Tonotopic Specializations in Number, Size, and Reversal Potential of GABAergic Inputs Fine-Tune Temporal Coding at Avian Cochlear Nucleus.

GABAergic inhibition in neurons plays a critical role in determining the output of neural circuits. Neurons in avian nucleus magnocellularis (NM) use several tonotopic-region-dependent specializations to relay the timing information of sound in the auditory nerve to higher auditory nuclei. Previously, we showed that feedforward GABAergic inhibition in NM has a different dependence on the level of auditory nerve activity, with the low-frequency region having a low-threshold and linear relationship, while the high-frequency region has a high-threshold and step-like relationship. However, it remains unclear how the GABAergic synapses are tonotopically regulated and interact with other specializations of NM neurons. In this study, we examined GABAergic transmission in the NM of chickens of both sexes and explored its contributions to the temporal coding of sound at each tonotopic region. We found that the number and size of unitary GABAergic currents and their reversal potential were finely tuned at each tonotopic region in the NM. At the lower-frequency region, unitary GABAergic currents were larger in number but smaller in size. In addition, their reversal potential was close to the resting potential of neurons, which enabled reliable inhibition despite the smaller potassium conductance. At the higher-frequency region, on the other hand, unitary GABAergic currents were fewer, larger, and highly depolarizing, which enabled powerful inhibition via activating the large potassium conductance. Thus, we propose that GABAergic synapses are coordinated with the characteristics of excitatory synapses and postsynaptic neurons, ensuring the temporal coding for wide frequency and intensity ranges.SIGNIFICANCE STATEMENT We found in avian cochlear nucleus that the number and size of unitary GABAergic inputs differed among tonotopic regions and correlated to respective excitatory inputs; it was larger in number but smaller in size for neurons tuned to lower-frequency sound. Furthermore, GABAergic reversal potential also differed among the regions in accordance with the size of Kv1 current; it was less depolarized in the lower-frequency neurons with smaller Kv1 current. These differentiations of GABAergic transmission maximized the effects of inhibition at each tonotopic region, ensuring precise and reliable temporal coding across frequencies and intensities. Our results emphasize the importance of optimizing characteristics of GABAergic transmission within individual neurons for proper neural circuit function.

Excitatory-Inhibitory Synaptic Coupling in Avian Nucleus Magnocellularis.

The activity of neurons is determined by the balance between their excitatory and inhibitory synaptic inputs. Neurons in the avian nucleus magnocellularis (NM) integrate monosynaptic excitatory and polysynaptic inhibitory inputs from the auditory nerve, and transmit phase-locked output to higher auditory centers. The excitatory input is graded tonotopically, such that neurons tuned to higher frequency receive fewer, but larger, axon terminals. However, it remains unknown how the balance between excitatory and inhibitory inputs is determined in NM. We here examined synaptic and spike responses of NM neurons during stimulation of the auditory nerve in thick brain slices of chicken of both sexes, and found that the excitatory-inhibitory balance varied according to tonotopic region, ensuring reliable spike output across frequencies. Auditory nerve stimulation elicited IPSCs in NM neurons regardless of tonotopic region, but the dependence of IPSCs on intensity varied in a systematic way. In neurons tuned to low frequency, IPSCs appeared and increased in parallel with EPSCs with elevation of intensity, which expanded dynamic range by preventing saturation of spike generation. On the other hand, in neurons tuned to higher frequency, IPSCs were smaller than EPSCs and had higher thresholds for activation, thus facilitating high-fidelity transmission. Computer simulation confirmed that these differences in inhibitory input were optimally matched to the patterns of excitatory input, and enabled appropriate level of neuronal output for wide intensity and frequency ranges of sound in the auditory system.SIGNIFICANCE STATEMENT Neurons in nucleus magnocellularis encode timing information of sound across wide intensity ranges by integrating excitatory and inhibitory synaptic inputs from the auditory nerve, but underlying synaptic mechanisms of this integration are not fully understood. We here show that the excitatory-inhibitory relationship was expressed differentially at each tonotopic region; the relationship was linear in neurons tuned to low-frequency, expanding dynamic range by preventing saturation of spike generation; by contrast inhibitory input remained much smaller than excitatory input in neurons tuned to higher frequency, thus ensuring high-fidelity transmission. The tonotopic regulation of excitatory and inhibitory input optimized the output across frequencies and intensities, playing a fundamental role in the timing coding pathway in the auditory system.

