Future Internet, Volume 14, Issue 12 (December 2022) – 39 articles

Head detection is a fundamental task, and it plays an important role in many head-related problems. The difficulty in creating the local and global context in the face of significant lighting, orientation, and occlusion uncertainty, among other factors, still makes this task a remarkable challenge. To tackle these problems, this paper proposes an effective detector, the Context Refinement Network (CRN), that captures not only the refined global context but also the enhanced local context. We use simplified non-local (SNL) blocks at hierarchical features, which can successfully establish long-range dependencies between heads to improve the capability of building the global context. We suggest a multi-scale dilated convolutional module for the local context surrounding heads that extracts local context from various head characteristics. In comparison to other models, our method outperforms them on the Brainwash and the HollywoodHeads datasets. Full article

We present a graph-based method for the lexical task of labeling senses of polysemous lexemes. The labeling task aims at generalizing sense features of a lexical item in a corpus using more abstract concepts. In this method, a coordination dependency-based lexical graph is first constructed with clusters of conceptually associated lexemes representing related senses and conceptual domains of a source lexeme. The label abstraction is based on the syntactic patterns of the x is_a y dependency relation. For each sense cluster, an additional lexical graph is constructed by extracting label candidates from a corpus and selecting the most prominent is_a collocates in the constructed label graph. The obtained label lexemes represent the sense abstraction of the cluster of conceptually associated lexemes. In a similar graph-based procedure, the semantic class representation is validated by constructing a WordNet hypernym relation graph. These additional labels indicate the most appropriate hypernym category of a lexical sense community. The proposed labeling method extracts hierarchically abstract conceptual content and the sense semantic features of the polysemous source lexeme, which can facilitate lexical understanding and build corpus-based taxonomies. Full article

The choice of furniture in a retail store is usually based on a product catalog and simplistic product renderings with different configurations. We present a preliminary field study that tests a Multi-Sensory In-Store Virtual Reality Customer Journey (MSISVRCJ) through a virtual catalog and a product configurator to support furnishings sales. The system allows customers to stay immersed in the virtual environment (VE) while the sales expert changes the colors, textures, and finishes of the furniture, also exploring different VEs. In addition, customers can experience realistic tactile feedback with in-store samples of furniture they can test. The journey is implemented for a furniture manufacturer and tested in a flagship store. Fifty real customers show positive feedback in terms of general satisfaction, perceived realism, and acceptance. This method can increase purchase confidence, reduce entrepreneurial costs, and leverage in-store versus online shopping. Full article

Human pose estimation (HPE) has become a prevalent research topic in computer vision. The technology can be applied in many areas, such as video surveillance, medical assistance, and sport motion analysis. Due to higher demand for HPE, many HPE libraries have been developed in the last 20 years. In the last 5 years, more and more skeleton-based HPE algorithms have been developed and packaged into libraries to provide ease of use for researchers. Hence, the performance of these libraries is important when researchers intend to integrate them into real-world applications for video surveillance, medical assistance, and sport motion analysis. However, a comprehensive performance comparison of these libraries has yet to be conducted. Therefore, this paper aims to investigate the strengths and weaknesses of four popular state-of-the-art skeleton-based HPE libraries for human pose detection, including OpenPose, PoseNet, MoveNet, and MediaPipe Pose. A comparative analysis of these libraries based on images and videos is presented in this paper. The percentage of detected joints (PDJ) was used as the evaluation metric in all comparative experiments to reveal the performance of the HPE libraries. MoveNet showed the best performance for detecting different human poses in static images and videos. Full article

As the technical specifications of the 5th Generation (5G) wireless communication standard are being wrapped up, there are growing efforts amongst researchers, industrialists, and standardisation bodies on the enabling technologies of a 6G standard or the so-called Beyond 5G (B5G) one. Although the 5G standard has presented several benefits, there are still some limitations within it. Such limitations have motivated the setting up of study groups to determine suitable technologies that should operate in the year 2030 and beyond, i.e., after 5G. Consequently, this Special Issue of Future Internet concerning what possibilities lie ahead for a 6G wireless network includes four high-quality research papers (three of which are review papers with over 412 referred sources and one regular research). This editorial piece summarises the major contributions of the articles and the Special Issue, outlining future directions for new research. Full article

