Search
218 articles for “deep learning and neural networks”
-
Artificial Intelligence in Entomology: Global Advances, Applications, and Future Directions in Insect Research and Pest Management
Abstract: Artificial Intelligence (AI) is transforming entomology by enabling scalable, data-driven approaches to insect identification, ecological monitoring, and sustainable pest management. This review synthesizes recent global advances in AI applications across taxonomy, behavioral ecology, predictive modeling, and precision agriculture. Machine learning and deep learning techniques—including convolutional neural networks, acoustic classification models, and ensemble predictive algorithms—have demonstrated high classification accuracies (often exceeding 90% under controlled conditions) and improved early detection of pest …
Published in International Journal of Insects · Vol. 3, Issue 1, 2026 · pp. 29–40 Read article
-
Deep Learning models for real time detection of crop diseases in the Maharashtra/Mumbai district
Abstract: This research project addresses the critical agricultural challenge of crop disease management in the Maharashtra region of India by leveraging modern deep learning techniques. The primary objective is to identify, implement, and compare the efficacy of various deep learning architectures—including Convolutional Neural Networks (CNNs), MobileNet, and EfficientNet—for the real-time classification of diseases in key crops such as cotton, soybean, and sugarcane. A custom dataset of agricultural images specific to Maharashtra's …
Published in Research and Reviews : Journal of Crop science and Technology · Vol. 15, Issue 2, 2026 · pp. 36–48 Read article
-
Adaptive E-Learning Algorithms and Heutagogy: A Systematic Analysis
Abstract: The proliferation of artificial intelligence (AI) and machine learning (ML) technologies has transformed the digital education landscape by enabling adaptive e-learning systems capable of personalizing content and optimizing learning paths. This study provides a systematic analysis of adaptive e-learning algorithms within the framework of heutagogy, an educational paradigm that emphasizes learner autonomy, self-direction, and capability development. The convergence of adaptive technologies with heutagogical principles offers new avenues for creating more …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 3, 2025 · pp. 33–38 Read article
-
Machine Learning Assisted Timing Violation Prediction in Sub-7nm VLSI Physical Design
Abstract: The continuous scaling of semiconductor technology into the sub-7nm regime has introduced significant challenges in timing closure due to process variability, interconnect delay, power density, and manufacturing uncertainties. Conventional static timing analysis techniques often require extensive computational resources and iterative optimization cycles, resulting in increased design complexity and longer turnaround time. This research proposes a Machine Learning Assisted Timing Violation Prediction framework for sub-7nm VLSI physical design to improve early-stage …
Published in International Journal of VLSI Circuit Design & Technology · Vol. 4, Issue 1, 2026 Read article
-
Detection of Pneumonia in COVID-19 Patients Using X-ray Images
Abstract: This study explores the use of chest X-ray image analysis and deep learning methods to identify pneumonia in COVID-19 patients. Due to the pandemic, Proper as well as immediate examination of COVID-19 is now essential for patient care and disease control. This study proposes a novel approach that uses convolutional neural networks (CNNs) to automatically predict pneumonia in COVID-19 patients using chest X-ray images. In this study, an X-ray of …
Published in International Journal of Radio Frequency Innovations · Vol. 1, Issue 1, 2023 · pp. 13–23 Read article
-
Facial Emotion Detection and Its Applications
Abstract: Facial emotion detection (FED) is an interdisciplinary field that integrates artificial intelligence, computer vision, and machine learning to recognize and interpret human emotions based on facial expressions. The development of FED systems has been propelled by advancements in deep learning, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which enhance recognition accuracy. Feature extraction techniques, including geometric and appearance-based methods, play a crucial role in classifying emotional states. …
Published in International Journal of Optical Innovations & Research · Vol. 3, Issue 1, 2025 · pp. 8–12 Read article
-
A Study of Cloud-Enabled Deep Learning for Monitoring and Predicting Soil Health in Agriculture
