ABSTRACT
The intrusion detection process is important in various applications to identify unauthorized Internet of Things (IoT) network access. IoT devices are accessed by intermediators while transmitting the information, which causes security issues. Several intrusion detection systems are developed to identify intruders and unauthorized access in different software applications. Existing systems consume high computation time, making it difficult to identify intruders accurately. This research issue is mitigated by applying the Interrupt-aware Anonymous User-System Detection Method (IAU-S-DM). The method uses concealed service sessions to identify the anonymous interrupts. During this process, the system is trained with the help of different parameters such as origin, session access demands, and legitimate and illegitimate users of various sessions. These parameters help to recognize the intruder's activities with minimum computation time. In addition, the collected data is processed using the deep recurrent learning approach that identifies service failures and breaches, improving the overall intruder detection rate. The created system uses the TON-IoT dataset information that helps to identify the intruder activities while accessing the different data resources. This method's consistency is verified using the metrics of service failures of 10.65%, detection precision of 14.63%, detection time of 15.54%, and classification ratio of 20.51%.
ABSTRACT
A major portion of Bangladesh is currently experiencing a scarcity of safe drinking water because of arsenic contamination, high salinity and human-induced pollution. The objectives of this study were to identify locations with a high scarcity of drinking water and suitability of harvesting rainwater. Kriging interpolation algorithms of Geographical Information System (GIS) was employed to identify the probable water scarce zones as well as suitable zones of harvesting rain water from the available data of secondary sources. Statistical methods were employed to cluster, correlate, and regress variables such as rainfall, salinity, and As. The results showed that groundwater quality in the southwestern parts of Bangladesh is saline with high concentration (>10000 µS/cm). On the other hand, the northeastern and southwestern parts of Bangladesh are also vulnerable to arsenic contamination (60 %-97 % of tubewells), compared to other regions. The rainfall zonation map, covering the years 1951-2022, indicated that the Sylhet division had the highest potential for rainfall (ranging from 2600 to 3900 mm). From this study it was demonstrated that Sylhet, Noakhali, Bhola, Barishall, Patuakhali, Bagerhat, and Khulna were identified as suitable places for sustainable rainwater harvesting (RWH). The findings of this study may play significant role towards achieving sustainable potable water supply in vulnerable zones, if they receive attention from policymakers.
ABSTRACT
Offshore Freshened Groundwater (OFG) reservoirs are gaining attention, as evidence suggests they are more prevalent worldwide than previously thought. OFG systems are generally classified as either passive, a relic of ancient, lower sea levels, or as active, with an onshore-offshore hydrogeologic connection and associated discharge offshore. Previous studies on the mechanisms of OFG were conducted in various hydrogeologic settings, but the role of faults remains understudied. Based on geologic data, we apply hydrogeologic modeling of a faulted submarine confined aquifer in the Levant basin (eastern Mediterranean), to study the impact of faults on OFG. We find that faults that are close to the coastline and within the brackish zone that would have developed without a fault control the offshore salinities regardless of initial conditions. The influence of distal faults, in contrast, depends on antecedent conditions. When initial salinities are such that the distal fault lies in the fresh part of the aquifer, the saline wedge migrates landward toward the fault with sea-level rise, and the fault dictates the steady-state salinity distribution. If the fault is initially within the saline part of the aquifer, freshwater never reaches the fault, likely due to the density-driven flow barrier that the underlying saline wedge generates. These findings suggest a new mode of OFG in which the same geologic system can be either active or passive depending on the hydrologic history. This should be considered in future studies of OFG systems, the functioning of which has implications for marine ecosystems, seafloor geomorphology, and coastal water resources.
