Search

Image classification plays a vital role in classifying different objects without the human supervision. In manual system of image classification is more time consuming process and it is not suitable for future automated systems. The lack of a completely automated, low-cost system for real-time picture categorization highlights the continued difficulty of the subject. In this work, we offer Multiple Fruit Maturity Stage Classification, a method for automatically categorizing the ripeness of various fruits using computer vision and deep learning techniques. Convolution neural network (CNN) is used to extract the appropriate features for accurate classification. When opposed to its forerunners, Convolution neural network's (CNN) key benefit is that it can discover crucial elements automatically, without human intervention. The system shows better accuracy for both test and validation. [ABSTRACT FROM AUTHOR]

Deep learning and machine learning are essential since most companies require smart analytics to stay competitive. Artificial intelligence gave rise to machine learning, which in turn gave rise to deep learning. Machine Learning still dominates business analytics with its algorithms, despite the high-end uses of Deep Learning in areas like Computer Vision and Natural Language Processing. By summarizing the numerous machine learning models that are currently available on the market, this survey article demonstrates the learning transition from machine learning to deep learning. It also provides insight into deep learning models and methodologies, as well as the challenges faced and the expected future course of deep learning. A potent, cutting-edge method for analyzing photos, especially remote sensing (RS) images, is deep learning (DL). Remote sensing image scene classification, which attempts to assign semantic categories to remote sensing images based on their contents, has a variety of applications. Thanks to the powerful feature learning capabilities of DNNs, deep learning-based remote sensing image scene categorization has generated a lot of interest and made significant progress. A range of remote sensing applications, such as estimating water availability, monitoring water change over time, and predicting droughts and floods, can benefit from surface water mapping. [ABSTRACT FROM AUTHOR]

In the present day, deep learning applications are widely used in every field of development. In this paper, such a type of application is discussed in real-time. Mura dataset is the largest abnormal dataset given by the University of Stanford. In this research paper, we will understand the pre-processing of the image dataset. Kera's and TensorFlow libraries are used to build this model. We are classifying images using different ML models where accuracy is compared to get the best model build. This paper gives us a clear understanding of building deep learning models, understanding pre-processing techniques, and working on heavy data. This research's main agenda is to create a model which can classify bone fracture images and also give a small path for further development in the deep learning area. In this project we are using Resnet50, InceptionV3, Mobile Net and DenseNet with optimizer Adam and comparing their accuracies graphically. [ABSTRACT FROM AUTHOR]

Automatic Speech Recognition (ASR) is an efficient method of converting speech signals into textual format and is often referred to as Speech-to-Text System (S2T). We present an End-to-End (E2E) Deep Learning based Continuous Speech Recognition system in Kannada using Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Units (Bi-GRU) as a variant of Recurrent Neural Network (RNN). The model was built using 120 hours of manually selected continuous Kannada speech data. Experimentation has been performed on two different deep learning-based models. The accuracy with lowest Character Error Rate (CER) of 18.62% was achieved. The outcome of this experiment has been quite encouraging for developing end-to-end automatic speech recognition systems. [ABSTRACT FROM AUTHOR]

Deep learning models have been successfully applied in a variety of computer vision tasks. In particular, GANs (Generative Adversarial Networks) have proved very effective in generative applications involving images. This research work aims to apply GANs in the creation of handwritten digital pictures. Further, Conditional Deep Convolutional Generative Adversarial networks have been applied to generate handwritten letters. Our experiments have unambiguously underscored the extraordinary power and versatility of GANs in the arenas of character and digit generation. [ABSTRACT FROM AUTHOR]

Physicians could significantly augment their understanding of the stress trends exhibited by their patients through the in-depth analysis of continuously monitored stress data. This proactive approach enables healthcare professionals to provide more accurate and tailored therapeutic recommendations based on comprehensive assessments of stress patterns. The primary objective of this research is to leverage diverse recurrent neural network (RNN) architectures for the analysis of continuous sensor data, specifically focusing on actigraph data obtained from patients. The overarching aim is to develop robust classification models distinguishing between stressed and non-stressed states. The experimental phase of this study involves the rigorous comparison of the performance of the proposed RNN-based models with that of conventional techniques. This comparative analysis is conducted using authentic datasets, ensuring the reliability and relevance of the findings. The juxtaposition of experimental results serves as a critical component in evaluating the efficacy of the RNN approaches in stress level classification. Subsequently, the research provides pertinent recommendations based on the observed outcomes, offering valuable insights into the potential applications and benefits of employing advanced neural network methodologies in stress monitoring and management within a healthcare context. [ABSTRACT FROM AUTHOR]

The study analyzed scientific publications on students' problems in learning physics in different countries. Physics is considered to be a difficult subject that requires in-depth understanding of concepts and application in real-world contexts. In this context, bibliometric approaches are used to identify patterns in scientific literature and analyze related research. The aim is to provide useful information for educators, researchers, and stakeholders in developing more efficient and creative educational strategies. Through the collection, analysis, and interpretation of quantitative data, this method offers a better understanding of patterns, trends, and research contributions in this field. The results of the study showed a significant increase in research on student physics learning problems, especially in the United States and Indonesia. Expect international research collaboration and information sharing to understand students' problems in greater depth. These initiatives can help improve the quality of physical education and find the right solutions through the development of learning media that suits students' difficulties. With a better understanding of students' problems in physics learning, positive transformations are expected to occur in physical education globally [ABSTRACT FROM AUTHOR]

Power plants become critical facilities that need to run every time without failure. The component in the power plant system has been equipped with sensors. These sensors will monitor the element's condition by periodically sending the related metric data to the control room or storing it for later evaluation. These sensor data can be analyzed for early anomaly detection on power plants. Traditional methods still need humans as experts to detect these anomalies; hence, human error is a factor. Using deep learning, we can take advantage of abundant data to learn the usual pattern and detect anomalies in future data. Many deep learning algorithms have been implemented in this case. However, the selection of these algorithms depends on the data's characteristics. This paper aims to provide a comprehensive, structured analysis of the data features and the algorithm used to detect anomalies in the data. Twenty-two recent power plant anomaly detection studies were compiled as a systematic review. This review will discuss power plant sensor data characteristics that need to be considered, such as raw data format, label usage, data dependence, and detection results. This review also discusses methods used to process unsupervised data, the relation of the multivariate data, and anomaly detection. This review aims to ease the selection of the appropriate anomaly detection algorithm for future research by considering the data characteristics. [ABSTRACT FROM AUTHOR]

