Search

IntroductionCotton, being a crucial cash crop globally, faces significant challenges due to multiple diseases that adversely affect its quality and yield. To identify such diseases is very important for the implementation of effective management strategies for sustainable agriculture. Image recognition plays an important role for the timely and accurate identification of diseases in cotton plants as it allows farmers to implement effective interventions and optimize resource allocation. Additionally, deep learning has begun as a powerful technique for to detect diseases in crops using images. Hence, the significance of this work lies in its potential to mitigate the impact of these diseases, which cause significant damage to the cotton and decrease fibre quality and promote sustainable agricultural practices.MethodsThis paper investigates the role of deep transfer learning techniques such as EfficientNet models, Xception, ResNet models, Inception, VGG, DenseNet, MobileNet, and InceptionResNet for cotton plant disease detection. A complete dataset of infected cotton plants having diseases like Bacterial Blight, Target Spot, Powdery Mildew, Aphids, and Army Worm along with the healthy ones is used. After pre-processing the images of the dataset, their region of interest is obtained by applying feature extraction techniques such as the generation of the biggest contour, identification of extreme points, cropping of relevant regions, and segmenting the objects using adaptive thresholding.Results and DiscussionDuring experimentation, it is found that the EfficientNetB3 model outperforms in accuracy, loss, as well as root mean square error by obtaining 99.96%, 0.149, and 0.386 respectively. However, other models also show the good performance in terms of precision, recall, and F1 score, with high scores close to 0.98 or 1.00, except for VGG19. The findings of the paper emphasize the prospective of deep transfer learning as a viable technique for cotton plant disease diagnosis by providing a cost-effective and efficient solution for crop disease monitoring and management. This strategy can also help to improve agricultural practices by ensuring sustainable cotton farming and increased crop output.

IntroductionThe rapid advancement of science and technology has significantly expanded the capabilities of artificial intelligence, enhancing diagnostic accuracy for gastric cancer.MethodsThis research aims to utilize endoscopic images to identify various gastric disorders using an advanced Convolutional Neural Network (CNN) model. The Kvasir dataset, comprising images of normal Z-line, normal pylorus, ulcerative colitis, stool, and polyps, was used. Images were pre-processed and graphically analyzed to understand pixel intensity patterns, followed by feature extraction using adaptive thresholding and contour analysis for morphological values. Five deep transfer learning models—NASNetMobile, EfficientNetB5, EfficientNetB6, InceptionV3, DenseNet169—and a hybrid model combining EfficientNetB6 and DenseNet169 were evaluated using various performance metrics.Results & discussionFor the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection.

Social networking platforms have become one of the most engaging portals on the Internet, enabling global users to express views, share news and campaigns, or simply exchange information. Yet there is an increasing number of fake and spam profiles spreading and disseminating fake information. There have been several conscious attempts to determine and distinguish genuine news from fake campaigns, which spread malicious disinformation among social network users. Manual verification of the huge volume of posts and news disseminated via social media is not feasible and humanly impossible. To overcome the issue, this research presents a framework to use sentiment analysis based on emotions to investigate news, posts, and opinions on social media. The proposed model computes the sentiment score of content-based entities to detect fake or spam and detect Bot accounts. The authors also present an investigation of fake news campaigns and their impact using a machine learning algorithm with highly accurate results as compared to other similar methods. The results presented an accuracy of 99.68 %, which is significantly higher as compared to other methodologies delivering lower accuracy.

On a daily basis, an abundance of opinions, thousands or even millions of comments are generated by various individuals on social media. Collecting and evaluating these comments using traditional methods and algorithms is accompanied by less accuracy. Therefore, the development of a robust sentiment analysis system is essential for the accurate analysis of users’ sentiments. Current methods have limited accuracy. Therefore, an idea to overcome this limitation is to get benefit of several classifiers together. Ensemble methods, through the combination of several different algorithms with diverse structures, can generate a new framework capable of better analyzing the sentiments. In the present study, an ensemble-based model is introduced to extract meaningful information from Persian comments on the Instagram social media platform. The model is proposed for the classification and prediction of users’ behaviors or emotions across distinct categories. This hybrid model comprises three main phases. The first phase is pre-processing and word embedding. Word2Vec is used for this manner. The second phase consists of four proposed deep models, namely CNN, LSTM, CNN-LSTM, and LSTM-CNN which are used as classifiers. Finally, in the third phase, ensemble techniques like MLP and Voting ensemble are employed to aggregate the results derived from the previous phase. To evaluate the performance of the proposed ensemble-based model, the model is applied to the Insta.csv dataset, containing Persian comments on Instagram. Experimental results demonstrate that the proposed ensemble-based model, utilizing the Voting ensemble, outperforms other ensemble methods. In terms of accuracy, it achieves 72.337%, therefore, the Voting ensemble shows a 4.9% improvement over the MLP ensemble.