ABSTRACT
Climate change and excessive groundwater extraction are major contributors to rising groundwater salinization due to seawater intrusion in coastal aquifers. This study aims to define a wide-applicable approach in which hydrological balance, boundary conditions, and irrigation water demand, defined over time considering climate change predictions, can integrated into a numerical model of the groundwater system. The approach was tested in a selected coastal aquifer. The approach spans from the past, used to define steady or almost natural conditions for calibration purposes (1950-2000 in the test), to the future (2100), divided in decade steps. The water balance analysis is based on an inverse hydrogeological water balance approach. The future climate change predictions are used to assess variations in boundary conditions of the groundwater model concerning salinity and sea level, recharge, and inflow from upstream aquifers. The approach considers changes in agricultural activities, groundwater demand, and river stage. The regional model is generated using the MODFLOW code for the groundwater flow model and the SEAWAT code for the salt transport model. The test concerns the Metaponto coastal plain, in which a porous aquifer is at salinization risk due to seawater intrusion. In this way, different influences of climate change and human activities are combined to define a 3d view of groundwater depletion and salinization effects. Quantifying these potential effects or risks, adaptation scenarios with numerical assessments are outlined in this study.
ABSTRACT
Facebook is one of the most popular social networking sites. However, Facebook intrusion or addiction is a growing concern as it involves an excessive attachment to Facebook, which disrupts daily functioning. To date, few studies have examined whether cross-cultural differences in the measurement of Facebook addiction exist. The aim of this study was to investigate the cross-cultural validity and measurement invariance of the Facebook Intrusion Questionnaire (FIQ), one of the most widely used measures of Facebook addiction, across 25 countries (N = 12,204, 62.3% female; mean age = 25 years). Multigroup confirmatory factor analyses (MGCFA) assessed cross-cultural validity as well as invariance. Additionally, individual confirmatory factor analyses evaluated the factorial structure and measurement invariance across genders in each country. The FIQ demonstrated partial metric invariance across countries and metric (13 countries), scalar (11 countries) or residual (10 countries) invariance across genders within individual countries. A one-factor model indicated a good fit in 18 countries. Cronbach's alpha for the entire sample was .85. Our findings suggest that the FIQ may provide an adequate assessment of Facebook addiction that is psychometrically equivalent across cultures. Moreover, the questionnaire seems to be universal and suitable for studying different social media in distinct cultural environments. Consequently, this robust tool can be used to explore behaviours related to specific media that are particularly popular in any given country.
ABSTRACT
In this paper, an enhanced equilibrium optimization (EO) version named Levy-opposition-equilibrium optimization (LOEO) is proposed to select effective features in network intrusion detection systems (IDSs). The opposition-based learning (OBL) approach is applied by this algorithm to improve the diversity of the population. Also, the Levy flight method is utilized to escape local optima. Then, the binary rendition of the algorithm called BLOEO is employed to feature selection in IDSs. One of the main challenges in IDSs is the high-dimensional feature space, with many irrelevant or redundant features. The BLOEO algorithm is designed to intelligently select the most informative subset of features. The empirical findings on NSL-KDD, UNSW-NB15, and CIC-IDS2017 datasets demonstrate the effectiveness of the BLOEO algorithm. This algorithm has an acceptable ability to effectively reduce the number of data features, maintaining a high intrusion detection accuracy of over 95%. Specifically, on the UNSW-NB15 dataset, BLOEO selected only 10.8 features on average, achieving an accuracy of 97.6% and a precision of 100%.
ABSTRACT
Fluorination is one of the most efficient and universal strategies to increase the hydrophobicity of materials and consequently their water stability. Zeolitic-imidazolate frameworks (ZIFs), which have limited stability in aqueous media and even lower stability when synthesized on a nanometric scale, can greatly benefit from the incorporation of fluorine atoms, not only to improve their stability but also to provide additional properties. Herein, we report the preparation of two different fluorinated ZIFs through a simple and scalable approach by using mixed ligands [2-methylimidazole, as a common ligand, and 4-(4-fluorophenyl)-1H-imidazole (monofluorinated linker) or 2-methyl-5-(trifluoromethyl)-1H-imidazole (trifluorinated linker) as a dopant], demonstrating the high versatility of the synthetic method developed to incorporate different fluorine-containing imidazole-based ligands. Second, we demonstrate for the first time that these nanoscale fluorinated ZIFs outperform the pristine ZIF-8 for water intrusion/extrusion, i.e., for storing mechanical energy via forced intrusion of nonwetting water due to the improved hydrophobicity and modified framework dynamics. Moreover, we also show that by varying the nature of the F-imidazole ligand, the performance of the resulting ZIFs, including the pressure thresholds and stored/dissipated energy, can be finely tuned, thus opening the path for the design of a library of fluorine-modified ZIFs with unique behavior.
