Journal of Autonomous Intelligence最新文献

{"title":"Semantic pixel encoding visual secret sharing technique for balancing quality and security in color images","authors":"Kanchan Patil, Jyotsna Barpute, Mrudul Arkadi, S. Bhirud, C. A, J. A., S. G., Shibani Raju S","doi":"10.32629/jai.v7i3.1159","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1159","url":null,"abstract":"Color images are widely utilized across various domains, encompassing digital media and extending to critical applications in satellite and military arenas. As the significance of these images has grown, the need to protect their content from unauthorized access and potential threats has been underscored. Visual Secret Sharing (VSS) schemes have been proposed as effective mechanisms, with images being encrypted into multiple shares that, individually, offer no discernible information about the original content. Nevertheless, issues such as pixel expansion have been noted in traditional VSS methods, which result in increased complexity and a potential compromise in image quality. Maintaining impeccable image quality is emphasized, mainly since critical application decisions are often based on the clarity and accuracy of image details. The Semantic Pixel Encoding Visual Secret Sharing (SPEVSS) technique is proposed to address these identified challenges. A robust mechanism has been formulated through the integration of semantic pixel encoding with VSS, effectively countering pixel expansion while preserving the fidelity of the original image. As a result of this research, computational complexity has been significantly reduced, decryption methodologies have been made more efficient, and a more robust security framework for colour images has been established. The performance of the proposed SPEVSS shows the reconstructed images show the PSNR of 42 dB has been recorded in images processed, underscoring the method’s capability to balance security and optimal image quality.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"39 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139385034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of cell line Halm machine data in solar panel production factories using artificial intelligence models","authors":"İrfan Yilmaz, Demiral Akbar, Murat Şimşek","doi":"10.32629/jai.v7i3.1140","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1140","url":null,"abstract":"A solar energy module consists of solar cells that convert sunlight into electrical energy. The quality of these cells is the most important determinant of panel performance and lifespan. High-quality cells increase energy efficiency and extend panel life. Solar cells are typically composed of crystalline silicon, thin layers, and organic materials. Each material has its own advantages and disadvantages. However, what all cells have in common is that they produce electrical energy when exposed to solar radiation. Solar cells can be classified and ranked. This classification indicates the efficiency and performance of the cell. Solar energy modules are widely used to meet the energy needs of many homes and businesses. Accurately measuring cell performance can improve the overall efficiency of the panel. Therefore, AI (artificial intelligence) modeling offers many advantages in optimizing cell performance. The study yielded several benefits associated with modeling solar panel cells with artificial intelligence. Some of the benefits derived from this research are: Improved efficiency, Error detection and correction, Reduced maintenance costs, predictability, Increased production. These advantages demonstrate that AI modeling can help optimize solar panel cell performance.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"68 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139385466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep ResNet 18 and enhanced firefly optimization algorithm for on-road vehicle driver drowsiness detection","authors":"S. Nandyal, Sharanabasappa Sharanabasappa","doi":"10.32629/jai.v7i3.975","DOIUrl":"https://doi.org/10.32629/jai.v7i3.975","url":null,"abstract":"The driver drowsiness detection (DDD) technology is based on vehicle safety, and this system prevents many accidents and deaths that occur due to driver drowsiness. As a result, it is monitored and detected when vehicle drivers become drowsy. The DDD method, which is aided by AlexNet and deep learning models, has limitations such as vanishing gradients and overfitting issues as the depth of the model increases. The enhanced firefly optimisation algorithm has solved the problem of lower optimisation exploration. The National Tsing Hua University Driver Drowsiness Detection (NTHU-DDD) dataset’s input image contains individual groups of female and male drivers of various vehicles. The Min-max normalisation method is a general method for normalising data. The convolutional neural network (CNN) is used to extract features from input images and images classified by the neural network. ResNet 18 refers to the deepest of the convolutional neural network’s 18 layers. A network of pre-trained models can be used to classify the model classified by the 1000 image objects. The state-of-the-art Hierarchical Deep Drowsiness Detection (HDDD) model with Support Vector Machine (SVM) assistance has an effective high dimensional space. The CNN-EFF-ResNet 18 models have a high accuracy of 91.3%, while the HDDD method has a higher accuracy of 87.19% than the ensemble and Pyramid Multi-level Deep Belief (PMLDB) methods in DDD.