The emergence of federated learning (FL) technique in fog-enabled healthcare system has leveraged enhanced privacy towards safeguarding sensitive patient information over heterogeneous computing platforms. In this paper, we introduce the FedHealthFog framework, which was meticulously developed to overcome the difficulties of distributed learning in resource-constrained IoT-enabled healthcare systems, particularly those sensitive to delays and energy efficiency. Conventional federated learning approaches face challenges stemming from substantial compute requirements and significant communication costs. This is primarily due to their reliance on a singular server for the aggregation of global data, which results in inefficient training models. We present a transformational approach to address these problems by elevating strategically placed fog nodes to the position of local aggregators within the federated learning architecture. A sophisticated greedy heuristic technique is used to optimize the choice of a fog node as the global aggregator in each communication cycle between edge devices and the cloud. The FedHealthFog system notably accounts for drop in communication latency of 87.01%, 26.90%, and 71.74%, and energy consumption of 57.98%, 34.36%, and 35.37% respectively, for three benchmark algorithms analyzed in this study. The effectiveness of FedHealthFog is strongly supported by outcomes of our experiments compared to cutting-edge alternatives while simultaneously reducing number of global aggregation cycles. These findings highlight FedHealthFog's potential to transform federated learning in resource-constrained IoT environments for delay-sensitive applications.

Abstract Colorectal cancer is the third most common type of cancer diagnosed annually, and the second leading cause of death due to cancer. Early diagnosis of this ailment is vital for preventing the tumours to spread and plan treatment to possibly eradicate the disease. However, population-wide screening is stunted by the requirement of medical professionals to analyse histological slides manually. Thus, an automated computer-aided detection (CAD) framework based on deep learning is proposed in this research that uses histological slide images for predictions. Ensemble learning is a popular strategy for fusing the salient properties of several models to make the final predictions. However, such frameworks are computationally costly since it requires the training of multiple base learners. Instead, in this study, we adopt a snapshot ensemble method, wherein, instead of the traditional method of fusing decision scores from the snapshots of a Convolutional Neural Network (CNN) model, we extract deep features from the penultimate layer of the CNN model. Since the deep features are extracted from the same CNN model but for different learning environments, there may be redundancy in the feature set. To alleviate this, the features are fed into Particle Swarm Optimization, a popular meta-heuristic, for dimensionality reduction of the feature space and better classification. Upon evaluation on a publicly available colorectal cancer histology dataset using a five-fold cross-validation scheme, the proposed method obtains a highest accuracy of 97.60% and F1-Score of 97.61%, outperforming existing state-of-the-art methods on the same dataset. Further, qualitative investigation of class activation maps provide visual explainability to medical practitioners, as well as justifies the use of the CAD framework in screening of colorectal histology. Our source codes are publicly accessible at: https://github.com/soumitri2001/SnapEnsemFS .

Ease of flexibility, convenience, and smartness have made the Internet of Things (IoT) the industry, and user favorite device has recently piqued the industry's interest. With the widespread use of this technology, an unprecedented number of IoT endpoints, including devices in our homes, are now connected to external networks. Firmware of this type is typically heterogeneous and closed source. At the firmware level, it is harder to detect and evaluate security vulnerabilities since their effects are faster and larger. In recent years, several similarity-based firmware security detection techniques and tools have become research hotspots. Security concerns and attacks have risen to the top of the list for IoT security equipment, particularly IoT cameras. Firmware has historically been one of the most neglected areas of device security, leaving it exposed to malicious actors. This research proposes a unique twelve-step process to perform firmware analysis and security assessment of Smart IoT-based Camera devices.

Music has been an integral part of the history of humankind with theories suggesting it is more antediluvian than speech itself. Music is an ordered succession of tones and harmonies that produce sounds characterized by melody and rhythm. Our paper proposes an ensemble deep learning musical instrument classification (MIC) framework, named as MIC_FuzzyNET model which aims to classify the dominant instruments present in musical clips. Firstly, the musical data is converted to three different spectrograms: Constant Q-Transform, Semitone Spectrogram, and Mel Spectrogram, which are then stacked to form 3 channel 2D data. This stacked spectrogram is fed to transfer learning models namely, EfficientNetV2 and ResNet18 which output the preliminary classification scores. A fuzzy rank ensemble model is finally employed that assigns the classifier ranks, on the testing data to achieve final enhanced classification scores which reduces error and biases for the constituent CNN architectures. Our proposed framework has been evaluated on the Persian Classical Music Instrument Recognition (PCMIR) dataset and Instrument Recognition in Musical Audio Signals (IRMAS) dataset. It has achieved considerably high accuracy, making our proposed framework a robust MIC model.