Digitalization is one of the factors that affects the acceleration of the application of telecommunications technologies such as 5G. The 5G technology that has been developed today does not yet meet different performance and manageability standards, particularly for data center networks as a supportive technology. Software-defined networking (SDN) and network function virtualization (NFV) are two complementary technologies that are currently used by almost all data centers in the telecommunications industry to rectify performance and manageability issues. In this study, we deliver an integrated SDN-NFV architecture to simplify network management activities in telecommunication companies. To improve network performance at the computing level, we performed a modification of a networking system at the computing level, underlying NFV devices by replacing the default virtual switch with a data plane development kit (DPDK) and single root I/O virtualization (SR-IOV). This study evaluated the proposed architecture design in terms of network performance and manageability. Based on 30 days of observation in prime time, the proposed solution increased throughput up to 200 Mbps for the server leaf and 1.6 Gbps for the border leaf compared to the legacy architecture. Meanwhile, the latency decreased to 12 ms for the server leaf and 17 ms for the border leaf. For manageability, we tested three different scenarios and achieved savings of 13 min for Scenario 1, 22 min for Scenario 2 and 9 min for Scenario 3. Full article

Federated Learning (FL) provides a promising solution for preserving privacy in learning shared models on distributed devices without sharing local data on a central server. However, most existing work shows that FL incurs high communication costs. To address this challenge, we propose a clustering-based federated solution, entitled Federated Learning via Clustering Optimization (FedCO), which optimizes model aggregation and reduces communication costs. In order to reduce the communication costs, we first divide the participating workers into groups based on the similarity of their model parameters and then select only one representative, the best performing worker, from each group to communicate with the central server. Then, in each successive round, we apply the Silhouette validation technique to check whether each representative is still made tight with its current cluster. If not, the representative is either moved into a more appropriate cluster or forms a cluster singleton. Finally, we use split optimization to update and improve the whole clustering solution. The updated clustering is used to select new cluster representatives. In that way, the proposed FedCO approach updates clusters by repeatedly evaluating and splitting clusters if doing so is necessary to improve the workers’ partitioning. The potential of the proposed method is demonstrated on publicly available datasets and LEAF datasets under the IID and Non-IID data distribution settings. The experimental results indicate that our proposed FedCO approach is superior to the state-of-the-art FL approaches, i.e., FedAvg, FedProx, and CMFL, in reducing communication costs and achieving a better accuracy in both the IID and Non-IID cases. Full article

Reasoning on temporal knowledge graphs, which aims to infer new facts from existing knowledge, has attracted extensive attention and in-depth research recently. One of the important tasks of reasoning on temporal knowledge graphs is entity prediction, which focuses on predicting the missing objects in facts at current time step when relevant histories are known. The problem is that, for entity prediction task on temporal knowledge graphs, most previous studies pay attention to aggregating various semantic information from entities but ignore the impact of semantic information from relation types. We believe that relation types is a good supplement for our task and making full use of semantic information of facts can promote the results. Therefore, a framework of Enhanced Relational Graph Convolution Network (ERGCN) is put forward in this paper. Rather than only considering representations of entities, the context semantic information of both relations and entities is considered and merged together in this framework. Experimental results show that the proposed approach outperforms the state-of-the-art methods. Full article

Image recognition technology systems have existed in the realm of computer security since nearly the inception of electronics, and have seen vast improvements in recent years. Currently implemented facial detection systems regularly achieve accuracy rates close to 100 percent. This includes even challenging environments, such as with low light or skewed images. Despite this near perfect performance, the problem of gender bias with respect to accuracy is still inherent in many current facial recognition algorithms. This bias needs to be addressed to make facial recognition a more complete and useful system. In particular, current image recognition system tend to have poor accuracy concerning underrepresented groups, including minorities and female individuals. The goal of this research is to increase the awareness of this bias issue, as well as to create a new model for image recognition that is gender independent. To achieve this goal, a variety of Convolutional Neural Networks (CNNs) will be tested for accuracy as it pertains to gender bias. In the future, the most accurate CNNs will then be implemented into a new network with the goal of creating a program which is better able to distinguish individuals with a high accuracy, but without gender bias. At present, our research has identified two specific CNNs, VGG-16 and ResNet50, which we believe will be ideal for the creation of this new CNN algorithm. Full article

