importance in the Intelligent Transportation System. A highly accurate and real-time vehicle categorization system will help to support many applications not only in the security aspect but also many walks of life. In this paper, facing the growing importance of this study, we present an image dataset named Frontal-103 to promote the development of the vision-based research on the vehicle, and particularly for the task of fine-grained vehicle categorization. This paper provides a detailed analysis of Frontal-103 in its current state: 1,759 fine-grained vehicle models in 103 vehicle makes and 65,433 web-nature images in total. Apart from the specific viewpoint and vehicle hierarchy, Frontal-103 is superior to the other state-of-the-art vehicle image datasets not only in the scale and diversity but also the accuracy and fine-grained level. We further discuss the peculiar challenges and issues lies in the task of fine-grained vehicle categorization and illustrate the usefulness of our dataset in addressing those problems. We hope Frontal-103 will be beneficial to the vision-based vehicle analysis and contribute to the computer vision community.

In the past decades, there have been numerous advancements in the field of technology. This has led to many scientific breakthroughs in the field of medical sciences. In this, rapidly transforming world we are having a difficult time and the problem of fatigue is becoming prevalent. So, this study aimed to understand what is fatigue, its repercussions, and techniques to detect it using machine learning (ML) approaches. This paper introduces, discusses methods and recent advancements in the field of fatigue detection. Further, we categorized the methods that can be used to detect fatigue into four diverse groups, i.e., Mathematical Models, Rule-Based Implementation, ML and Deep Learning. This study presents, compares and contrasts various algorithms to find the most promising approach that can be used for the detection of fatigue. Finally, the paper discusses the possible areas for improvement.

Mobile malware are malicious programs that target mobile devices. They are an increasing problem, as seen in the rise of detected mobile malware samples per year. The number of active smartphone users is expected to grow, stressing the importance of research on the detection of mobile malware. Detection methods for mobile malware exist but are still limited. In this paper, we provide an overview of the performance of machine learning (ML) techniques to detect malware on Android, without using privileged access. The ML-classifiers use device information such as the CPU usage, battery usage, and memory usage for the detection of 10 subtypes of Mobile Trojans on the Android Operating System (OS). We use a real-life dataset containing device and malware data from 47 users for a year (2016). We examine which features, i.e. aspects, of a device, are most important to monitor to detect (subtypes of) Mobile Trojans. The focus of this paper is on dynamic hardware features. Using these dynamic features we apply state-of-the-art machine learning classifiers: Random Forest, K-Nearest Neighbour, and AdaBoost. We show classification results on different feature sets, making a distinction between global device features, and specific app features. None of the measured feature sets require privileged access. Our results show that the Random Forest classifier performs best as a general malware classifier: across 10 subtypes of Mobile Trojans, it achieves an F1 score of 0.73 with a False Positive Rate (FPR) of 0.009 and a False Negative Rate (FNR) of 0.380. The Random Forest, K-Nearest Neighbours, and AdaBoost classifiers achieve F1 scores above 0.72, an FPR below 0.02 and, an FNR below 0.33, when trained separately to detect each subtype of Mobile Trojans., Comment: 14 pages content, 22 pages total, to be published in ACM DTRAP (currently in last revision phase)

Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images in the computer vision area. Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation and time-series data imputation. While several reviews for GANs in computer vision have been presented, no one has considered addressing the practical applications and challenges relevant to spatio-temporal data. In this paper, we have conducted a comprehensive review of the recent developments of GANs for spatio-temporal data. We summarise the application of popular GAN architectures for spatio-temporal data and the common practices for evaluating the performance of spatio-temporal applications with GANs. Finally, we point out future research directions to benefit researchers in this area., This paper has been accepted by ACM Transactions on Intelligent Systems and Technology (TIST)

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before DNNs are deployed, adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications. However, under the challenging black-box setting, the attack success rate, i.e., the transferability of adversarial examples, still needs to be improved. Based on image augmentation methods, this paper found that random transformation of image brightness can eliminate overfitting in the generation of adversarial examples and improve their transferability. In light of this phenomenon, this paper proposes an adversarial example generation method, which can be integrated with Fast Gradient Sign Method (FGSM)-related methods to build a more robust gradient-based attack and to generate adversarial examples with better transferability. Extensive experiments on the ImageNet dataset have demonstrated the effectiveness of the aforementioned method. Whether on normally or adversarially trained networks, our method has a higher success rate for black-box attacks than other attack methods based on data augmentation. It is hoped that this method can help evaluate and improve the robustness of models.

