Search

Have you thought about the quality of the air we breathe? Living a healthy and happy life is so important in the wake of the COVID-19 pandemic. To live a healthy life, everyone needs to be aware of the quality of the air they breathe and how their actions impact current and future air quality. This project presents his IoT-based system for measuring, monitoring, communicating, and predicting future air quality. The system was developed using a combination of IoT and machine learning to monitor, analyze and predict air quality in real-time. Air quality can be measured using various gas sensors, temperature and humidity sensors. It also measures the number of hazardous gases emitted in industrial areas. Machine learning models are applied to data values from various sensors to predict future air quality. The proposed solution monitors the current air quality on the device through a small smart application, observes fluctuations using graphs, and sends SMS alerts if air quality parameters exceed acceptable values. can. Another important feature is the addition of AERO, a virtual assistant that allows anyone to communicate atmospheric details. This system allows businesses, organizations, industries, farmers, gardeners, healthcare workers, city dwellers, etc. to easily connect, communicate, and monitor the current air quality in their daily lives and lead healthier lives. You will be able to. This will allow you to perform the necessary actions.

In recent years, Biometric system are the one, which is widely used method for the recognition and identification of an individual that are highly demanded approach for its absolute security and accuracy which plays a vital roles in banking, commercials, business and other fields. Moreover this research is based on the multimodal biometrics which is recommended for its high recognition performances and it overcome the demerits of unimodal biometric approach. This research concentrate two multi-modal biometric traits such as face and iris, and propose Gradient Neural Network (Gen-NN) method to improve the biometric authentication by using the VISA face and iris multi-modal biometric database also used ResNet-101 and WaveNet for the feature extraction where the input of face and iris can be extracted.

The endeavors to explore and map the dynamic terrain of cloud computing, designated as the CloudVerse. Through a meticulous examination of recent advancements and emerging patterns in cloud technologies, this study aims to furnish a comprehensive portrayal of the present state and future trajectories of cloud computing. Utilizing a blend of literature review and industry scrutiny, the paper identifies pivotal domains of innovation within the CloudVerse, encompassing hybrid cloud infrastructures, serverless computing models, edge computing paradigms, and AI-driven cloud solutions. Furthermore, it delves into the ramifications of these advancements across diverse sectors and deliberates on strategic imperatives for enterprises embracing cloud technologies. Ultimately, this inquiry strives to demarcate the contours and potentials inherent in the CloudVerse, proffering nuanced insights for navigating the intricacies of contemporary cloud computing landscapes.

Breast carcinoma stands as one of the most perilous afflictions affecting females, lacking an effective treatment to date. Recent advancements in deep learning techniques, coupled with artificial intelligence (AI), have demonstrated promising results in breast cancer identification. This innovation facilitates early detection, consequently enhancing patient survival rates. Deep learning necessitates minimal human intervention for feature extraction, contrasting with traditional machine learning methods. The ML and DL techniques are practised and comparison of all these techniques were shown. Specifically, emphasis is placed on genomic and histopathologic imaging data. Various algorithms, including R, SVM, logistic regression, KNN, Naïve Bayes, CNN, and ANN, are thoroughly researched and valuated to gauge their efficacy. Furthermore, many screening protocols were deployed to identify and examine the datasets. Lastly, the paper explores the challenges encountered and the most possible directions to detect the breast cancer .Hence researchers and clinicians with a thorough understanding and insights into this deep learning domain.

Several AI-based methods have substantially progressed the area of medical image and video-based diagnostics, which encompasses radiography, pathology, endoscopy, and the categorization of gastrointestinal (GI) diseases. When it comes to classifying numerous GI disorders, the majority of prior research that relies solely on spatial cues performs poorly. While some prior research has made use of temporal features trained on a 3D convolution neural network, these studies have focused on a very small subset of the gastrointestinal system and have used very few classes. To address these concerns, we introduce an all-inclusive AI-based system for classifying different GI illnesses using endoscopic recordings. This system can extract spatial and temporal data concurrently, leading to improved classification performance. For temporal variables, we employ a long short-term memory model; for spatial features, we employ two independent residual networks in cascade mode.

The collection of unique and diverse tumors known as soft-tissue sarcomas (STS) is hindered by a number of factors, such as delayed or inaccurate diagnosis, and a lack of clinical knowledge, and a restricted range of treatment alternatives. The tissues that surround, link, and support other body organs and structures are the target of a rare type of cancer known as soft tissue sarcomas. Muscle, fat, blood vessels, deep skin tissues, tendons, and ligaments are among the tissues that can be impacted by soft tissue sarcomas. Soft tissue sarcomas can arise in nearly every body component, including the arms, legs, and abdomen. The way that patients are treated medically is severely harmed by these diagnostic mistakes. Numerous machine learning models have been proposed by researchers to categorize cancers, but none of them have sufficiently addressed the issue of misdiagnosis. Furthermore, the majority of comparable research that has suggested models for the assessment of these malignancies do not take the heterogeneity and volume of the data into account. This research presents the comparison between machine and deep learning methods for the improved categorization of soft tissue sarcomas. This research further proposes on the early detection of STS. In the next stage of classification, an optimal Convolution Neural Network (CNN) is employed.

