Skin tumor detection and classification have an important role which is applied in the field of research, particularly in the field of medical diagnosis. The classification of tumors in skin cells is of more significance since the number of affected people is increasing. The focus of this research work is to come up with a new and efficient method of enhancing skin images as well as identifying tumors from other areas on computed tomographic skin images. This work is mainly concerned with medical application methods on computed tomography (CT) skin tumor images that are developed and applied effectively. The first step is acquiring images. It can be seen that the Boosted Notch Diffusion Filtering - Mean Pixel Histogram Equalization (BNDF-MPHE) algorithm serves as the preprocessing step within the context of the presented model. The proposed step involves Superpixel Contour Metric Segment Clustering (SCMSC) followed by an Online Patch Fuzzy Region Based Segmentation (OPFRBS) Algorithm for effective segmentation of the skin tumor cells with an accuracy of 99.25% for benign and 97.39% for malignant tumors respectively. The time required for processing the lesion is less than 2 sec. The proposed method uses MATLAB 2024a workbench and accuracy is quite higher compared with other existing algorithms for both benign and malignant samples respectively. The proposed research methodology has been validated with real-time clinical samples effectively and throws light on the patient's life to resume normalcy and live long.

The premier goal of this research is to develop the Fuzzy Deep Neural Sliding Mode Fractional Order Proportional Integral Derivative (FDN-SM-FOPID) controller system for controlling liquid in quadruple spherical tank systems. This is used in non-linear spherical systems to control the level of liquid in real time. These models' dynamics allow for a more accurate identification of the spherical tank system that generates control signals from liquid samples obtained at reference levels. However, because the system is susceptible to outside disturbances, error minimization is not done. Therefore, it requires the addition of a special controller to lessen this flaw. The suggested Deep Neural Fuzzy model's six-layered network is optimized using the back-propagation method. As a result, the system's efficient training reduces offset model errors, steady state errors, and unmeasured disturbances. The liquid level is maintained and controlled by this neural intelligence system, which meets the necessary design requirements such as no overshoot, time constant, less settling and rise time, which is used in various platforms. The FOMCON toolbox in MATLAB software is used for research simulation work. The chemical industry, wastewater treatment, the aerospace industry, and the pharmaceutical industry have all employed the suggested quadruple spherical tank system to test its practicality. The experimental and simulation results are demonstrated by a real-time liquid control experimental setup.

Cloud computing and IoT are two great technologies which have the potential to reform the healthcare industry and enhance the systems that are in place to offer the best care to the frustrated patients, to manage a large number of data and to change the working processes. This chapter explained the role of cloud and IoT in healthcare domain and shifted focus to the key issues and challenges such as data security and privacy or, IoT and cloud integration and standardization and the issues with the big data management and analytics. Patient's personal information is quite high and it is critical to protect the data of patients in contemporary healthcare. Additionally, establishing connectivity between IoT devices and Clouds, programs possess certain limitations pertaining to various encoding and data transmission methodologies. Finally, the chapter about the challenge of managing and understanding big data ends with the assertion that it can only be done if a big-cloud structure and expensive sophisticated analytical methods are used to extract useful information out of it.

In today's competing business environment, the development and sustainability of an organization are meticulously tangled to the development and advancement of its employees. Career encroachment is not only a strategic persuader for employees but also an acute factor in improving organizational performance. Recognizing employees with high prospective and strategically investing in their development can build ways for improvement in productivity, innovation, and long-term success. In this paper, the prediction of employee promotion is handled by analyzing their performance based on various facts such as the number of trainings they attended, their KPI (Key Point Indicators) achievements, number of years they have served as the workforce and they training scores via our Promotion Predictive Analysis (PPA). These factors play a crucial role in determining the growth of an employee’s career and their worth as an asset to the organization. By understanding the fact that the growth of several individual employees directly comes together to influence the growth of a company, it is possible to see a direction for improvement. For this, it is imperative that the organization is able to use various techniques and tools to classify these individuals into different groups. This is done by examining the aforementioned factors and how they relate to each other, thus providing a way to strategize employee performance and career development by using a machine learning based model called SMOTEd-Boost which combined XGBoost with Synthetic Minority Oversampling technique (SMOTE) to deal with imbalanced data and classification of KPI indicators. Also our method is compared with the existing Naive Bayes and Support Vector Machines (SVM) algorithms for performance validation. Therefore, our PPA model helps others to understand the significance of the relation between an employee’s growth and an organization’s future and the need for a classification system to realize which employee’s serve the potential to be a crucial asset to the organization’s future and give them a suitable platform and also equip them with the abilities to maximize their capabilities. This would also prove to strengthen the bond between a company and their employees.