Rainbow antimagic coloring is a research topic on graphs that can be applied in everyday life. The graph neural network itself is a deep learning architecture that is used to solve machine learning problems on data in the form of graphs. Graph Neural Networks (GNNs) are a topic that researchers are currently discussing. GNNs are capable of performing tasks that Convolutional Neural Networks cannot do. By looking at existing literature, this research will examine the use of Rainbow Antimagic Coloring of Graph and Graph Neural Networks. The integration of Rainbow Antimagic Coloring of Graph and Graph Neural Networks is expected to be able to solve problems in life. Based on the results obtained from existing literature, the rainbow antimagic coloring concept can be combined with the neural network concept to solve real-life problems, including irrigation systems and supply chain management. [ABSTRACT FROM AUTHOR]

Dental disease is the first complaint of 10 major diseases in Indonesia. Almost the entire population of Indonesia has dental and oral health problems. Delay in early detection of dental and oral health problems can result in loss of productivity, longer duration of treatment, loss of teeth, higher costs, complications with other organs, which can lead to death due to cancer. We propose the invention concerns wireless oral image recording instruments and identification methods thereof. Several existing inventions do not yet have the following features including wireless connection, object detection, and prediction of oral and dental diseases that integrate the knowledge of clinical experts using the application. The purpose of this invention was to add to the features mentioned above by using Artificial Intelligence of Medical Things (AIoMT) concept, designing object detection based on deep learning (DL) algorithms, and integrating prediction systems high performance using collaborative datasets. This invention integrated intraoral image recording hardware in the Intraoral Camera Unit (ICU) with software in the Display Processing Unit (DPU) which produces visualization of predicted results, and a webserver unit as a data collection unit and image classifier according to the validated disease interpretation. The integration of these three units can then be used by medical scholars, researchers and medical practitioners to strengthen the reliability of the interpretation process, especially related to oral diseases using an integrated digital dental support system. [ABSTRACT FROM AUTHOR]

In this article, a method has been proposed to predict stroke on earlier basis to prevent any critical damage or death caused by it. The aim is to predict stroke in earlier basis so the necessary steps can be taken to stave off any critical damage. For this purpose, the parameters like heart disease, smoking habit, hypertension, glucose level, body mass index level, age, and work pressure have been considered. Moreover, previously happened stroke is also being considered to observe and empathize the situations and based on these facts real time stroke prediction analysis using deep learning and machine learning approaches has been suggested. At the present time "machine learning" and "deep learning" tactics are put on for finding the problems' solutions in "computer vision", forecasting and "convolutional neural network". This work proposes a before time prediction of stroke using various machine learning methodologies with occurrences of parameters based on which different classifiers are trained and data processing is done which attains a better outcome than other methodologies. [ABSTRACT FROM AUTHOR]

In Today's internet world, detecting Fake News is facing a difficult task. Data integrity has been of maximum importance in the current news era due to the extensive range of free text. Therefore, generating and developing fraudulent information is more painless than ever. The spreading of such fake news influences society from diverse inappropriate views. Online Social Networks has become increasingly popular to obtain news and information on the internet due to their widespread uses. However, false information has been spread widely due to the internet's rapid growth. As a result, detecting fabricated information is critical in our present culture. As a resolution, in this paper, a Deep learning approach is suggested to confirm the trustworthiness of news. It is also proposed as a Multimodal faked information detection method that utilizes both the textual and graphical content of the data to determine its authenticity. The first step is to pretrain the BERT model to achieve the textual feature representation vector. As a second step, pretraining the VGG-19 model generates a visual characteristic representation vector. Two MCBP (Multimodal Compact Bilinear Pooling) modules have been created based on the proposed methodology. Graphic feature representation vectors with alerts are obtained using the first MCBP module. MCBP's second module combines the visual feature with the attention process and the vector of textual elements. With a second MCBP module, the attention process and a textual feature vector are utilized to input visual quality. You may be able to exploit the linked vector to your advantage in detecting fake information. In this article, a comparison is performed between the proposed method and two standard methods. EANN and Spot Fake approaches have been compared in this work, and it has been found that the proposed strategy in this article outperforms both in terms of accuracy, precision, and recall. [ABSTRACT FROM AUTHOR]

Polycystic Ovary Syndrome (PCOS) is a common hormonal disorder among women of reproductive age and is characterised by disrupted ovulation cycles and an increase in androgen secretion. It is allied with metabolic and cardiovascular risks as well as a greater risk of developing hormone dependent-cancer. Due to its high prevalence in the current society coupled with its potential hazards, its early and accurate diagnosis is of utmost importance. The diversity of symptoms often delays the process of confirmatory diagnosis and more than 50% of women remain undiagnosed. To address these issues by facilitating rapid detection, this article proposes early diagnosis of PCOS with hormonal test and ultrasound images using various Machine Learning and Deep Learning algorithms. In this paper, we have used Generative Adversarial Networks to extend our dataset, and Transfer Learning using Residual Networks (ResNets) and Inception Networks for the ultrasound images. For the hormonal dataset, after pre-processing, we have compared the performance of multiple models, where CatBoost produces the highest accuracy. [ABSTRACT FROM AUTHOR]

Ensemble classifier of submarine acoustic wave enables efficient audio spectrum utilization using additional proposals includes noise reduction and fish and other aquatic organisms prevention. Acoustic transmission primarily employs various modulation schemes. Sensors and telecommunications can accomplish inside a comparable spectrum also with minimal possible of interference when such encoding pattern of a monitor and control is evaluated. Such mechanism too can reveal how well a system is being operated beyond the allowable parameters. In particular for undersea acoustic telecommunication, autonomous modulation prediction model sometimes use computer vision and optimization algorithms techniques. This research develops an entirely new array of learning-based modulation signal categorization algorithms for undersea acoustic transmission utilizing this as its driving force. In addition, several supervised neural frameworks are utilized to identify and extract first from before the transmitter square spectrum and periodic pattern. Furthermore moreover, black widow optimization has been employed to tweak the input variables of learning algorithm to optimum. The outcomes from the three deep learning models are therefore aggregated just use a combination of voting systems. In acoustic connection, the presented system can accurately perform forth a variation identification phase. The functionality of the proposed method gets evaluated below a range of instances, but a detailed evaluation of the results confirmed the supremacy to far more methodologies. [ABSTRACT FROM AUTHOR]