ABSTRACT
In the current international context characterized by the tendency to stricter limits for P concentration in treated wastewater and a strong drive towards phosphate recovery, it is crucial to develop cost-effective technologies to remove and recover phosphate from municipal wastewater (MWW). In this study, an initial screening of the phosphate adsorption performances of 9 sorbents including several hydrotalcites led to the selection of calcined pyroaurite - an innovative material composed of mixed Mg/Fe oxides - as the best-performing one. The assessment of calcined pyroaurite by means of isotherms and continuous-flow adsorption/desorption tests conducted with actual MWW resulted in a high P sorption capacity (12 mgP g-1 at the typical phosphate concentration in MWW), the capacity to treat 730 BVs at the 1 mgP L-1 breakpoint imposed by the current EU legislation, and a 93 % phosphate recovery. Calcined pyroaurite resulted in satisfactory performances also in a test conducted with a saline MWW deriving from a hotspot of seawater intrusion, a rapidly increasing phenomenon as a result of climate change. Five consecutive adsorption/desorption cycles conducted in a 20-cm column at a 5-min empty bed contact time resulted stable in terms of P adsorption/recovery performances, specific surface area and chemical structure of calcined pyroaurite. In the perspective to apply phosphate recovery with calcined pyroaurite at full scale, the process scale-up to a 60-cm packed bed - close to the column heights of industrial applications - resulted in stable performances. Calcium phosphate, widely used to produce phosphate-based fertilizers, can be obtained from the desorbed product by precipitation with Ca(OH)2. These results point to calcined pyroaurite as a very promising material for phosphate removal and recovery from MWW and from other P-rich effluents in a circular economy perspective.
ABSTRACT
The aim of this study was to assess whether the psychological impact of the COVID-19 pandemic on children and adolescents had decreased four years after the initial assessment. This study aimed to determine if children with an active lifestyle and participation in sports activities were protected against this traumatic stress. This study included a total of 284 Italian participants assessed at two different time points: the first assessment was conducted in 2020 when the children were aged 9-12 years, and a second assessment was carried out four years later when the participants were aged 13-16. Participants completed the Impact of Event Scale-Revised questionnaire (IES-R), with the IES-8 and IES-15 versions used accordingly based on age group. In the 2020 assessment, 146 (51.4%) reported a score higher than the cut-off for significant traumatic stress, while in 2024, only 49 participants (17.2%). The chi-square analysis indicated that this decrement was statistically significant (p < 0.001). RM-ANOVA showed a significant reduction for both Intrusion Score and Avoidance Score (p < 0.001). A statistical interaction between gender and time was observed. There were weak correlations between the level of children's sport practice, and no differences between those who engage in individual or team sports. Despite this study showing that young people are overcoming the pandemic crisis and its consequences, identifying potential modifiable risk factors and empowering protective factors remains crucial, especially for those who continue to experience psychological issues. The restrictions particularly impacted active children by disrupting their routine, which may have compromised the universally recognized protective value of sports.