Programming skills should be taught and developed; Scratch and App Inventor are two tools that can contribute significantly to developing this competence in university students. This study aims to investigate the use and effect of the programming language Scratch and App Inventor on the development of skills and competencies for learning (autonomy, attention, motivation, critical thinking, creative thinking, computational thinking, communication, problem solving and social interaction) in higher education. To achieve this goal, a systematic review of articles in English and Spanish was carried out using the PRISMA statement (research publication guidelines designed to improve the integrity of systematic review and meta-analysis reports). A search for studies was conducted in the Web of Science (WOS), Dialnet, and SCOPUS. A total of 405 papers were analyzed, of which 11 were finally selected. The results showed that both Scratch and App Inventor favor the development of skills and competencies for learning in the context of higher education, despite being underutilized strategies that all knowledge disciplines should promote. Full article

The accurate and reliable predictive estimation of signal attenuation loss is of prime importance in radio resource management. During wireless network design and planning, a reliable path loss model is required for optimal predictive estimation of the received signal strength, coverage, quality, and signal interference-to-noise ratio. A set of trees (100) on the target measured data was employed to determine the most informative and important subset of features, which were in turn employed as input data to the Particle Swarm (PS) model for predictive path loss analysis. The proposed Random Forest (RF-PS) based model exhibited optimal precision performance in the real-time prognostic analysis of measured path loss over operational 4G LTE networks in Nigeria. The relative performance of the proposed RF-PS model was compared to the standard PS and hybrid radial basis function-particle swarm optimization (RBF-PS) algorithm for benchmarking. Generally, results indicate that the proposed RF-PS model gave better prediction accuracy than the standard PS and RBF-PS models across the investigated environments. The projected hybrid model would find useful applications in path loss modeling in related wireless propagation environments. Full article

The Internet has rapidly grown into a distributed and collaborative network with over one billion users, e.g., the Internet of Things (IoT). The future Internet will become the core of the next information infrastructure in regard to computation and communication, being capable of extensibility, survivability, mobility, and adaptability. However, with the increasing complexity of the future Internet and boost in information sharing, there is a threat to such infrastructure in the aspects of security, trust, and privacy. This editorial discusses the state-of-the-art advancements in information and the future internet. Full article

Edge detectors are widely used in computer vision applications to locate sharp intensity changes and find object boundaries in an image. The Canny edge detector is the most popular edge detector, and it uses a multi-step process, including the first step of noise reduction using a Gaussian kernel and a final step to remove the weak edges by the hysteresis threshold. In this work, a spike-based computing algorithm is presented as a neuromorphic analogue of the Canny edge detector, where the five steps of the conventional algorithm are processed using spikes. A spiking neural network layer consisting of a simplified version of a conductance-based Hodgkin–Huxley neuron as a building block is used to calculate the gradients. The effectiveness of the spiking neural-network-based algorithm is demonstrated on a variety of images, showing its successful adaptation of the principle of the Canny edge detector. These results demonstrate that the proposed algorithm performs as a complete spike domain implementation of the Canny edge detector. Full article

As information technology advances quickly, so does the 5G–6G network management system, which is moving toward greater integration, decentralization, diversity, and intelligence. As flexibility is a crucial criterion for 5G–6G network architecture, we use the Software Defined Network (SDN) paradigm to make the programmability more flexible. Due to their ability to replace the current TCP/IP architecture with one that separates the control plane and data plane, software-defined networks have gained much popularity. However, they are susceptible to routing attacks. Therefore, this work proposes Lightweight Security Framework that combines blockchain technology with Software-Defined Networking (LSSDNF) to address this problem. The proposed framework adds the routing data that the controller withheld to the multichain blockchain. Here, a mininet network simulator is used to model the proposed framework. The data transfer rate or network throughput, bandwidth variation, and jitter have all been used to assess the performance of single-controller-SDN networks and multi-controller-SDN networks. The results demonstrate that the proposed framework performs better than the conventional single-controller-SDN architecture in terms of throughput, bandwidth fluctuation, and jitter. Full article