Abstract: Soil health is a critical factor in ensuring sustainable agricultural practices and food security. Traditional methods for soil health assessment are often time-consuming, localized, and lack scalability. This study explores the integration of cloud-enabled deep learning techniques to monitor and predict soil health efficiently. Leveraging data from IoT sensors, satellite imagery, and lab-based analyses, a cloud-based framework is proposed to process and analyze soil health parameters such as pH, moisture …
Published in Journal of Remote Sensing & GIS · Vol. 16, Issue 2, 2025 · pp. 8–16 Read article
-
A Neuromorphic-Inspired, Low-Power VLSI Architecture for Edge AI in IoT Sensor Nodes
Abstract: As the proliferation of Internet of Things (IoT) devices continues to rise, there is an increasing demand for real-time, energy-efficient artificial intelligence (AI) processing directly at the network edge. Traditional edge AI accelerators, often based on deep learning models like convolutional neural networks (CNNs), struggle to meet the ultra-low-power requirements of battery-constrained IoT sensor nodes. In response to this challenge, this study introduces a neuromorphic-inspired, low-power very- large-scale integration (VLSI) …
Published in Journal of Microelectronics and Solid State Devices · Vol. 12, Issue 2, 2025 · pp. 41–47 Read article
-
Attendance System Based on Facial Recognition
Abstract: Attendance management is a fundamental aspect of educational institutions and workplaces, ensuring accountability, discipline, and operational efficiency. Traditional methods, such as manual roll calls, RFID cards, and fingerprint scanners, are often time-consuming, error-prone, and susceptible to fraud. This research presents an automated attendance management system utilizing face recognition technology to address these challenges effectively. The proposed system employs OpenCV for real-time image processing, the face recognition library for accurate facial …
Published in International Journal of Electronics Automation · Vol. 3, Issue 1, 2025 · pp. 28–34 Read article
-
Detection and Classification of Brain Tumor from MRI And CT Images using Harmony Search Optimization and Deep Learning
Abstract: Primary brain tumor detection and classification are critical factors in ensuring effective treatment and, ultimately, improving patient well-being. This paper describes a novel method for detecting and classifying brain tumors with the help of magnetic resonance imaging (MRI) and computed tomography (CT) images. The suggested method combines harmony search optimization (HSO) and Convolution Neural Networks (CNN) based on deep learning techniques, yielding an impressive accuracy rate of 99.13% for both …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 11, Issue 3, 2024 · pp. 31–49 Read article
-
Design and Development of Agrobot Using Feed Forward Network for Smart Farming Agriculture
Abstract: The Agrobot framework is a form of natural language processing that requires training to understand human language and meet user needs accordingly. The development of a chatbot tailored for the agricultural industry represents a significant advancement in agricultural technology. This chatbot serves as an interactive tool to assist farmers in various aspects of agricultural practices, including crop management, pest control, weather forecasting, and market information. The main objective of this …
Published in Journal of Advancements in Robotics · Vol. 11, Issue 1, 2024 · pp. 6–14 Read article
-
Artificial Intelligence in Cerebellum Activation
Abstract: Neuroscience plays a significant function during the progression of artificial intelligence. It provided inspiration for the development of human-like AI. There are two ways that neuroscience encourages us to develop AI systems. Neural networks that replicate human cognition and those that match the structure of the brain are the two objectives. Neural networks, which draw inspiration from the architecture of the human brain, are the engine behind contemporary artificial intelligence …
Published in International Journal of Cheminformatics · Vol. 1, Issue 1, 2023 · pp. 14–26 Read article
-
Sustainable Cotton Crop Productivity through Precision Weed Detection: A Deep Learning-Based Approach with UAV Integration
Abstract: Weeds present a major challenge to crop productivity by competing with crops for vital resources, including water, sunlight, and nutrients, often resulting in significant yield reductions. On a global scale, weeds are responsible for approximately 13.2% of annual crop losses, a quantity sufficient to feed nearly one billion people. These invasive plants disrupt agricultural systems and adversely impact crop yields. Given their uneven distribution in fields, ground or aerial robots …
Published in Journal of Aerospace Engineering & Technology · Vol. 15, Issue 1, 2025 · pp. 19–26 Read article
-
Analysis and Identification of Malicious Mobile Applications Using Machines Learning
