Search
10 articles for “XGBoost”
-
Comparative Analysis of Air Quality Indices Across Five Eastern States of India Using ML Models and Pollutant Based Insights
Abstract: This paper presents a comparative study of Air Quality Index (AQI) levels in five eastern Indian states–Arunachal Pradesh, Assam, Meghalaya, Nagaland, and Tripura. Using historical data, the study explores the concentration of key pollutants, including PM2.5, PM10, NO2, SO2, CO, and Ozone, highlighting regional variations in air quality. Assam, with its higher levels of urbanization and industrial activity, shows elevated AQI levels, especially for pollutants like PM10 and NO2. In …
Published in International Journal of Distributed Computing and Technology · Vol. 11, Issue 1, 2025 · pp. 31–42 Read article
-
Intrusion Detection System Using Gated Recurrent Neural Network
Abstract: In the realm of cybersecurity, the constant evolution of threats demands sophisticated intrusion detection systems (IDSs) capable of discerning intricate patterns in network traffic. This study proposes an IDS leveraging the capabilities of gated recurrent neural networks (GRNNs) to enhance the detection of anomalies and potential security breaches. The GRNN architecture, employing mechanisms like long short-term memory (LSTM) and gated recurrent unit (GRU), demonstrates efficacy in capturing long-range dependencies within …
Published in International Journal of Software Computing and Testing · Vol. 10, Issue 1, 2024 · pp. 1–8 Read article
-
AI-Based Deepfake Voice Detection Model for Hindi Language
Abstract: Most current research on deepfake voice detection focuses heavily on English or Mandarin, creating a significant security gap for Hindi speakers. To address this, we developed a detection framework specifically tailored for the Hindi language using a lightweight approach: Mel-Frequency Cepstral Coefficient (MFCC) feature extraction paired with an XGBoost classifier. We trained the system on a large dataset comprising over 99,000 real voice samples and roughly 3,800 synthetic samples, each …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 2, 2026 Read article
-
Cost-Constrained Sensor Reduction for Deployment AwareIoT-Based Multiclass Water Quality Monitoring
Abstract: Large-scale Internet of Things deployment for water quality monitoring systems is bounded by the capital and several other costs associated with the multi-dimensional sensor. While prior research demonstrates strong predictive performance using multi- parameter physicochemical sensing, limited attention has been given to explicit sensing cost constraints and deployment feasibility. This work formulates multiclass water quality classification as a cost-constrained learning problem in which sensing dimensionality is minimized subject to bounded …
Published in International Journal of Digital Communication and Analog Signals · Vol. 12, Issue 2, 2026 Read article
-
Predicting Traffic Congestion in Mumbai Using Artificial Intelligence
Abstract: Abstract — Mumbai's ongoing traffic problems are brought on by the city's fast urbanization, population expansion, and growing reliance on private automobiles. The majority of traffic management technologies in use today are reactive, frequently reacting only after congestion has already arisen. Using information from a variety of sources, such as commuter surveys, weather reports, and traffic incident logs, this study explores the application of artificial intelligence (AI) and machine learning …
Published in International Journal of Transportation Engineering and Traffic System · Vol. 12, Issue 2, 2026 Read article
-
Data Science for Environmental Modelling
Abstract: Abstract: Soil moisture is a critical Earth system variable linking atmospheric, hydrological, and ecological processes. However, observations are sparse and fragmented: in situ gauges provide point data, satellite missions (SMAP, SMOS, Sentinel-1) offer broad coverage at coarse resolutionQ, and land‐surface models (GLDAS, ERA5, etc.) yield estimates with their own biase. Here we propose a conceptual framework for integrated environmental data modelling, combining rainfall, temperature, and soil moisture information with machine …
Published in International Journal of Water Resources Engineering · Vol. 12, Issue 1, 2026 · pp. 33–40 Read article
-
Data Science for Environmental Modelling
Abstract: Abstract: Soil moisture is a critical Earth system variable linking atmospheric, hydrological, and ecological processes. However, observations are sparse and fragmented: in situ gauges provide point data, satellite missions (SMAP, SMOS, Sentinel-1) offer broad coverage at coarse resolutionQ, and land‐surface models (GLDAS, ERA5, etc.) yield estimates with their own biase. Here we propose a conceptual framework for integrated environmental data modelling, combining rainfall, temperature, and soil moisture information with machine …
Published in International Journal of Water Resources Engineering · Vol. 12, Issue 1, 2026 Read article
-
Bot Defender: A Collaborative Defense Framework for Botnet Intrusion Mitigation
Abstract: Botnet attacks represent a significant threat to cybersecurity, compromising vast numbers of devices and causing extensive harm. BOT DEFENDER is a novel collaborative defense framework designed to mitigate botnet intrusions effectively. This framework leverages the power of collective intelligence, integrating data from multiple sources to detect and respond to botnet threats in real-time. By utilizing advanced machine learning algorithms, BOT DEFENDER can identify anomalous network behavior indicative of botnet activities, …
Published in International Journal of Broadband Cellular Communication · Vol. 11, Issue 2, 2026 · pp. 6–11 Read article
-
A Review of AI and Machine Learning Techniques in Dew Point Pressure Prediction for Gas Condensate Systems
Abstract: Condensate gas reservoirs pose considerable management challenges due to their intricate phase behavior and the critical need for accurate predictions of dew point pressure (PDew). A precise determination of PDew is vital for optimizing production strategies, estimating reserves, and planning enhanced oil recovery operations. Traditional methods for PDew determination often involve experimental analyses that can be both costly and time-consuming, highlighting the necessity for alternative predictive models. This review consolidates …
Published in International Journal of Chemical Engineering and Processing · Vol. 11, Issue 1, 2025 Read article
-
Vehicle Number Plate Detection and Recognition System in Nigeria Using Deep Learning
Abstract: With over 200 million citizens, Nigeria is one of Africa’s largest and most populous nations. It is now essential to automate traffic management due to the rising number of vehicles in the nation. With the use of a deep learning technique known as the YOLO method, the study was able to construct an automatic vehicle license plate identification system that will recognize each of the vehicle license plates when many …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 9, Issue 2, 2023 · pp. 32–45 Read article