LSTM
18 articles · search the full text for this term
-
EcoSense AI: An Intelligent IoT-Based Environmental Monitoring and Forecasting System
Abstract: Environmental degradation caused by air, water, and soil pollution poses a severe global threat to human health and ecosystem stability. Existing IoT- based monitoring systems classify only current pollution levels but lack predictive capability, geospatial context, and tamper-proof data integrity. This paper presents EcoSense AI—a unified low-cost intelligent environmental monitoring system built on an ESP32 microcontroller with MQ135, DHT11, turbidity, and GPS sensors. The system integrates a Random Forest classifier …
Published in Journal of Instrumentation Technology & Innovations · Vol. 16, Issue 3, 2026 Read article
-
Digital Twin Assisted Intelligent Prediction of Polymer Composite Degradation Under Environmental Exposure
Abstract: Polymer matrix composites (PMCs) deployed in aerospace, marine, automotive, and renewable-energy structures are continuously subjected to coupled environmental stressors — ultraviolet (UV) radiation, moisture ingress, thermal cycling, and mechanical loading — that progressively degrade their mechanical performance. Conventional accelerated ageing tests and empirical lifetime models are time-consuming, destructive, and poorly suited to in-service, asset-specific degradation forecasting. This paper proposes a Digital Twin (DT) assisted intelligent prediction framework that fuses a …
Published in Journal of Polymer & Composites · Vol. 14, Issue 4, 2026 Read article
-
Real-Time Deepfake Detection in Video Conferencing Systems
Abstract: Deepfake technology presents non-exemplary threats to video conferencing platforms, enabling advanced fraud, impression and misinformation campaigns worth billions annually. Current detection methods either exhibit latencies exceeding 100ms or rely on server-side cloud processing, raising privacy concerns. This paper presents DeepConfGuard, a lightweight hybrid architecture combining MobileNetV2 for spatial feature extraction, a bidirectional LSTM with attention for temporal modelling, and EfficientNetV2 for refinement. It reaches 94.8% accuracy with 85 ms end‑to‑end …
Published in International Journal of Electronics Automation · Vol. 4, Issue 2, 2026 Read article
-
Lightweight Models for Per-PC Energy Consumption Forecasting: Comparative Study with ML and DL Approaches
Abstract: We have collected primary data from automated logging of parameters like CPU utilization, estimated power, active or idle state, user logging activity, and the type of day. Additionally, survey data showed user awareness, energy-saving behaviour, and PC usage patterns. The data is pre-processed and merged by applying processes such as data cleaning, normalization, and feature extraction, i.e., determining the peak active timings and downtime. Developed lightweight prediction models based on …
Published in Journal of Alternate Energy Sources & Technologies · Vol. 17, Issue 1, 2026 Read article
-
A SEIR-Informed Stacked Fusion of Prophet, XGBoost, and LSTM for Ward-Level Epidemic Forecasting in Amravati Municipal Corporation
Abstract: Municipal epidemic preparedness depends on accurate short-horizon forecasts at fine spatial granularity. Ward-level incidence series are typically nonstationary due to changing contact patterns, interventions, reporting delays, and heterogeneous demographic and environmental factors. This paper presents a mathematically formulated hybrid forecasting architecture designed for Amravati Municipal Corporation (AMC). The method decomposes observed incidence into (i) a mechanistic SEIR baseline that enforces epidemiological structure and (ii) a data-driven residual learned using Prophet …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 13, Issue 1, 2026 · pp. 17–23 Read article
-
Enhancing IoT Network Security with Hybrid Deep Learning Classifiers for DDoS Attack Detection
Abstract: The security and operational dependability of Internet of Things (IoT) networks are seriously threatened by the growing susceptibility to Distributed Denial of Service (DDoS) assaults brought about by their rapid expansion. The intricacy and dynamic character of these advanced attacks can provide a challenge to conventional intrusion detection systems. This study presents a novel method for strengthening IoT network security by combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory …
Published in Journal of Web Engineering & Technology · Vol. 13, Issue 1, 2026 · pp. 23–33 Read article
-
An Intelligent Neural Networks Approach for Monitoring of Soilless Urban Farms
Abstract: Urban agriculture is increasingly recognized as a sustainable approach to addressing food security challenges in rapidly growing and densely populated cities. Conventional soil-based farming often faces limitations such as space scarcity, excessive water consumption, and environmental degradation. To overcome these challenges, soilless farming techniques such as hydroponics and aeroponics have gained significant attention due to their efficient utilization of space, reduced water requirements, and potential for year-round crop production. However, …
Published in Journal of Water Resource Engineering and Management · Vol. 12, Issue 3, 2025 · pp. 31–37 Read article
-
Phisherman: A Phishing Email Detection Browser Extension
Abstract: Phishing attacks continue to pose significant security risks, exploiting email as a primary vector to deceive users and compromise sensitive information. To counter these threats, Phisherman presents a sophisticated, real-time phishing detection system that integrates both rule-based methods and deep learning for heightened accuracy. Built as a cross-browser extension, compatible with Chrome, Firefox, and Edge through the WebExtension API, Phisherman combines traditional verification checks, such as DNS blacklisting, SPF, DKIM, …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 2, 2025 · pp. 99–105 Read article
-
Investigation of High reliable electric vehicles drive with fast charging system