Preliminary pile tests are becoming increasingly routine in piling projects, some of which are instrumented to help optimise working pile design. However, the execution of a successful test on an instrumented concrete pile (ICP) is not straightforward; practitioners are often faced with difficulties in interpreting the results from the instrumentation due to factors such as installation and curing effects, insufficient and/or malfunctioning gauges and testing procedures. A detailed methodology for the successful execution of an instrumented pile test addressing all of these factors is provided in this paper. Established and emerging trends in ICP testing are captured through a database of over 100 published case histories from the literature. It is envisaged that the methodologies described in this paper, together with the companion paper on strain interpretation, will provide practitioners with a helpful guide to enable a successful ICP test. The authors wish to thank Dr Nicky de Battista of University of Cambridge, Dr Andrew Galbraith of Geowynd, and Drs David Gill and Eric Farrell of AGL Consulting for permission to reuse the various figures referenced in the paper. The first author was sponsored by the College of Engineering and Informatics Fellowship and University Foundation Bursary during his doctoral studies at NUI Galway. The views expressed in this paper are solely the opinions of the authors and do not represent the views of AGL Consulting. peer-reviewed 2022-11-03

Many clinicians remain wary of machine learning due to long-standing concerns about "black box" models. "Black box" is shorthand for models that are sufficiently complex that they are not straightforwardly interpretable to humans. Lack of interpretability in predictive models can undermine trust in those models, especially in health care where so many decisions are literally life and death. There has recently been an explosion of research in the field of explainable machine learning aimed at addressing these concerns. The promise of explainable machine learning is considerable, but it is important for cardiologists who may encounter these techniques in clinical decision support tools or novel research papers to have a critical understanding of both their strengths and their limitations. This paper reviews key concepts and techniques in the field of explainable machine learning as they apply to cardiology. Key concepts reviewed include interpretability versus explainability and global versus local explanations. Techniques demonstrated include permutation importance, surrogate decision trees, local interpretable model-agnostic explanations, and partial dependence plots. We discuss several limitations with explainability techniques, focusing on the how the nature of explanations as approximations may omit important information about how black box models work and why they make certain predictions. We conclude by proposing a rule of thumb about when it is appropriate to use black box models with explanations, rather than interpretable models.

With the prevalence of online social platforms, social recommendation has emerged as a promising direction that leverages the social network among users to enhance recommendation performance. However, the available social relations among users are usually extremely sparse and noisy, which may lead to inferior recommendation performance. To alleviate this problem, this paper novelly exploits the implicit higher-order social influence and dependencies among users to enhance social recommendation. In this paper, we propose a novel embedding method for general bipartite graphs, which defines inter-class message passing between explicit relations and intra-class message passing between implicit higher-order relations via a novel sequential modelling paradigm. Inspired by recent advances in self-attention-based sequential modelling, the proposed model features a self-attentive representation learning mechanism for implicit user-user relations. Moreover, this paper also explores the inductive embedding learning for social recommendation problems to improve the recommendation performance in cold-start settings. The proposed inductive learning paradigm for social recommendation enables embedding inference for those cold-start users and items (unseen during training) as long as they are linked to existing nodes in the original network. Extensive experiments on real-world datasets demonstrate the superiority of our method and suggest that higher-order implicit relationship among users is beneficial to improving social recommendation.

Many decisions in a machine learning pipeline involve non-differentiable and discontinuous objectives and search spaces. Examples include feature selection, model selection and hyper-parameter tuning, where candidate solutions in an outer optimization loop must be evaluated via a learning subsystem. Evolutionary algorithms (EAs) are prominent gradient-free methods to handle such tasks. However, EAs are known to pose steep computational challenges, especially when dealing with large-instance datasets. As opposed to prior works that often fall back on parallel computing hardware to resolve this big data problem of EAs, in this paper we propose a novel algorithm-centric solution based on evolutionary multitasking. Our approach involves the creation of a band of minions, i.e., small data proxies to the main target task, that are constructed by subsampling a fraction of the large dataset. We then combine the minions with the main task in a single multi-task optimization framework, boosting evolutionary search by using small data to quickly optimize for the large dataset. Our key algorithmic contribution in this setting is to allocate computational resources to each of the tasks in a principled manner. The paper considers wrapper-based feature selection as an illustrative case study of the broader idea of using multitasking to speedup outer-loop evolutionary configurations of any machine learning subsystem. The experiments reveal that multitasking can indeed speedup baseline EAs, by more than 40% on some datasets.

Building on the achievements of the BiLSTM-CRF in named-entity recognition (NER), this paper introduces the BiLSTM-SSVM, an equivalent neural model where training is performed using a structured hinge loss. The typical loss functions used for evaluating NER are entity-level variants of the F1 score such as the CoNLL and MUC losses. Unfortunately, the common loss function used for training NER - the cross entropy - is only loosely related to the evaluation losses. For this reason, in this paper we propose a training approach for the BiLSTM-CRF that leverages a hinge loss bounding the CoNLL loss from above. In addition, we present a mixed hinge loss that bounds either the CoNLL loss or the Hamming loss based on the density of entity tokens in each sentence. The experimental results over four benchmark languages (English, German, Spanish and Dutch) show that training with the mixed hinge loss has led to small but consistent improvements over the cross entropy across all languages and four different evaluation measures.