Subject(s)
COVID-19 , Exercise , Stress Disorders, Post-Traumatic , Humans , COVID-19/psychology , COVID-19/epidemiology , Adolescent , Male , Female , Child , Cross-Sectional Studies , Stress Disorders, Post-Traumatic/epidemiology , Stress Disorders, Post-Traumatic/psychology , Italy/epidemiology , Surveys and Questionnaires , SARS-CoV-2 , Sports/psychologyABSTRACT
In the context of the 5G network, the proliferation of access devices results in heightened network traffic and shifts in traffic patterns, and network intrusion detection faces greater challenges. A feature selection algorithm is proposed for network intrusion detection systems that uses an improved binary pigeon-inspired optimizer (SABPIO) algorithm to tackle the challenges posed by the high dimensionality and complexity of network traffic, resulting in complex models, reduced accuracy, and longer detection times. First, the raw dataset is pre-processed by uniquely one-hot encoded and standardized. Next, feature selection is performed using SABPIO, which employs simulated annealing and the population decay factor to identify the most relevant subset of features for subsequent review and evaluation. Finally, the selected subset of features is fed into decision trees and random forest classifiers to evaluate the effectiveness of SABPIO. The proposed algorithm has been validated through experimentation on three publicly available datasets: UNSW-NB15, NLS-KDD, and CIC-IDS-2017. The experimental findings demonstrate that SABPIO identifies the most indicative subset of features through rational computation. This method significantly abbreviates the system's training duration, enhances detection rates, and compared to the use of all features, minimally reduces the training and testing times by factors of 3.2 and 0.3, respectively. Furthermore, it enhances the F1-score of the feature subset selected by CPIO and Boost algorithms when compared to CPIO and XGBoost, resulting in improvements ranging from 1.21% to 2.19%, and 1.79% to 4.52%.
ABSTRACT
Liquid porosimetry experiments reveal a peculiar trend of the intrusion pressure of water in hydrophobic Cu2(3,3',5,5'-tetraethyl-4,4'-bipyrazolate) MOF. At lower temperature (T) range, the intrusion pressure (Pi) increases with T. For higher T values, Piâ first reaches a maximum and then decreases. This is at odds with the Young-Laplace law, which for systems showing a continuous decrease of contact angle with T predicts a corresponding reduction of the intrusion pressure. Though the Young-Laplace law is not expected to provide quantitative predictions at the subnanoscale of Cu2(tebpz) pores, the physical intuition suggests that to a reduction of their hydrophobicity corresponds a reduction of the Pi. Molecular dynamics simulations and sychrothron experiments allowed to clarify the mechanism of the peculiar trend of Pi with T. At increasing temperatures the vapor density within the MOF' pores grows significantly, bringing the corresponding partial pressure to ≈5 MPa. This pressure, which is consistent with the shift of Pi observed in liquid porosimetry, represents a threshold to be overcame before intrusion takes place. Beyond some value of temperature, the phenomenon of reduction of hydrophobicity (and water surface tension) dominated over the opposite effect of increase of vapor pressure and Pi inverts its trend with T.
ABSTRACT
Maintaining security in communication networks has long been a major concern. This issue has become increasingly crucial due to the emergence of new communication architectures like the Internet of Things (IoT) and the advancement and complexity of infiltration techniques. For usage in networks based on the Internet of Things, previous intrusion detection systems (IDSs), which often use a centralized design to identify threats, are now ineffective. For the resolution of these issues, this study presents a novel and cooperative approach to IoT intrusion detection that may be useful in resolving certain current security issues. The suggested approach chooses the most important attributes that best describe the communication between objects by using Black Hole Optimization (BHO). Additionally, a novel method for describing the network's matrix-based communication properties is put forward. The inputs of the suggested intrusion detection model consist of these two feature sets. The suggested technique splits the network into a number of subnets using the software-defined network (SDN). Monitoring of each subnet is done by a controller node, which uses a parallel combination of convolutional neural networks (PCNN) to determine the presence of security threats in the traffic passing through its subnet. The proposed method also uses the majority voting approach for the cooperation of controller nodes in order to more accurately detect attacks. The findings demonstrate that, in comparison to the prior approaches, the suggested cooperative strategy can detect assaults in the NSLKDD and NSW-NB15 datasets with an accuracy of 99.89 and 97.72 percent, respectively. This is a minimum 0.6 percent improvement.
