Solid State Technology

Comparative Analysis of Ensemble Based Learning and Hybrid Models for Improving DoS Attack Prediction Accuracy in Networking Environments

2024-05-29T10:59:07+00:00

DDoS assaults threaten computer networks and systems. These attacks flood the targeted system with traffic from many sources, disrupting service. Cyber security now requires real-time attack detection.. The current approach of detecting DDoS attacks is plagued by the issue of elevated percentages of false positives. Moreover, the classifiers employed in the current methodologies may lack the capability to comprehend the intricate patterns of the DDoS assault flow, resulting in diminished accuracy. This paper presents a refined method for identifying DDoS assaults by utilizing a classifier based on ensemble learning and a hybrid machine learning model. The ensemble-based Voting Classifier has the capability to combine many machine learning algorithms (SVC, Logistic Regression, Random Forest, and Naïve Bayes) in order to enhance classification accuracy. This makes it a superior choice for detecting DDoS attacks compared to a single machine learning-based classifier. The challenge of detecting Denial of Service (DoS) attacks in extensive sets of network traffic data is addressed by employing an ensemble of classifiers, known as the Hybrid method, which is designed to survive network attacks. The aim of this study is to construct a collection of classifiers that outperforms individual classifiers in terms of accuracy. The classifiers used in this experiment include SVC, Logistic Regression, Random Forest, and Naive Bayes. The suggested approach is compared against single classifiers using the metrics of accuracy, precision, recall, and F-measure. Outcome. The tests were conducted using Python 3.7.4 in Jupyter Notebook. The studies utilized the publicly available NSL-KDD dataset, which consists of network traffic data. The dataset was segmented into two classes: attack and regular network behavior traffic. The conducted experiments have confirmed the efficacy of the proposed methodology. The suggested Hybrid ML Model for network threats identification surpasses the performance of individual classifiers as well as the Ensemble Based Classifier. The Hybrid ML model attained a detection accuracy of 98.41%, whilst the Ensemble learning Method achieved a detection accuracy of 97%. The results imply that the proposed method has greater efficacy in terms of accuracy when compared to other individual classifiers such as SVM, Naïve Bayes, and Logistic regression and ensemble learning. In order to improve the analysis of network traffic attacks, investigations will be carried out on genuine big data sets.

Using the Simulation Method to Estimate the Parameters of the Normal Twisted and Truncated Distribution

2024-07-01T11:57:34+00:00

The current research aims to estimate the features of the amputated metabolic natural distribution, which is considered one of the educational distributions derived from the metaphysical distribution after cutting (amputation) the negative part of the surface sub -curve for the naturally mired distribution, in two ways the greatest possibility and the way of determination and then estimate the use of the average meter of the IMSE error box for the purpose of the purpose The comparison between the preference of these methods, as Simulation results show that the method is the best for prediction. amputated twisted features is the best because it has the lowest value for the average of the Gamblian error square.

Synthesis, Anticancer Activity and in Silico Modelling of Cephalexin Drug

2024-07-15T07:02:37+00:00

cephalexin is an antibiotic that can kill certain types of bacteria that cause infections. We synthesized a novel cefalexin-Schiff base (A and B), namely (Z)-7-(2-((3-bromo-4-hydroxybenzylidene)amino)-3-phenylpropanamido)-3-methyl-8-oxo-5-thia-1-azabicyclo[4.2.0]-oct-2-ene-2-carboxylic acid as derivative A and (Z)-7-(2-((2-methyl-4-methylbenzylidene)amino)-3-phenylpropanamido)-3-methyl-8-oxo-5-thia-1-azabicyclo[4.2.0]oct-2-ene-2-carboxylic acid as derivative B. These derivatives are synthesized from 3-Bromo-4-hydroxybenzaldehyde and 2,4-Dimethylbenzaldehyde that react with cephalexin. Characterization of these derivatives by FTIR and diffusion method is used to determine how these derivatives interact with various bacteria, such as S. aureus and E. coli. The derivative A gives a good result in inhibiting the growth of bacteria. The derivative (A) has been evaluated for breast cancer MCF-7 by MTT assay. The drug's functional groups established two hydrogen bonds with the GLU885 and HIS1026 residues in the receptor's active site.