Wireless sensor networks (WSNs) have proven to be incredibly useful for forest applications that rely on sensing technologies for event detection and monitoring. This radical sensing technology has revolutionized data gathering, analysis, and application. Despite the many advantages of this technology, one key drawback is the rapid drain on sensor batteries caused by their intensive processing activities and communication processes. The effectiveness of sensor nodes is strongly influenced by two factors: the amount of energy they consume and the length of their coverage lifetimes. Using our proposed method, we can find fire zones in a forest, detect and monitor battlefield surveillance, combat monitoring and intruder detection, and then wirelessly send all the information to a central station. So, extending the life of WSNs is essential to ensure that Sensor Nodes (SN) will always be available. Our proposed EEWBP (energy-efficient weighted-based protocol) technique uses a composite weighted metric that includes system elements such as the node degree, residual energy, the number of neighbors’ nodes, average flying speed, and trust value, which are evaluated separately and then added together to help in cluster-building and node-scheduling processes. Our proposed protocol makes it easy to set up many clusters of SNs, each with their own cluster head (CH). This way, data can be sent between clusters in a way that uses the least amount of energy and makes coverage last longer. After putting our cluster-based routing strategy in place, we tested how it worked and evaluated it with different network parameters. The simulation results show that EEWBP consumes less energy and maintains a higher level of consistency in the CH than coverage preserving clustering protocol (CPCP), coverage clustering protocol (CACP), coverage aware unequal clustering algorithm (CUCA), and low-energy adaptive clustering hierarchy (LEACH). EEWBP also shows a better packet delivery rate and an improvement in first-node death.

The human body is designed to experience stress and react to it, and experiencing challenges causes our body to produce physical and mental responses and also helps our body to adjust to new situations. However, stress becomes a problem when it continues to remain without a period of relaxation or relief. When a person has long-term stress, continued activation of the stress response causes wear and tear on the body. Chronic stress results in cancer, cardiovascular disease, depression, and diabetes, and thus is deeply detrimental to our health. Previous researchers have performed a lot of work regarding mental stress, using mainly machine-learning-based approaches. However, most of the methods have used raw, unprocessed data, which cause more errors and thereby affect the overall model performance. Moreover, corrupt data values are very common, especially for wearable sensor datasets, which may also lead to poor performance in this regard. This paper introduces a deep-learning-based method for mental stress detection by encoding time series raw data into Gramian Angular Field images, which results in promising accuracy while detecting the stress levels of an individual. The experiment has been conducted on two standard benchmark datasets, namely WESAD (wearable stress and affect detection) and SWELL. During the studies, testing accuracies of 94.8% and 99.39% are achieved for the WESAD and SWELL datasets, respectively. For the WESAD dataset, chest data are taken for the experiment, including the data of sensor modalities such as three-axis acceleration (ACC), electrocardiogram (ECG), body temperature (TEMP), respiration (RESP), etc.

Many children with attention deficit hyperactivity disorder (ADHD) perform poorly in their academic studies. They also have difficulties in their social lives due to a lack of interpersonal skills and this often continues into adult life. Appropriate early therapies and medications can be very beneficial. In this paper, we introduce and demonstrate the benefits of a new type of treatment, namely, an eye-contact game which successfully exploits mixed reality technology. None of the patients in our experiment were older than ten years of age. They were able to pay attention and sustain interest in the treatment sessions over a span of six weeks. After participating in the treatment sessions with our game, the omission/commission errors which were evaluated in an attention test taken by the experimental group decreased significantly and appeared within the normal range. In addition to the improvement in error rates, the mean response time to an interactive metronome test significantly decreased. Importantly, our game allows patients to conduct this treatment by themselves at home without professional assistance. To the best of our knowledge, this study is one of the first studies to use a mixed reality head-mounted display to treat children with attention deficit hyperactivity disorder and to prove its potential as a treatment for clinically diagnosed children.

This paper presents an open innovation strategy by identifying the patent impact index and cooperation network through patent analysis for leading companies developing technology in the UAM field. Among companies developing UAM technology, patent analysis was conducted on the leading companies with active patent activities, technology classification was used to match companies by parts, and a technical capability index was utilized to identify the companies. When developing UAM technology in the future, this can help companies seek effective partners to improve competitiveness in technology development. To the best of our knowledge, the work done in this paper is unprecedented, as it suggests methods for patent analysis and verifies them by analyzing the UAM patents with the proposed method.

