Location Constraints Research Articles

DFN modelling constrained by multiple seismic attributes using the steering pyramid technology

Fracture modelling is essential for understanding fluid flow in fractured hydrocarbon reservoirs, particularly in the phase of production; however, traditional discrete fracture network (DFN) modelling methods lack constraints that reflect characteristics of fracture development. Fractures or fracture networks exhibit a high degree of randomness; as such, it is difficult to model fracture characteristics. This paper proposes a new approach for DFN modelling constrained by seismic attributes. Firstly, the steerable pyramid method is adopted to improve seismic data resolution; secondly, multiple seismic attributes are extracted and combined into a composite attribute to characterize fracture spatial distribution; finally, a DFN modelling method is established by using the composite attribute as a location constraint. To verify the effectiveness of the approach, a case study is conducted in the Bonan Depression, in East China. The results show that, compared with the traditional DFN modelling methods, the DFN modelling with the location constraint create a more realistic fracture model which accurately reflects fracture distribution characteristics. The application demonstrates the potential of wide application prospects in fractured reservoirs.

Ballistic Missile Trajectory Design Considering Impact Angle Constraint

The current paper investigates the problem of guiding ballistic re-entry vehicles to the terminal point under the additional terminal constraint of final flight path angle. In this regard, the classical Lambert’s Problem is reformulated to include the final flight path angle constraint. The proposed solution of the modified Lambert’s problem consists of a minimum of two different trajectories starting from the same initial location and intersecting each other at a location, which is determined by applying the desired time of flight and terminal flight path angle constraints. The modified Lambert strategy strategy is shown to satisfy terminal flight path angle constraint along with the time of flight, initial and final location constraints. This scheme requires the ballistic vehicle to perform an additional stage burn during descent in-order to switch from an initial trajectory, using Lambert strategy, to a final trajectory which satisfies the final flight path angle constraint. An additional stage burn is provided such that the position and velocity of the vehicle traveling in the initial trajectory is matched with that required for it to be on the final trajectory. It is also found that the amount of propellant required for the trajectory transfer, is dependent on the total time of flight and the altitude at which the additional stage burn occurs. The optimal values of these two parameters are found using interior-point optimization technique.

Joint Information-Theoretic Secrecy and Covertness for UAV-Assisted Wireless Transmission With Finite Blocklength

In this paper, we study a novel joint information-theoretic secrecy and covertness model for an unmanned aerial vehicle (UAV)-assisted finite blocklength transmission system, in which an UAV delivers classified information to a ground user (Bob) in the presence of two unauthorized users (Eve and Willie). Specifically, Eve tries to decode the legitimate information while Willie tries to detect if the UAV's transmission is present or not. Firstly, we assume that the perfect location knowledge of both Eve and Willie is known at the UAV. In this scenario, to guarantee security and covertness, the average secrecy rate maximization problem is formulated via joint design of the UAV's transmit power and three dimensional (3D) trajectory under Willie's covertness constraint. Technically speaking, the optimization problem is non-convex and mathematically intractable to tackle owing to the coupling of multiple variables. To address this non-convex problem, an iterative alternating optimization (AO) algorithm is developed with the assistance of the successive convex approximation (SCA) technique. After that, we extend the system model to both Eve's and Willie's imperfect location knowledge case, which is more sophisticated compared to the perfect location knowledge case due to the uncertain location constraints. We still utilize the iterative AO algorithm combined with SCA and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal {S}$</tex-math></inline-formula> -procedure techniques to cope with the nonconvex problem. Numerical results indicate that our proposed 3D optimization algorithm performs better than the conventional two dimensional (2D) scheme and the benchmark scheme for both perfect and imperfect location knowledge cases.