Artificial intelligence (AI) has emerged as a transformative force in the area of thrust production. The substantial effects of AI-powered tools on the production of engines, turbine systems, and propulsion that create lift for aircraft are examined in this chapter. Green aviation is advancing due to electric hybrid engine technology, which reduces emissions and solve environmental issues. Artificial intelligence, additive manufacturing, and technological innovation are shaping its evolution. This chapter explores developments and emerging themes offering an overview of the opportunities facing the aerospace sector. Software for process optimization examines data in real time to find bottlenecks and boost output effectiveness. Design optimization is aided by AI-driven models, while operational safety and fuel efficiency are enhanced by performance monitoring systems. These developments bring in a new age of technological growth and excellence by highlighting the crucial role that AI plays in enhancing reliability, productivity, and safety of thrust manufacturing.

With a high mortality rate worldwide, Chronic Lymphocytic Leukemia (CLL) poses a serious health risk. Radiologists view the ability to detect blood tumor cells as both important and difficult. It is challenging for many of the current studies to properly examine these blood cancer cells. An intellectual system for separating healthy cells from tumor cells is suggested in this research work. This research primarily depends on the effective implementation of computed tomography (CT) samples of both benign and malignant blood samples. In this research paper, novel methodologies called public active contour pixel mapping and Deep Neural Eagle Perch Fuzzy Segmentation (DNEPFS) are proposed, which help in detecting the blood cell boundary of the unaffected cells. It is quite similar to an eagle using the claw searching algorithm. Here, the eagle uses its sharp claws to tear the prey's skin during the search for its food. 99.64% and 99.32% accuracy are obtained during the research work for benign and malignant nodules using MATLAB R2023a. The computational complexity was found to be less, which is 7.13 s. Different segmentation techniques are used for comparative analyses. According to the research results, this proposed flow is superior to all segmentation techniques currently in use for the accurate detection of tumor cells. Based on the expert's annotation on online samples and clinical samples, the methodology has been validated to prove their effectiveness and throw light on the life of affected patients to resume normalcy - live long. The research work was tested in real-time clinical samples which deliver promising and encouraging results in leukemia detection procedures.

The objective of this research work is to create autonomous toll collection using solar energy, a renewable energy source. The Arduino UNO and RFID reader connect when a car with an RFID tag approaches the toll booth so that the Arduino may obtain vehicle data and distinguish between tags that are registered and which are not. The car enters the toll gate if the tag is registered, and the appropriate toll amount is subtracted. The deducted amount and remaining balance are displayed on an integrated display within the car, and an email-based automated acknowledgment containing information on the deducted amount, remaining balance, toll location, and toll name is delivered to the vehicle owner via Internet of Things technology. Access to the toll booth is prohibited if the RFID tag is not registered. By utilizing renewable energy, promoting effective toll collecting, and abiding by Indian toll station management laws, this research study intends to optimize toll booth operations.

To successfully increase the security of the system in today's environment, person authentication is required. It is undeniably true that most individuals would prefer to be authenticated in the simplest and most transparent way possible, without having to remember a personal identification number. Identity verification is necessary for many everyday activities. Both the ear and the palm's features are recorded, and corresponding feature vectors are created. The score level values are obtained following the fusion process, and the values below the threshold values are deleted and the values over the threshold values are authenticated using the Gaussian Log Gabor filtering method. In this regard, a multi-biometric system based on a person's gesture can be employed. It uses the complementing physical and behavioral characteristics of the ear and palm, two separate biometrics. The transfer function is the log Gabor method. The system's reliability is effectively increased by the aforementioned technique. The main benefit was created based on the merging of two biometric systems to enhance performance as a whole. Various feature extraction, feature matching, and data fusion approaches are used to determine the saliency and correlation of the data that each sensor has collected. The outcomes also imply that the proposed algorithms outperform existing algorithms in terms of performance.

