78 hasil
Menampilkan 1–20 · 0,18 detik · RSS
تحلیل مدارها، داده ها و سامانه ها
ISSN 2981-1295 · ISLAMIC AZAD UNIVERSITY · 78 artikel di indeks
-
Artikel Jurnal
A Novel Method in Cardiac Signal Processing for Detecting Premature Ventricular Contractions Using Multi-domain Feature Engineering and Deep Learning Techniques
The present study proposes a novel processing framework for the automatic detection of premature ventricular contractions (PVCs). Cardiac arrhythmias are one of the most significant challenges in the healthcare sector, and their timely detection plays a decisive role in preventing cardiac…
-
Artikel Jurnal
Comparative Analysis of the Performance of Explainable Learning Classifier Systems Using Data Streams and Dynamic Evolutionary Algorithms
With the exponential growth of streaming data in intelligent systems, the demand for adaptive and explainable learning methods has become more critical than ever. Learning Classifier Systems, which integrate reinforcement learning with evolutionary search, provide a robust foundation for analyzing…
-
Artikel Jurnal
A Reactive and Adaptive Protocol (EERP+) for Energy-Aware Clustering in Wireless Sensor Networks
With the rapid expansion of Wireless Sensor Networks (WSNs), optimizing energy consumption has become a critical challenge due to the limited power resources of sensor nodes. This paper presents EERP+ (Enhanced Energy-Efficient Reactive Protocol), a novel reactive and adaptive routing protocol…
-
Artikel Jurnal
Improving detection of phishing websites using machine learning and deep learning models
Phishing attacks represent a significant cybersecurity threat, targeting internet users to steal confidential information. This research presents a hybrid deep learning model that employs data preprocessing, data balancing via SMOTE, and dimensionality reduction via PCA. The primary innovation of…
-
Artikel Jurnal
A method for identifying social influence using embedded similarity and homophily in location-based social networks
Location-based social networks are very important in the field of targeted commerce and advertising due to their valuable location data and user relationships. A key issue in these networks is determining the social influence of users to identify influential users. Research has proven the role of…
-
Artikel Jurnal
Exploring new methods for detecting Android malware
Android malware detection has consistently faced numerous challenges due to the continuous evolution of hacking and penetration techniques targeting the Android operating system. Consequently, many classic and legacy methods for detecting Android malware are no longer adequate. Hackers can conceal…
-
Artikel Jurnal
Optimal sizing and techno-economic analysis of combined solar-wind power system, fuel cell and tidal turbines using meta-heuristic algorithms: a case study of Lavan Island
To find the ideal sizes of PV, wind, hydrogen, battery, and fuel cell systems with electrolysers for remote areas (like Lavan Island), this study developed a generalized mathematical model that is independent of the electricity distribution network. The goal was to provide electricity at a lower…
-
Artikel Jurnal
Simulation and Online Monitoring of DC-Link Capacitors in Power Electronic Converters Used in Substation Battery Chargers
DC-link capacitors, particularly electrolytic types, are among the most critical yet vulnerable components in power electronic converters used for substation battery charging. The primary indicators of capacitor aging are an increase in equivalent series resistance (ESR) and a decrease in…
-
Artikel Jurnal
Noise-resistant single-image Super-Resolution using adaptive sparse representation
Practically, Single-image super-resolution (SISR) in the presence of noise and incomplete scene information poses a major challenge in image processing. This paper presents a robust and adaptive SISR algorithm based on sparse representation that recovers high-resolution images without prior…
-
Artikel Jurnal
Utilizing Machine Learning Algorithms to Enhance the Selectivity of Metal Oxide Sensors: A Review
Metal oxide (MOS) sensors are widely used for gas detection due to their low cost, small size, and good reversibility. However, their inherent detection mechanism, based on resistance changes upon gas adsorption, suffers from poor selectivity, limiting use in complex gas mixtures. To overcome this…
-
Artikel Jurnal
A Hybrid Algorithm of Kalman Filter and Adaptive Least Squares for Object Tracking Under Occlusion in Video
Occlusion in video surveillance, caused by environmental factors and camera angles, significantly impacts target tracking and introduces substantial limitations to the video object tracking process. The central challenge in video object tracking lies in accurately following an occluded target. This…
-
Artikel Jurnal
A tourism recommender system using the bat algorithm based on the information available on the Instagram social network
Recommender systems are a core component of personalized location-based services. They function by filtering information presented to users and generating suggestions aligned with their interests. The exponential growth of information on the World Wide Web challenges user decision-making across…
-
Artikel Jurnal
Symbolically Modeled Reverse-Nested Miller Compensation for High-Performance Four-Stage CMOS Amplifiers
Leveraging nested Miller loops and low-power differential blocks, an efficient frequency compensation is presented. The compensation frequency network emulates the reversed nested Miller approach while the case is a four-stage CMOS amplifier. The suggested scheme is linearly modeled using a…
-
Artikel Jurnal
Optimizing Data Collection in Drones-based MIoT Networks: A BPSO Approach
Numerous IoT-based networks have explored the integration of Unmanned Aerial Vehicles (UAVs) as data collectors, forming what is commonly referred to as the Internet of Drones (IoD) or drone-based IoT networks. This paper presents a drones-based Medical IoT (DMIoT) architecture for efficient data…
-
Artikel Jurnal
The impact of Beamforming on the Coverage of Wireless Access Networks
Deploying wireless access networks involves a wide range of techniques and considerations, including equipment selection and access point placement. In this paper, various techniques for deploying a wireless access network, wireless access network deployment scenarios, and factors involved in…
-
Artikel Jurnal
Detecting and Adapting to Concept Drift in Data Streams: A Review of Incremental Decision Tree Approaches
In dynamic and non-static data flow environments, the phenomenon of concept drift is a fundamental challenge, during which the distribution of data changes over time and causes a gradual decrease in the accuracy of learning models. Incremental decision trees have been proposed as one of the…
-
Artikel Jurnal
Link Prediction Using Negative Sampling Method
Knowledge graph embedding methods efficiently represent entities and relationships in vector space. The main challenge is the lack of high-quality negative samples, which reduces link prediction accuracy. To address this challenge, this study explores a method called distance-based simple negative…
-
Artikel Jurnal
Purposeful Input Selection for Nonlinear Systems Identification
Accurate identification of nonlinear systems is one of the essential prerequisites for designing and implementing advanced controllers. Although classical identification techniques—especially recursive algorithms—are suitable for online applications, they typically face challenges such as long…
-
Artikel Jurnal
Using convolutional neural networks to detect the tumor size and lymph node metastasis of colon cancer patients in MRI
Colon cancer is the third most common cancer from all cancers in 2020. In determining the appropriate treatment, the oncologist has to know the stage of the tumor, which is the most common method of the “Tumour, Node, Metastasis” staging system. Therefore, in this study, an attempt is made to…
-
Artikel Jurnal
The effect of climatic design of the building on the reduction of Embodied energy and comparison with the consumed electricity (A case-study of Shiraz city)
This research has evaluated the reduction of embodied energy consumption in the building (energy consumed during construction) and comparing it with energy consumption during the exploitation period (electricity consumption). First, according to field and library studies, influential independent…