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139388468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An investigation and analysis on automatic speech recognition systems","authors":"R. V. Siva Balan, K. Vignesh, Teena Jose, P. Kalpana, Jothikumar R.","doi":"10.32629/jai.v7i3.1060","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1060","url":null,"abstract":"A crucial part of a Speech Recognition System (SRS) is working on its most fundamental modules with the latest technology. While the fundamentals provide basic insights into the system, the recent technologies used on it would provide more ways of exploring and exploiting the fundamentals to upgrade the system itself. These upgrades end up in finding more specific ways to enhance the scope of SRS. Algorithms like the Hidden Markov Model (HMM), Artificial Neural Network (ANN), the hybrid versions of HMM and ANN, Recurrent Neural Networks (RNN), and many similar are used in accomplishing high performance in SRS systems. Considering the domain of application of SRS, the algorithm selection criteria play a critical role in enhancing the performance of SRS. The algorithm chosen for SRS should finally work in hand with the language model conformed to the natural language constraints. Each language model follows a variety of methods according to the application domain. Hybrid constraints are considered in the case of geography-specific dialects.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"138 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139387487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Student sports data analysis and physical fitness evaluation based on convolutional neural networks","authors":"Hesong Zhao, Chuan Shu","doi":"10.32629/jai.v7i3.1439","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1439","url":null,"abstract":"In order to achieve the analysis of student sports data and physical fitness evaluation, the author proposes a method based on convolutional neural networks. A hybrid algorithm combining genetic algorithm and error backpropagation algorithm (BP) is used to train convolutional neural networks. The algorithm first uses genetic algorithm for global training, and then uses BP algorithm for local precise training. This overcomes the drawbacks of traditional BP networks such as long training time and frequent local atmospheric drift, and improves global circulation performance. A neural network model was established to display the relationship between the total physical activity score and multiple test scores of high school students by utilizing electrical networks to demonstrate the connectivity of the neural network. This model aims to evaluate the athletic performance of college students and compare the results with other experimental models. The results indicate that the neural network-based model for evaluating college student physical activity can reflect the differences in physical activity and scores among all students, making it a suitable standard for evaluating high school student physical activity. The fitting accuracy of deterministic neural network models is higher than that of multiple linear regression models, which means that neural network models better reflect the performance of the network. The accuracy of various indicators of student physical fitness and total score makes the model easy to operate, accurate to predict, and effective analysis is scientifically reasonable.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"116 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139390830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CETR: CenterNet-Vision transformer model for wheat head detection","authors":"K. G. Suma, Gurram Sunitha, Ramesh Karnati, E. R. Aruna, Kachi Anvesh, Navnath Kale, P. Krishna Kishore","doi":"10.32629/jai.v7i3.1189","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1189","url":null,"abstract":"Wheat head detection is a critical task in precision agriculture for estimating crop yield and optimizing agricultural practices. Conventional object detection architectures often struggle with detecting densely packed and overlapping wheat heads in complex agricultural field images. To address this challenge, a novel CEnternet-vision TRansformer model for Wheat Head Detection (CETR) is proposed. CETR model combines the strengths of two cutting-edge technologies—CenterNet and Vision Transformer. A dataset of agricultural farm images labeled with precise wheat head annotations is used to train and evaluate the CETR model. Comprehensive experiments were conducted to compare CETR’s performance against convolutional neural network model commonly used in agricultural applications. The higher mAP value of 0.8318 for CETR compared against AlexNet, VGG19, ResNet152 and MobileNet indicates that the CETR model is more effective in detecting wheat heads in agricultural images. It achieves a higher precision in predicting bounding boxes that align well with the ground truth, resulting in more accurate and reliable wheat head detection. The higher performance of CETR can be attributed to the combination of CenterNet and ViT as a two-stage architecture taking advantage of both methods. Moreover, the transformer-based architecture of CETR enables better generalization across different agricultural environments, making it a suitable solution for automated agricultural applications.