Cloud computing leads to efficient resource allocation for network users. In order to achieve efficient allocation, many research activities have been conducted so far. Some researchers focus on classical optimisation theory techniques (such as multi-objective optimisation, evolutionary optimisation, game theory, etc.) to satisfy network providers and network users’ service-level agreement (SLA) requirements. Normally, in a cloud data centre network (CDCN), it is difficult to jointly satisfy both the cloud provider and cloud customer’ utilities, and this leads to complex combinatorial problems, which are usually NP-hard. Recently, machine learning and artificial intelligence techniques have received much attention from the networking community because of their capability to solve complicated networking problems. In the current work, at first, the holistic utility satisfaction for the cloud data centre provider and customers is formulated as a reinforcement learning (RL) problem with a specific reward function, which is a convex summation of users’ utility functions and cloud provider’s utility. The user utility functions are modelled as a function of cloud virtualised resources (such as storage, CPU, RAM), connection bandwidth, and also, the network-based expected packet loss and round-trip time factors associated with the cloud users. The cloud provider utility function is modelled as a function of resource prices and energy dissipation costs. Afterwards, a Q-learning implementation of the mentioned RL algorithm is introduced, which is able to converge to the optimal solution in an online and fast manner. The simulation results exhibit the enhanced convergence speed and computational complexity properties of the proposed method in comparison with similar approaches from the joint cloud customer/provider utility satisfaction perspective. To evaluate the scalability property of the proposed method, the results are also repeated for different cloud user population scenarios (small, medium, and large). Full article

The stability of physicians’ authority over patients despite decades of changes in medicine conflicts with newer institutionalist accounts of professionals as change agents rather than instruments of reproduction. We analyzed whether the cultural scripts that twenty-one residents used to justify their approach to a new change, the electronic health record (EHR), signaled a leveling of the patient-physician hierarchy. Residents are intriguing because their position makes them open to change. Indeed, residents justified using the EHR in ways that level the patient-physician hierarchy, but also offered rationales that sustain it. For the latter, residents described using the EHR to substantiate their expertise, situate themselves as brokers between patients and the technology, and preserve the autonomy of clinicians. Our findings highlight how professionals with little direct experience before a change can selectively apply incumbent scripts to sustain extant structures, while informing newer institutionalist accounts of professionals and the design of EHR systems. Full article

During a ship evacuation, many people panic as they do not know the direction that leads to the emergency muster station. Moreover, sometimes passengers get crowded in corridors or stairs, so they cannot save their lives. This paper proposes an IoT-enabled architecture for digital signage systems that directs passengers to the muster stations of a cruise ship by following the less dangerous route. Thus, crews’ and passengers’ safety risks during a ship evacuation can be low, and human health hazards may be limited. The system is based on a low-cost and open-source architecture that can also be used in a variety of fields in industrial IoT applications. The proposed modular digital signage architecture utilizes Light Emitting Diode (LED) strips that are remotely managed through a private Long-Term Evolution (LTE)/Fourth Generation (4G) cellular network. Publish–subscribe communication protocols were used for the control of the digital strips and particularly through a Message Queuing Telemetry Transport (MQTT) broker who publishes/subscribes every message to specific topics of the realized IoT platform, while the overall digital signage system centralization was implemented with an appropriate dashboard supported from an open-source RESTful API. Full article

As sensors are distributed among wireless sensor networks (WSNs), ensuring that the batteries and processing power last for a long time, to improve energy consumption and extend the lifetime of the WSN, is a significant challenge in the design of network clustering techniques. The sensor nodes are divided in these techniques into clusters with different cluster heads (CHs). Recently, certain considerations such as less energy consumption and high reliability have become necessary for selecting the optimal CH nodes in clustering-based metaheuristic techniques. This paper introduces a novel enhancement algorithm using Aquila Optimizer (AO), which enhances the energy balancing in clusters across sensor nodes during network communications to extend the network lifetime and reduce power consumption. Lifetime and energy-efficiency clustering algorithms, namely the low-energy adaptive clustering hierarchy (LEACH) protocol as a traditional protocol, genetic algorithm (GA), Coyote Optimization Algorithm (COY), Aquila Optimizer (AO), and Harris Hawks Optimization (HHO), are evaluated in a wireless sensor network. The paper concludes that the proposed AO algorithm outperforms other algorithms in terms of alive nodes analysis and energy consumption. Full article