The influence of event-related factors on sport fans' purchase intention: a study of sponsored products during televised sporting events

PurposeIt is not possible for every fan of a sport to watch matches at stadiums because of the capacity and location constraints. Furthermore, although sport fans could not physically attend sporting events during the COVID-19 pandemic, corporations still showed interest in sponsoring such events. To better understand this phenomenon, this study examined the effects of fans' event involvement on event reputation, event commercialization, corporate brand credibility, corporate brand image and purchase intentions of the corporate sponsor brand.Design/methodology/approachA total of 646 responses were collected from fans of Indian Premier League teams. Confirmatory factor analysis and covariance-based structural equation modelling analyses were conducted on the collected data.FindingsResults showed that fans' involvement in televised sporting events had a positive influence on the events' reputation, which, in turn, had a significant impact on their corporate brand credibility and image. Furthermore, the corporate brand credibility and image had a positive impact on the fans' purchasing decisions.Originality/valueThis study provides valuable implications for marketing managers aiming to enhance their understanding of the impact of event sponsorship on corporate brands. In addition, the findings provide insight into how to support the development of effective sponsorship strategies in the future. The results suggest that sponsoring companies should consider maintaining the credibility and image of their brands to achieve the desired outcomes from sponsoring such sporting events.

A new rock fracture reconstruction method under the constraints of microseismic location and focal mechanism

Under mining conditions, rock masses can experience progressive damage that leads to fracture initiation, propagation and coalescence and thus trigger fracture-controlled disasters, which are dynamic and complex. Therefore, the dynamic characterization of three-dimensional (3D) fractures is critical for revealing disaster-causing mechanisms of rock masses and preventing disasters and has become one of the important problems in the engineering rock mass. This paper proposes a new 3D rock discrete fractures reconstruction method that incorporates microseismic (MS) event location and focal mechanism constraints. The proposed method incorporates a statistical outlier removal (SOR) algorithm, a Gaussian mixed model with expectation maximization (GMM-EM) algorithm for MS events clustering, an intensity-weighted total least square (IWTLS) algorithm for fracture fitting, and moment tensor inversion (MTI) method for fracture orientation optimization. In addition, laboratory uniaxial compression tests with acoustic emission (AE) monitoring were conducted to verify the applicability of the proposed method. Finally, the proposed method was applied to an iron mine with water inrush disasters. The formation process and distribution characteristics of fractures that control water inrush channels were analyzed, and formation mechanisms of water-conducting fractures induced by the mining were determined. The proposed method helps to characterize the dynamic evolution of fractures during rock mass failure under mining disturbance and provides a new idea for recognizing the failure mechanism of rock masses and calibrating water inrush channels.

Short-term solar radiation forecasting using hybrid deep residual learning and gated LSTM recurrent network with differential covariance matrix adaptation evolution strategy

Developing an accurate and robust prediction of long-term average global solar irradiation plays a crucial role in industries such as renewable energy, agribusiness, and hydrology. However, forecasting solar radiation with a high level of precision is historically challenging due to the nature of this source of energy. Challenges may be due to the location constraints, stochastic atmospheric parameters, and discrete sequential data. This paper reports on a new hybrid deep residual learning and gated long short-term memory recurrent network boosted by a differential covariance matrix adaptation evolution strategy (ADCMA) to forecast solar radiation one hour-ahead. The efficiency of the proposed hybrid model was enriched using an adaptive multivariate empirical mode decomposition (MEMD) algorithm and 1+1EA-Nelder–Mead simplex search algorithm. To compare the performance of the hybrid model to previous models, a comprehensive comparative deep learning framework was developed consisting of five modern machine learning algorithms, three stacked recurrent neural networks, 13 hybrid convolutional (CNN) recurrent deep learning models, and five evolutionary CNN recurrent models. The developed forecasting model was trained and validated using real meteorological and Shortwave Radiation (SRAD1) data from an installed offshore buoy station located in Lake Michigan, Chicago, United States, supported by the National Data Buoy Centre (NDBC). As a part of pre-processing, we applied an autoencoder to detect the outliers in improving the accuracy of solar radiation prediction. The experimental results demonstrate that, firstly, the hybrid deep residual learning model performed best compared with other machine learning and hybrid deep learning methods. Secondly, a cooperative architecture of gated recurrent units (GRU) and long short-term memory (LSTM) recurrent models can enhance the performance of Xception and ResNet. Finally, using an effective evolutionary hyper-parameters tuner (ADCMA) reinforces the prediction accuracy of solar radiation.

