- Network Security and Intrusion Detection
- Smart Agriculture and AI
- Anomaly Detection Techniques and Applications
- Advanced Malware Detection Techniques
- Air Quality and Health Impacts
- Air Quality Monitoring and Forecasting
- Internet Traffic Analysis and Secure E-voting
- Imbalanced Data Classification Techniques
- Electricity Theft Detection Techniques
- Artificial Intelligence in Healthcare
- Surgical Simulation and Training
- Spam and Phishing Detection
- Stock Market Forecasting Methods
- Financial Distress and Bankruptcy Prediction
- Leaf Properties and Growth Measurement
- Impact of Light on Environment and Health
- Bee Products Chemical Analysis
- Essential Oils and Antimicrobial Activity
- Artificial Intelligence in Healthcare and Education
- Colorectal Cancer Screening and Detection
- COVID-19 Clinical Research Studies
- ECG Monitoring and Analysis
- Spectroscopy and Chemometric Analyses
- Greenhouse Technology and Climate Control
- Atmospheric chemistry and aerosols
Mohammed V University
2017-2025
Abstract An intrusion detection system (IDS) is a device or software application that monitors network for malicious activity policy violations. It scans harmful security breaching. IDS protects networks (Network-based NIDS) hosts (Host-based HIDS), and work by either looking signatures of known attacks deviations from normal activity. Deep learning algorithms proved their effectiveness in compared to other machine methods. In this paper, we implemented deep solutions detecting based on Long...
Over the past few decades, due to human activities, industrialization, and urbanization, air pollution has become a life-threatening factor in many countries around world. Among pollutants, Particulate Matter with diameter of less than 2.5μm ( PM2.5 ) is serious health problem. It causes various illnesses such as respiratory tract cardiovascular diseases. Hence, it necessary accurately predict concentrations order prevent citizens from dangerous impact beforehand. The variation depends on...
Abstract As credit card becomes the most popular payment mode particularly in online sector, fraudulent activities using technologies are rapidly increasing as a result. For this end, it is obligatory for financial institutions to continuously improve their fraud detection systems reduce huge losses. The purpose of paper develop novel system based on sequential modeling data, attention mechanism and LSTM deep recurrent neural networks. proposed model, compared previous studies, considers...
Abstract The purpose of this study is to develop and test machine learning-based models for COVID-19 severity prediction. samples from 337 positive patients at Cheikh Zaid Hospital were grouped according the their illness. Ours first estimate illness by combining biological non-biological data with COVID-19. Moreover use ML therapeutic purposes in Morocco currently restricted, ours investigate When analysis approaches used uncover patterns essential characteristics data, C-reactive protein,...
The rapid spread of SARS-CoV-2 threatens global public health and impedes the operation healthcare systems. Several studies have been conducted to confirm infection examine its risk factors. To produce more effective treatment options vaccines, it is still necessary investigate biomarkers immune responses in order gain a deeper understanding disease pathophysiology. This study aims determine how cytokines influence severity infection. We measured plasma levels 48 blood 87 participants...
The growing volume of spam Emails has generated the need for a more precise anti-spam filter to detect unsolicited Emails.One most common representations used in filters is Bag-of-Words (BOW).Although BOW very effective classification emails, it number weaknesses.In this paper, we present hybrid approach filtering based on Neural Network model Paragraph Vector-Distributed Memory (PV-DM).We use PV-DM build up compact representation context an email and also its pertinent features.This...
Abstract Cardiovascular diseases had been for a long time one of the essential medical problems. As indicated by World Health Association, heart ailments are at highest point ten leading reasons death. Correct and early identification is vital step in rehabilitation treatment. To diagnose defects, it would be necessary to implement system able predict existence diseases. In current article, our main motivation develop an effective intelligent based on machine learning techniques, aid...