In recent years, image and video super-resolution have gained attention outside the computer vision community due to the outstanding results produced by applying deep-learning models to solve the super-resolution problem. These models have been used to improve the quality of videos and images. In the last decade, video-streaming applications have also become popular. Consequently, they have generated traffic with an increasing quantity of data in network infrastructures, which continues to grow, e.g., global video traffic is forecast to increase from 75% in 2017 to 82% in 2022. In this paper, we leverage the power of deep-learning-based super-resolution methods and implement a model for video super-resolution, which we call VSRGAN+. We train our model with a dataset proposed to teach systems for high-level visual comprehension tasks. We also test it on a large-scale JND-based coded video quality dataset containing 220 video clips with four different resolutions. Additionally, we propose a cloud video-delivery framework that uses video super-resolution. According to our findings, the VSRGAN+ model can reconstruct videos without perceptual distinction of the ground truth. Using this model with added compression can decrease the quantity of data delivered to surrogate servers in a cloud video-delivery framework. The traffic decrease reaches 98.42% in total. Full article

The rapid emergence of low-power embedded devices and modern machine learning (ML) algorithms has created a new Internet of Things (IoT) era where lightweight ML frameworks such as TinyML have created new opportunities for ML algorithms running within edge devices. In particular, the TinyML framework in such devices aims to deliver reduced latency, efficient bandwidth consumption, improved data security, increased privacy, lower costs and overall network cost reduction in cloud environments. Its ability to enable IoT devices to work effectively without constant connectivity to cloud services, while nevertheless providing accurate ML services, offers a viable alternative for IoT applications seeking cost-effective solutions. TinyML intends to deliver on-premises analytics that bring significant value to IoT services, particularly in environments with limited connection. This review article defines TinyML, presents an overview of its benefits and uses and provides background information based on up-to-date literature. Then, we demonstrate the TensorFlow Lite framework which supports TinyML along with analytical steps for an ML model creation. In addition, we explore the integration of TinyML with network technologies such as 5G and LPWAN. Ultimately, we anticipate that this analysis will serve as an informational pillar for the IoT/Cloud research community and pave the way for future studies. Full article

Cybersecurity plays an increasing role in today’s digital space, and its methods must keep pace with the changes. Both public and private sector researchers have put efforts into strengthening the security of networks by proposing new approaches. This paper presents a method to solve a game theory model by defining the contents of the game payoff matrix and incorporating honeypots in the defense strategy. Using a probabilistic approach we propose the course-of-action Stackelberg game (CoASG), where every path of the graph leads to an undesirable state based on security issues found in every host. The reality of the system is represented by a cost function which helps us to define a payoff matrix and find the best possible combination of the strategies once the game is run. The results show the benefits of using this model in the early prevention stages for detecting cyberattack patterns. Full article

Network function virtualization (NFV) is a novel technology that virtualizes computing, network, and storage resources to decouple the network functions from the underlying hardware, thus allowing the software implementation of such functions to run on commodity hardware. By doing this, NFV provides the necessary flexibility to enable agile, cost-effective, and on-demand service delivery models combined with automated management. Different management and orchestration challenges arise in such virtualized and distributed environments. A major challenge in the selection of the most suitable edge nodes is that of deploying virtual network functions (VNFs) to meet requests from multiple users. This article addresses the VNF placement problem by providing a novel integer linear programming (ILP) optimization model and a novel VNF placement algorithm. In our definition, the multi-objective optimization problem aims to (i) minimize the energy consumption in the edge nodes; (ii) minimize the total latency; and (iii) reducing the total cost of the infrastructure. Our new solution formulates the VNF placement problem by taking these three objectives into account simultaneously. In addition, the novel VNF placement algorithm leverages VNF sharing, which reuses VNF instances already placed to potentially reduce computational resource usage. Such a feature is still little explored in the community. Through simulation, numerical results show that our approach can perform better than other approaches found in the literature regarding resource consumption and the number of SFC requests met. Full article