Reproductive Performance of Bali Cows through Artificial Insemination Program in Polewali Mandar Regency, West Sulawesi Province

Intensification of artificial insemination (AI) in Bali cattle is a government program to increase the population and productivity of local cattle. The objective of this study was to examine the reproductive performance of Bali cows through the AI program in Polewali Mandar Regency, West Sulawesi. The study was conducted in two different locations, i.e. in the low lands (&lt;300mASL) including Wonomulyo and Campalagian Districs, and high lands (&gt;300mASL) including Limboro and Bulo Districts. Data collection was carried out on farmers and inseminators profiles, and cow’s reproductive parameters including service per conception (S/C), conception rate (CR), calving rate (CvR), calving interval (CI) and Calf Mortality (CM). These data were calculated and analyzed descriptively. The cows in this study were raised by farmers in small-scale farm, mostly under 5 heads. The cattle breeding through AI program was carried out by inseminators with over 10 years of experience. In the lowlands, S/C values were 1.26-1.17 and CI were 360 to 366.31 days, respectively. Bali cows that were inseminated using Bali bull semen had a CvR of 75.69% which were higher than those using Simmental bull semen (CvR 49.69%;). While in the highlands, Bali cows that were inseminated with Bali bull semen tended to have higher S/C (1.30) and CI (356.95 days) values but had CvR of 61.00% and CR 77.00% which was also higher than that of Simmental bull semen (S/C 1,50; CI 412,86 days; CvR 50.00%; CR 66.67%). The high S/C in the highlands (1.50) is due to location constraints or the distance between the livestock and the inseminator's residence which is quite far, so it takes time to carry out AI services and is one of the factors that can cause the provision of AI services for female cows in heat is not optimal. In the highlands, most of the cattle are grazed in the grazing areas, making it difficult for breeders to detect estrus. In general, Bali cattle produced by AI in the low lands of Polewali Mandar district tended to have better reproductive performance than those in the high lands. The S/C in the low lands (1.26 and 1.17) is lower than that in the high lands (1.3 and 1.5). Keywords: AI, Bali cows, lower land, high land reproductive performance

The Effectiveness of a Blended Learning-Based Life Design Course: Implications of Instruction and Application of Technology.

Due to the outbreak of the COVID-19 pandemic in 2021 in Taiwan, we have adapted the face-to-face Life Design course to a blended learning approach with educational technology to cope with the problem of cross-generational confusion and anxiety towards later life from learners.The objectives of this study are to.evaluate learners' reactions after attending the Life Design course including their level of satisfaction, engagement (Level 1), and the applicability of courses in their life.evaluate their learning outcomes after attending the Life Design course, such as their acquisition of knowledge, skills, attitudes, confidence, commitment (Level 2), and behavioral changes (Level 3).explore the factors that enable and prevent students from transferring their learning in this course to the action taking and making behavioral changes.explore how the application of educational technology can enhance the teaching and learning in the Life Design course. This study used an action research method to solve two main problems we identified in practice: students' confusion about their future life and the shortcomings of traditional teaching methods, which cannot meet the learning needs of this type of course due to the requirement of intensive personal reflection and self-disclosure. Participants were 36 master's students who completed the Life Design course. Based on this course's design, implementation, and evaluation, we used the new Kirkpatrick Learning Assessment Model (Kirkpatrick J, Kirkpatrick WK. An introduction to the new world Kirkpatrick Model. Kirkpatrick Partners, 2021) to analyze the learning effectiveness on the Reaction, Learning, and Behavioral levels. To facilitate learners to overcome the cross-generational confusion of their life design and solve the shortage of face-to-face teaching methods, we took biographical learning as the core theme for this Life Design course and designed online and offline learning activities. The blended learning approach with educational technology allowed us to go beyond time and location constraints and provide a holistic and inseparable learning experience in both formats. The result of the evaluation shows that students who took the Life Design course were highly satisfied with the overall course design, topics, and the suitability of a blended learning approach, which motivated them to extend their learning outside the classroom and helped them benefit from a more trusted, personal and hybrid interaction with teachers and their peers both online and offline. On the learning level, students not only learned the correct knowledge of age perspectives, changed their views of career and personal development, and acquired skills for life design, but were also confident and committed to applying what they have learned in their future life. After the course, many students applied and integrated the learning into behavioral changes in their life. In terms of the difficulties and hindrances encountered in action taking, many students mentioned the lack of peers' support and constraints from their busy daily life. Many suggested providing extra support after the course with regular impulse, follow-ups, and individual feedback from teachers and peers in an online learning community. This indicates how educational technology can better support these elements in continuous learning and the transfer of learning. Based on these results, we affirm that implementing this Life Design course with a blended learning approach is indeed better than a fully physical course. However, the focus of a blended learning approach should be on learners from a pedagogical perspective rather than technology.