Conversion of Non-Optical Material to Photo-Active Nanocomposites through Non-Conventional Techniques for Water Purification by Solar Energy.

Development of optical materials has attracted strong attention from scientists across the world to obtain low band gap energy and become active in field of solar energy. This challenge, which cannot be accomplished by the usual techniques, has overcome through the current study using non-conventional techniques. This study has used explosive reactions to convert non-optical alumina to series of new optical nanocomposites with very low band gap energy for the first time. In this trend, alumina nanoparticles were prepared and modified by explosive reactions using ammonium nitrate as a solid fuel. By using methanol or ethanol as a source of carbon species, three nanocomposites were produced indicating a gradual reduction of the band gap energy of alumina from 4.34 eV to 1.60 eV. These nanocomposites were obtained by modifying alumina via two different carbon species; core-shell structure and carbon nanotubes. This modification led to sharp reduction for the band gap energy to become very sensitive in sunlight. Therefore, these nanocomposites caused fast decolorization and mineralization of green dyes after illuminating in sunlight for ten minutes. Finally, it can be concluded that reduction of the band gap energy introduces new optical materials for developing optical nano-devices and solar cells.

Removal of Lead from Wastewater Using Synthesized Polyethyleneimine-Grafted Graphene Oxide.

In this work, polyethyleneimine-grafted graphene oxide (PEI/GO) is synthesized using graphene, polyethyleneimine, and trimesoyl chloride. Both graphene oxide and PEI/GO are characterized by a Fourier-transform infrared (FTIR) spectrometer, a scanning electron microscope (SEM), and energy-dispersive X-ray (EDX) spectroscopy. Characterization results confirm that polyethyleneimine is uniformly grafted on the graphene oxide nanosheets and, thus, also confirm the successful synthesis of PEI/GO. PEI/GO adsorbent is then evaluated for the removal of lead (Pb2+) from aqueous solutions, and the optimum adsorption is attained at pH 6, contact time of 120 min, and PEI/GO dose of 0.1 g. While chemosorption is dominating at low Pb2+ concentrations, physisorption is dominating at high concentrations and the adsorption rate is controlled by the boundary-layer diffusion step. In addition, the isotherm study confirms the strong interaction between Pb2+ ions and PEI/GO and reveals that the adsorption process obeys well the Freundlich isotherm model (R2 = 0.9932) and the maximum adsorption capacity (qm) is 64.94 mg/g, which is quite high compared to some of the reported adsorbents. Furthermore, the thermodynamic study confirms the spontaneity (negative ΔG° and positive ΔS°) and the endothermic nature (ΔH° = 19.73 kJ/mol) of the adsorption process. The prepared adsorbent (PEI/GO) offers a potential promise for wastewater treatment because of its fast and high uptake removal capacity and could be used as an effective adsorbent for the removal of Pb2+-ions and other heavy metals from industrial wastewater.

Stereotactic Delivery of Helper-dependent Adenoviral Viral Vectors at Distinct Developmental Time Points to Perform Age-dependent Molecular Manipulations of the Mouse Calyx of Held.