Abstract: Per capita, India has the world's biggest battery electric vehicle market. For the last several years, there has been a lot of discussion about the challenges and prospects of integrating electric vehicles (EV) with an electric grid. A battery model of an EV should have suitable control mechanisms to interact with an electric grid. The growth of and accessibility of fast-charging technology is one of the many technological concerns being …
Published in Trends in Electrical Engineering · Vol. 15, Issue 1, 2025 · pp. 44–50 Read article
-
Robustness of Deepfake Detection Systems Against Adversarial Attacks
Abstract: This paper explores a deep learning system to detect deepfake videos, a common type of fake media. With the use of sophisticated methods such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), our system can reliably discern between authentic and altered videos. It analyzes both the images and the audio in videos to find signs of deepfake manipulation. We process video frames and audio, extract features with CNNs …
Published in Journal of Instrumentation Technology & Innovations · Vol. 14, Issue 2, 2024 Read article
-
Deep Plate: A Deep Learning Approach to Recipe Generation from Food Images
Abstract: In the deep learning era, image understanding is advancing in sophistication, encompassing both semantic interpretation and the generation of meaningful image descriptions. To achieve this, deep neural networks must undergo specific cross-model training; these networks must be both simple enough to handle a wide range of inputs and complex enough to encode the fine contextual information associated with the image. An appropriate example of the previously described picture comprehension problem …
Published in Journal of Operating Systems Development & Trends · Vol. 11, Issue 2, 2024 · pp. 15–22 Read article
-
Stock Market Analysis Using Data Science
Abstract: Stock market prediction using data science has become a popular area of research and application in recent years. This is because the stock market is a complex system with many variables and factors that affect its behavior, making it difficult to predict with certainty. The stock market has always been the aggression of buyers and sellers of stocks, therefore in the global finance market, stock trading is one of the …
Published in E-Commerce for Future & Trends · Vol. 11, Issue 1, 2024 · pp. 1–4 Read article
-
Sign Language Recognition Using Deep Learning
Abstract: People with hearing/speech disabilities use sign language to communicate their thoughts and feelings, but non-disabled people often find it hard to comprehend these hand gestures since they do not know sign language. This project aims to create a system that uses MediaPipe, LSTM and Keras for sign language recognition. The webcam will capture video footage of people performing sign language gestures, then MediaPipe will extract and identify the hand landmarks …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 10, Issue 2, 2023 · pp. 35–43 Read article
-
Providing Captions to the Detected Images: Deep Neural Networks and LSTM
Abstract: Automatically generating captions for images seems to be very interesting but at the same time the task is quite challenging as training a machine with proper comprehension of the image, it’s background, detecting the objects present in it and finally generating the captions is only the frontline projection; The difficult part happens behind the scenes: selecting the dataset, training the model, validating the model, developing pre-trained models to test the …
Published in Recent Trends in Parallel Computing · Vol. 8, Issue 3, 2021 · pp. 30–38 Read article
-
A Survey on Deep Learning based Detection of Abnormal Human Behaviour using Computer Vision Human Activity Recognition System
Abstract: Abnormal Human activity recognition (Abnormal HAR) systems are very popular among researchers nowadays, they attempt to identify and analyze human activities using acquired information from sensors. Several papers have already been published in the abnormal HAR topics, the technologies in this field have multidisciplinary nature. They need constant updates. Our literature survey divided the approaches into three categories, the first one is about wearable sensor-based approach, the second one is …
Published in Journal of Computer Technology & Applications · Vol. 12, Issue 3, 2021 · pp. 32–41 Read article
-
Wind Forecasting Using Various Neural Networks in Machine Learning
Abstract: Wind Power Forecasting, as the name applies is a process in which data of past is used to tell what kind of output can be expected from a wind turbine in the foreseeable future. Machine learning, can be said to be a derivation of artificial intelligence that makes it possible for the system to learn automatically and improve upon itself from faults, without needing to tell the system to do …
Published in Journal of Telecommunication, Switching Systems and Networks · Vol. 8, Issue 2, 2021 · pp. 32–43 Read article
-
Early Warning Flood Forecasting Using Long Short-Term Memory Network
Abstract: AbstractFlooding is the natural disaster which leads to massive loss of life and property as well. India faces this situation every year and millions of people are being displaced due to loss of shelter. Early warning of flood disaster in corresponding locality provides sufficient time to protect their precious life and property. However, the range of flood prediction introduces the issue of cost, reliability and maintenance. We are proposing the …
Published in Current Trends in Information Technology · Vol. 10, Issue 3, 2020 · pp. 30–34 Read article
-
Stock Price Prediction Using RNN and LSTM
Abstract: Prediction of stock market has been an attractive topic to the stockbrokers. In stock market the decision on when buying or selling stock is important in order to achieve profit. There are number of techniques that can be used to help investors in order to make a decision for financial gain. In this research work we have proposed a prediction algorithm that will give the relation between the dependent factor …
Published in Journal of Open Source Developments · Vol. 5, Issue 3, 2018 · pp. 26–34 Read article