Spatial Heterogeneity and Influencing Factors of High-Grade Tourist Attractions in the Tibetan Plateau.

The construction of the world tourism destination on the Tibetan Plateau is inseparable from the traditional tourist attractions, which are significant landscape ecological units. Based on the data of high-grade tourist attractions on the Tibetan Plateau, the spatial heterogeneity and influence factors are studied employing the Standard Deviation Ellipse (SDE), Kernel Density Estimation (KDE), spatial autocorrelation (SA), and modified tourism gravity model methods. The results show that: (1) the overall spatial distribution characteristic of high-grade tourist attractions is in the direction of northeast-southwest, with solid centripetal force, and the center of gravity of the ellipse is in Yushu City. (2) The spatial heterogeneity of the kernel density distribution is remarkable, clustered in the southeastern half of the plateau, showing a double nucleus-driven and strip-connected pattern. The distribution among cities has a hierarchical heterogeneity, and the two capital cities of Xining and Lhasa play a crucial role. (3) The high-grade tourist attractions are spatially dependent, with evident characteristics of large dispersion and small clustering, and the spatial association type is mainly negative. (4) This paper verifies the significant single-factor mechanism affecting the spatial distribution from supportive and intrinsic dimensions with natural environmental base, tourism resource endowment, socio-economic development, transportation location constraints, and spatial tourism linkages. Finally, the article provides suggestions for the high-quality development of high-grade tourist attractions on the Tibetan Plateau.

Spatial location constraint prototype loss for open set recognition

One of the challenges in pattern recognition is open set recognition. Compared with closed set recognition, open set recognition needs to reduce not only the empirical risk, but also the open space risk, and how to reduce the open space risk is the key of open set recognition. Compared with the previous work, this paper analyzes the distribution rules of the known and unknown features, which is highly related to the open space risk. Then, this paper proposes the matching theory to explain the origin of the open space risk. On this basis, the spatial location constraint prototype loss function is proposed to reduce both risks simultaneously. Extensive experiments on multiple benchmark datasets and many visualization results verify the validity of the proposed matching theory and the effectiveness of the proposed method.

Boundary-Sensitive Loss Function With Location Constraint for Hard Region Segmentation.

In computer-aided diagnosis and treatment planning, accurate segmentation of medical images plays an essential role, especially for some hard regions including boundaries, small objects and background interference. However, existing segmentation loss functions including distribution-, region- and boundary-based losses cannot achieve satisfactory performances on these hard regions. In this paper, a boundary-sensitive loss function with location constraint is proposed for hard region segmentation in medical images, which provides three advantages: i) our Boundary-Sensitive loss (BS-loss) can automatically pay more attention to the hard-to-segment boundaries (e.g., thin structures and blurred boundaries), thus obtaining finer object boundaries; ii) BS-loss also can adjust its attention to small objects during training to segment them more accurately; and iii) our location constraint can alleviate the negative impact of the background interference, through the distribution matching of pixels between prediction and Ground Truth (GT) along each axis. By resorting to the proposed BS-loss and location constraint, the hard regions in both foreground and background are considered. Experimental results on three public datasets demonstrate the superiority of our method. Specifically, compared to the second-best method tested in this study, our method improves performance on hard regions in terms of Dice similarity coefficient (DSC) and 95% Hausdorff distance (95%HD) of up to 4.17% and 73% respectively. In addition, it also achieves the best overall segmentation performance. Hence, we can conclude that our method can accurately segment these hard regions and improve the overall segmentation performance in medical images.