Harmful Algae Blooms (HABs) have emerged as a critical environmental concern, causing significant damage to marine ecosystems and coastal communities worldwide. Sabah, a coastal region in Malaysia, has experienced increased frequency and intensity of HAB events, leading to severe ecological and economic consequences. Traditional methods for detecting and predicting HABs are limited by their manual and time-consuming nature, hindering timely responses and effective mitigation strategies. To address this issue, this study presents an approach for predicting HABs in Sabah using a Deep Learning model. The proposed deep learning model harnesses the potential of artificial intelligence by integrating historical HAB occurrence records. In the first phase, the researcher collected and organized data from the Sabah Fisheries Department, then carefully cleaned and transformed it into a more practical format. After reviewing existing research, the study chose two promising techniques: the Artificial Neural Networks (ANNs) algorithm and the Long Short-Term Memory (LSTM). These techniques were experimented with to determine the most effective one for predicting HABs. Phase three involved rigorous testing of the prediction model using existing data, providing insights into how well it functions with the dataset and revealing the results obtained. In Phase four, the focus shifted to evaluating the model's performance, specifically identifying any reduced accuracy or shortcomings in the prediction percentages. This study adopts various evaluation metrics to assess the model's performance, such as accuracy, precision, recall, and F1-score, on a dataset with distinct training, validation, and testing sets. The authors also conducted usability testing to gather users' feedback on the proposed system. By providing timely predictions, the proposed model empowers stakeholders to take proactive measures to mitigate the ecological and socio-economic impacts of HABs on the marine ecosystem and coastal communities in Sabah. The findings will contribute substantially to the community by improving early warning systems and optimizing resource allocation for monitoring and controlling HABs. [ABSTRACT FROM AUTHOR]

At present, detection and recognition of animals remain a complicated task and no distinctive technique can solve all situations strongly and effectively. Animal detection in images is challenging because of the complexity of wild environments. Including several different things: The large differences in shapes and color appearances of variations of objects which belong to the same class, and Lighting/Illumination Conditions. This paper presents an effective and efficient animal detection system for Birds detection in images. MobileNet SSD model is a Single Shot Multibox Detection (SSD) suggested in this work, which is capable of handling different shapes and view angles of the objects. This approach allows extracting features of image regions and using deep learning techniques for classifying regions into two categories: (bird and non-animal). The experimental results demonstrated the efficiency of classification and detection of single and multi-animals even in difficult environmental conditions. The accuracy of detection and classification is up to 98.8%. This methodology is more accurate than other similar approaches. This paper exhibits a method for training a convolutional neural network (CNN) based on object detection classifiers. [ABSTRACT FROM AUTHOR]

This research describes a new model inspired by Mobilenetv2 that was trained on a very diverse dataset. The goal is to enable fire detection in open areas to replace physical sensor-based fire detectors and reduce false alarms of fires, to achieve the lowest losses in open areas via deep learning. A diverse fire dataset was created that combines images and videos from several sources. In addition, another self-made data set was taken from the farms of the holy shrine of Al-Hussainiya in the city of Karbala. After that, the model was trained with the collected dataset. The test accuracy of the fire dataset that was trained with the new model reached 98.87%. [ABSTRACT FROM AUTHOR]

The convoluted and dynamic nature of cancer growth makes it difficult to predict long-term cancer survival. Evolutionary deep learning techniques have been growing in popularity as efficient and accurate prediction techniques in recent years. Long-term cancer survival prediction has been developed to utilize evolutionary deep-learning techniques. This research combines the power of evolutionary algorithms using Particle Swarm Optimization (PSO) with some deep learning techniques to improve the performance and accuracy of the deep learning models by optimizing its parameters and minimizing the error between the predicted and actual outputs. Overall, combining evolutionary algorithms with deep learning models for cancer survival analysis prediction demonstrates the potential to significantly improve the accuracy and efficiency of cancer survival predictions, leading to better treatment decisions and improved patient outcomes. This paper uses the gbsg2 survival analysis dataset, a well-known dataset commonly used in survival analysis studies. [ABSTRACT FROM AUTHOR]

The global demand for energy is surpassing its availability owing to the increase in population and advancements in technology. It is essential to move closer to a dependable, economical, and sustainable renewable energy source to meet future energy demands. All alternative energy sources, including photovoltaic (PV) energy, have the potential to be renewable resources that can be used to address these ongoing issues with the energy crisis. PV systems are subject to the dynamic and fluctuating nature of the surrounding environment, which can lead to the manifestation of a diverse array of defects. It is essential to promptly identify and rectify any defects in order to ensure that the photovoltaic panel's efficiency, endurance, and durability remain uncompromised. The significance of automated defect detection is increasing in the PV industry due to the limitations of manual or visual inspection and the expanding production of PV modules. Therefore, this paper aims to develop a deep learning (DL) system that can accurately classify and detect defects in Electrouminescent (EL) images of PV cells, more specifically through implementing Convolutional Neural Networks CNN. Surprisingly, the suggested PV fault detection model outperformed commercially available PV fault detection systems by resolving existing challenges. The proposed model was further evaluated in terms of accuracy, loss, recall, f1 measure, and precision. The precision measure was 97.4% and the accuracy was 91.2%. [ABSTRACT FROM AUTHOR]