Synapses are specialized structures that enable neuronal communication, which is essential for brain function and development. Alterations in synaptic proteins have been linked to various neurological and neuropsychiatric disorders. Therefore, manipulating synaptic proteins in vivo can provide insight into the molecular mechanisms underlying these disorders and aid in developing new therapeutic strategies. Previous methods such as constitutive knock-out animals are limited by developmental compensation and off-target effects. The current approach outlines procedures for age-dependent molecular manipulations in mice using helper-dependent adenovirus viral vectors (HdAd) at distinct developmental time points. Using stereotactic injection of HdAds in both newborn and juvenile mice, we demonstrate the versatility of this method to express Cre recombinase in globular bushy cells of juvenile Rac1fl/fl mice to ablate presynaptic Rac1 and study its role in synaptic transmission. Separately, we overexpress CaV2 α1 subunits at two distinct developmental time points to elucidate the mechanisms that determine presynaptic CaV2 channel abundance and preference. This method presents a reliable, cost-effective, and minimally invasive approach for controlling gene expression in specific regions of the mouse brain and will be a powerful tool to decipher brain function in health and disease. Key features Virus-mediated genetic perturbation in neonatal and young adult mice. Stereotaxic injection allows targeting of brain structures at different developmental stages to study the impact of genetic perturbation throughout the development.

Confocal Imaging and 3D Reconstruction to Determine How Genetic Perturbations Impact Presynaptic Morphology at the Mouse Calyx of Held.

Neurons communicate via synapses-specialized structures that consist of a presynaptic terminal of one neuron and a postsynaptic terminal of another. As knowledge is emerging that mutations in molecules that regulate synaptic function underpin many neurological disorders, it is crucial to elucidate the molecular mechanisms regulating synaptic function to understand synaptic strength, plasticity, modulation, and pathology, which ultimately impact neuronal circuit output and behavior. The presynaptic calyx of Held is a large glutamatergic presynaptic terminal in the auditory brainstem, which due to its accessibility and the possibility to selectively perform molecular perturbations on it, is an ideal model to study the role of presynaptic proteins in regulating synaptic function. In this protocol, we describe the use of confocal imaging and three-dimensional reconstruction of the calyx of Held to assess alterations in gross morphology following molecular perturbation. Using viral-vector delivery to perform molecular perturbations at distinct developmental time points, we provide a fast and cost-effective method to investigate how presynaptic proteins regulate gross morphology such as surface area and synapse volume throughout the lifetime of a neuronal circuit. Key features Confocal imaging and 3D reconstruction of presynaptic terminals. Used with a virus-mediated expression of mEGFP to achieve efficient, cell-type specific labeling of the presynaptic compartment. Protocol was developed with the calyx of Held but is suitable for pre- and postsynaptic compartments of various neurons across multiple mammalian and invertebrate species.

Mercury Removal from Water Using a Novel Composite of Polyacrylate-Modified Carbon.

The contamination of groundwater by mercury (Hg) is a serious global threat, and its removal is of great importance. Activated carbon (AC) is considered a very promising adsorbent to remove Hg from water systems. However, specific functional groups can be added to AC to enhance its adsorption efficiency. In this work, AC was synthesized from palm shells and grafted with a copolymer of acrylamide and methacrylic acid to produce a polyacrylate-modified carbon (PAMC) composite. The synthesized adsorbent (PAMC) was characterized by Fourier-transform infrared (FTIR) spectroscopy, scanning electron microscopy (SEM), electron dispersive X-ray (EDX) spectroscopy, and Brunauer-Emmett-Teller (BET) analysis. PAMC was then evaluated for Hg removal from aqueous solutions, and the adsorption efficiency was optimized under several parameters (pH, contact time, and PAMC dosage). Kinetic, isotherm, and thermodynamic investigations were performed to gain a further understanding of the adsorption properties. The adsorption data were best fitted by pseudo-second-order and Redlich-Peterson models. Also, the thermodynamic investigation confirmed the spontaneity and the endothermic nature of the Hg adsorption process over PAMC. The maximum adsorption capacity (q m) of PAMC was found to be 76.3 mg/g ,which is relatively higher than some activated carbon-based adsorbents. Therefore, PAMC offers a potential promise for wastewater treatment due to its fast and high uptake removal capacity in addition to the cheap and environmentally friendly activated carbon source.

Pyrolysis Kinetic Study of Polylactic Acid.