The backbone of the Indian economy, agriculture is essential to Indians' standard way of life. Plant disease monitoring by hand typically involves a tremendous labor and takes more time to perform. The primary goal of this research is to help farmers, particularly those who are dealing with blast disease in rice crops, by quickly and reliably detecting plant diseases. The primary goal of the research is to catalog the diseases that affect rice and identify crop infections early on. Therefore, the development of soft computing and image processing technologies for smart agriculture applications is the subject of this research study, with a special emphasis on applications in innovative design for the detection of diseases in rice. The key methods of analysis used include preprocessing, classification, feature extraction, and picture acquisition. The lands used for agriculture are the source of input images. Dmey wavelet filtering is the first step in the pre-processing procedure which removes noise from images. Next, image-based crop feature extraction techniques are utilized to perform an extensive study. The proposal is to use the Adaptive deep neural network (ADNN) to address the overlapping issue. In ADNN, the total accuracy is 97.3%. A wide range of rice blast diseases are correctly identified with the desired accuracy, regardless of the obscured settings, according to the evaluation results of the suggested method.

The most serious disease that affect the women worldwide is breast cancer. Early identification of breast cancer contributes to lower death rates. Through the process of histopathological examination, a pathologist looks at the tissues’ microscopic features to find different malignant patterns. However, the process of manual histological analysis is challenging, unreliable, and time-consuming. Therefore, in order to determine the malignancy, a computer-aided system created to analyze these images must take these two magnifications into account completely. As a result, this research suggests a distinct deep neural algorithms for the categorization of breast cancer histological images, designed to imitate a pathologist. ResNet-50 focuses on possible locations that are relevant for the precise classification of tumor images by utilizing global and local information in an integrated manner. Preprocessing of the images with nuclei is therefore regarded as the first stage in this procedure. To get an equalized preprocessing result, the input images are subjected to Color normalization. After additional processing, these pictures are divided into two group called benign and malignant. The efficacy of the suggested models in improving nuclei is demonstrated by experimental evaluation on both public and private datasets. The experimental evaluation shows the best result with the proposed research technique.

Waiting in a long queue while shopping has become tiresome in today’s hectic society. And this takes up a lot of the user’s time when they are shopping. We suggest an automated smart tram billing solution to get around this issue. As a result, the user’s billing period is shorter. Moreover, for billing, users are no longer required to wait in a huge queue. The suggested solution made use of cutting-edge technology including RFID, Arduino, and Internet of Things (IoT). In this paper, a Canny Cart, which is nothing but a smart trolley for easy shopping is designed and developed. The user may shop using prepaid systems, but they must put enough money in their carts to meet their demands. A scanner scans the product and its weight is detected finally automatic billing is done. The amount for each item that person adds to their shopping basket will be automatically determined. If the added item is removed from the basket, the amount will be credited to the user’s prepaid shopping account. Here, RFID is used to specifically identify each item in the supermarket and to find out about other details like pricing. IoT is used to connect the entire system. Long Short-Term Memory (LSTM), a type of Recurrent Neural Network (RNN) architecture is utilized for this work. Training of 150 products is done using LSTM model with Batch Normalization (BN) for better accuracy. The proposed Canny Cart is very easy to use, low-cost, efficient with real-time interactions, highly secure, compatible, has better user-friendly interface and saves time and money. Such type of cart is recommended to be used in shopping and industrial applications.

Connected Autonomous Vehicles (CAV) is happening due to sensors incorporation in all road conditions and make driving judgements, and these sensors must be reliable for the vehicles to be safe. Accelerated devices hold the main segment among entire hindrance recognition devices. Generally, estimated to be built on vehicles more often. To identify obstacles, these sensors analyze ultrasonic emission and reflection data. Using the intrinsic weaknesses in sensors, we developed adaptive attacks using jamming, random spoofing, and spoofing on ultrasonic sensors. By doing this, we were able to a car into stopping when it shouldn't have and let it keep going. It substantiates our assaults using independent devices and mobile automobiles, like a Tesla Model that has Autopilot. Here, results show that occurrences induce blindness and malfunctions in both autonomous vehicles and sensors, which could lead towards crashes. The proposed deuce resistance strategies nearly improve the safety of accelerated devices and CAV with two methods of verifying signals. The suggested verified signals are sensor leveling physical shift authentication and multiple sensor consistency check, which uses multiple sensors to verify signals at the system level.