Serverless computing hides infrastructure management from developers and runs code on-demand automatically scaled and billed during the code’s execution time. One of the most popular serverless backend services is called Function-as-a-Service (FaaS), in which developers are often confronted with cloud-specific requirements. Function signature requirements, and the usage of custom libraries that are unique to cloud providers, were identified as the two main reasons for portability issues in FaaS applications, leading to various vendor lock-in problems. In this work, we define three cloud-agnostic models that compose FaaS platforms. Based on these models, we developed QuickFaaS, a multi-cloud interoperability desktop tool targeting cloud-agnostic functions and FaaS deployments. The proposed cloud-agnostic approach enables developers to reuse their serverless functions in different cloud providers with no need to change code or install extra software. We also provide an evaluation that validates the proposed solution by measuring the impact of a cloud-agnostic approach on the function’s performance, when compared to a cloud-non-agnostic one. The study shows that a cloud-agnostic approach does not significantly impact the function’s performance. Full article

The study examines the cumulative impact of factors that affect usability testing for user-centered web design, namely the so-called ‘contextual fidelity model’ factors that include product properties, task features, user traits, and environment/context factors. Today, the design, user experience and usability (DUXU) research experiences a lack of studies that would assess combinatorial, rather than individual, effects of these factors upon user performance. We address this gap by seeing both independent factors and the resulting user states as complex and dynamic, and testing the combined impact of aesthetic quality of websites, user traits, and individual/group experiment settings upon formation of two dysfunctional user states that critically affect user performance, namely monotony and anxiety. We develop a research design that allows for assessing the combinatorial effects in formation of user dysfunctionality. For that, we conduct a study with 80 assessors of Russian/European and Chinese origin in individual/group setting, employing two types of tasks and websites of high/low aesthetic quality. As the results of our experiment show, group task solving enhances the synchronous impact of website aesthetics and task features upon user states. Interaction of high-quality design, group environment, and monotonous tasks provides for an antagonistic effect when aesthetic layout in a group environment significantly reduces the fatigue rate. Low aesthetic quality in a group environment leads to cumulative enhancing of dysfunctionality for both monotony and anxiety. We conclude by setting questions and prospects for further research. Full article

Malicious websites are web locations that attempt to install malware, which is the general term for anything that will cause problems in computer operation, gather confidential information, or gain total control over the computer. In this paper, a novel approach is proposed which consists of the implementation of the genetic programming symbolic classifier (GPSC) algorithm on a publicly available dataset to obtain a simple symbolic expression (mathematical equation) which could detect malicious websites with high classification accuracy. Due to a large imbalance of classes in the initial dataset, several data sampling methods (random undersampling/oversampling, ADASYN, SMOTE, BorderlineSMOTE, and KmeansSMOTE) were used to balance the dataset classes. For this investigation, the hyperparameter search method was developed to find the combination of GPSC hyperparameters with which high classification accuracy could be achieved. The first investigation was conducted using GPSC with a random hyperparameter search method and each dataset variation was divided on a train and test dataset in a ratio of 70:30. To evaluate each symbolic expression, the performance of each symbolic expression was measured on the train and test dataset and the mean and standard deviation values of accuracy (ACC), $AUC$, precision, recall and f1-score were obtained. The second investigation was also conducted using GPSC with the random hyperparameter search method; however, 70%, i.e., the train dataset, was used to perform 5-fold cross-validation. If the mean accuracy, $AUC$, precision, recall, and f1-score values were above 0.97 then final training and testing (train/test 70:30) were performed with GPSC with the same randomly chosen hyperparameters used in a 5-fold cross-validation process and the final mean and standard deviation values of the aforementioned evaluation methods were obtained. In both investigations, the best symbolic expression was obtained in the case where the dataset balanced with the KMeansSMOTE method was used for training and testing. The best symbolic expression obtained using GPSC with the random hyperparameter search method and classic train–test procedure (70:30) on a dataset balanced with the KMeansSMOTE method achieved values of $\overline{ACC}$, $\overline{AUC}$, $\overline{Precsion}$, $\overline{Recall}$ and $\overline{F1\text{-}score}$ (with standard deviation) $0.9992\pm 2.249\times {10}^{-5}$, $0.9995\pm 9.945\times {10}^{-6}$, $0.9995\pm 1.09\times {10}^{-5}$, $0.999\pm 5.17\times {10}^{-5}$, $0.9992\pm 5.17\times {10}^{-6}$, respectively. The best symbolic expression obtained using GPSC with a random hyperparameter search method and 5-fold cross-validation on a dataset balanced with the KMeansSMOTE method achieved values of $\overline{ACC}$, $\overline{AUC}$, $\overline{Precsion}$, $\overline{Recall}$ and $\overline{F1\text{-}score}$ (with standard deviation) $0.9994\pm 1.13\times {10}^{-5}$, $0.9994\pm 1.2\times {10}^{-5}$, $1.0\pm 0$, $0.9988\pm 2.4\times {10}^{-5}$, and $0.9994\pm 1.2\times {10}^{-5}$, respectively. Full article