Polylactic acid (PLA) is a biodegradable polymer and is mainly used in the textile and food packaging fields. The aim of this work is to build knowledge on the kinetics of the pyrolysis of PLA with the help of thermogravimetric analysis (TGA) using four model-free methods, namely Friedman, Flynn-Wall-Qzawa (FWO), Kissinger-Akahira-Sunose (KAS), and Starink. Additionally, two model-fitting methods (the Coats-Redfern and Criado methods) were applied. TGA data at 5, 10, 20, and 30 K/min heating rates were collected. The obtained activation energies of the pyrolysis of PLA at different conversions by the model-free models were in good agreement and the average values were 97, 109, 104, and 104 kJ/mol for Friedman, FWO, KAS, and Starink, respectively. The Criado model was used together with the Coats-Redfern model to identify the most appropriate reaction mechanism. As per this work, the best controlling reaction mechanism of the PLA pyrolysis can be expressed by the geometrical contraction model (R2).

Groundwater Quality: The Application of Artificial Intelligence.

Humans and all other living things depend on having access to clean water, as it is an indispensable essential resource. Therefore, the development of a model that can predict water quality conditions in the future will have substantial societal and economic value. This can be accomplished by using a model that can predict future water quality circumstances. In this study, we employed a sophisticated artificial neural network (ANN) model. This study intends to develop a hybrid model of single exponential smoothing (SES) with bidirectional long short-term memory (BiLSTM) and an adaptive neurofuzzy inference system (ANFIS) to predict water quality (WQ) in different groundwater in the Al-Baha region of Saudi Arabia. Single exponential smoothing (SES) was employed as a preprocessing method to adjust the weight of the dataset, and the output from SES was processed using the BiLSTM and ANFIS models for predicting water quality. The data were randomly divided into two phases, training (70%) and testing (30%). Efficiency statistics were used to evaluate the SES-BiLSTM and SES-ANFIS models' prediction abilities. The results showed that while both the SES-BiLSTM and SES-ANFIS models performed well in predicting the water quality index (WQI), the SES-BiLSTM model performed best with accuracy (R = 99.95% and RMSE = 0.00910) at the testing phase, where the performance of the SES-ANFIS model was R = 99.95% and RMSE = 2.2941 × 100-07. The findings support the idea that the SES-BilSTM and SES-ANFIS models can be used to predict the WQI with high accuracy, which will help to enhance WQ. The results demonstrated that the SES-BiLSTM and SES-ANFIS models' forecasts are accurate and that both seasons' performances are consistent. Similar investigations of groundwater quality prediction for drinking purposes should benefit from the proposed SES-BiLSTM and SES-ANFIS models. Consequently, the results demonstrate that the proposed SES-BiLSTM and SES-ANFIS models are useful tools for predicting whether the groundwater in Al-Baha city is suitable for drinking and irrigation purposes.

Presynaptic Rac1 controls synaptic strength through the regulation of synaptic vesicle priming.

Synapses contain a limited number of synaptic vesicles (SVs) that are released in response to action potentials (APs). Therefore, sustaining synaptic transmission over a wide range of AP firing rates and timescales depends on SV release and replenishment. Although actin dynamics impact synaptic transmission, how presynaptic regulators of actin signaling cascades control SV release and replenishment remains unresolved. Rac1, a Rho GTPase, regulates actin signaling cascades that control synaptogenesis, neuronal development, and postsynaptic function. However, the presynaptic role of Rac1 in regulating synaptic transmission is unclear. To unravel Rac1's roles in controlling transmitter release, we performed selective presynaptic ablation of Rac1 at the mature mouse calyx of Held synapse. Loss of Rac1 increased synaptic strength, accelerated EPSC recovery after conditioning stimulus trains, and augmented spontaneous SV release with no change in presynaptic morphology or AZ ultrastructure. Analyses with constrained short-term plasticity models revealed faster SV priming kinetics and, depending on model assumptions, elevated SV release probability or higher abundance of tightly docked fusion-competent SVs in Rac1-deficient synapses. We conclude that presynaptic Rac1 is a key regulator of synaptic transmission and plasticity mainly by regulating the dynamics of SV priming and potentially SV release probability.