Facial palsy (FP) is an inflammation or disorder of the seventh nerve that leads to sagging of the facial muscles on the affected side and loss of control over movements and expressions. All ages and genders are susceptible to this disease. The medical diagnosis of this disease is prone to errors because it is based on the doctor's visual observation. Deep learning based technologies are the perfect solution for real-time FP detection. This study used a set of pre-trained deep learning based models including ResNet, AlexNet, DenseNet, GoogleNet and VGG16, to detect in real time FP, age and gender using a Raspberry Pi equipped with a digital camera. The accuracy obtained in the proposed system reaches 98% by using a wide variety of data consisting of 20,600 images, which includes 19,000 normal images and 1,600 images of persons with FP with different side of the injury. Thus, the proposed detection system can be considered as an effective and high accurate diagnostic system for FP, age and gender detection. [ABSTRACT FROM AUTHOR]

Water scarcity starts affecting the world and the trend remains the same even worse over the time due to the increasing global population which is expected to be more than 9 billion by 2050. The major portion of the fresh water was consumed by agriculture sector predominantly on irrigation. India has 4% of world's freshwater resources to assist 18% of world population. Unlike USA and China, India takes 2-4 % more water for its agricultural production. Continuous harvesting without the sufficient measurement and provisioning of the soil nutrient may endanger the sustainability of the agriculture. The amount of macro and micronutrients, pH level and water is used to measure the fertility of the soil. In case of soil nutrient deficiency, fertilizers to be added to the soil to maintain the nutrient levels. Most of the farmers apply the fertilizers manually. The right amount of nutrient to be maintained or else it may affect the plant life cycle and reduce the yield. Therefore, there is a need to adopt the advanced technologies in agro irrigation system by applying intelligent systems and services for the effective usage of fresh water and to maintain soil nutrient. Intelligent Irrigation System (IIS) which schedules the irrigation dynamically based on the soil features. Deep learning model for soil moisture and nutrient prediction, the same model can be deployed into other domains such textile and home automation. Mobile application to the farmers to know the status of the irrigation and soil fertility information. [ABSTRACT FROM AUTHOR]

Brain Cancer is the most dangerous type of cancer, which affects hundreds of thousands of people worldwide every year. Early identification of brain tumor is essential for timely treatment, which is crucial for the patient's survival. Researchers have found it challenging to develop Computer-Aided Diagnosis (CAD) for Brain Tumor Identification. Many studies have discussed the feasibility of Deep Convolutional Neural Network algorithms like ResNet, Inception, VGG in Brain Tumor Classification and Detection. These Deep Learning algorithms seem to have struggled from vanishing gradient, model bias with overfitting due to smaller medical datasets available. The proposed model TumorNet adopts a custom activated Deep CNN Architecture for classifying the more dangerous malignant tumors from benevolent tumors. The proposed model is trained from scratch and able to train with a smaller dataset consisting of MRI scans. It is evaluated, and it gives an impressive accuracy of 98.24%, outperforming other state-of-the-art CNN models, ResNet-101 and EfficientNet-B0. In comparison, the F1 scores of the proposed model are estimated at 98.05%, significantly higher than the other two models, which are 82.46 and 88.33%, respectively. [ABSTRACT FROM AUTHOR]

COVID-19 is a highly infectious disease caused by the coronavirus and has resulted in a global pandemic since 2019. The virus evolves, mutating into several very subtle variants to escape the conventional infection testing methods such as RT-PCR, leaving them obsolete against such new variants. Due to a shortage of resources and rapidly growing infection and mortality rate, a much more robust and more efficient way of testing and diagnosing COVID-19 was developed using deep learning algorithm-based solutions that analyze Chest Radiographs. Existing algorithms suffer from model bias and lack knowledge interpretability by classifying the given image into two classes: healthy or infected. CovidXDetector is a deep learning-based algorithm that detects and localizes Chest Abnormalities on Chest X-Ray Radiographs with critical feature annotations in the image that serves as clinical evidence to diagnose the diagnosis COVID-19. Based on Cascade R-CNN, it achieves an Average Precision score of 0.642 and outperforms YOLOv5 and SSD based detection algorithms by over 14% and 22%, respectively. This study affirms that our proposed model is a practical, easy-to-use and efficient solution for real-time diagnosis of COVID-19 using Chest Radiographs. [ABSTRACT FROM AUTHOR]

The primary objective of this study is to evaluate the efficacy of the Blaze Pose Algorithm, a new method for human pose detection, in comparison to that of Convolutional Neural Networks. Unlike the current method, which relies on static neural networks, Blazepose is a novel deep learning model for estimating human poses. Pretest power is 0.8, and there are 163 participants in each group. Data was gathered from the MPII Human Pose Dataset, which contains over 25,000 photos taken from various web videos. Researchers found that Blazepose's accuracy was slightly higher than that of a traditional neural network (90.3% vs. 40%). Independent sample T-test results show a 95% level of confidence that there is a statistically significant difference between the proposed and existing groups, with a significance value of P = 0.001 (P 0.05) 2-tailed. The Blazepose outperforms the traditional neural network in terms of improved accuracy, as seen by the comparison findings. [ABSTRACT FROM AUTHOR]

False news is characterized as a made-up story with a goal to bamboozle or to delude. In this paper we present the answer for the errand of fake news discovery by using Deep Learning structures. Fake news identification is carried out utilizing two AI calculations, Natural Language Processing Algorithm(N=10) and Deep Learning algorithm(N=10) calculations. False and True these two sorts of dataset is utilized for Fake news recognition, and it is gathered from kaggle.com. Dataset comprises lines and 6 fundamental boundaries that are connected with the False news that information gathered from twitter. For each gathering more than 30 examples are taken, and it is separated into preparing and testing. Accuracy for Natural Language handling calculation is 91.300% and for Support Vector Machine calculation is 77.500%. There exists an insightful critical distinction between Natural Language Processing Technique and Support Vector Machine calculations with p<0.05. Fake news location utilizing Natural Language Processing calculation seems to acquire higher precision than the Support Vector Machine calculation. [ABSTRACT FROM AUTHOR]

The aim of this study was to improve the accuracy in predicting COVID and tuberculosis using innovative deep learning algorithm FNN in comparison with SVM algorithm. The report was created using a typical local 3000 page format, and the data sets for COVID (N=154), tuberculosis (N=113), and normal (N=160) were obtained. The parameters were maintained as threshold by 0.5, enrollment ratio as 1, 95%,confidence level, G power at 80%. In accordance with regular protocol, the results were analysed using COVID and the tuberculosis login site. Higher mean values (83.9865) and error mean (0.3652) were obtained for standard algorithms compared to machine learning algorithms. There exists a statistically insignificant difference between the two groups (p=0.542, p>0.05). This study reduces the time required for manual classification to half and eliminates human error rate. [ABSTRACT FROM AUTHOR]