Wireless sensor networks (WSNs) have recently been viewed as the basic architecture that prepared the way for the Internet of Things (IoT) to arise. Nevertheless, when WSNs are linked with the IoT, a difficult issue arises due to excessive energy utilization in their nodes and short network longevity. As a result, energy constraints in sensor nodes, sensor data sharing and routing protocols are the fundamental topics in WSN. This research presents an enhanced smart-energy-efficient routing protocol (ESEERP) technique that extends the lifetime of the network and improves its connection to meet the aforementioned deficiencies. It selects the Cluster Head (CH) depending on an efficient optimization method derived from several purposes. It aids in the reduction of sleepy sensor nodes and decreases energy utilization. A Sail Fish Optimizer (SFO) is used to find an appropriate route to the sink node for data transfer following CH selection. Regarding energy utilization, bandwidth, packet delivery ratio and network longevity, the proposed methodology is mathematically studied, and the results have been compared to identical current approaches such as a Genetic algorithm (GA), Ant Lion optimization (ALO) and Particle Swarm Optimization (PSO). The simulation shows that in the proposed approach for the longevity of the network, there are 3500 rounds; energy utilization achieves a maximum of 0.5 Joules; bandwidth transmits the data at the rate of 0.52 MBPS; the packet delivery ratio (PDR) is at the rate of 96% for 500 nodes, respectively.

Movies are one of the integral components of our everyday entertainment. In today’s world, people prefer to watch movies on their personal devices. Many movies are available on all popular Over the Top (OTT) platforms. Multiple new movies are released onto these platforms every day. The recommendation system is beneficial for guiding the user to a choice from among the overloaded contents. Most of the research on these recommendation systems has been conducted based on existing movies. We need a recommendation system for forthcoming movies in order to help viewers make a personalized decision regarding which upcoming new movies to watch. In this article, we have proposed a framework combining sentiment analysis and a hybrid recommendation system for recommending movies that are not yet released, but the trailer has been released. In the first module, we extracted comments about the movie trailer from the official YouTube channel for Netflix, computed the overall sentiment, and predicted the rating of the upcoming movies. Next, in the second module, our proposed hybrid recommendation system produced a list of preferred upcoming movies for individual users. In the third module, we finally were able to offer recommendations regarding potentially popular forthcoming movies to the user, according to their personal preferences. This method fuses the predicted rating and preferred list of upcoming movies from modules one and two. This study used publicly available data from The Movie Database (TMDb). We also created a dataset of new movies by randomly selecting a list of one hundred movies released between 2020 and 2021 on Netflix. Our experimental results established that the predicted rating of unreleased movies had the lowest error. Additionally, we showed that the proposed hybrid recommendation system recommends movies according to the user’s preferences and potentially promising forthcoming movies.

Introduction: The rapid advancement of science and technology has significantly expanded the capabilities of artificial intelligence, enhancing diagnostic accuracy for gastric cancer. Methods: This research aims to utilize endoscopic images to identify various gastric disorders using an advanced Convolutional Neural Network (CNN) model. The Kvasir dataset, comprising images of normal Z-line, normal pylorus, ulcerative colitis, stool, and polyps, was used. Images were pre-processed and graphically analyzed to understand pixel intensity patterns, followed by feature extraction using adaptive thresholding and contour analysis for morphological values. Five deep transfer learning models—NASNetMobile, EfficientNetB5, EfficientNetB6, InceptionV3, DenseNet169—and a hybrid model combining EfficientNetB6 and DenseNet169 were evaluated using various performance metrics. Results & discussion: For the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection. [ABSTRACT FROM AUTHOR]

The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human handwriting. The majority of currently available methods use either a generative adversarial network (GAN) or a recurrent neural network (RNN) to generate new handwriting styles. This is why these techniques frequently fall short of producing diverse and realistic text pictures, particularly for terms that are not commonly used. To resolve that, this research proposes a novel deep learning model that consists of a style encoder and a text generator to synthesize different handwriting styles. This network excels in generating conditional text by extracting style vectors from a series of style images. The model performs admirably on a range of handwriting synthesis tasks, including the production of text that is out-of-vocabulary. It works more effectively than previous approaches by displaying lower values on key Generative Adversarial Network evaluation metrics, such Geometric Score (GS) (3.21 x 10-5) and Fréchet Inception Distance (FID) (8.75), as well as text recognition metrics, like Character Error Rate (CER) and Word Error Rate (WER). A thorough component analysis revealed the steady improvement in image production quality, highlighting the importance of specific handwriting styles. Applicable fields include digital forensics, creative writing, and document security. [ABSTRACT FROM AUTHOR]