Abstract: Over the past few years, malware attacks on the Android platform have surged, posing significant risks to users' financial security, personal information, and device integrity. In the first half of 2019 alone, approximately 25 million smartphones were infected, highlighting the severity of these threats. The model ranks manifest features based on their frequency in normal and malicious apps, identifying key components that distinguish benign from malicious applications. To improve detection …
Published in Journal of Microcontroller Engineering and Applications · Vol. 12, Issue 2, 2025 · pp. 17–24 Read article
-
A Review of AI-Based Intrusion Detection Systems for Mobile Ad Hoc Networks (MANETs)
Abstract: Mobile Ad Hoc Networks (MANETs) comprise wireless networks that lack any conventional infrastructure . Their chief features include highly changing network topologies, lack of centralized administration, and open nature of communication, which collectively result in making MANETs of the wireless kind very susceptible to a diverse range of cyber-attacks like blackhole, greyhole, wormhole, flooding, Sybil and denial-of-service (DoS) among others. Conventionally, Intrusion Detection Systems (IDS) relying on static rule-based methods …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 13, Issue 3, 2025 Read article
-
Intrinsic Evaluation of Graph Embeddings: Assessing Clustering and Community Detection Performance
Abstract: This paper presents an intrinsic evaluation of some graph embedding techniques on clustering and community detection tasks. We analyze a diverse set of embedding methods, ranging from traditional techniques such as Laplacian eigenmaps to more recent approaches like graph autoencoders, high-order proximity preserved embedding (HOPE), and graph attention network (GAT), using two widely studied datasets, Cora and CiteSeer. Our evaluation relies on two main metrics: Silhouette score with respect to …
Published in International Journal of Algorithms Design and Analysis Review · Vol. 3, Issue 1, 2025 · pp. 40–48 Read article
-
Optimizing Mango Harvest Timing in the Nasik Region (Maharashtra, India) by CNNs (Residual Network 101)
Abstract: The determination of optimal harvest timing is one of the most critical decisions in mango production, directly affecting postharvest quality, market value, transportation resilience, and export readiness. In regions such as Nashik, Maharashtra—one of India’s major fruit- producing belts—the climatic variability, cultivar differences, monsoon patterns, and market- driven pressures make accurate harvest timing essential. Traditional maturity assessment relies on subjective visual inspection, specific gravity, or destructive testing, each of which …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 13, Issue 1, 2026 Read article
-
Evaluation of composite material based on different phases of Face recognition System
Abstract: Composite materials can indeed play a crucial role in various phases of a face recognition system, offering advantages such as lightweight construction, durability, and tailored mechanical properties. Let's explore how composite materials can be utilized in different phases of a face recognition system. A composite material based different phases of Face recognitions System is software that recognizes or verifies a person based on a digital image or a frame from …
Published in Journal of Polymer & Composites · Vol. 12, Issue 2, 2024 · pp. 195–204 Read article
-
An Empirical Study of Hyperparameter Impact on Deep Learning Models for Cardamom Leaf Disease Classification
Abstract: Recent advancements in deep learning models like convolutional neural networks and self- attention mechanisms have achieved great success in the field of plant disease classification. This study investigates the efficacy of two pre-trained models, ConvNeXT-Tiny and Swin Transformer-Tiny, for leaf disease classification in cardamom using a publicly available dataset constituting three categories of leaves, namely Healthy, Colletotrichum Blight and Phyllosticta Leaf Spot. The effectiveness of the models highly depends on …
Published in Current Trends in Information Technology · Vol. 15, Issue 3, 2025 · pp. 48–60 Read article
-
Deep Learning Architectures for Predictive Modeling in Financial Time Series
Abstract: This study investigates the application of deep learning architectures, particularly convolutional neural networks (CNNs), to the challenging task of financial time series forecasting. Financial markets are inherently complex and influenced by a range of factors, making accurate prediction of price movements a difficult problem. In this research, historical financial data including stock prices, volumes, and other relevant indicators are used to train CNN models aimed at capturing the underlying patterns …
Published in Current Trends in Signal Processing · Vol. 15, Issue 3, 2025 · pp. 45–55 Read article