This study's goal is to estimate the price range for mobile devices using the Deep Neural Network algorithm and the Random Forest model. When N = 10 sample iterations were used to test the accuracy of the model for the validation of the mobile price range, two groups—the Deep Neural Network algorithm and the Random Forest model— with G power (value = 0.8) were studied. The Deep Neural Network model's accuracy results have a possible range of 84.183 percent, and the Random Forest model has an accuracy of (74.80 percent). The Deep Neural Network and Random Forest had statistically significant differences (p = 0.005). The Deep Neural Network technique outperforms the Random Forest approach in terms of performance and significance, according to the study findings for validating the pricing range for mobile devices. [ABSTRACT FROM AUTHOR]

Person identification based on human action recognition is a dynamic field that combines computer vision, deep learning, and motion analysis to identify and authenticate individuals based on their actions or movements. This technology finds applications in various domains, including security, surveillance, healthcare, and human-computer interaction. In this comprehensive overview, we will delve into the key components, methods, and models used in neural networks for person identification based on human action recognition. An analysis of algorithms working on the basis of these models for personal identification is presented. Also, currently, methods of evaluating and recognizing and identifying human behavior through video images are rapidly developing. Intelligent analysis and processing of video data for personal identification is one of the promising, fastest growing research areas and is widely used in various fields of human activity. In particular, it can be used to solve problems such as video surveillance for security and access to facilities for various purposes (security systems, control systems), fire protection systems, navigation, quality and quantity control of manufactured products, and many videosurveillance. This system helps to catch criminals at airports, railway stations and seaports. [ABSTRACT FROM AUTHOR]

As per our health is concern main parameter we can consider like sleep for our health regeneration, memorization and main aspect like recovery of our immune system. An essential part of overall health. Before detecting sleep issues in our body suppose if we have some machine or any ideas that helps to patients who is goes in narrow for their sleep issues for that if we can go with some tools and help us to analyzed before happening to sleep disorder. Using the algorithm of DL, we can explore the research in healthcare system. DL models helps to work with wide range of unformatted dataset which helps to understand how sleep issues are coming into human being based on some parameters we can learn some procedure. By using survey, we are going to specifies the different DL models are used to detect various types of problems present into the human being with different sleep stages. It compares different approaches by several authors who are working in this area, consider some different channels like eeg, ecg and many more. Also, they have worked with classification of DL models and different Methodologies with some pros, cons and conclusion. The main and very important aspect is sleep for regenerating some cells of body during sleeping time of any human being. As we consider better sleep in any people, they need to take proper nutrition, sleep, enough amount of H2O, breathing rate to balance. It is as important as eating, drinking and breathing, necessary for the normal maintenance of fitness and psychological filling well. There are many health issues are related to sleep disorders like sugar level, heart problems, long time sleeping, not getting sleep and many others. [ABSTRACT FROM AUTHOR]

Emotion recognition plays an important role in human-computer intercommunication, in the medical field, in call centers, etc. Gradually, the chances of Emotion Computing are increasing. The main six primary emotions are anger, disgust, fear, joy, sadness, and surprise. Many types of emotion recognition methods are available to recognize these emotions. But they mainly focus on facial expressions, speech, and gestures. Using visible emotion cues cannot capture people's true emotions. To get real emotions, emotion recognition using a Convolutional neural network (CNN), Recurrent neural network (RNN), and support vector machine (SVM), LSTM becomes essential. This article discusses various methods used for emotion recognition using RNN, LSTM using machine learning and deep learning techniques, data mining methods, and their databases. It also includes the experimental results and accuracy of each method. With this focus on building an emotionless machine, brilliance can be achieved. [ABSTRACT FROM AUTHOR]

Coronary atherosclerosis is a chronic & ever-evolving condition that can present clinically as anything from symptoms to acute coronary syndrome, heart failure, or sudden cardiac death. Coronary atherosclerosis develops and progresses due to environmental or genetic causes. Unquestionably, CVD is one of the primary causes of mortality worldwide. One of the most common disorders associated with CVD is CAD. Atherosclerosis, which restricts blood flow to the heart muscle, is the major cause of CAD. The amount of gold for geometrical assessment, angiography, is now used to examine atherosclerosis, which is a difficult condition to diagnose. The diagnosis of the lesion or visual evaluation by the clinician are absolutely necessary for the angiography. In this study, DL potent feature extraction abilities provide it a significant advantage in the area of defect diagnostics. A Resnet50, Resnet101, and VGG19 were used. A ResNet-50 pre-trained on a dataset of coronary artery segments was used to substitute the backbone. Three classification systems' effectiveness in predicting heart disease is examined and contrasted with earlier research. Numerical outcomes demonstrate the increased 95.2 % accuracy of percentage of risk estimation of suggested approach Resnet50 as contrasted to other two approaches. [ABSTRACT FROM AUTHOR]

The frequency and sophistication of cyberattacks have significantly increased over the past several years, it is crucial to mention. This highlights the need for effective and efficient methods for detecting and mitigating these attacks. Deep learning has been discovered to be an useful tactic for combating this issue, but there are still many open research questions and opportunities for improvement. As such, ongoing research and development in this field is crucial for staying ahead of the evolving threat landscape. Deep learning has evolved into a powerful technology for detecting cyber-attacks. We survey the most relevant deep learning models and datasets used for cyber-attack identification in this research. We will be discussing the various sorts of cyber based attacks that can be identified using deep learning, such as detection of network intruder, malware detection, as well as detection of anomaly in network in this survey. The most prominent deep learning architectures for cyber-attack detection, such as recurrent neural networks, deep belief neural network convolutional neural networks & autoencoders, are then examined. We also discuss the importance of using diverse and representative datasets for training and evaluating these models, and review some of the most widely used datasets in the field. At last, we talk about a few of the challenges and future headings within the field of profound learning for cyber-attack discovery. [ABSTRACT FROM AUTHOR]