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"109 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139391282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph attention network and radial basis function neural network-based hybrid framework for epileptic seizure detection from EEG signal","authors":"Ferdaus Anam Jibon, Alif Tasbir, M. H. Miraz, Hwang Ha Jin, Fazlul Hasan Siddiqui, Md. Sakib, Nazibul Hasan Nishar, Himon Thakur, Mayeen Uddin Khandaker","doi":"10.32629/jai.v7i3.1149","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1149","url":null,"abstract":"Epileptic seizure is a neurological disorder characterized by recurrent, abrupt behavioral changes attributed to transient shifts in excessive electrical discharges within specific brain cell groups. Electroencephalogram (EEG) signals are the primary modality for capturing seizure activity, offering real-time, computer-assisted detection through long-term monitoring. Over the last decade, extensive experiments through deep learning techniques on EEG signal analysis, and automatic seizure detection. Nevertheless, realizing the full potential of deep neural networks in seizure detection remains a challenge, primarily due to limitations in model architecture design and their capacity to handle time series brain data. The fundamental drawback of current deep learning methods is their struggle to effectively represent physiological EEG recordings; as it is irregular and unstructured in nature, which is difficult to fit into matrix format in traditional methods. Because of this constraint, a significant research gap remains in this research field.  In this context, we propose a novel approach to bridge this gap, leveraging the inherent relationships within EEG data. Graph neural networks (GNNs) offer a potential solution, capitalizing on their ability to naturally encapsulate relational data between variables. By representing interacting nodes as entities connected by edges with weights determined by either temporal associations or anatomical connections, GNNs have garnered substantial attention for their potential in configuring brain anatomical systems. In this paper, we introduce a hybrid framework for epileptic seizure detection, combining the Graph Attention Network (GAT) with the Radial Basis Function Neural Network (RBFN) to address the limitations of existing approaches. Unlike traditional graph-based networks, GAT automatically assigns weights to neighbouring nodes, capturing the significance of connections between nodes within the graph. The RBFN supports this by employing linear optimization techniques to provide a globally optimal solution for adjustable weights, optimizing the model in terms of the minimum mean square error (MSE). Power spectral density is used in the proposed method to analyze and extract features from electroencephalogram (EEG) signals because it is naturally simple to analyze, synthesize, and fit into the graph attention network (GAT), which aids in RBFN optimization. The proposed hybrid framework outperforms the state-of-the-art in seizure detection tasks, obtaining an accuracy of 98.74%, F1-score of 96.2%, and Area Under Curve (AUC) of 97.3% in a comprehensive experiment on the publicly available CHB-MIT EEG dataset.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":" 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139144246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LW-CNN-based extraction with optimized encoder-decoder model for detection of diabetic retinopathy","authors":"B. Gunapriya, T. Rajesh, Arunadevi Thirumalraj, Manjunatha B","doi":"10.32629/jai.v7i3.1095","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1095","url":null,"abstract":"In the field of computer vision, automatic diabetic retinopathy (D.R.) screening is a well-established topic of study. It’s tough since the retinal vessels are hardly distinguishable from the backdrop in the fundus picture, and the structure is complicated. To learn data representations at numerous levels of abstraction, deep learning (DL) allows for the development of computational representations with several processing layers. Small, inconspicuous lesions generated by the disorder are hard to detect since they are tucked away beneath the eye’s structure. In this research, a lightweight convolutional neural network (LW-CNN) was used to extract structures from images of blood vessels, and different