Thermal Behavior of Mixed Plastics at Different Heating Rates: I. Pyrolysis Kinetics.

The amount of generated plastic waste has increased dramatically, up to 20 times, over the past 70 years. More than 50% of municipal plastic waste is composed of polystyrene (PS), polypropylene (PP), and low-density polyethylene (LDPE) products. Therefore, this work has developed a kinetic model that can fully describe the thermal decomposition of plastic mixtures, contributing significantly towards the efficiency of plastic waste management and helping to save the environment. In this work, the pyrolysis of different plastic mixtures, consisting of PP, PS, and LDPE, was performed using a thermogravimetric analyzer (TGA) at three different heating rates (5, 20, and 40 K/min). Four isoconversional models, namely Friedman, Flynn-Wall-Qzawa (FWO), Kissinger-Akahira-Sunose (KAS), and Starink, have been used to obtain the kinetic parameters of the pyrolysis of different plastic mixtures with different compositions. For the equi-mass binary mixtures of PP and PS, the average values of the activation energies were 181, 144 ± 2 kJ/mol obtained using the Freidman and integral (FWO, KAS, and Starink) models, respectively. However, higher values were obtained for the equi-mass ternary plastic mixtures of PP, PS, and LDPE (Freidman: 255 kJ/mol, FWO: 222 kJ/mol, KAS: 223 kJ/mol, and Starink: 222 kJ/mol). The most suitable reaction mechanisms were obtained using the Coats-Redfern model. The results confirm that the most controlling reaction mechanisms obey the first-order (F1) and the third-order (F3) reactions for the pyrolysis of the equi-mass binary (PS and PP) and equi-mass ternary (PS, PP, and LDPE) mixtures, respectively. Finally, the values of the pre-exponential factor (A) were obtained using the four isoconversional models and the linear relationship between ln A and the activation energy was confirmed.

Development of Polymeric Membranes for Oil/Water Separation.

In this work, the treatment of oily wastewater was investigated using developed cellulose acetate (CA) membranes blended with Nylon 66. Membrane characterization and permeation results in terms of oil rejection and flux were compared with a commercial CA membrane. The solution casting method was used to fabricate membranes composed of CA and Nylon 66. Scanning Electron Microscopy (SEM) analysis was done to examine the surface morphology of the membrane as well as the influence of solvent on the overall structure of the developed membranes. Mechanical and thermal properties of developed blended membranes and a commercial membrane were examined by thermogravimetric analysis (TGA) and universal (tensile) testing machine (UTM). Membrane characterizations revealed that the thermal and mechanical properties of the fabricated blended membranes better than those of the commercial membrane. Membrane fluxes and rejection of oil as a function of Nylon 66 compositions and transmembrane pressure were measured. Experimental results revealed that the synthetic membrane (composed of 2% Nylon 66 and Dimethyl Sulfoxide (DMSO) as a solvent) gave a permeate flux of 33 L/m2h and an oil rejection of around 90%, whereas the commercial membrane showed a permeate flux of 22 L/m2h and an oil rejection of 70%.

Pyrolytic Behavior of Polyvinyl Chloride: Kinetics, Mechanisms, Thermodynamics, and Artificial Neural Network Application.