The rise of cyber-attacks such as Distributed Denial of Service (DDoS) and SQL injection has become a significant concern for organizations and individuals who rely on the internet. Traditional detection methods have become increasingly ineffective in addressing these challenges, necessitating the development of new and innovative solutions. This paper proposes using Convolutional Neural Networks (CNNs) to detect DDoS and SQL injection attacks. Our paper proposes a Convolutional Neural Network model with a multi-layer neural and relu activation function optimizer that reaches a higher degree of precision than previous Deep Learning models. In this study, we tested the relatively new dataset CIC-IDS-2018, which contains different types of attacks. With this dataset, our model achieves an unprecedented accuracy of>96%, minimizing computational time. [ABSTRACT FROM AUTHOR]

Automated diagnosis of the cardiovascular disease from heartbeats of an individual is a difficult and challenging task. Essentially, it requires continuous monitoring system to track the irregular heartbeats in order to reduce the fatality rates. Electrocardiogram (ECG) is considered as one of the cheapest and most efficient clinical record used in hospitals to examine the cardiovascular condition of a heart patient. It is treated as a benchmark for sensing and identifying irregular heart rhythms. In modern era, due to abrupt increase in number of heart patients, cardiovascular health has become more important. In this paper, the aim of the research is to classify and predict the abnormal heartbeats from five different pre-defined classes such as, 'Fusion of Ventricular and Normal Beat', 'Supraventricular Premature Beat', 'Normal', 'Premature Ventricular Contraction' and 'Unclassifiable Beat'. The pre-trained VGG19 and DenseNet201 deep transferred learning models is used for classification and prediction. The proposed method is able to achieve overall 98% and 99% accuracy for VGG19 and DenseNet201 models, respectively. [ABSTRACT FROM AUTHOR]

Monkeypox disease was declared a Public Health Emergency of International Concern (PHEIC) by the World Health Organization (WHO) on July 23rd, 2022. The purpose of this designation is to encourage the global community to take coordinated measures to contain the spread of the disease and protect communities. The recovery period for Monkeypox disease typically ranges from 2 to 4 weeks, and in some cases, the disease can resolve spontaneously with or without treatment. However, severe cases have been reported, which can lead to fatalities. The fatality ratio for Monkeypox disease is estimated between 3% to 6% at present. It is essential to take precautionary measures to prevent the spread of this disease and seek medical attention if any symptoms are observed. Monkeypox is not highly contagious, and it generally spreads through close contact with an infected person. However, in May 2022, a significant number of cases of Monkeypox disease were identified, indicating that the disease was spreading rapidly. In light of this situation, it is crucial to track and isolate suspected cases promptly to prevent further transmission. Rapid and effective contact tracing, along with timely isolation of cases, is essential to contain the spread of the disease and prevent it from becoming an epidemic. Identifying, controlling, and taking measures to control the spread of Monkeypox disease is of utmost importance. To aid in this effort, this paper aims to create a large-scale dataset of Monkeypox disease images using Generative Adversarial Networks (GANs). GANs have proven to be highly effective in generating high-quality images and can aid in creating a more comprehensive and diverse dataset. The generated images will be used to train different deep learning models for image classification to diagnose Monkeypox disease. The deep learning models will be compared, and their performance will be evaluated using images of infected human skin with Monkeypox disease and healthy skin images. The results obtained from this paper will improve the accuracy of previous works, aiding in the early diagnosis and treatment of Monkeypox disease. [ABSTRACT FROM AUTHOR]

Kidney is one of the significant organs in the human body which performs filtering out blood, balances fluid, removes the waste, maintains the level of electrolytes and hormone levels. So, any disorder or dysfunction in kidney needs to be detected on time in order to preserve life. Segmentation on kidney tumor in medical field is a critical task and many conventional methods have been employed for early prediction of kidney abnormalities but with limitations such as high cost, extended time for computation and analysis with huge amount of data. Due to all such problems, the prediction rate and accuracy has reduced considerably. In order to overcome the challenges, Artificial Intelligence (AI) technology has penetrated into the field of medicine particularly in the renal department. The evolution of AI in kidney therapies improve the process of diagnosis through several Machine Learning (ML) and Deep Learning (DL) algorithms. It has the capability of improving and influencing on the status with its capacity of learning from the massive data and apply them accordingly to differentiate on the circumstances. The storage of larger data and segmentation with AI assistance are highly helpful for the analysis of occurrence of the disease. AI algorithms have predicted the severity of tumor stages with effective accuracies. Hence, this paper provides a critical review of different AI based algorithms being used in the kidney tumor prognostication. Its numerous benefits in field of segmentation have been researched from the existing works and provides an insight on the contribution of AI in the kidney disease prediction. [ABSTRACT FROM AUTHOR]

Deep learning has produced major advancements in computer vision, and its application for analyzing medical data has expanded considerably. A brain tumor is a disorder in which the brain's surrounding brain cells grow inappropriately and quickly spread to any region of the body. By identifying tumor patterns in brain images and fragmenting the features of brain tumors in those images, brain tumor can be identified. Multi-modal data provides more feature specific weights of same patient. Throughout the experiment we have taken BraTS2018 data set with 285 subjects for the training of the network and every subject contain 4 modalities of brain MRI like T1, T2, T1ce, FLAIR. In this work we propose a network, where a combined modality is generated with the fusion of four different modality features to train the network. It takes 128*128*128 image input size. Segmentation is done with the help of 3D u-net neural network architecture. This approach out-performs different networks such as CNN and other U-Net networks. At the end of the experimentation our proposed approach is found superior than different State of the art approaches. [ABSTRACT FROM AUTHOR]

This paper reviewed the Hand Sign Recognition system from 2018 to 2022. Based on the review, much research is done on Deep learning-based hand sign recognition. Many of these studies are published annually in article, journals, and conference proceedings. Additionally, we also examined the performance of the HGR system in terms of recognition accuracy. In this paper we concentrate on the data environment, the data acquisition, and the hand gesture presentation— three crucial components of the vision-based HGR system. We also looked at how well the vision-based HGR system performed regarding recognition accuracy. [ABSTRACT FROM AUTHOR]

