Explore the vast range of titles available.

One of the most critical aspects of quality assurance is inspecting products for defects before they are sold or shipped. A good product is more vital than having more of the same item for a customer’s enjoyment. The client has a significant role in determining the quality of a product. Another way to think about quality is as the total of all the characteristics that contribute to the creation of items that the client enjoys. Recently, the application of machine vision and image processing technology to improve the surface quality of fruits and other foods has increased significantly. This is primarily because these technologies make significant advancements in areas where the human eye falls short. This means that, by utilizing computer vision and image processing techniques, time-consuming and subjective industrial quality control processes can be eliminated. This article discusses how to check and assess food using picture segmentation and machine learning. It is capable of classifying fruits and determining whether a piece of fruit is rotten. To begin, Gaussian elimination is used to remove noise from images. Then, photos are subjected to histogram equalization in order to improve their quality. Segmentation of the image is carried out using the K-means clustering technique. Then, fruit photos are classified using machine learning methods such as KNN, SVM, and C4.5. These algorithms determine if a fruit is damaged or not.

The advent of IoT devices increased internet usage more than smartphones and personal computers. The manual analysis of the Web Service Description Language (WSDL) document is quite expensive and time-consuming, hence this paper proposes a novel deep learning architecture to overcome the issue associated with web service classification. A structural self-organized deep belief network (SSODBN) is used for real-time web service classification in different fields such as Education, Smart electricity, Intelligent road networks, Health and social care, and Sports, water, and gas distribution. The SSODBN architecture utilizes a dropout strategy to minimize the interrelationship between the feature detectors and a regularized reinforced transfer function to eliminate the irrelevant weights. The main advantage offered by the S-DBN architecture is the improved preprocessing with feature selection. The Starling Murmuration Optimizer (SMO) is utilized in this paper to minimize the reconstruction error of the S-DBN architecture. The security of the smart city architecture is mainly improved via the blockchain defined network (BDN) using user-authenticated blocks. The experimental results revealed that the proposed method managed the scalability, latency, and centralization issues with superior data transmission.

Primary User Emulation Attack (PUEA) is the most serious concern in Cognitive Radio (CR). The PUEA are malevolent users attempt to imitate primary signals and confuse CR users to prevent them from accessing vacant frequency bands. The proposed technique detects energy and assigns an appropriate threshold value for identifying attackers in the network using unique Smart Threshold detection (STD). The free space propagation model and two ray ground models are considered for finding the attacks. The authentication confirmation process (ACP) is carried out for detecting multiple PUEAs; ACP uses DNA sequencing using Binary to Excess One (BEO). The objective of this paper is to identify the PUEAs from the network and not providing the vacant frequency bands to the PUEAs and the frequent bands should be used by the primary and the secondary user efficiently. Here the secondary user will find out whether the PUEA or primary user is accessing the vacant bands using the STD-ACP technique. The simulation process is executed in the MATLAB platform. The Proposed STD-ACP finds out the attack strength, probability of detection, probability of error, probability of false alarms, and identifies the number of PUEAs. By simulating the performance of the primary user will be increased while the PUEAs can be detached from the network. The proposed STD-ACP approach is compared with attack-aware threshold selection (AATS), optimal voting rule, and K-out-of-N rule methods respectively.

Introduction: The identification and monitoring of benign moles and skin cancers leads to a challenging task because of the usual standard significant skin patches. Actually, the skin lesions vary very little in their look and only limited amount of information is available. There are seven fundamental types of skin cancer like Basal Cell Carcinoma (BCC), Melanoma and Squamous Cell Carcinoma (SCC) whereas Melanoma is the highly risky which has low survival rate. Objective: This work classifies skin lesions with the help of Convolution Neural Network and the images are trained end-to-end. A dataset comprised of 10000 clinical images were trained using Convolution Neural Network (CNN). Materials and Methods: The skin cancer identification process is generally separated into two basic components, image pre-processing which includes classification of images and removing the duplicate images and sharpening, which resizes the skin image. This work discusses a methodology to segment the high-level skin lesion and identification of malignancy more accurately with the help of deep learning: 1) Construction of a neural network, which detects the edge of a huge lesion accurately; 2) Designing model that can run on mobile phones. The model designed a transfer learning which is based deep on neural network and the fine turning that supports to attain high prediction accuracy. Results: The dataset comprises of a total of 10,000 images stored in two folders. The information about the data is stored in a data frame. Total 10000 dermoscopic images contains 374 melanoma images, 254 seborrheic keratosis images and 1372 nevus images. Using transfer learning validation loss, Top-2 accuracy and Top-3 accuracy have been calculated. The result has been compared with the different models. Conclusions: The proposed system can categorize healthy skin lesions, eczema, acne, malignant and benign skin lesions. The proposed work investigates the attributes acquired by the deep convolutional neural network. The attributes are extracted and the datasets were divided into seven different categories. Based on that categories the data was trained and validated. Based on the calculation the validation loss, top-2 accuracy, top-3 accuracy was calculated.