Abstract Network attacks are illegal activities on digital resources within an organizational network with the express intention of compromising systems. A cyber attack can be directed by individuals, communities, states or even from anonymous source. Hackers commonly conduct to alter, damage, steal private data. Intrusion detection systems (IDS) best and most effective techniques when it comes tackle these threats. An IDS is a software application hardware device that monitors traffic...
The escalating prevalence of cybersecurity risks calls for a focused strategy in order to attain efficient resolutions. This study introduces detection model that employs tailored methodology integrating feature selection using SHAP values, shallow learning algorithm called PV-DM, and machine classifiers like XGBOOST. efficacy our suggested is highlighted by employing the NSL-KDD UNSW-NB15 datasets. Our approach dataset exhibits exceptional performance, with an accuracy 98.92%, precision...
The swift proliferation and extensive incorporation of the Internet into worldwide networks have rendered utilization Intrusion Detection Systems (IDS) essential for preserving network security. Nonetheless, considerable difficulties, especially in precisely identifying attacks from minority classes. Current methodologies literature predominantly adhere to one two strategies: either disregarding classes or use resampling techniques equilibrate class distributions. these methods may constrain...
In this study, we present an integrated approach utilizing IoT data and machine learning models to enhance precision agriculture. We collected extensive secondary dataset from online repository, including environmental parameters such as temperature, humidity, soil nutrient levels, various sensors deployed in agricultural fields. This dataset, consisting of over 1 million points, provided comprehensive insights into the conditions affecting crop yield. The were preprocessed used develop...
A profitable agriculture system is the fundamental foundation of a rising economy. Precise prediction crop yield focuses primarily on research that has significant effect making decisions such as import-export, pricing, and distribution specific crops. There severe need to utilize advanced technologies in order improve quality creation, anticipate yields, study diseases/infections. The most prevalent issue among farmers they do not select appropriate based their soil needs. As result, see...
The economic prosperity of a country is highly dependent on agriculture. use technology in agriculture has greatly contributed to the industrialized countries and crucial for growth emerging countries. One major challenge detection control plant diseases, which can affect food production population well-being. Plant illnesses have substantial effect productivity quality. various types diseases plants with bare eyes time consuming difficult task little precision. Mainly our primary concern...
With the growing usage of credit card transactions, financial fraud crimes have also been drastically increased leading to loss huge amounts in finance industry. Having an efficient detection method has become a necessity for all banks order minimize such losses. In fact, system involves major challenge: data sets are highly imbalanced since number fraudulent transactions is much smaller than legitimate ones. Thus, many traditional classifiers often fail detect minority class objects these...
Abstract Context-aware system (CAS) is a that can understand the context of given situation and either share this with other systems for their response or respond by itself. In surgery, these are intended to assist surgeons enhance scheduling productivity operating rooms (OR) surgical teams, promote comprehensive perception consciousness OR. Furthermore, automated tool classification in medical images real-time computerized assistance conducting different operations. Moreover, deep learning...
Achieving sustainable agricultural advancements necessitates optimizing crop yields while maintaining environmental stewardship. Our research addresses this critical imperative by introducing an innovative predictive model that refines recommendation systems through advanced machine learning techniques, specifically random forest and SHapley Additive exPlanations (SHAP). This study aims to overcome the limitations of traditional advisory approaches incorporating interpretability tools,...
Phishing is referred as an attempt to obtain sensitive information, such usernames, passwords, and credit card details (and, indirectly, money), for malicious reasons, by disguising a trustworthy entity in electronic communication [1]. Hackers users, often use Emails phishing tools the personal data of legitimate sending with authentic identities, content, but also URL, which help them steal consumer's data. The high dimensional context contains large number redundant features that...
Forecasting air pollution is crucial as it not only affects the physical health of people but also provides guidance for control. Particulate Matter with a diameter less than <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2.5\mu m$</tex> (PM <inf xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> ) one major contributors to which can cause acute and chronic effects on human health. PM involves various meteorological factors well influence...