Pyrolysis of waste polyvinyl chloride (PVC) is considered a promising and highly efficient treatment method. This work aims to investigate the kinetics, and thermodynamics of the process of PVC pyrolysis. Thermogravimetry of PVC pyrolysis at three heating rates (5, 10, and 20 K/min) showed two reaction stages covering the temperature ranges of 490-675 K, and 675-825 K, respectively. Three integral isoconversional models, namely Flynn-Wall-Qzawa (FWO), Kissinger-Akahira-Sunose (KAS), and Starink, were used to obtain the activation energy (Ea), and pre-exponential factor (A) of the PVC pyrolysis. On the other hand, the Coats-Redfern non-isoconversional model was used to determine the most appropriate solid-state reaction mechanism/s for both stages. Values of Ea, and A, obtained by the isoconversional models, were very close and the average values were, for stage I: Ea = 75 kJ/mol, A = 1.81 × 106 min-1; for stage II: Ea = 140 kJ/mol, A = 4.84 × 109 min-1. In addition, while the recommended mechanism of the first stage reaction was P2, F3 was the most suitable mechanism for the reaction of stage II. The appropriateness of the mechanisms was confirmed by the compensation effect. Thermodynamic study of the process of PVC pyrolysis confirmed that both reactions are endothermic and nonspontaneous with promising production of bioenergy. Furthermore, a highly efficient artificial neural network (ANN) model has been developed to predict the weight left % during the PVC pyrolysis as a function of the temperature and heating rate. The 2-10-10-1 topology with TANSIG-LOGSIG transfer function and feed-forward back-propagation characteristics was used.

Application of Artificial Neural Networks to Predict the Catalytic Pyrolysis of HDPE Using Non-Isothermal TGA Data.

This paper presents a comprehensive kinetic study of the catalytic pyrolysis of high-density polyethylene (HDPE) utilizing thermogravimetric analysis (TGA) data. Nine runs with different catalyst (HZSM-5) to polymer mass ratios (0.5, 0.77, and 1.0) were performed at different heating rates (5, 10, and 15 K/min) under nitrogen over the temperature range 303-973 K. Thermograms showed clearly that there was only one main reaction region for the catalytic cracking of HDPE. In addition, while thermogravimetric analysis (TGA) data were shifted towards higher temperatures as the heating rate increased, they were shifted towards lower temperatures and polymer started to degrade at lower temperatures when the catalyst was used. Furthermore, the activation energy of the catalytic pyrolysis of HDPE was obtained using three isoconversional (model-free) models and two non-isoconversional (model-fitting) models. Moreover, a set of 900 input-output experimental TGA data has been predicted by a highly efficient developed artificial neural network (ANN) model. Results showed a very good agreement between the ANN-predicted and experimental values (R2 > 0.999). Besides, A highly-efficient performance of the developed model has been reported for new input data as well.

Pyrolysis of Mixed Plastic Waste: I. Kinetic Study.

Plastic wastes have become one of the biggest global environmental issues and thus recycling such massive quantities is targeted. Low-density polyethylene (LDPE), high-density polyethylene (HDPE), polypropylene (PP), and polystyrene (PS) are considered among the main types of plastic wastes. Since pyrolysis is one of the most promising recycling techniques, this work aims to build knowledge on the co-pyrolysis of mixed polymers using two model-fitting (Criado and Coats-Redfern) methods. Seventeen co-pyrolysis tests using a thermogravimetric analyzer (TGA) at 60 K/min for different mixed compositions of LDPE, HDPE, PP, and PS were conducted. It was observed that the pyrolysis of the pure polymer samples occurs at different temperature ranges in the following order: PS < PP < LDPE < HDPE. However, compared to pure polymer samples, the co-pyrolysis of all-polymer mixtures was delayed. In addition, the synergistic effect on the co-pyrolysis of polymer blends was reported. The Master plot of the Criado model was used to determine the most suitable reaction mechanism. Then, the Coats-Redfern model was used to efficiently obtain the kinetic parameters (R2 ≥ 97.83%) and the obtained values of the activation energy of different polymer blends were ranging from 104 to 260 kJ/mol. Furthermore, the most controlling reaction mechanisms were in the following orders: First order reaction (F1), Contracting sphere (R3), and then Contracting cylinder (R2).

Pyrolysis of Low Density Polyethylene: Kinetic Study Using TGA Data and ANN Prediction.

