Browse Items (11810 total)
Sort by:
-
Improving Indoor occupancy estimation using a hybrid CNN-LSTM approach
Indoor Air Quality (IAQ) monitoring has been a significant research domain in energy conservation. Many energy resources are required to maintain the IAQ using airconditioning or other ventilation systems. Currently, the research works highly optimize an on-demand driven energy usage depending on the occupant present inside the building. In the last decade, numerous research works have evolved for such an optimization by installing sensors and predicting occupants using machine learning techniques. This research fails to deploy non-intrusive sensors and appropriate machine learning algorithms to predict the occupancy count. Advancement in neural network techniques termed deep learning has made significant performance in recognition and cognitive tasks. Thus, this paper proposes a hybrid deep learning model that stacks the convolutional neural network (CNN) and long short term memory (LSTM) to improve the prediction rate of the occupancy count. Experimentation has been carried out in real-time multivariate sensor data for the occupancy estimation and evaluated the performance in terms of accuracy, RMSE, MAPE, and coefficients of determinants. 2022 IEEE. -
Improving Image Clarity with Artificial Intelligence-Powered Super-Resolution Methods
Super-resolution has advanced significantly in the last 20years, particularly with the application of deep learning methods. One of the most important image processing methods for boosting an image's resolution in computer vision is image super-resolution besides providing an extensive overview of the most recent developments in artificial intelligence and deep learning for single-image super-resolution. This study delves into the subject of image enhancement by investigating sophisticated AI-based super-resolution techniques. High-quality photographs have become more and more in demand in a variety of industries recently, including medical imaging, satellite imaging, entertainment, and surveillance. Pixilation reduction and detail preservation are two areas where traditional image enhancing techniques fall short. Artificial intelligence has demonstrated amazing promise in addressing these issues, especially with regard to Deep Learning models. The applications, benefits, and difficulties of modern super-resolution techniques are thoroughly examined in this work. We also suggest new approaches and push the limits of image enhancement by experimenting with state-of-the-art artificial intelligence algorithms. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Improving Groundwater Forecasting Accuracy with a Hybrid ARIMA-XGBoost Approach.
In addressing the critical challenge of accurate groundwater level prediction, this study explores the comparative performance of various machine learning models. We implement a novel hybrid model combining ARIMA and Extreme Gradient Boosting (XGB) for the prediction of groundwater levels, and compare it against traditional models including ARIMA, XGBoost, LightGBM, Random Forest, and Decision Trees. Traditional approaches often rely on single models; however, our research seeks to delve into the intricacies of hybrid model architectures. Combining the strengths of ARIMA and XGB, we aim to build a highly accurate and efficient groundwater level prediction system. Comprehensive evaluations were conducted using metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), The future scope of machine learning in water resource management includes integrating such models with real-time monitoring systems and expanding their applications to diverse environmental conditions and regions. 2024 IEEE. -
Improving crop production using an agro-deep learning framework in precision agriculture
Background: The study focuses on enhancing the effectiveness of precision agriculture through the application of deep learning technologies. Precision agriculture, which aims to optimize farming practices by monitoring and adjusting various factors influencing crop growth, can greatly benefit from artificial intelligence (AI) methods like deep learning. The Agro Deep Learning Framework (ADLF) was developed to tackle critical issues in crop cultivation by processing vast datasets. These datasets include variables such as soil moisture, temperature, and humidity, all of which are essential to understanding and predicting crop behavior. By leveraging deep learning models, the framework seeks to improve decision-making processes, detect potential crop problems early, and boost agricultural productivity. Results: The study found that the Agro Deep Learning Framework (ADLF) achieved an accuracy of 85.41%, precision of 84.87%, recall of 84.24%, and an F1-Score of 88.91%, indicating strong predictive capabilities for improving crop management. The false negative rate was 91.17% and the false positive rate was 89.82%, highlighting the framework's ability to correctly detect issues while minimizing errors. These results suggest that ADLF can significantly enhance decision-making in precision agriculture, leading to improved crop yield and reduced agricultural losses. Conclusions: The ADLF can significantly improve precision agriculture by leveraging deep learning to process complex datasets and provide valuable insights into crop management. The framework allows farmers to detect issues early, optimize resource use, and improve yields. The study demonstrates that AI-driven agriculture has the potential to revolutionize farming, making it more efficient and sustainable. Future research could focus on further refining the model and exploring its applicability across different types of crops and farming environments. The Author(s) 2024. -