The traces of process executions are a strategic source of information, from which a model of the process can be mined. In our recent work, we have proposed SIM (semantic interactive miner), an innovative process mining tool to discover the process model incrementally: it supports the interaction with domain experts, who can selectively merge parts of the model to achieve compactness, generalization, and reduced redundancy. We now propose a substantial extension of SIM, making it able to exploit (both automatically and interactively) pre-encoded taxonomic knowledge about the refinement (ISA relations) and composition (part-of relations) of process activities, as is available in many domains. The extended approach allows analysts to move from a process description where activities are reported at the ground level to more user-interpretable/compact descriptions, in which sets of such activities are abstracted into the “macro-activities” subsuming them or constituted by them. An experimental evaluation based on a real-world setting (stroke management) illustrates the advantages of our approach. Full article

The development of nanomedicine involves complex nanomaterial research involving magnetic nanomaterials and their use in magnetic hyperthermia. The selection of the optimal treatment strategies is time-consuming, expensive, unpredictable, and not consistently effective. Delivering personalized therapy that obtains maximal efficiency and minimal side effects is highly important. Thus, Artificial Intelligence (AI) based algorithms provide the opportunity to overcome these crucial issues. In this paper, we briefly overview the significance of the combination of AI-based methods, particularly the Machine Learning (ML) technique, with magnetic hyperthermia. We considered recent publications, reports, protocols, and review papers from Scopus and Web of Science Core Collection databases, considering the PRISMA-S review methodology on applying magnetic nanocarriers in magnetic hyperthermia. An algorithmic performance comparison in terms of their types and accuracy, data availability taking into account their amount, types, and quality was also carried out. Literature shows AI support of these studies from the physicochemical evaluation of nanocarriers, drug development and release, resistance prediction, dosing optimization, the combination of drug selection, pharmacokinetic profile characterization, and outcome prediction to the heat generation estimation. The papers reviewed here clearly illustrate that AI-based solutions can be considered as an effective supporting tool in drug delivery, including optimization and behavior of nanocarriers, both in vitro and in vivo, as well as the delivery process. Moreover, the direction of future research, including the prediction of optimal experiments and data curation initiatives has been indicated. Full article

Object detection is a computer vision task of detecting instances of objects of a certain class, identifying types of objects, determining its location, and accurately labelling them in an input image or a video. The scope of the work presented within this paper proposes a modern object detection network called NextDet to efficiently detect objects of multiple classes which utilizes CondenseNeXt, an award-winning lightweight image classification convolutional neural network algorithm with reduced number of FLOPs and parameters as the backbone, to efficiently extract and aggregate image features at different granularities in addition to other novel and modified strategies such as attentive feature aggregation in the head, to perform object detection and draw bounding boxes around the detected objects. Extensive experiments and ablation tests, as outlined in this paper, are performed on Argoverse-HD and COCO datasets, which provide numerous temporarily sparse to dense annotated images, demonstrate that the proposed object detection algorithm with CondenseNeXt as the backbone result in an increase in mean Average Precision (mAP) performance and interpretability on Argoverse-HD’s monocular ego-vehicle camera captured scenarios by up to 17.39% as well as COCO’s large set of images of everyday scenes of real-world common objects by up to 14.62%. Full article