Effective network intrusion detection using stacking-based ensemble approach

The increasing demand for communication between networked devices connected either through an intranet or the internet increases the need for a reliable and accurate network defense mechanism. Network intrusion detection systems (NIDSs), which are used to detect malicious or anomalous network traffic, are an integral part of network defense. This research aims to address some of the issues faced by anomaly-based network intrusion detection systems. In this research, we first identify some limitations of the legacy NIDS datasets, including a recent CICIDS2017 dataset, which lead us to develop our novel dataset, CIPMAIDS2023-1. Then, we propose a stacking-based ensemble approach that outperforms the overall state of the art for NIDS. Various attack scenarios were implemented along with benign user traffic on the network topology created using graphical network simulator-3 (GNS-3). Key flow features are extracted using cicflowmeter for each attack and are evaluated to analyze their behavior. Several different machine learning approaches are applied to the features extracted from the traffic data, and their performance is compared. The results show that the stacking-based ensemble approach is the most promising and achieves the highest weighted F1-score of 98.24%.

     

A hierarchical congestion control method in clustered internet of things

The Journal of Supercomputing - Internet of things (IoT) is a modern technology where data can be transmitted to any things (human, animal, or object) over communications networks, whether internet...     

Parallel sentence generation from comparable corpora for improved SMT

A parallel corpus is an essential resource for statistical machine translation (SMT) but is often not available in the required amounts for all domains and languages. An approach is presented here which aims at producing parallel corpora from available comparable corpora. An SMT system is used to translate the source-language part of a comparable corpus and the translations are used as queries to conduct information retrieval from the target-language side of the comparable corpus. Simple filters are then used to score the SMT output and the IR-returned sentence with the filter score defining the degree of similarity between the two. Using SMT system output gives the benefit of trying to correct one of the common errors by sentence tail removal. The approach was applied to Arabic–English and French–English systems using comparable news corpora and considerable improvements were achieved in the BLEU score. We show that our approach is independent of the quality of the SMT system used to make the queries, strengthening the claim of applicability of the approach for languages and domains with limited parallel corpora available to start with. We compare our approach with one of the earlier approaches and show that our approach is easier to implement and gives equally good improvements.     

A Hybrid System for Customer Churn Prediction and Retention Analysis via Supervised Learning

Telecom industry relies on churn prediction models to retain their customers. These prediction models help in precise and right time recognition of future switching by a group of customers to other service providers. Retention not only contributes to the profit of an organization, but it is also important for upholding a position in the competitive market. In the past, numerous churn prediction models have been proposed, but the current models have a number of flaws that prevent them from being used in real-world large-scale telecom datasets. These schemes, fail to incorporate frequently changing requirements. Data sparsity, noisy data, and the imbalanced nature of the dataset are the other main challenges for an accurate prediction. In this paper, we propose a hybrid model, name as “A Hybrid System for Customer Churn Prediction and Retention Analysis via Supervised Learning (HCPRs)” that used Synthetic Minority Over-Sampling Technique (SMOTE) and Particle Swarm Optimization (PSO) to address the issue of imbalance class data and feature selection. Data cleaning and normalization has been done on big Orange dataset contains 15000 features along with 50000 entities. Substantial experiments are performed to test and validate the model on Random Forest (RF), Linear Regression (LR), Naïve Bayes (NB) and XG-Boost. Results show that the proposed model when used with XGBoost classifier, has greater Accuracy Under Curve (AUC) of 98% as compared with other methods.     

The use of Neem biomass for the biosorption of zinc from aqueous solutions

An adsorbent was developed from mature leaves and stem bark of the Neem (Azadirachta indica) tree for removing zinc from water. Adsorption was carried out in a batch process with several different concentrations of zinc by varying pH. The uptake of metal was very fast initially, but gradually slowed down indicating penetration into the interior of the adsorbent particles. The data showed that optimum pH for efficient biosorption of zinc by Neem leaves and stem bark was 4 and 5, respectively. The maximum adsorption capacity showed that the Neem biomass had a mass capacity for zinc (147.08 mg Zn/g for Neem leaves and 137.67 mg Zn/g Neem bark). The experimental results were analyzed in terms of Langmuir and Freundlich isotherms. The adsorption followed pseudo-second-order kinetic model. The thermodynamic assessment of the metal ion-Neem tree biomass system indicated the feasibility and spontaneous nature of the process and DeltaG degrees values were evaluated as ranging from -26.84 to -32.75 (Neem leaves) kJ/mol and -26.04 to -29.50 (Neem bark) kJ/mol for zinc biosorption. Due to its outstanding zinc uptake capacity, the Neem tree was proved to be an excellent biomaterial for accumulating zinc from aqueous solutions.     

Efficacy of modified distillation sludge of rose (Rosa centifolia) petals for lead(II) and zinc(II) removal from aqueous solutions

Removal of lead(II) and zinc(II) from aqueous solutions was studied using chemically modified distillation sludge of rose (Rosa centifolia) petals by pretreatment with NaOH, Ca(OH)(2), Al(OH)(3), C(6)H(6), C(6)H(5)CHO and HgCl(2). The adsorption capacity of biomass was found to be significantly improved. NaOH pretreated biomass showed remarkable increase in sorption capacity. Maximum adsorption of both metal ions was observed at pH 5. When Freundlich and Langmuir isotherms were tested, the latter had a better fit with the experimental data. The overall adsorption process was best described by pseudo second order kinetics. The thermodynamic assessment of the metal ion-Rosa centifolia biomass system indicated the feasibility and spontaneous nature of the process and DeltaG degrees was evaluated as ranging from -26.9501 to -31.652 KJmol(-1) and -24.1905 to -29.8923KJmol(-1) for lead(II) and zinc(II) sorption, respectively, in the concentration range 10-640mgL(-1). Distribution coefficient (D) showed that the concentration of metal ions at the sorbent-water interface is higher than the concentration in the continuous aqueous phase. Maximum adsorption capacity of biomass tends to be in the order Pb(II) (87.74mgg(-1))>Zn(II) (73.8mgg(-1)) by NaOH pretreated biomass.     

Synthesis of mono layer graphene oxide from sonicated graphite flakes and their Hall effect measurements

Graphene, a single atom thick sheet is considered a key candidate for the future nanotechnology, due to its unique extraordinary properties. Researchers are trying to synthesize bulk graphene via chemical route from graphene oxide precursor. In the present work, we investigated a safe and efficient way of monolayer graphene oxide synthesis. To get a high degree of oxidation, we sonicated the graphite flakes before oxidation. X-ray diffraction (XRD) and Fourier transform infrared spectroscopy (FTIR) results confirmed graphene oxide formation and high degree of oxidation. Raman spectroscopy and atomic force microscopy (AFM) results revealed a monolayer of graphene oxide (GO) flakes. The sheet like morphology of the GO flakes was further confirmed by scanning electron microscopy (SEM). The Hall effect measurements were performed on the GO film on a silica substrate to investigate its electrical properties. The results obtained, revealed that the GO film is perfectly insulating, having electrical resistivity up to 8.4 × 10⁸ (Ω·cm) at room temperature.