Improving Consumer Engagement with AI Chatbots: Exploring Perceived Humanness, Social Presence, and Interactivity Factors
In many consumer industries, AI robots are becoming more and more popular because they let businesses communicate with their customers in a cheap and quick way. However, how well these measures work rests on how real and present people think they are in social situations. The main things that affect how customers deal with AI chatbots are looked into in this research. These are interaction, social presence, and perceived humanity.A wide range of users will be asked to fill out quantitative polls that will be used to judge how humanlike AI chatbots are, how well they can interact with others, and how much they interact with people. Additionally, performing qualitative interviews will give you a fuller picture of what customers want and how they interact with AI chatbots. Companies can make their chatbot exchanges with customers better by figuring out what makes the bots act like humans: friendly, interested, and sociable. This will allow them to make chatbots that are very specific to their customers' needs and tastes. The goal of this researchprogramme is to make customers happier, more loyal to brands, and have better experiences by creating AI chatbots that can have conversations with people like real people. 2024 IEEE. -
Improvement to Recommendation system using Hybrid techniques
Currently, recommendation systems are a common tool for providing individualized recommendations and item information to users. For personalization in the recommendation system, there are a variety of strategies that can be used. To improve system performance and offset the shortcomings of individual recommendation strategies, a hybrid recommender system integrates two or even more recommendation techniques. The demand to summarize all of the knowledge on actual methods and algorithms utilized in hybrid recommended systems necessitates the need for a systematic review in the domain. These materials will be employed to aid in the development of an auto-switching hybrid recommender system. In the content-based filtering technique, the algorithm is based on the contents of items and the collaborative filtering technique algorithm combines the relationship between user and item. Both of the approaches of recommendation system are suffers from some limitations, this is a big issue to predict better recommendations to the user. Hybrid systems are introduced to overcome the main limitations of both techniques. These systems are made with a combination of content-based and collaborative filtering techniques and have advantages of both techniques. With the use of hybrid systems, the quality of recommendations is improved. Hybrid recommendation systems use previous data of a user to find his/her interest and then they target the set of an adjacent user which is similar with that user and according to adjacent user recommend things to the user. Hybrid systems offer the items that share the common things that a user rated highly (Content-based filtering) and make suggestions by comparing the interest of a similar user (Collaborative filtering). 2022 IEEE. -
Improvement of Speech Emotion Recognition by Deep Convolutional Neural Network and Speech Features
Speech emotion recognition (SER) is a dynamic area of research which includes features extraction, classification and adaptation of speech emotion dataset. There are many applications where human emotions play a vital role for giving smart solutions. Some of these applications are vehicle communications, classification of satisfied and unsatisfied customers in call centers, in-car board system based on information on drivers mental state, human-computer interaction system and others. In this contribution, an improved emotion recognition technique has been proposed with Deep Convolutional Neural Network (DCNN) by using both speech spectral and prosodic features to classify seven human emotionsanger, disgust, fear, happiness, neutral, sadness and surprise. The proposed idea is implemented on different datasets such as RAVDESS, SAVEE, TESS and CREMA-D with accuracy of 96.54%, 92.38%, 99.42% and 87.90%, respectively, and compared with other pre-defined machine learning and deep learning methods. To test the real-time accuracy of the model, it has been implemented on the combined datasets with accuracy of 90.27%. This research can be useful for development of smart applications in mobile devices, household robots and online learning management system. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Improvement of Automatic Glioma Brain Tumor Detection Using Deep Convolutional Neural Networks
This article introduces automatic brain tumor detection from a magnetic resonance image (MRI). It provides novel algorithms for extracting patches and segmentation trained with Convolutional Neural Network (CNN)'s to identify brain tumors. Further, this study provides deep learning and image segmentation with CNN algorithms. This contribution proposed two similar segmentation algorithms: one for the Higher Grade Gliomas (HGG) and the other for the Lower Grade Gliomas (LGG) for the brain tumor patients. The proposed algorithms (Intensity normalization, Patch extraction, Selecting the best patch, segmentation of HGG, and Segmentation of LGG) identify the gliomas and detect the stage of the tumor as per taking the MRI as input and segmented tumor from the MRIs and elaborated the four algorithms to detect HGG, and segmentation to detect the LGG works with CNN. The segmentation algorithm is compared with different existing algorithms and performs the automatic identification reasonably with high accuracy as per epochs generated with accuracy and loss curves. This article also described how transfer learning has helped extract the image and resolution of the image and increase the segmentation accuracy in the case of LGG patients. Copyright 2022, Mary Ann Liebert, Inc., publishers 2022. -