Cashless transactions, which include internet, credit card, and mobile wallet transactions, are growing in popularity and have recently become well-known in financial transactions. The use of online transactions has increased, and there may be rapid improvement in e-trade and online banking in the coming decade. As the number of these cashless Transaction rises, so does the number of fraudulent transactions. Fraud can be identified by analyzing prior customer (user) spending patterns data on Transaction. This paper presents a review of various fraud detection techniques and discuss the issues regarding the financial dataset used in fraud detection technique. [ABSTRACT FROM AUTHOR]

Congestion on traffic lanes is a key issue impeding the growth of a metropolitan metropolis. The reason for this is the growing number of cars on the road, which causes significant time delays at traffic lights. Several strategies and procedures have been developed over the years to address this issue and make traffic control systems more dynamic. The static traffic control systems operated on predetermined timings that were assigned to each traffic lane and could not be changed. There was also no mechanism for counting and detecting pedestrians at zebra crossings, nor for detecting emergency vehicles in traffic. Here in this research, we will investigate multiple machine learning and deep learning models for car and pedestrian identification in traffic-prone lanes. Furthermore, we will propose a system that will contain a deep learning model to recognize various types of cars, pedestrians, and overlapping and intersecting vehicles on traffic lanes. Finally, a choice will be taken to free up the crowded lanes depending on the traffic count on each lane. [ABSTRACT FROM AUTHOR]

The Dubas bug (Db) is a deadly pest that affects palm and agricultural crops; however, early automatic identification of frond diseases of this type can thus help reduce human effort and reduce economic losses. Traditional methods of detection rely on human vision and hands to spot and categorise the palms affected, while more recent research has begun applying deep learning networks due to their effectiveness in classification tasks. This paper presents a strategy of automatic recognition of Dubas blight based on identification of diseased palms. Data was collected in natural climatic conditions using a drone camera and several pre-processing steps were applied. In particular, pre-sets were created by slicing the images into small parts and using Lifting Wavelet transformations (LWT) to shrink the data in size; this was then used to train a convolutional neural network (CNN) with the assistance of pre-trained Xception, InceptionV3, DenseNet121, and ResNet101 models with different parameters. Dropout and data augmentation was used to avoid overfitting, and the highest classification accuracy was determined to be that offered by the Xception model, with experimental results suggesting that this developed more than 99% accuracy. [ABSTRACT FROM AUTHOR]

One of the most significant qualities of the human brain is cognition, which incorporates both attention and recall. Attention is the initial process used when dealing with sensory inputs, prior to cognition, which acts to identify the nature of the stimuli as it impacts the individual's sensory system to select which details will be retained, processed, and recognised. Based on the increased use of e-learning, it has thus become necessary to determine the extent of student attention under the learning circumstances by looking at the state of the brain during this process. This can be achieved by reading brain signals using modern and advanced technologies with sensors that detect brain signals such as electroencephalography (EEG). The attention spans of students and their situational interest during learning have been studied for many years with respect to classroom learning; however, e-learning is becoming a highly popular method of learning, and the goal of this study is thus to use brain signals to measure learner attention levels in e-learning settings as compared to those seen in traditional classroom learning. The standard approach records EEG signals and their frequency bands across several subjects as they listen to a lecture in a classroom setting, characterising students' mental states as attentive or no attentive by means of machine learning classification models and algorithms. In this work, the best result were achieved with training using the Random Forest Classifier on the frequency band data set, which gave an accuracy of 91.4%, and by training using the Gated Recurrent Units neural network on the raw signal data set, which gave an accuracy of 96.4%. [ABSTRACT FROM AUTHOR]

Ocular biometrics and retina are essential in creating vision. Damage to this area can cause irreversible visual field loss. Accurate early diagnosis is important to prevent these structures' abnormalities. Deep Learning (DL) technology has been widely used to improve diagnosis quality lately. This technology has the potential to be used in the diagnosis of eye disorders. This systematic review was written to highlight the DL implementation of ocular biometric abnormalities and retinopathy diagnosis. The articles were selected and assessed by Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) protocols. Reported works have been analyzing DL-based diagnosis of glaucoma, diabetic macular edema, corneal disease, and retinopathy. These studies obtained significant results due to a high accuracy approaching human-level performance. Several convolutional models, which are either built from scratch or using pre-trained networks, were used in these studies. The DL diagnosis model achieved an average accuracy, specificity, and sensitivity of over 90%. DL has the potential to help medical workers determine ocular biometric and retinal image parameters–that happened to detect various eye diseases. [ABSTRACT FROM AUTHOR]

Physical disabilities cause significant distress in people's daily routine, especially for leg amputees as their movement is restricted. The civilized society has the responsibility to provide them with better prosthetics so they can live a normal life. Previously, prosthetic legs were developed for lower leg amputees. Today's electronic prosthesis provides a wide range of mobility compared to a mechanical prosthesis. Powered prosthetics are quite expensive and hence not widely used. We have proposed a low-cost control system above-knee powered prosthetics leg that is reliable, and the complexity of the model is less. The prostheses works by taking input from a sensor placed in the model and six FSR402 sensor and an IMU sensor that record force muscle activity of the thigh during variation of leg movement. The value of motion of the joint knee angle is determined by sensors. In this paper, we are discussing and comparing potential deep learning control system namely artificial neural network (ANN) as baseline and recurrent neural network-long short term memory (RNN-LSTM) to predict human gait cycle. A multi-layer perceptron (MLP) method is implemented. In general, network architecture consists of input layer which is represents by six inputs of the FSR402 sensor and an IMU sensor, fully connected layers, and an output layer as joint knee angle. As the result model of ANN as baseline has metric value MAE and R squared are 6.21 and 68.7% respectively whereas model of RNN-LSTM has metric value MAE and R squared are 4.99 and 96.9% respectively. The result indicates the RNN-LSTM model is most likely to perform fewer errors based on the dataset. RNN-LSTM outperforms the task with a greater value compared to the ANN model as the baseline. This present study suggests that deep learning with the recurrent neural network-long short term memory (RNN-LSTM) is suitable for the prediction of human gait cycle movement from the FSR402 and an IMU signal in the overall walking task. [ABSTRACT FROM AUTHOR]