Millions of people throughout the globe suffer from diabetes mellitus, a debilitating illness that increases the risk of severe complications and early death. To take preventative measures and tailor treatment to each individual's needs, it is essential to identify diabetes early and estimate risk accurately. This research provides a data-driven strategy for predicting diabetes based on SVM models. This work uses a large dataset, including clinical and demographic data from a wide range of people, including those with and without diabetes, to conduct our analysis. A prediction model that divides people into diabetes and non-diabetic groups based on their input attributes is constructed using the SVM algorithm. Engineers use feature selection and other engineering methods to improve the model's efficacy and readability. The results of the research show that the SVM algorithm is capable of producing reliable predictions of diabetes risk. Measures of the model's efficacy include its sensitivity to false positives, specificity in identifying true positives, and area under the Receiver Operating Characteristics curve (AUC-ROC). In addition, feature significance analysis improves the model's interpretability by illuminating the most critical risk variables for diabetes. The accuracy and interpretability of the proposed SVM-based diabetic prediction model are promising, making it a valuable tool for healthcare practitioners and policymakers to identify those at high risk of developing diabetes and modify preventative measures and interventions appropriately.

Clinical procedures, which require a large number of personnel and medical resources, receive the majority of the current focus on thyroid nodule diagnosis. An automated thyroid ultrasound nodule identification system is built using image texture data and convolutional neural networks in this study. The following are the major phases: The underlying stages in building a ultrasound thyroid knob dataset incorporate gathering positive and negative examples, normalizing pictures, and portioning the knob region. Second, a texture features model is built by selecting features, reducing the dimensionality of the data, and extracting texture features. Third, deep neural networks in move learning are utilized to create an element model of the knob in an image. The convolutional brain network highlight model and the surface component model were combined to create the brand-new knob include model known as the Feature Fusion Network. The Feature Fusion Network is used to prepare and improve performance over a single organization in order to create a demonstrative model for deep neural networks that can adapt to a variety of knob features. 1874 clinical ultrasonography thyroid knobs were gathered for this investigation. The musical normal F-score considering Accuracy and Review is utilized as an assessment metric. With an F-score of 92.52 percent, the study’s findings suggest that the Element Combination Organization can differentiate between benign and harmful thyroid knobs. As far as execution, this methodology performs better compared to standard ML procedures and convolutional neural networks.

The increasing propagation in recent years of hatred on social media and the dire requirement for counter measures have drawn critical speculation from state run administrations, organizations, and analysts. Despite the fact that specialists have observed that disdain is an issue across different Social media stages, there is an absence of models for online disdain location utilizing this multi-stage information. Different techniques have been produced for robotizing disdain discovery on the web. Here we will begin by giving the current issue that comes the right to speak freely of discourse on the Internet and the abuse of virtual entertainment stages like Twitter, as well as distinguishing the holes present in the current works. At long last, figured out how to tackle these issues. It is a considerably more testing task, as examination of the language in the common datasets shows that disdain needs one of a kind, discriminative highlights and in this manner making it challenging to find. Removing a few exceptional and significant elements and joining them in various sets to look at and dissect the presentation of different machine learning classification calculations as to each list of capabilities. At long last, subsequent to leading a top to bottom investigation, results show that it is feasible to fundamentally expand the classification score acquired.

One of the most common causes of death is auto accidents. The worst thing that may happen to a road user is a traffic accident, despite the fact that they happen regularly. The worst part is that we fail to learn from our on-the-road errors. Most people who use roads regularly are extremely familiar with the fundamental guidelines and safety procedures that should be followed, but it is only their own negligence that results in accidents and wrecks. Accidents and crashes are primarily caused by human error. Here are some examples of normal human actions that result in accidents. 1. Driving too fast; 2. Driving while intoxicated; 3. Distracting the driver; 4. Running red lights; 5. Avoid utilizing safety equipment, such as seatbelts and helmets; 6. Driving erratically and overtaking improperly in order to save lives in a traffic collision, we’re going to construct an Arduino-based car accident alert system that combines GPS, GSM, and an accelerometer. If the accelerometer detects an abrupt shift in the vehicle’s axis, the GSM module alerts you and communicates the location of the accident to your cell phone. The GPS module’s latitude and longitude are utilized to pinpoint the accident’s location, which is provided as a Google Map link. The message also contains the vehicle’s speed in knots.

Breast cancer is a major public health issue that may be remedied with early identification and efficient organ therapy. The diagnosis and prognosis of severe and serious illnesses are likely to be followed and examined by a biopsy of the affected organ in order to identify and classify the malignin cells or tissues. The histopathology of tissue is one of the major advancements in modern medicine for the identification of breast cancer. Haematoxylin and eosin staining slides are used by pathologists to identify benign or malignant tissue in clinical instances of invasive breast cancer. A digital whole slide imaging (WSI) is a high-resolution digital file that is permanently stored in memory for flexible use. This article will look at and compare how breast cancer cells are categorised manually and automatically. lobular carcinoma in situ and ductal carcinoma in situ are the two types of breast cancer. Here, detailed explanations of numerous techniques utilised in histopathology pictures for nucleus recognition, segmentation, feature extraction, and classification are given. The pre-processed image is utilised to extract the nucleus patch using several feature extraction approaches. Thanks to the great computational capability of the general processing unit (GPU), algorithms may be implemented effectively and efficiently. Deep Convolution Neural Network (DCNN), Support Vector Machines (SVM), and other machine learning methods are the most popular and effective computer algorithms.