Text-to-image synthesis is a computer vision task that involves understanding and converting textual descriptions into corresponding and relevant images. Recently, Generative Adversarial Networks (GANs) and Contrastive Language-Image Pre-training (CLIP) have been employed to accomplish this objective. VQGAN comprises of a generator and a discriminator network that work together in a competitive manner to create realistic images based on input descriptions. In contrast, CLIP is a transformer-based language model that has been pre-trained using a diverse set of text and image data. Integrating the capabilities of both VQGAN and CLIP can lead to notable enhancements in text-to-image generation compared to using either technique individually. This abstract offers a concise overview of the latest progress in this area and emphasizes the potential advantages of leveraging a combination of GANs and CLIP for text-to-image synthesis.

Recent population expansion has caused individuals to become less aware of the value of preserving a healthy environment. The world is growing more intelligent for safety purpose, perceptive with intelligent resource optimization solutions in order to rapidly change consumers life based on the need. This need resulted in choosing the creation of secure, smart cities that connect the virtual and physical worlds. These cities use IOT technology to deliver real-time services that adapt to changing circumstances. This system makes use of a variety of sensors to keep track of a city's infrastructure. Using wireless connection, an ATmega16 microcontroller is connected to the system's sensors. The controller gathers data from sensors, transmits using Wi-Fi module to be connected to the cloud, and displays it on a monitor.

The most common challenge faced by dermoscopy images is the automatic detection of lesion features. All the existing solutions focus on complex algorithms to provide accurate detections. In this research work, proposed Online Tigerclaw Fuzzy Region Segmentation with Deep Learning Classification model, an intellectual model is proposed that provides discrimination of features with classification even in fine-grained samples. This model works on four different stages, which include the Boosted Anisotropic Diffusion filter with Recursive Pixel Histogram Equalization (BADF-RPHE) in the preprocessing stage. The next step is the proposed Online Tigerclaw Fuzzy Region Segmentation (OTFRS) algorithm for lesion area segmentation of dermoscopic images, which can achieve 98.9% and 97.4% accuracy for benign and malignant lesions, respectively. In the proposed OTFRS, an accuracy improvement of 1.4% is achieved when compared with previous methods. Finally, the increased robustness of lesion classification is achieved using Deep Learning Classification –DenseNet 169 with 500 images. The proposed approach was evaluated with accuracy classifications of 100% and 98.86% for benign and malignant lesions, respectively, and a processing time of less than 18 sec. In the proposed DensetNet-169 classification technique, an accuracy improvement of 3% is achieved when compared with other state-of-art methods. A higher range of true positive values is obtained for the Region of Convergence (ROC) curve, which indicates that the proposed work ensures better performance in clinical diagnosis for accurate feature visualization analysis. The methodology has been validated to prove its effectiveness and throw light on the lives of affected patients so they can resume normalcy and live long. The research work was tested in real-time clinical samples, which delivered promising and encouraging results in skin cell detection procedures.

Image dehazing is frequently used as a preprocessing step to enhance image clarity in various computer vision tasks, such as object tracking, intelligent surveillance and face recognition. It helps in the restoration of hazy images. Deep learning techniques have recently been utilized to significantly improve the quality of visual representation of images, but it takes a lengthy time to compute. In order to avoid the phenomenon of latency in the primary image analysis tasks, we have to monitor the time required for processing. An end-to-end modeling for real-time image dehazing network is proposed in this research paper. A complete network processing model for dehazing in real-time is proposed in this research paper. To record dependencies with reference to the positions and channels of the feature map, a non-local slice module is created. A region proposal network is also used to provide candidates with great sensitivity, hence raising true positive rates. The dark channel is estimated from the given input image along with the saliency of the detected image. The multi-scale feature maps are then used to suggest a false positive reduction module. An extensive comparative experiments were conducted using SANet's performance with a number of cutting-edge CNN-based detection techniques. The usefulness of our suggested method to gradually recover haze images utilising a coarse-to-fine strategy is demonstrated by evaluation results on SANet. The proposed method demonstrated real-time performance comparable to existing method in experimental findings using a publicly available dataset.