A new era of data access and management has begun with the use of cloud computing in the healthcare industry. Despite the efficiency and scalability that the cloud provides, the security of private patient data is still a major concern. Encryption, network security, and adherence to data protection laws are key to ensuring the confidentiality and integrity of healthcare data in the cloud. The computational overhead of encryption technologies could lead to delays in data access and processing rates. To address these challenges, we introduced the Enhanced Parallel Multi-Key Encryption Algorithm (EPM-KEA), aiming to bolster healthcare data security and facilitate the secure storage of critical patient records in the cloud. The data was gathered from two categories Authorization for Hospital Admission (AIH) and Authorization for High Complexity Operations.We use Z-score normalization for preprocessing. The primary goal of implementing encryption techniques is to secure and store massive amounts of data on the cloud. It is feasible that cloud storage alternatives for protecting healthcare data will become more widely available if security issues can be successfully fixed. As a result of our analysis using specific parameters including Execution time (42%), Encryption time (45%), Decryption time (40%), Security level (97%), and Energy consumption (53%), the system demonstrated favorable performance when compared to the traditional method. This suggests that by addressing these security concerns, there is the potential for broader accessibility to cloud storage solutions for safeguarding healthcare data. [ABSTRACT FROM AUTHOR]

Demand Responsive Transit (DRT) responds to the dynamic users' requestswithout any fixed routes and timetables and determines the stop and the start according to the demands. This study explores the optimization of dynamic vehicle scheduling and real-time route planning in urban public transportation systems, with a focus on bus services. It addresses the limitations of current shared mobility routing algorithms, which are primarily designed for simpler, single origin/destination scenarios, and do not meet the complex demands of bus transit systems. The research introduces an route planning algorithm designed to dynamically accommodate passenger travel needs and enable real-time route modifications. Unlike traditional methods, this algorithm leverages a queue-based, multi-objective heuristic A* approach, offering a solution to the inflexibility and limited coverage of suburban bus routes. Also, this study conducts a comparative analysis of the proposed algorithm with solutions based on Genetic Algorithm (GA) and Ant Colony Optimization Algorithm (ACO), focusing on calculation time, route length, passenger waiting time, boarding time, and detour rate. The findings demonstrate that the proposed algorithmsignificantly enhances route planning speed, achieving an 80-100-fold increase in efficiency over existing models, thereby supporting the real-time demands of Demand-Responsive Transportation (DRT) systems. The study concludes that this algorithm not only optimizes route planning in bus transit but also presents a scalable solution for improving urban mobility. [ABSTRACT FROM AUTHOR]

Interaction with virtual objects is crucial for presence in Virtual Reality (VR) and Augmented Reality (AR) applications. However, controllers are still predominantly used for operations in virtual spaces. Hand gestures offer a more intuitive approach than keyboards and mice for interactions in these environments. In previous research, hand motion classification was implemented using only simple heuristics. This study introduces a User Interface (UI) employing MediaPipe and artificial intelligence to utilize hand gestures as an input device. Unlike the previous research, which could only identify one gesture, the current implementation successfully classifies three gestures with 95.4% accuracy: pointer, pick, and fist. Efforts were made to optimize the process, including the examination of multi-threading and PyWin32. While multi-threading did not yield significant improvements, the use of PyWin32 resulted in approximately three times higher Frames Per Second (FPS) compared to the absence of PyWin32. Further gestures can potentially be added to enhance the system's capabilities. This line of research has potential applications in diverse fields such as gaming, simulation, rehabilitation, and smart home technology. [ABSTRACT FROM AUTHOR]

As the demand for high-quality rendering for mixed reality, videogame, and simulation has increased, global illumination has been actively researched. Monte Carlo path tracing can realize global illumination and produce photorealistic scenes that include critical effects such as color bleeding, caustics, multiple light, and shadows. If the sampling rate is insufficient, however, the rendered results have a large amount of noise. The most successful approach to eliminating or reducing Monte Carlo noise uses a feature-based filter. It exploits the scene characteristics such as a position within a world coordinate and a shading normal. In general, the techniques are based on the denoised pixel or sample and are computationally expensive. However, the main challenge for all of them is to find the appropriate weights for every feature while preserving the details of the scene. In this paper, we compare the recent algorithms for removing Monte Carlo noise in terms of their performance and quality. We also describe their advantages and disadvantages. As far as we know, this study is the first in the world to compare the artificial intelligence-based denoising methods for Monte Carlo rendering. [ABSTRACT FROM AUTHOR]