The aims of this study are to describe how the interest of biology teacher students towards the use of three-dimensional software in the study of plant anatomy courses and see how the relationship between 3D representation using software and learning outcomes that have been done in the process of learning plant anatomy courses. This research uses quantitative methods with an associative and descriptive approach. Associative data analysis is conducted between 3D representation using blender software with the learning results of prospective biology teachers, to descriptively by analyzing the results of students' interest in biology teachers on learning using three-dimensional software. Sampling was done by purposive sampling by looking at the completeness of instrument data obtained by 63 students of prospective biology teachers. The instruments used are 3D representation scores, learning score and interest questionnaires. The results showed a strong relationship between 3D representation of learning outcomes, with a correlation coefficient value of 0.74, the relationship obtained was also significant. For the highest interest in student learning, it is about student activities, because students feel that they make their own 3D representations, often ask questions, and always follow the learning well. [ABSTRACT FROM AUTHOR]

This paper aims to develop a student worksheet with a discovery learning-STEM model on dynamic electric material to build on students' problem-solving skills in YAPPI Wonosari Vocational High school. The method used is R&D with a 4-D model that includes defining, designing, developing, and disseminating. The instruments used include validation sheets and tests—data in a physics worksheet to improve students' problem-solving skills. This study's data collection methods contain expert validation, observation, pre-test, and post-test—the data analysis using the sign test. The results showed that 1) the development of student worksheets with discovery learning-STEM on dynamic electric material was feasible in terms of the validation results. This can be seen from the results of validation that show the feasibility of physics worksheets for improving problem-solving skills is in the excellent category, and 2) the effectiveness of using physics worksheet with discovery learning-STEM based on data obtained from the pre-test and post-test results can improve problem-solving skills as a problem in the implementation class. Thus, student worksheet developed with discovery learning STEM is compatible with improving problem-solving skills. [ABSTRACT FROM AUTHOR]

The purpose of this study attempts to: (1) determine the use of Truth or Dare media cards assisted by Physics Spinning Wheel on physics learning outcomes (2) determine the use of Truth or Dare cards assisted by Physics Spinning Wheel cards towards learning interest. This research is a quasi experiment with a nonequivalent control group design. The research data was collected at islamic senior high schools in Sleman with a total of 25 subjects in experimental class and 25 students in control class. The research instrument has been through the validation stage by expert judgment namely the lecturer and the practitioner. Physics learning outcomes are measured by pretest and posttest in the form of multiple-choice questions analyzed using AnBuso. Improved physics learning outcomes and students' learning interest are analyzed using standard gain. The effectiveness between physics learning outcomes and learning interests was analyzed using the Manova Test with 0.016 effect size. The results of this study are: (1) Truth or Dare card media assisted by Physics Spinning Wheel can improve learning outcomes in physics with an increase score of 0.580 in the medium category and (2) Truth or Dare card media assisted by Physics Spinning Wheel can increase participants' learning interest students with an increase score of 0.150 with the low category. [ABSTRACT FROM AUTHOR]

Based on Badan Nasional Penanggulangan Bencana (BNPB), December 28, 2021, throughout 2021 from January 1 to December 28, 2021, natural disasters that occurred in Indonesia reached 3,058 events. Flood disasters dominate natural disasters that hit almost all parts of Indonesia, reaching 1,288 events or 42.1% [6]. this number is not a small number but quite large, of course this has a very bad impact on human survival in the future. Flooding is a condition in which an area is inundated by large amounts of water. This disaster is usually caused by an increase in the volume of water in a water reservoir, such as rivers, lakes, seas, etc., resulting in the overflow of water dams from their natural limits that submerge the land. Rob flood is an event of rising sea water caused by tidal activity of sea water that inundates the coastal land or a place lower than the highwater level. Tidal flooding is a threat to people in coastal areas because it can cause a lot of harm to the social and economic life of the local community. The puddle of water caused by the tidal flood occurred due to land use and topography that were no longer able to absorb water. The distribution of puddles due to the Rob flood that is not immediately resolved can cause losses to the affected area, so to prevent this from happening it is necessary to conduct an in-depth study to detect areas affected by the Rob flood by using Deep Learning. Deep learning is one of the implementations of Machine Learning which aims to imitate the workings of the human brain using an Artificial Neural Network. Deep Learning with a number of algorithms as "neurons" will work together in determining and digesting certain characteristics in a data set. Programs in Deep Learning usually use more complex capabilities in studying, digesting, and also classifying data. In this study, researchers used the KTrain and ResNet-50 method. The expected output of this research is the establishment of a reliable system to detect the Rob area as a form of handling the Rob flood disaster. [ABSTRACT FROM AUTHOR]

The deaf people tend not to get a good education in developing countries. Adults with hearing disabilities also have a high unemployment rate. This condition is triggered by the difficulty of people with speech and hearing impairment in communicating with other people which make it difficult for them to attend lessons, live independently, or have a decent income. Sign language is the main method of communication for people with speech and hearing impairments. Meanwhile, deep learning as a subset of machine learning in the artificial intelligence domain has shown a lot of progress in object detection. Convolutional Neural Network (CNN) is one of the algorithms in deep learning with an excellent ability to recognize objects, and MediaPipe is a machine learning-based framework to solve objects recognition problems such as detecting faces, eyes, hair, hands, gestures, and others. This study aims to develop a machine learning-based sign language translator that can be used by people in Indonesia with speech and hearing impairments to communicate. [ABSTRACT FROM AUTHOR]

This study aims to create a sentiment analysis model for the Halal Product Guarantee Act (JPH) No 33/2014 and the Job Creation Law (UU Cipta Kerja) related to JPH to help facilitate content analysis of existing legislation. The automated sentiment analysis process uses a deep learning approach with the LSTM (Long Short Term Memory) algorithm. The results show that the content of the JPH Law and the UU Cipta Kerja related to JPH contains negative (44.5%), positive (45.0%), and neutral (10.5%) content and is dominated by the words halal certificates, laws, halal products, and BPJPH (halal regulator). The results of the LSTM model test show accuracy in the range of 75% and epoch in the field of 80. [ABSTRACT FROM AUTHOR]