Deep learning based image resolution reconstruction has gained popularity recently. Using sensors, underwater pictures are captured. Due to the water's exponential attenuation of the transmitted light, underwater photographs have poor visibility, including low contrast and color blurring. The identification of targets and further evaluation are made more difficult by the underwater images' degradation. This paper offers a hybrid underwater image processing method called deep learning based transmission binary mapping algorithm that combines a color balance algorithm with an underwater picture restoration technique to solve these issues. This research work proposes an enhanced picture super-resolution reconstruction approach. It is based on transmission based binary mapping algorithm for enhancement in the efficiency of machine learning concepts. To calculate transmission maps, RGB attenuation for each channels are decomposed. These suggested approach can efficiently determine light at the background and combined transmission binary mapping at underwater images, which can then be used to recover these image. In addition, color attenuation balancing technique helps to provide upgraded scenes that seems realistic. Finally, thorough testing are put into place to evaluate how well our method works. The suggested method surpasses a number of popular underwater image enhancement and restoration techniques, according to tests on photographs taken in various underwater situations.

Most people are losing their lives each year as a result of vehicle accidents caused by sleepy drivers. A device that can identify tiredness and notify the driver to it is necessary to prevent car accidents and save lives. Finding drowsy drivers is perhaps the most important step in stopping any traffic accident, everywhere in the globe. The goal of this work is to create alert strategy for smart vehicles which immediately halt drowsy driving problems. However, feeling tired is a normal physical phenomenon that can happen for a number of different causes. In order to stop the accident’s cause, an accurate alarm system must be developed. The system for alerting sleepy drivers that has been developed using this technique is discussed in the proposed study where Video Stream Processing (VSP) is processed using the blinking criteria based on the eyes Euclidean distance. Additionally, the face marking method is created. The results of proposed work uses Dlib, an OpenCV deep learning technique using Raspberry Pi with a mounted camera for accurate detection, showing good results for detecting drowsiness, reducing the accident occurrence on the roads. The facial recognition algorithm developed by Haar starts with collected photographs as its input and outputs faces that are identified.

A street scene in a city can be split into several different objects. The primary focus of this paper is on developing an autonomous recognition system for detecting and recognising traffic sign elements in use, with a variety of options for setting parameters and constraints. The algorithms and methods used by the system are effective for identifying elements of traffic signs inside camera-generated images. Bitmap image algorithms and geometrical element techniques are merged in the recognition process in order to increase recognition success and make the operation more time-effective and efficient. The first step is to remove the previously specified image from the camera using deep learning based edge detection. The following stage is standardization, which is frequently carried out via a binarization image search that scans the image for continuous portions. Periodic symptomatic evaluation, the main criterion for decision-making for the action recognition system, is done in these areas. In order to accurately identify some of the discovered relationships, they are then connected with predefined items. Due to the scanning and processing of cameras in the control and safety car applications, a sophisticated autonomous system structure is created for real-time application. With a driving aid, the proposed technology reduces the possibility of human error. The suggested approach improves overall performance favourably and segments even small objects significantly better.

Skin tumor acts as a premier factor for high death rate throughout the world. To segment the skin tumor the radiologists find it impotent. Various research works find it to be an ineffective manifestation. The intention of this research work is to provide an efficient enhancement method and tumor detection from other unaltered regions. This work relies mainly on computed tomography (CT) tumor images of the skin, benign or malignant, that has been implemented efficiently. In this research paper, a novel methodology called Online Tiger Claw Region Based Segmentation (OTCRBS) is proposed which is used mainly to detect the boundary of unaffected Skin Cell, similar to tiger which uses its claws to tear off the skin of its prey during the search for its food. By using metric for the region, various properties can be formulated for the detection of anomalous skin cells. 98.68 and 97.71% accuracy is produced for procurement of benign and malignant nodule in MATLAB 2018a, respectively. Computation time was only 7.65 s. Comparative analysis is made with different segmentation methods. Experimental results establish that the proposed flow outperforms all the existing segmentation methods for the proper detection of tumor cells.