Runway determination using two-point time difference method

Around airports having multiple runways, aircraft noise affected areas vary depending on the runway operation because the flight path changes by the operation. Therefore, it is important to figure out exactly which runway was used for analyzing the noise impact on the surrounding area. For this purpose, runway information included in flight data provided by the airport operator can be used in most commercial airports. However, for some airports, the data is unavailable or not always accurate. We developed "Takeoff/ landing runway determination system; DL-TLS" for determining runway operations and have been utilizing it to aircraft noise analysis. However, that system requires to place measurement stations at the end of each runway to ensure the high level of accuracy. To solve this issue, we focused on difference in acquisition time of the same transponder signal at two measurement stations. This new approach achieved satisfactory level of runway determination accuracy, by matching the time difference changes with template for each runway. We proved that this method can be used in combination with the current DL-TLS with even higher accuracy. In addition, we showed the possibility of reducing number of measurement stations and eliminating the measurement location constraint.

Detection and Intelligent Control of Cloud Data Location Using Hyperledger Framework

Cloud Computing and its security issues have always drawn technical attention. Specifically, the compliance issues associated with the location of cloud data have always been a concern of a Cloud Service Consumer (CSC). On the other hand, blockchain based smart contracts have become very popular nowadays for automatizing legal transactions. They eliminate the need of mediators to verify a process and secure the same using digital signatures. Moreover, the in-built immutable nature of the blockchain makes it to compromise its security. A “Hyperledger Fabric” (Androulaki et al., 2018) based blockchain framework is used in this work to solve the locational constraints of cloud based services and guarantee a compliant geographical transfer of the cloud data when required. Our contribution towards configuring the hyperledger network and designing the chaincodes guarantee an organization wise segregation of the location information and prevent illegitimate users from accessing the same. Add-on security measures including port segregation, TLS (Transport Layer Security) certificates and access control rules are implemented to secure the configuration files, chaincodes and ledgers, respectively. The simulation results reflect a scalable system as denoted by the performance graphs. Security effectiveness value is calculated based on the NIST threat model.

Joint Reconfigurable Intelligent Surface Location and Passive Beamforming Optimization for Maximizing the Secrecy-Rate

The physical layer security (PLS) is investigated for reconfigurable intelligent surface (RIS) assisted wireless networks, where a source transmits its confidential information to a legitimate destination with the aid of a single small RIS in the presence of a malicious eavesdropper. A new joint RIS location and passive beamforming (J-LPB) optimization scheme is proposed for the sake of maximizing the secrecy rate under the RIS location constraint and the constraint that the modulus of the reflecting coefficient at each RIS's unit is not larger than 1. Specifically, we analyze the optimal location of the RIS, and conclude that the product involving the source-RIS distance and the RIS-destination distance should be minimized. Since the product minimization problem is nonconvex, we then propose a two-tier optimization algorithm for solving it. Based on the near-optimal RIS 3D location obtained, we further formulate the passive beamforming optimization problem, and then propose to apply the Charnes-Cooper transformation along with the sequential rank-one constraint relaxation (SROCR) algorithm to solve it. Our numerical results show that the secrecy rate of the proposed J-LPB optimization scheme is higher than that of the benchmarks. Explicitly, we use the following benchmarks: the near-source-based RIS location and passive beamforming (NSB-LPB) optimization scheme, the near-destination-based RIS location and passive beamforming (NDB-LPB) optimization scheme, and the random RIS location and passive beamforming (R-LPB) optimization scheme. Finally, the benefits of our J-LPB scheme are further increased with the number of RIS units.