Revolutionizing Facial Recognition: A Dolphin Glowworm Hybrid Approach for Masked and Unmasked Scenarios

2024-10-19T08:57:38+00:00

Machine learning has several essential applications, including classification and recognition. Both people and objects may be identified using the Machine learning technique. It is particularly important in the verification process since it recognizes the characteristics of human eyes, fingerprints, and facial patterns. With the advanced technology developments, nowadays, Facial recognition is used as one of the authentication processes by utilizing machine learning and deep learning algorithms and it has been the subject of several academic studies. These algorithms performed well on faces without masks, but not well on faces with masks. since the masks obscured the preponderance of the facial features. As a result, an improved algorithm for facial identification with and without masks is required. After the Covid-19 breakout, deep learning algorithms were utilized in research to recognize faces wearing masks. Those algorithms, however, were trained on both mask- and mask-free faces. Hence, in this, the cropped region for the faces is only used for facial recognition. Here, the features were extracted using the texture features, and the best-optimized features from the glow worm optimization algorithm are used in this paper. With these features set, the hybrid Dolphin glow worm optimization is used for finding the optimal features and spread function value for the neural network. The regression neural network is trained with the optimized feature set and spread function for the face recognition task. The performance of the suggested method will be compared to that of known approaches such as CNN-GSO and CNN for face recognition with and without masks using accuracy, sensitivity, and specificity will next be examined.

Using the Average Weight Method to Solve the Problem of Ambiguity and Predict the Quantities of Iraq's Oil Exports

2024-10-22T06:31:04+00:00

Economies in developing countries are considered fragile economies that depend on unilateral revenues, whose revenues are from one source or contribute a large percentage to the state budget. Many countries depend in their budget on oil exported from their countries, including Iraq, which depends on exported oil as it constitutes Approximately 95% of the central budget revenues. The data was collected by SOMO Company, which is a government company affiliated with the Ministry of Oil that works to sell petroleum products produced by the oil fields according to international selling prices. The data was announced by the company and the data was suffering from Therefore, the ambiguity was treated using the center of gravity method, then the data for the years 2023 to 2025 was predicted by month using the general trend method, and it was concluded that there will be an increase in exported quantities, and work must be done to invest this increase in other sectors.

Deep Learning Approach for Emotion Recognition Using EEG Signals

2024-10-22T06:43:23+00:00

The complex state of feeling known as emotion causes psychological and physical changes that have an impact on one's thoughts and actions. Emotions can be characterised as happy or negative experiences connected to a specific pattern of physiological activity from a scientific standpoint. Emotion recognition is the action of recognizing the psychological state of a person. Recognition is done using EEG signals. Electroencephalography (EEG) is used to monitor the chemical reactions that occur due to ions in the human brain which results in specific emotions. It can provide a simple, portable, ease- to-use and cheap solution for detecting the mental state of a person. Electrodes are used to assess the neuronal activity in various brain areas using EEG data. Based on the signal output we need to analyse the emotion of a person whether his reaction is negative, neutral or positive.

Techniques and Protocols for Computer and Communications Networks

2024-10-26T06:16:37+00:00

Transmission Control Protocol (TCP), Real-time Transport Protocol (RTP), and Simple Mail Transfer Protocol (SMTP) are some of the more important protocols that shall be discussed in this study. TCP is widely used for Internet applications and network communication is based on the Internet Protocol (IP), where the devices can be assigned IP addresses and data are transmitted through the public networks. As for HTTP, this is a channel that allows for the exchange of hypertext and thereby makes it possible to perform what is known as ‘‘surfing’’ on the site as well as interact with the site. FTP, however, allows the transfer of data in a smooth manner across computers in TCP/IP networks. RTP is of great importance in the transfer of real-time audio and video information; the spouses apply RTP in Voice over Internet Protocol (VoIP) interactions and the streaming of live videos. The three main communication protocols used in email messaging are SMTP, POP3, and IMAP which help in the transmission, reception, and arrangement of email messages. Each of the protocols considered is investigated with respect to its detailed features, such as its procedures, messaging format, security considerations, and recent advancements. The research also continues to explore the advantages and limitations of various protocols in different network environments. This study aims to contribute to a better understanding of computer and communications networks by analyzing diverse methodologies and protocols.