Improvement in food preservation with nanozymes
To ensure safety, quality, and extended shelf life of perishable food products, food preservation is a critical aspect of food industries. Concerns regarding the potential health risks and loss of nutritional value of food because of traditional methods of preservation such as using chemical additives and high temperatures have set the need for finding alternative methods of preservation, for the betterment of health and the environment. Enzymes have the potential to kill microorganisms. Enzymes such as oxidases, peroxidases, hydrolases, catalases, and others have been extensively studied for their microbicidal activities. However, natural enzymes have shortfalls as they can be easily denatured and cannot be recycled. Nanozymes have gained the limelight in recent years as they can be applied in food industries to overcome the shortfalls of natural enzymes. They embody the highly beneficial properties of both enzymes and nanoparticles at the same time. Due to their enzyme-mimicking properties and versatile applications, nanozymes have become more popular in the last few years. Nanozymes have evolved as a promising alternative for food preservation and the detection of various contaminants in food. However, before the integration of nanozymes into the food industry, several factors such as their stability, biocompatibility, longevity, toxicity, cost-effectiveness, scalability, and regulatory approval need to be addressed. This chapter discusses the concept of nanozymes, its classification, and various applications in food industries specially designed for preservation of food products. 2024 Elsevier Inc. All rights are reserved including those for text and data mining AI training and similar technologies. -
Improved tweets in English text classification by LSTM neural network
This paper analyzes the performance of an LSTM-type neural network in the sentiment analysis task in tweets in English about the COVID-19 pandemic. Primarily, the organization and cleaning a database of tweets about the COVID-19 pandemic is performed. From the original database, two other databases through different discretizations of the polarities of the tweets using Heaviside-type functions are created. Vectorization of tweets using the Word2Vec word embedding technique is carried out. Computational implementations of LSTM neural networks to the context of our research problem are adapted. Analyzes and discussions on the feasibility of the proposed solution taking into account different types of hyperparametric adjustments in the neural network models is carried out. Publicly available databases organized through the Mendeley Data public data repository are used. 2023 IEEE. -
Improved Security of the Data Communication in VANET Environment Using ASCII-ECC Algorithm
Now-a-days, with the augmenting accident statistics, the Vehicular Ad-hoc Networks (VANET) are turning out to be more popular, helping in prevention of accidents in addition to damage to the vehicles together with populace. In VANET, message can well be transmitted within a pre-stated region to attain systems safety and also improveits efficacy. Ensuring authenticity of messages is a challenge in such dynamic environment. Though few researchers worked on this, security level is very less. Hence enhanced communicationsecurity on the VANET environment utilizing the American Standard Code for Information Interchange centred Elliptic Curve Cryptography (ASCII-ECC) is proposedin this paper. The network design is definedinitially. Subsequently, the entire vehicles get registered to the Trusted Authority (TA); similarly, all vehicle users areregistered with their On-Board Unit (OBU). This is followed byMedian-centred K-Means (MKM) performs the cluster formation together with Cluster Head Selection (CHS). Next, TA takes care of the verification procedure. Modified Cockroach Swarm Optimization (MCSO) calculates the shortest path and the ASCII-ECC carries out the secure data communication if the vehicle is an authorized one. If not, TA sends the alert message for discarding the request. The system renders better performance when it was weighed against the top-notch methods. 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. -
Improved reptile search algorithm with sequential assignment routing based false packet forwarding scheme for source location privacy protection on wireless sensor networks
Source Location Privacy (SLP) in Wireless Sensor Networks (WSNs) refers to a set of techniques and strategies used to safeguard the anonymity and confidentiality of the locations of sensor nodes (SNs) that are the source of transmitted data within the network. This protection is important in different WSN application areas like environmental monitoring, surveillance, and healthcare systems, where the revelation of the accurate location of SNs can pose security and privacy risks. Therefore, this study presents metaheuristics with sequential assignment routing based false packet forwarding scheme (MSAR-FPFS) for source location privacy protection (SLPP) on WSN. The contributions of the MSAR-FPFS method revolve around enhancing SLP protection in WSNs through the introduction of dual-routing, SAR technique with phantom nodes (PNs), and an optimization algorithm. In the presented MSAR-FPFS method, PNs are used for the rotation of dummy packets using the SAR technique, which helps to prevent the adversary from original data transmission. Next, the MSAR-FPFS technique uses an improved reptile search algorithm (IRSA) for the optimal selection of routes for real packet transmission. Moreover, the IRSA technique computes a fitness function (FF) comprising three parameters namely residual energy (RE), distance to BS (DBS), and node degree (ND). The experimental evaluation of the MSAR-FPFS system was investigated under different factors and the outputs show the promising achievement of the MSAR-FPFS system compared to other existing models. 2024-IOS Press. All rights reserved. -
