Distributed Denial of Service (DDoS) attacks are among the primary concerns in internet security today. Machine learning can be exploited to detect such attacks. In this paper, a multi-layer perceptron model is proposed and implemented using deep machine learning to distinguish between malicious and normal traffic based on their behavioral patterns. The proposed model is trained and tested using the CICDDoS2019 dataset. To remove irrelevant and redundant data from the dataset and increase learning accuracy, feature selection is used to select and extract the most effective features that allow us to detect these attacks. Moreover, we use the grid search algorithm to acquire optimum values of the model’s hyperparameters among the parameters’ space. In addition, the sensitivity of accuracy of the model to variations of an input parameter is analyzed. Finally, the effectiveness of the presented model is validated in comparison with some state-of-the-art works.

Many roads in forest areas are located along the steep hills. The cut and fill method is currently used for construction of these roads. Settlement or consolidation in not enough compacted soil or creep in down slope, can lead to subsidence and cracks in roads. General methods for solving settlement related problems such as reconstruction, retaining structure and … are expensive. Deep patch method is a low- cost method for increasing the stability of slopes. In this method, the upper parts of the subsided area are excavated and replaced with reinforcement materials such as Geo grid in accordance with compacted soil. In this paper, limit equilibrium method has been implemented for determining the safety factor of a planar slip surface in a slope. Furthermore, graphs for determining safety factor of reinforced soil slope with Geo synthetics have been proposed.

In traditional speech processing, feature extraction and classification were conducted as separate steps. The advent of deep neural networks has enabled methods that simultaneously model the relationship between acoustic and phonetic characteristics of speech while classifying it directly from the raw waveform. The first convolutional layer in these networks acts as a filter bank. To enhance interpretability and reduce the number of parameters, researchers have explored the use of parametric filters, with the SincNet architecture being a notable advancement. In SincNet's initial convolutional layer, rectangular bandpass filters are learned instead of fully trainable filters. This approach allows for modeling with fewer parameters, thereby improving the network's convergence speed and accuracy. Analyzing the learned filter bank also provides valuable insights into the model's performance. The reduction in parameters, along with increased accuracy and interpretability, has led to the adoption of various parametric filters and deep architectures across diverse speech processing applications. This paper introduces different types of parametric filters and discusses their integration into various deep architectures. Additionally, it examines the specific applications in speech processing where these filters have proven effective.

Backgrounds: Regarding the prevalence of injuries to flexor tendon in Zone II and its known side effects after routine repair, and also with respect to the possible diameter increase of repaired region after repairing with modified Kessler core suture followed by epitenon peripheral suture which in turn could cause problems in tendon motion in Zone II. This study has been developed to determine the efficacy of deep peripheral first suture technique (D.P.F.S.) in patients referring to 15 Khordad Hospital during the academic years of 1996 till 1998. Materials and methods: This clinical trial of semi-experimental type has been carried out on 50 patients suffering from tendon rupture of 70 digits in Zone [I. Patients were followed for 6 months. Strickland classification has been used for result analysis. Results: Among 50 patients with mean age of 30, 70% were male and the remaining 30% were female. Left hand was hurt in 70% of the cases and right hand in 30%. Third finger was the most common site of injury. Rupturing of both superficial and deep tendons was reported in 72% of the cases. Injury to the digital nerve was seen in 34% of the patients. Conclusion: Regarding the satisfactory results obtained in our study, deep peripheral first suture technique (D.P.F.S.) revealed to be a successful method in primary flexor tendon repair in Zone n. In the meanwhile, another clinical trial to compare this technique with other successful routine methods is strongly recommended.

Plastic hinge properties play a crucial role in predicting the nonlinear response of structural elements. The plastic hinge region of reinforced concrete normal beams has been previously studied experimentally and analytically. The main objective of this research is to evaluate the behavior of the plastic hinge region of reinforced concrete deep beams and its comparison with normal beams through finite element simulation. To do so, ten beams contain six deep beams, and four normal beams, under concentrated and uniformly distributed loading, are investigated. Lengths in the plastic hinge region involving curvature localization, rebar yielding, and concrete crushing zones are studied. The results indicate that the curvature localization zone is not suitable for the prediction of plastic hinge length in reinforced concrete deep beams. Based on the results it can be stated that in simply supported normal beams the concrete crushing zone is focused on the middle span, but in simply supported deep beams by creating a compression strut between loading place and support, the concrete crushing zone spreads along the compression trajectory. The rebar yielding zone of simply supported beams increases as the loading type is changed from the concentrated load at the middle to the uniformly distributed load.

Single Cell Peotein (SCP) refers to the dried microbial cells or total protein extracted from pure microbial cell culture which can be used as food supplement to humans or animals. The choice of substrates that are normally abundant and in proximity to the production plant has determined the design and strategy of SCP processes. The aim of this study was the optimization of SCP production in pilot plant scale. So the continuous cultivation of Methylobacteriuum sp (strain 69) was carried on Minimal salt medium (MSB) with methanol as sole canbone and energy source.In continuous fermentation in a deep jet fermenter of 1000L capacity, with a workingvolume of 600 liters, production of 25 g/L of dryied biomass was observed and the cell yield based on substrate was 0.4 g/g. The stoichiometry for the conversion of methanol into cell biomass was. The total protein contenet of the product was uo to 74% and because of high content of essential amino acids it can be a suitable replacement for animal feed.

Identification of the exact location of an exon in a DNA sequence is an important research area of bioinformatics. The main issues of the previous signal processing techniques are accuracy and robustness for the exact locating of exons. To address the mentioned issues, in this study, a method has been proposed based on deep learning. The proposed method includes a new preprocessing, a new mapping method, and a multi-scale modified and hybrid deep neural network. The proposed preprocessing method enriches the network to accept and encode genes at any length in a new mapping method. The proposed multi-scale deep neural network uses a combination of an embedding layer, a modified CNN, and an LSTM network. In this study, HMR195, BG570, and F56F11.4 datasets have been used to compare this work with previous studies. The accuracies of the proposed method have been 0.982, 0.966, and 0.965 on HMR195, BG570, and F56F11.4 databases, respectively. The results reveal the superiority and effectiveness of the proposed hybrid multi-scale CNN-LSTM network.

A difficult clinical management is considered for Patients with Cl II malocclusion and severe deep bite. This is due to the fact that any changes lead the situation to a deeper and traumatic bite. High pull J Hook Head gear (H.J.H.G) with an extra oral anchorage has been introduced as being able to easily intrude anterior teeth in association to the use of a rectangular wire. This combination has a good control on root torque. This article discusses the clinical aspect of H.J.H.G with presentation of a case.