Doing Counseling Online: Is It Effective For Farmers?

The current online-based era is part of advanced technology powered by the internet and has brought many changes in result. This study aimed to discern how online-based counseling communication has developed in farmer groups, and determine the effect of online-based counseling communication improvement on the work volume of farmer groups. This research conducted from September 2021 to March 2022 in Telaga Subdistrict, Gorontalo Regency. Simple random sampling was used to collect the data and determined by Slovin formula. Data were analyzed using multiple linear regression analysis techniques, and hypothesis testing was carried out. The results of the study revealed that The right person, and The right communication tools partially had a positive and significant influence on the effectiveness of online-based counseling. This study found that location constraints were not a problem in online-based counseling activities, but extension support and the communication tools used greatly determined the effectiveness of online-based counseling.

Throughput Maximization for UAV-Enabled Integrated Periodic Sensing and Communication

Driven by unmanned aerial vehicle (UAV)’s advantages of flexible observation and enhanced communication capability, it is expected to revolutionize the existing integrated sensing and communication (ISAC) system and promise a more flexible joint design. Nevertheless, the existing works on ISAC mainly focus on exploring the performance of both functionalities simultaneously during the entire considered period, which may ignore the practical asymmetric sensing and communication requirements. In particular, always forcing sensing along with communication may make it is harder to balance between these two functionalities due to shared spectrum resources and limited transmit power. To address this issue, we propose a new integrated periodic sensing and communication (IPSAC) mechanism for the UAV-enabled ISAC system to provide a more flexible trade-off between two integrated functionalities. Specifically, the system achievable rate is maximized via jointly optimizing UAV trajectory, user association, target sensing selection, and transmit beamforming, while meeting the sensing frequency and beam pattern gain requirement for the given targets. Despite that this problem is highly non-convex and involves closely coupled integer variables, we derive the closed-form optimal beamforming vector to dramatically reduce the complexity of beamforming design, and present a tight lower bound of the achievable rate to facilitate UAV trajectory design. Based on the above results, we propose a two-layer penalty-based algorithm to efficiently solve the considered problem. To draw more important insights, the optimal achievable rate and the optimal UAV location are analyzed under a special case of infinity number of antennas. Furthermore, we prove the structural symmetry between the optimal solutions in different ISAC frames without location constraints in our considered UAV-enabled ISAC system. Based on this, we propose an efficient algorithm for solving the problem with location constraints. Numerical results validate the effectiveness of our proposed designs and also unveil a more flexible trade-off in ISAC systems over benchmark schemes.

Optimal resource allocation in practical quantum key distribution optical networks

In the application research of large-scale quantum communication network, one generally realizes resource allocation by constructing virtual service network and mapping it to actual physical space. In this mapping process, some assumptions are often made to simplify the model. For example, the key resource in the physical topology is assumed to be a fixed value, that is, the actual physical conditions and the performance differences of key supply caused by different protocols are ignored. This assumption may lead the network to fail to run appropriately in practical applications. In order to solve the above problems, from the perspective of link mapping, this paper proposes an improved virtual service mapping model and virtual service mapping algorithm with the quantum key distribution optical network as the underlying network, which makes it closer to the actual application scenario. On the one hand, by increasing the constraints of geographical location, the range from virtual nodes to the mappable physical nodes is reasonably restricted. On the other hand, from the perspective of hardware cost and actual key generation rate, the cost performance evaluation index is proposed to allocate and manage resources. In addition, by combining three mainstream quantum key distribution protocols (BB84, measurement-device-independent, and twin-field), we construct a universal virtual service mapping model in the quantum key distribution optical network, and realize the recommendation of the optimal protocol and the optimal allocation and management of resources.