ABSTRACT
The number of connected devices or Internet of Things (IoT) devices has rapidly increased. According to the latest available statistics, in 2023, there were approximately 17.2 billion connected IoT devices; this is expected to reach 25.4 billion IoT devices by 2030 and grow year over year for the foreseeable future. IoT devices share, collect, and exchange data via the internet, wireless networks, or other networks with one another. IoT interconnection technology improves and facilitates people's lives but, at the same time, poses a real threat to their security. Denial-of-Service (DoS) and Distributed Denial-of-Service (DDoS) attacks are considered the most common and threatening attacks that strike IoT devices' security. These are considered to be an increasing trend, and it will be a major challenge to reduce risk, especially in the future. In this context, this paper presents an improved framework (SDN-ML-IoT) that works as an Intrusion and Prevention Detection System (IDPS) that could help to detect DDoS attacks with more efficiency and mitigate them in real time. This SDN-ML-IoT uses a Machine Learning (ML) method in a Software-Defined Networking (SDN) environment in order to protect smart home IoT devices from DDoS attacks. We employed an ML method based on Random Forest (RF), Logistic Regression (LR), k-Nearest Neighbors (kNN), and Naive Bayes (NB) with a One-versus-Rest (OvR) strategy and then compared our work to other related works. Based on the performance metrics, such as confusion matrix, training time, prediction time, accuracy, and Area Under the Receiver Operating Characteristic curve (AUC-ROC), it was established that SDN-ML-IoT, when applied to RF, outperforms other ML algorithms, as well as similar approaches related to our work. It had an impressive accuracy of 99.99%, and it could mitigate DDoS attacks in less than 3 s. We conducted a comparative analysis of various models and algorithms used in the related works. The results indicated that our proposed approach outperforms others, showcasing its effectiveness in both detecting and mitigating DDoS attacks within SDNs. Based on these promising results, we have opted to deploy SDN-ML-IoT within the SDN. This implementation ensures the safeguarding of IoT devices in smart homes against DDoS attacks within the network traffic.
ABSTRACT
INTRODUCTION: One of the main concerns around the use of antibiotic-loaded bone cement (ALBC) is the potential reduction in the mechanical properties of the cement when antibiotics are admixed. The purpose of this study was to determine whether there is a difference between plain cement and ALBC in terms of radiological intrusion into the bone in total knee arthroplasties (TKAs). METHODS: Prospective randomized study of 80 consecutive patients who underwent TKA. Depending on the cement used, patients were divided into two groups by a computer-generated randomization programme: the cement without antibiotic (Group 1) or the ALBC (Group 2). Cement intrusion was measured in postoperative radiographs in eight different regions in the tibial component and six regions in the femoral component. RESULTS: The average cement intrusion was similar in both groups (p = nonsignificance [n.s.]). Group 1 (plain cement) had an average cement intrusion in the femur of 1.4 mm (±0.4) and 2.4 mm (±0.4) in the tibia. In Group 2 (ALBC), the average cement intrusion in the femur came to 1.6 (±0.5) and 2.4 mm (±0.5) in the tibia. In 80% of the patients, the cement intrusion in the tibia averaged a minimum of 2 mm, being similar in both groups (p = n.s.). CONCLUSION: There are no differences in bone intrusion when comparing plain cement to ALBC. Therefore, the use of ALBC in primary TKA may be indicated, achieving optimal bone penetration. LEVEL OF EVIDENCE: Level I.
ABSTRACT
The constantly changing nature of cyber threats presents unprecedented difficulties for people, institutions, and governments across the globe. Cyber threats are a major concern in today's digital world like hacking, phishing, malware, and data breaches. These can compromise anyone's personal information and harm the organizations. An intrusion detection system plays a vital responsibility to identifying abnormal network traffic and alerts the system in real time if any malicious activity is detected. In our present research work Artificial Neural Networks (ANN) layers are optimized with the execution of Spider Monkey Optimization (SMO) to detect attacks or intrusions in the system. The developed model SMO-ANN is examined using publicly available dataset Luflow, CIC-IDS 2017, UNR-IDD and NSL -KDD to classify the network traffic as benign or attack type. In the binary Luflow dataset and the multiclass NSL-KDD dataset, the proposed model SMO-ANN has the maximum accuracy, at 100% and 99%, respectively.