Improved Random Forest Algorithm for Cognitive Radio Networks' Distributed Channel and Resource Allocation Performance
Modified Random Forest (MRF) machine learning algorithm aimed at improving the distributed channel allocation and resource allocation performance in cognitive radio networks (CRNs). The purpose of this research is to enhance the efficiency and effectiveness of CRNs by optimizing the allocation of channels and resources. The proposed MRF algorithm is developed by adapting and modifying the random forest technique to address the specific challenges of CRN allocation. Experimental evaluations demonstrate that the MRF algorithm achieves higher accuracy and efficiency compared to existing routing techniques and channel allocation algorithms like ACO and PSO. It exhibits a high packet delivery ratio, increased throughput, and reduced delay in channel selection, thus improving the overall performance of CRNs.The implications of this research are twofold. On a theoretical level, this study contributes to the field by extending the capabilities of the random forest algorithm and adapting it to the domain of CRNs. The modified algorithm demonstrates the potential of machine learning techniques in addressing allocation challenges in wireless communication systems. The findings emphasize the importance of advanced algorithms in improving the efficiency and effectiveness of channel and resource allocation processes. 2023, Success Culture Press. All rights reserved. -
Improved Photocatalytic Activity of g-C3N4/ZnO: A PotentialDirect Z-Scheme Nanocomposite
In this study, a Z-scheme g-C3N4/ZnO nanocomposite was synthesized using exfoliation process, which was further characterized using XRD, FT-IR, UV-DRS, SEM-EDAX, PL, EIS, and TGA techniques. The properties of g-C3N4 were enhanced when fabricated with ZnO resulting in a better electron mobility, high redox potential, and excellent semiconducting properties. The performance of this heterostructure was evaluated by photocatalytic degradation of malachite green (MG) under visible light irradiation. The g-C3N4/ZnO heterostructure achieved a degradation of 84.3 % within 60 min under visible light irradiation. The degradation reaction follows a pseudo first-order kinetic model with a reaction rate constant of 0.0329 min?1. The nanocomposite demonstrated outstanding stability and recyclability. 2020 Wiley-VCH GmbH -
Improved image denoising with the integrated model of Gaussian filter and neighshrink SURE
Image denoising, being an important preprocessing stage in image processing, minimizes the noise interfering with the information content of the image. The denoising problems are addressed by various techniques starting from the Fourier transforms to wavelets. Because of the localized time frequency features and advantages of multi resolution capabilities, the wavelets have been extensively used in the denoising process. The development of algorithms for the wavelet thresholding or shrinkage strategies along with different filters have resulted in the betterment of image quality after the denoising. Even though the image denoising algorithm based on a combination of Gaussian and Bilateral filters, shows good performance but lacks in consistency with respect to the noise levels and also the type of images used. This paper discusses the advantages of NeighShrink SURE rule in developing an effective thresholding strategy, thereby proposing a improved denoising method incorporating the NeighShrink SURE rule along with combination of Gaussian filter model. The methodology employs the use of subband thresholding derived from the NeighShrink SURE rule. The outcome of the proposed method exhibits a comparatively improved performance in Peak Signal to Ratio (PSNR) and Image Quality Index (IQI) values of the test images. BEIESP. -
Improved Henon Chaotic Map-based Progressive Block-based visual cryptography strategy for securing sensitive data in a cloud EHR system
The core objective of secret sharing concentrates on developing a novel technique that prevents the destruction and leakage of original data during the distribution and encoding processes. Progressive Visual Cryptography (VC) is considered for the potential over the traditional VC schemes since the former does not require and does not suffer from the limitations of requiring a minimum number of participants during the process of encryption and sharing. The chaotic map-based Progressive VC is superior in facilitating predominant secrecy under sharing and encryption. In this paper, an Improved Henon Chaotic Map-based Progressive Block-based VC (IHCMPBVC) scheme is proposed to prevent the leakage and destruction of sensitive information during an exchange and encryption. This proposed IHCMPBVC technique uses the merits of Henon and Lorentz maps for effective encryption since it introduces the option of deriving non-linear behavior that results in sequence generation that covers the complete range with proper distribution in order to minimize the degree of leaks in sharing. The simulation results of the proposed IHCMPBVC technique investigated using entropy, PSNR, and Mean Square Error were improved at an average rate of 27%, 23%, and 31%, predominant to the baseline VC approaches considered in the comparison. 2022 The Authors -
Improved File Security System Using Multiple Image Steganography