The Internet of Things (IoT) has become a rising and dynamic research area. It is the integration of numerous objects (things) to communicate information without human beings' intervention. Inappropriately, because of the qualities resource-constrained and limited communication range, it significantly relies upon the Cloud as outsourcing to store and compute the data. This reconciliation of IoT with the Cloud has brought new issues and poses difficulties regarding protection and security threats. The necessity for the wide arrangement of cloud-based IoT is rapidly expanding with significant security-related issues. This work plots existing security methodologies and vulnerabilities near to a portion of the current security strategies by a total review of existing work in the field of security in cloud-based IoT. This paper concentrated on security and protection in terms of privacy by investigating some potential difficulties and risks that should be resolved. The Cloud of Things (CoT) architectures and present applications have been explored and focused on the middleware layer's attacks. Furthermore, this paper outlines a concise scientific classification of the current security threats in cloudbased IoT, plans, and communication. Finally, a few captivating open issues are given with promising designs to trigger more research community research attempts.

A faulty situation occurred in Service Oriented Architecture (SOA) based systems can affect its functionality. It is challenging to guarantee the reliability of service utilization in a distributed, concurrent and dynamic composition of web services. This paper aims to present a fault detection approach of SOA using dependency analysis. Data and control dependencies are identified and a fault diagnosis approach based on these dependencies is proposed in this paper. The presented approach extends discrete state space techniques to simulate the concurrent and distributed behavior through Colored Petri Nets (CPNs) for the SOA-based systems in case of the faulty situation. Concrete translation from SOA based system to a CPN model is presented. Model-based technique is used and some heuristics are presented for dependency analysis and fault detection purpose. The experimental performance analysis shows the feasibility of our proposed approach.

The fast access to data and high parallel processing in high-performance computing instigates an urgent demand on the improvement of the NVMe storage within modern data centers. However, the former NVMe virtualization's unsatisfactory performance demonstrates that NVMe devices are often underutilized within cloud platforms. An NVMe virtualization mechanism with high performance and device sharing has captured researchers and developers' attention. This paper introduces MDev-NVMe, a new virtualization solution for NVMe storage device with (1) full NVMe storage virtualization for VMs running native NVMe driver, (2) a mediated pass-through mechanism for NVMe management, and (3) adaptive configuration of active polling optimization to simultaneously achieve high throughput, low latency performance, and substantial device scalability. We practically implement the MDev-NVMe as a Linux kernel module. This paper subsequently evaluates MDev-NVMe with Intel OPTANE and P3600 SSD by comparing several mainstream NVMe virtualization mechanisms using application-level I/O benchmarks. MDev-NVMe with active polling can demonstrate a 142% improvement over native (interrupt-driven) throughput and over 2.5 × the Virtio throughput with only 70% native average latency and 31% Virtio average latency. Finally, the advantages of MDev-NVMe and the importance of adaptive polling are discussed, offering evidence that MDev-NVMe is a superior virtualization choice for cloud storage.

The practice of sequentially testing a null hypothesis as data are collected until the null hypothesis is rejected is known as optional stopping. It is well-known that optional stopping is problematic in the context of p-value based null hypothesis significance testing: The false positive rates quickly overcome the single test’s significance level. However, the state of affairs under null hypothesis Bayesian testing, where p-values are replaced by Bayes factors, has perhaps surprisingly been much less consensual. Rouder (2014) used simulations to defend the use of optional stopping under null hypothesis Bayesian testing. The idea behind these simulations is closely related to the idea of sampling from prior predictive distributions. Deng et al. (2016) and Hendriksen et al. (2020) have provided mathematical evidence to the effect that optional stopping under null hypothesis Bayesian testing does hold under some conditions. These papers are, however, exceedingly technical for most researchers in the applied social sciences. In this paper we provide some mathematical derivations concerning Rouder’s approximate simulation results for the two Bayesian hypothesis tests that he considered. The key idea is to consider the probability distribution of the Bayes factor, which is regarded as being a random variable across repeated sampling. This paper therefore offers an intuitive perspective to the literature and we believe it is a valid contribution towards understanding the practice of optional stopping in the context of Bayesian hypothesis testing.

In the current ever-changing cybersecurity scenario, active cyber defense strategies are imperative. In this work, we present a standard testbed to measure the efficacy and efficiency of customized networks while analyzing various parameters during the active attack. The presented testbed can be used for analyzing the network behavior in presence of various types of attacks and can help in fine-tuning the proposed algorithm under observation. The proposed testbed will allow users to design, implement, and evaluate the active cyber defense mechanisms with good library support of nature-inspired and AI-based techniques. Network loads, number of clusters, types of home networks, and number of nodes in each cluster and network can be customized. While using the presented testbed and incorporating active-defense strategies on existing network architectures, users can also design and propose new network architectures for effective and safe operation. In this paper, we propose a unified and standard testbed for cyber defense strategy simulation and bench-marking, which would allow the users to investigate current approaches and compare them with others, while ultimately aiding in the selection of the best approach for a given network security situation. We have compared the network performance in difference scenarios namely, normal, under attack and under attack in presence of NICS-based adaptive defense mechanism and achieved stable experimental results. The experimental results clearly show that the proposed testbed is able to simulate the network conditions effectively with minimum efforts in network configuration. The simulation results of defense mechanisms verified on the proposed testbed got the improvement on almost 80 percent while increasing the turnaround time to 1–2 percent. The applicability of proposed testbed in modern technologies like Fog Computing and Edge Computing is also discussed in this paper.