Due to the Covid-19 pandemic which started in the year 2020, many nations had imposed lockdown to curb the spread of this virus. People have been sharing their experiences and perspectives on social media on the lockdown situation. This has given rise to increased number of tweets or posts on social media. Multi-class text classification, a method of classifying a text into one of the pre-defined categories, is one of the effective ways to analyze such data that is implemented in this paper. A Covid-19 dataset is used in this work consisting of fifteen pre-defined categories. This paper presents a multi-layered hybrid model, LSTM followed by GRU, to integrate the benefits of both the techniques. The advantages of word embeddings techniques like GloVe and BERT have been implemented and found that, for three epochs, the transfer learning based pre-trained BERT-hybrid model performs one percent better than GloVe-hybrid model but the state-of-the-art, fine-tuned BERT-base model outperforms the BERT-hybrid model by three percent, in terms of validation loss. It is expected that, over a larger number of epochs, the hybrid model might outperform the fine-tuned model.

The rapid expansion of hybrid renewable energy microgrid systems presents new challenges in maintaining system reliability and performance. This paper explores the application of machine learning algorithms for predictive maintenance in such systems, focusing on the early detection of potential failures to optimize operational efficiency and reduce downtime. By integrating real-time data from solar, wind, and storage components, the proposed models predict the remaining useful life (RUL) of critical components. The results demonstrate significant improvements in predictive accuracy, offering a robust solution for enhancing the reliability and longevity of renewable energy microgrids.

Diseases are causing high rates of mortality in the modern world, chronic kidney disease (CKD) is one of the major causes of mortality, and it has a long-term disability. The predisposing factors for CKD include diabetes mellitus, hypertension, cardiovascular diseases, smoking, obesity, family history of kidney disease and congenital kidney problems. CKD is associated with many complications such as, proteinuria, anaemia of CKD, CKDmineral and bone disorder, dyslipidemia and electrolytes imbalance. Renal replacement therapy (dialysis and kidney transplantation) is the treatment of choice for CKD. Data mining is an accurate technique helps to predict the disease using various methods includes logistic regression, naive bayes classification, k-nearest neighbours, and support vector machine. Apart from these previous techniques, it was necessary to use a classification method for data segmentation according to their diagnosis and regression method for finding risk factors. In this present study, data are classified using proposed Identification of Pattern Mining, Decision Tree methods and regression techniques are used to obtain the best levels and this can be taken as metrics that the proposed methods can help in diagnosing a patient with CKD.

One of the most difficult challenges of multimedia transmission during the last two decades has been the retrieval of degraded or missing regions of images and videos while maintaining satisfactory perceptual accuracy. The objective is to retrieve lost data by using the similarity between frames. Usually, error concealment (EC) schemes depend on replacing incorrect data with data that are identical to the initial. This is possible because video contains a high degree of self-similarity. This research focuses on applying an EC approach in transform-domain video sequences. To conduct EC on films, they must first be translated to frames and then transformed using one of the available transformations into frequency-domain images. Using successive frames, it is possible to recover lost or incorrect data from images. Intra-coded frames (I-frames) may be used to recreate lost knowledge in predictive (P-frames) and bidirectional predictive frames (B-frames). I-frame knowledge that has been lost may be restored using previous intra-coded frames. The use of wavelet error concealment generated more precise results than the other techniques. In this study, it was discovered that covering faults in the density sector with wavelets produces more reliable results than the other techniques.

The smart home automation system is designed to conveniently manage and monitor household appliances and lighting fixtures remotely, to save time and to use resources effectively. It is a control system for allowing access to home automation devices. The automation devices include lights, fan, camera and doors. It even enhances the main features of the project to control the home appliances from anywhere as remotely. With the camera module, continuous surveillance and protection of the home is accomplished. A significant improvement is achieved in utility costs by an optimal use of energy. Using inexpensive electronic and interactive tools, this initiative can be applied, making it economically, physically and operationally feasible. Basically it involves controlling everything remotely via a visual interface and mobile application. The automation system employs the use of MQTT protocol in order to secure the transmitted device based information to and from in the network. The defense against Man in the Middle attack (MITM) is the main focus of our automation system. The routed messages are checked at the intermediate hub to check for the occurrence of MITM based DoS attacks through manual reset points. .

Cloud computing is an innovative technology which provides services to users on-demand and pay per use. Since there are many providers in cloud, users get confused in selecting the optimal service provider for their tasks. To overcome this limitation, federated cloud management architecture was proposed. The proposed work provides a new federated cloud mechanism, in which Broker Manager takes the responsibility of providing optimal and ranked service provider for user requirements. To rank the service providers in the federated cloud, Differentiated Priority based Ranking algorithm is implemented at the level of BM. Attributes are differentiated based on their weights assigned by a user. Service providers are discovered and ranked based on the differentiated attributes. The proposed algorithm chooses the cloud service provider for execution, not only based on the rank list generated by the BM; but also based on the suggestion given by the user. The experimental result shows that the proposed algorithm improves the performance of resource provisioning than the existing model by 13%.