СУТНІСТЬ ТА КЛАСИФІКАЦІЯ МЕРЕЖЕВИХ ПІДПРИЄМНИЦЬКИХ СТРУКТУР

The article examines network entrepreneurial structures as new subjects of the digital economy. Defined and generalized understanding of the essence of such structures from the point of view of a separate unit that uses information technology networks to connect people, assets and ideas to create and distribute products and services without the constraints of traditional organizational boundaries or physical location; consolidation of business units in which human and work processes interact, seeking joint results and mutual benefit; formation of a network of people or organizations that are independent, implement a joint project or joint economic activity. It was found that in Ukraine, network business structures belong to the class of enterprise associations and are created in the form of concerns, holdings and other types of enterprise associations. It has been proven that rapid changes in information and communication technologies and the external environment, as well as the elimination of barriers between the enterprise and the environment, are the main prerequisites for the formation of network business structures. It was determined that both divisions of a large enterprise, as well as individual enterprises and freelancers, can be integrated into the network business structure. The typification of network business structures was formed according to six classification features, namely: branch direction; scope of activity; term of formation; management model; the nature of obligations; depending on the purpose of combining enterprises into a network business structure. The advantages of creating network business structures are systematized, namely: increased organizational flexibility; stability of ties between integrated enterprises within the network business structure; decentralization of the organizational structure; a higher level of coordination and communication between units integrated into the network business structure; openness to organizational changes; universality and adaptability of the network business structure; better access to resources and expertise; cost reduction; advanced innovation; increasing competitiveness.

Detection of Unknown DDoS Attack Using Reconstruct Error and One-Class SVM Featuring Stochastic Gradient Descent

The network system has become an indispensable component of modern infrastructure. DDoS attacks and their variants remain a potential and persistent cybersecurity threat. DDoS attacks block services to legitimate users by incorporating large amounts of malicious traffic in a short period or depleting system resources through methods specific to each client, causing the victim to lose reputation, finances, and potential customers. With the advancement and maturation of artificial intelligence technology, machine learning and deep learning are widely used to detect DDoS attacks with significant success. However, traditional supervised machine learning must depend on the categorized training sets, so the recognition rate plummets when the model encounters patterns outside the dataset. In addition, DDoS attack techniques continue to evolve, rendering training based on conventional data models unable to meet contemporary requirements. Since closed-set classifiers have excellent performance in cybersecurity and are quite mature, this study will investigate the identification of open-set recognition issues where the attack pattern does not accommodate the distribution learned by the model. This research proposes a framework that uses reconstruction error and distributes hidden layer characteristics to detect unknown DDoS attacks. This study will employ deep hierarchical reconstruction nets (DHRNet) architecture and reimplement it with a 1D integrated neural network employing loss function combined with spatial location constraint prototype loss (SLCPL) as a solution for open-set risks. At the output, a one-class SVM (one-class support vector machine) based on a random gradient descent approximation is used to recognize the unknown patterns in the subsequent stage. The model achieves an impressive detection rate of more than 99% in testing. Furthermore, the incremental learning module utilizing unknown traffic labeled by telecom technicians during tracking has enhanced the model’s performance by 99.8% against unknown threats based on the CICIDS2017 Friday open dataset.

Monitoring extreme meteo-marine events in the Mediterranean area using the microseism (Medicane Apollo case study)

Microseism is the continuous background seismic signal caused by the interaction between the atmosphere, the hydrosphere and the solid Earth. Several studies have dealt with the relationship between microseisms and the tropical cyclones, but none focused on the small-scale tropical cyclones that occur in the Mediterranean Sea, called Medicanes. In this work, we analysed the Medicane Apollo which impacted the eastern part of Sicily during the period 25 October-5 November 2021 causing heavy rainfall, strong wind gusts and violent sea waves. We investigated the microseism accompanying this extreme Mediterranean weather event, and its relationship with the sea state retrieved from hindcast maps and wave buoys. The spectral and amplitude analyses showed the space-time variation of the microseism amplitude. In addition, we tracked the position of Apollo during the time using two different methods: (i) a grid search method; (ii) an array analysis. We obtained a good match between the real position of Apollo and the location constraint by both methods. This work shows that it is possible to extract information on Medicanes from microseisms for both research and monitoring purposes.