preprocessing methods were employed. The features are extracted, and then D.R. is classified using the suggested learning technique, which includes an encoder, dense branch. Effective categorization relies on the usage of multi-scale information collected from various nodes in the network. Grasshopper’s optimisation algorithm (GHOA) is used to fine-tune the recommended classifier’s hyper-parameters. The DIARETDB1 benchmark dataset is assessed using 80% training data and 20% testing data to get a diagnosis of the disease’s severity. The proposed model improved D.R. image classification with accuracy of 0.992 for DIARETDB1 database and 0.981 for APTOS 2019 blindness detection dataset. The state-of-the-art models for D.R. dataset images only achieved less accuracy and precision as compared with the proposed model.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"9 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139145339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep convolutional neural network architecture for breast mass classification using mammogram images","authors":"S. G, V. K, G. R.","doi":"10.32629/jai.v7i3.1288","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1288","url":null,"abstract":"Breast cancer is one of the second most common cancer occurring worldwide. Early identification of the disease is a major interest that promises to propose several diagnostic procedures to prevent further surgical interventions. This research paper aims to develop a breast mass classifier system using deep learning to differentiate breast mass images from normal mammographic images. The benchmark mammographic datasets CBIS-DDSM, INbreast, and mini-MIAS are used for constructing the proposed model DELU-BM-CNN. The region of interest is identified by applying image processing techniques (median filter, binarization and dilation) and the images are enhanced and sharpened using adaptive histogram equalization and unsharp masking techniques. The pre-processed images are trained with a minimum of five deep convolutional layers activated by an Exponential Linear Unit (ELU) which is developed from scratch for feature learning and classifying the given whole mammographic images. Dropout, Data normalization, and Global average pooling are some of the regularization techniques adopted to prevent the model from over-fitting. The proposed models are able to classify CBIS-DDSM images with an accuracy of 96.60%, INbreast images with 96.20% and MIAS images with 97.40%. The experimental results are also compared with conventional Rectified Linear Unit (ReLU) and Leaky ReLU activation function that promises the proposed model as a good prognosticator than the state-of-art models for cancer diagnosis using mammogram images as input.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":"226 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139145562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance improvement of DC servo motor using sliding mode controller","authors":"Mahendra K. Dawane, G. Malwatkar, Suhas P. Deshmukh","doi":"10.32629/jai.v7i3.1162","DOIUrl":"https://doi.org/10.32629/jai.v7i3.1162","url":null,"abstract":"Sliding mode control has emerged as a valuable technique for enhancing dynamic response in various fields, including load frequency regulation and remote vehicle applications. While the widely adopted PID controller has proven effective for optimizing control tasks in industries, sliding mode control offers distinct advantages. By controlling the slope of the dynamical trends of state variable behavior, it enables rapid dynamic response with minimal or no overshoot, as well as negligible steady-state error. The robustness of sliding mode control, which makes it highly resilient to changes in plant parameters and outside disturbances, is one of its main advantages. A digital computer simulation was run using Simulink in the MATLAB software, concentrating on a position control system using an armature voltage-controlled D.C. servo motor to assess how well it performed. To learn more about the operation of sliding mode control, several control laws were used and state trajectories were examined. When compared to the conventional tuned PID control, the findings and discussion conclusively show sliding mode control to be more successful. The sliding mode technique has exceptional effectiveness, including enhanced dynamic response, less overshoot, and almost no steady-state error. Furthermore, its robust nature ensures consistent operation even in the face of parameter fluctuations and external disturbances. This study underscores the immense potential of sliding mode control as a powerful alternative to conventional control methods. Its ability to enhance system performance, coupled with its inherent robustness, makes it a compelling choice for various industrial applications where precise control and resilient operation are crucial.","PeriodicalId":307060,"journal":{"name":"Journal of Autonomous Intelligence","volume":" 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139142094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}