Steganography is the process of hiding a secret message within an ordinary message extracting it at its destination. Image steganography is one of the most common and secure forms of steganography available today. Traditional steganography techniques use a single cover image to embed the secret data which has few security shortcomings. Therefore, batch steganography has been adopted which stores data on multiple images. In this paper, a novel approach is proposed for slicing the secret data and storing it on multiple cover images. In addition, retrieval of this secret data from the cover images on the destination side has also been discussed. The data slicing ensures secure transmission of the vital data making it merely impossible for the intruder to decrypt the data without the encrypting details. 2019 IEEE. -
Improved Feature Selection Method for the Identification of Soil Images Using Oscillating Spider Monkey Optimization
Precision agriculture is the process that uses information and communication technology for farming and cultivation to improve overall productivity, efficient utilization of resources. Soil prediction is one of the primary phases in precision agriculture, resulting in good quality crops. In general, farmers perform the soil prediction manually. However, the efficiency of soil prediction may be enhanced by using current digital technologies. One effective way to automate soil prediction is image processing techniques in which soil images may be analyzed to determine the soil. This paper presents an efficient image analysis technique to predict the soil. For the same, a robust feature selection technique has been incorporated in the image analysis of soil images. The developed feature selection technique uses a new oscillating spider monkey optimization algorithm (OSMO) for the selection of features that are relevant and non-redundant. The new oscillating spider monkey optimization algorithm increases precision and convergence behavior by using an oscillating perturbation rate. A set of standard benchmark functions was deployed to visualize the performance of the new optimization technique (OSMO), and results were compared based on mean and standard deviation. Furthermore, the soil prediction approach is validated on a soil dataset, having seven categories. The proposed feature selection method selects the 41% relevant features, which provide the highest accuracy of 82.25% with 2.85% increase. 2013 IEEE. -
Improved dragonfly optimizer for intrusion detection using deep clustering CNN-PSO classifier
With the rapid growth of internet based services and the data generated on these services are attracted by the attackers to intrude the networking services and information. Based on the characteristics of these intruders, many researchers attempted to aim to detect the intrusion with the help of automating process. Since, the large volume of data is generated and transferred through network, the security and performance are remained an issue. IDS (Intrusion Detection System) was developed to detect and prevent the intruders and secure the network systems. The performance and loss are still an issue because of the features space grows while detecting the intruders. In this paper, deep clustering based CNN have been used to detect the intruders with the help of Meta heuristic algorithms for feature selection and preprocessing. The proposed system includes three phases such as preprocessing, feature selection and classification. In the first phase, KDD dataset is preprocessed by using Binning normalization and Eigen-PCA based discretization method. In second phase, feature selection is performed by using Information Gain based Dragonfly Optimizer (IGDFO). Finally, Deep clustering based Convolutional Neural Network (CCNN) classifier optimized with Particle Swarm Optimization (PSO) identifies intrusion attacks efficiently. The clustering loss and network loss can be reduced with the optimization algorithm. We evaluate the proposed IDS model with the NSL-KDD dataset in terms of evaluation metrics. The experimental results show that proposed system achieves better performance compared with the existing system in terms of accuracy, precision, recall, f-measure and false detection rate. 2022 Tech Science Press. All rights reserved. -
Improved diabetes disease prediction IWFO model using machine learning algorithms
Diabetic disease is the mostly affected and massive disease on a global level. Diagnosing the diabetic earlier will help the medicalist to give the improved and latest clinical treatment. The healthcare specialist unit uses many machine learning techniques, methodologies and tools for decision making in diabetic field. The machine learning techniques are utilized for the prediction of the diabetic diseases in the initial level. To eliminate such issues, optimized detection techniques are proposed. First of all, the training samples are increased using the sliding window protocol. Further, class imbalanced training data classes are balanced and resolved using the adaptive and gradient booster technique. Further, the diabetic feature selection process is improved by the Intensity Weighted Firefly Optimization firefly techniques (IWFO), in which irrelevant features are reduced based on the correlation between the features that deducts the unwanted features involved in the diabetic disease process. Then the feature transformation problem is faced by the PCA technique, which manages the several types of features. Finally, the improved and optimal hybrid random forest is applied into the normal and diabetes classes respectively. The proposed system predicts the diabetic disease efficiently and maximizes its precision of the prediction system. The present paper is compared with different classifiers to determine the efficiency of the work. Overall, the initiated system improved the present studies accuracy level. 2024 Author(s).