Predicting the Number of Cancer Patients Using the General Trend Method for the Years (2024-2048)

2024-11-05T06:21:55+00:00

Countries are working to study and evaluate health levels in the country and work to improve the health situation. One of the diseases that have spread in recent periods around the world in general and Iraq in particular is cancer, which contains many different types. Many researchers and specialists have been interested in studying, analyzing and conducting scientific tests in order to reach treatments for the problems and obstacles facing patients. Among the researcher's orientations is to work on studying this disease with some of its types, as in recent years the disease has spread widely among Iraqi society. Data was collected through official websites after arranging, classifying and tabulating them. Statistical analysis was conducted to predict the period from 2024 to 2024 using the general trend model for prediction, which concluded that for the predicted years there will be an increase in the number of people infected with cancer, especially the blood disease.

A Survey of Techniques and Challenges in Arabic Named Entity Recognition

2025-01-28T06:11:36+00:00

Arabic Named Entity Recognition (NER) serves as a crucial facet within Natural Language Processing, given the intricacies of the Arabic language. This survey consolidates the current landscape of Arabic NER, covering methodologies, challenges, and advancements. The review thoroughly examines various methods, from rule-based systems to advanced deep learning techniques, emphasizing their strengths and shortcomings. It also addresses the challenges inherent to Arabic NER, such as dialectal variations and limited annotated data, while exploring recent advancements and their applications in sentiment analysis, information retrieval, and other domains. This survey aims to provide a comprehensive overview that caters to researchers, practitioners, and enthusiasts in Arabic NER and NLP.

Influence of Atmospheric Plasma Spraying Angle and Concentration of (Ni/Cr) Nanosize on the Properties of (Y2O3- Ni /Cr) Composite Coating.

2025-03-19T10:38:42+00:00

This research investigated the effect of (Ni-Cr) nanopowder addition and spray angle on the mechanical, and structural properties of the prepared coating. First, the nickel and chromium powders were mechanically milled to reach the nano size. After the milling process, the sizes were reduced to the range between (55-75nm). Then the two elements were mixed in different weight ratios and then mixed with yttria at equal ratios. The powders were deposited using plasma deposition on steel substrates of type 304L. The mechanical and morphological properties of the resulting cermet coating were studied. It was found that the best results for mechanical and morphological properties and decreasing coating roughness when the spray angle (90?) and concentration (Ni60%, Cr40%), On the contrary, small spray angles increase of the coating defects. The mechanical properties were decreased and increasing of coating roughness when the spray angle is (30?) and the concentration of (Ni25%, Cr75%). Also, the use of nano-sized elements and mixing them with yttria led to a significant improvement in the properties. Increasing the nickel concentration of the sample (S3) was the best, and a homogeneous distribution of nickel and chromium elements was obtained and spread in the coating with yttria powder.The addition of nanoparticles will support the mechanical coating properties , due to their good reaction and bindig with the coating layers which will reduc of the coating defects.

Accuracy Measurements of the Dose Meter Comparison with Geiger counter

2025-04-25T10:14:15+00:00

Analytical study for this research included a comparison between the accuracy of readings of nuclear and atomic rays Using an It was used in the analytical study as shields for both sources: air, water, glass and aluminum. The practical results showed that there is a discrepancy in the accuracy of these results for both meters, as the sensitivity of the Geiger–Müller counter is more accurate than the radiation dose meter due to the difference in manufacturing technology and materials produced for both meters.