Subject(s)
Algorithms , Computer Security , Neural Networks, Computer , Animals , Atelinae/physiologyABSTRACT
Addressing the limitations of current railway track foreign object detection techniques, which suffer from inadequate real-time performance and diminished accuracy in detecting small objects, this paper introduces an innovative vision-based perception methodology harnessing the power of deep learning. Central to this approach is the construction of a railway boundary model utilizing a sophisticated track detection method, along with an enhanced UNet semantic segmentation network to achieve autonomous segmentation of diverse track categories. By employing equal interval division and row-by-row traversal, critical track feature points are precisely extracted, and the track linear equation is derived through the least squares method, thus establishing an accurate railway boundary model. We optimized the YOLOv5s detection model in four aspects: incorporating the SE attention mechanism into the Neck network layer to enhance the model's feature extraction capabilities, adding a prediction layer to improve the detection performance for small objects, proposing a linear size scaling method to obtain suitable anchor boxes, and utilizing Inner-IoU to refine the boundary regression loss function, thereby increasing the positioning accuracy of the bounding boxes. We conducted a detection accuracy validation for railway track foreign object intrusion using a self-constructed image dataset. The results indicate that the proposed semantic segmentation model achieved an MIoU of 91.8%, representing a 3.9% improvement over the previous model, effectively segmenting railway tracks. Additionally, the optimized detection model could effectively detect foreign object intrusions on the tracks, reducing missed and false alarms and achieving a 7.4% increase in the mean average precision (IoU = 0.5) compared to the original YOLOv5s model. The model exhibits strong generalization capabilities in scenarios involving small objects. This proposed approach represents an effective exploration of deep learning techniques for railway track foreign object intrusion detection, suitable for use in complex environments to ensure the operational safety of rail lines.
ABSTRACT
This paper presents a real-time intrusion detection system (IDS) aimed at detecting the Internet of Things (IoT) attacks using multiclass classification models within the PySpark architecture. The research objective is to enhance detection accuracy while reducing the prediction time. Various machine learning algorithms are employed using the OneVsRest (OVR) technique. The proposed method utilizes the IoT-23 dataset, which consists of network traffic from smart home IoT devices, for model development. Data preprocessing techniques, such as data cleaning, transformation, scaling, and the synthetic minority oversampling technique (SMOTE), are applied to prepare the dataset. Additionally, feature selection methods are employed to identify the most relevant features for classification. The performance of the classifiers is evaluated using metrics such as accuracy, precision, recall, and F1 score. The results indicate that among the evaluated algorithms, extreme gradient boosting achieves a high accuracy of 98.89%, while random forest demonstrates the most efficient training and prediction times, with a prediction time of only 0.0311 s. The proposed method demonstrates high accuracy in real-time intrusion detection of IoT attacks, outperforming existing approaches.