Pyrolysis of waste low-density polyethylene (LDPE) is considered to be a highly efficient, promising treatment method. This work aims to investigate the kinetics of LDPE pyrolysis using three model-free methods (Friedman, Flynn-Wall-Qzawa (FWO), and Kissinger-Akahira-Sunose (KAS)), two model-fitting methods (Arrhenius and Coats-Redfern), as well as to develop, for the first time, a highly efficient artificial neural network (ANN) model to predict the kinetic parameters of LDPE pyrolysis. Thermogravimetric (TG) and derivative thermogravimetric (DTG) thermograms at 5, 10, 20 and 40 K min-1 showed only a single pyrolysis zone, implying a single reaction. The values of the kinetic parameters (E and A) of LDPE pyrolysis have been calculated at different conversions by three model-free methods and the average values of the obtained activation energies are in good agreement and ranging between 193 and 195 kJ mol-1. In addition, these kinetic parameters at different heating rates have been calculated using Arrhenius and Coats-Redfern methods. Moreover, a feed-forward ANN with backpropagation model, with 10 neurons in two hidden layers and logsig-logsig transfer functions, has been employed to predict the thermogravimetric analysis (TGA) kinetic data. Results showed good agreement between the ANN-predicted and experimental data (R > 0.9999). Then, the selected network topology was tested for extra new input data with a highly efficient performance.

Adaptive Anomaly Detection Framework Model Objects in Cyberspace.

Telecommunication has registered strong and rapid growth in the past decade. Accordingly, the monitoring of computers and networks is too complicated for network administrators. Hence, network security represents one of the biggest serious challenges that can be faced by network security communities. Taking into consideration the fact that e-banking, e-commerce, and business data will be shared on the computer network, these data may face a threat from intrusion. The purpose of this research is to propose a methodology that will lead to a high level and sustainable protection against cyberattacks. In particular, an adaptive anomaly detection framework model was developed using deep and machine learning algorithms to manage automatically-configured application-level firewalls. The standard network datasets were used to evaluate the proposed model which is designed for improving the cybersecurity system. The deep learning based on Long-Short Term Memory Recurrent Neural Network (LSTM-RNN) and machine learning algorithms namely Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) algorithms were implemented to classify the Denial-of-Service attack (DoS) and Distributed Denial-of-Service (DDoS) attacks. The information gain method was applied to select the relevant features from the network dataset. These network features were significant to improve the classification algorithm. The system was used to classify DoS and DDoS attacks in four stand datasets namely KDD cup 199, NSL-KDD, ISCX, and ICI-ID2017. The empirical results indicate that the deep learning based on the LSTM-RNN algorithm has obtained the highest accuracy. The proposed system based on the LSTM-RNN algorithm produced the highest testing accuracy rate of 99.51% and 99.91% with respect to KDD Cup'99, NSL-KDD, ISCX, and ICI-Id2017 datasets, respectively. A comparative result analysis between the machine learning algorithms, namely SVM and KNN, and the deep learning algorithms based on the LSTM-RNN model is presented. Finally, it is concluded that the LSTM-RNN model is efficient and effective to improve the cybersecurity system for detecting anomaly-based cybersecurity.

Water Quality Prediction Using Artificial Intelligence Algorithms.

During the last years, water quality has been threatened by various pollutants. Therefore, modeling and predicting water quality have become very important in controlling water pollution. In this work, advanced artificial intelligence (AI) algorithms are developed to predict water quality index (WQI) and water quality classification (WQC). For the WQI prediction, artificial neural network models, namely nonlinear autoregressive neural network (NARNET) and long short-term memory (LSTM) deep learning algorithm, have been developed. In addition, three machine learning algorithms, namely, support vector machine (SVM), K-nearest neighbor (K-NN), and Naive Bayes, have been used for the WQC forecasting. The used dataset has 7 significant parameters, and the developed models were evaluated based on some statistical parameters. The results revealed that the proposed models can accurately predict WQI and classify the water quality according to superior robustness. Prediction results demonstrated that the NARNET model performed slightly better than the LSTM for the prediction of the WQI values and the SVM algorithm has achieved the highest accuracy (97.01%) for the WQC prediction. Furthermore, the NARNET and LSTM models have achieved similar accuracy for the testing phase with a slight difference in the regression coefficient (RNARNET = 96.17% and RLSTM = 94.21%). This kind of promising research can contribute significantly to water management.