ABSTRACT
The Internet of Medical Things (IoMT) has significantly advanced healthcare, but it has also brought about critical security challenges. Traditional security solutions struggle to keep pace with the dynamic and interconnected nature of IoMT systems. Machine learning (ML)-based Intrusion Detection Systems (IDS) have been increasingly adopted to counter cyberattacks, but centralized ML approaches pose privacy risks due to the single points of failure (SPoFs). Federated Learning (FL) emerges as a promising solution, enabling model updates directly on end devices without sharing private data with a central server. This study introduces the BFLIDS, a Blockchain-empowered Federated Learning-based IDS designed to enhance security and intrusion detection in IoMT networks. Our approach leverages blockchain to secure transaction records, FL to maintain data privacy by training models locally, IPFS for decentralized storage, and MongoDB for efficient data management. Ethereum smart contracts (SCs) oversee and secure all interactions and transactions within the system. We modified the FedAvg algorithm with the Kullback-Leibler divergence estimation and adaptive weight calculation to boost model accuracy and robustness against adversarial attacks. For classification, we implemented an Adaptive Max Pooling-based Convolutional Neural Network (CNN) and a modified Bidirectional Long Short-Term Memory (BiLSTM) with attention and residual connections on Edge-IIoTSet and TON-IoT datasets. We achieved accuracies of 97.43% (for CNNs and Edge-IIoTSet), 96.02% (for BiLSTM and Edge-IIoTSet), 98.21% (for CNNs and TON-IoT), and 97.42% (for BiLSTM and TON-IoT) in FL scenarios, which are competitive with centralized methods. The proposed BFLIDS effectively detects intrusions, enhancing the security and privacy of IoMT networks.
ABSTRACT
The knowledge about co-transport of goethite and As3+ to investigate the effect of goethite colloids on As3+ transport under various degrees of seawater intrusion, particular extremely conditions, in groundwater environment is still limited. The main objective is to investigate the influence of seawater intrusion on the sorption, migration, and reaction of As3+and goethite colloids into sand aquifer media under anoxic conditions by using the bench-scale and reactive geochemical modeling. The research consisted of two parts as follows: 1) column transport experiments consisting of 8 columns, which were packed by using synthesis groundwater at IS of 0.5, 50, 200, and 400 mM referring to the saline of seawater system in the study area, and 2) reactive transport modeling, the mathematical model (HYDRUS-1D) was applied to describe the co-transport of As3+ and goethite. Finally, to explain the interaction of goethite and As3+, the Derjaguin-Landau-Verwey-Overbeek (DLVO) calculation was considered to support the experimental results and HYDRUS-1D model. The results of column experiments showed goethite colloids can significantly inhibit the mobility of As3+ under high IS conditions (>200 mM). The Rf of As3+ bound to goethite grows to higher sizes (47.5 and 65.0 µm for 200 and 400 mM, respectively) of goethite colloid, inhibiting As3+ migration through the sand columns. In contrast, based on Rf value, goethite colloids transport As3+ more rapidly than a solution with a lower IS (0.5 and 50 mM). The knowledge gained from this study would help to better understand the mechanisms of As3+ contamination in urbanized coastal groundwater aquifers and to assess the transport of As3+ in groundwater, which is useful for groundwater management, including the optimum pumping rate and long-term monitoring of groundwater quality.
ABSTRACT
Internet of Things (IoT) applications and resources are highly vulnerable to flood attacks, including Distributed Denial of Service (DDoS) attacks. These attacks overwhelm the targeted device with numerous network packets, making its resources inaccessible to authorized users. Such attacks may comprise attack references, attack types, sub-categories, host information, malicious scripts, etc. These details assist security professionals in identifying weaknesses, tailoring defense measures, and responding rapidly to possible threats, thereby improving the overall security posture of IoT devices. Developing an intelligent Intrusion Detection System (IDS) is highly complex due to its numerous network features. This study presents an improved IDS for IoT security that employs multimodal big data representation and transfer learning. First, the Packet Capture (PCAP) files are crawled to retrieve the necessary attacks and bytes. Second, Spark-based big data optimization algorithms handle huge volumes of data. Second, a transfer learning approach such as word2vec retrieves semantically-based observed features. Third, an algorithm is developed to convert network bytes into images, and texture features are extracted by configuring an attention-based Residual Network (ResNet). Finally, the trained text and texture features are combined and used as multimodal features to classify various attacks. The proposed method is thoroughly evaluated on three widely used IoT-based datasets: CIC-IoT 2022, CIC-IoT 2023, and Edge-IIoT. The proposed method achieves excellent classification performance, with an accuracy of 98.2%. In addition, we present a game theory-based process to validate the proposed approach formally.