The project deals with the optimization of WEDM process parameters with the help of minitab and MATLAB softwares.

Three main challenges in Data Communication and Networking Modern information systems rely heavily on data communication and networking to effectively transmit and exchange data across a variety of devices and networks. However, there are several issues in this area that limit network performance and the smooth flow of data. This review paper explores the key challenges encountered in data communication and networking and discusses potential solutions to address these issues. This report offers insights into the present status of research and shows the ongoing attempts to address these difficulties through an analysis of relevant articles and journals. The results of this review can help for better understanding the complicated world of data networking and communication, which will support the creation of reliable and effective communication systems.

According to a UN report, India’s population is expected to reach 1.73 billion by 2050, with 25% of people leaving farming due to urbanization. However, we will require 70% more food than we do today by 2050. The Global Citizen’s Alliance (GCA) report states that India has only 4% of the world’s water resources, despite being home to 16% of the world’s population. Due to droughts and floods, irrigation is highly unpredictable. Furthermore, we need more water for irrigation than the US and China combined, due to mismanagement of water resources. Old farming practices must be changed urgently to address these challenges. Smart farming is a promising solution that utilizes the latest technology to achieve higher yields than conventional farming. With the help of AI and predictive analysis tools, scientists can predict diseases before they occur. The authors of this paper suggest that IoT is the best technology to ensure the quantity and quality of food. Precision irrigation and micro irrigation have replaced conventional irrigation in farms and greenhouses. In addition, wireless sensors have been used to track animals and analyze their behavior, leading to better livestock management. Farmers can remotely monitor their fields and cattle houses through mobile apps and take necessary actions with automation and robotics. In summary, this paper highlights the need for technology to address the challenges of food and water security in India. Smart farming techniques such as precision and micro irrigation, as well as the use of AI, predictive analysis, and IoT, can help us achieve higher yields and ensure food quality and quantity.

The detection of electricity theft, which focuses on privacy protection and system security, has been extensively researched in the smart grid. However, existing solutions have not taken into account the enormous communication overhead that will be incurred in practical environments due to the large scale of the smart grid and the vast number of smart meters. Furthermore, there has been a lack of further research on the detection models and periods. Therefore, we propose a lightweight privacy-preserving electricity theft detection scheme. Specifically, we introduce differential privacy in the inner product encryption process of electricity data and neural network weights under the vector type, providing strict privacy protection without affecting data utility. Secondly, a combination detection model that extracts local and global features of electricity data is proposed. Furthermore, we explore the impact of detection periods on six different datasets. The experimental results based on real electricity consumption data demonstrate that our scheme has lower communication overhead and higher accuracy.

This manuscript proposes a new deep-learning-based NILM (non-intrusive load monitoring) method.

The versatility of hafnium oxide-based ferroelectric memories to function as a storage class memory, a synaptic device for neuromorphic implementation, and a device capable of high-density integration have made them attractive candidates for next-generation technology. Ferroelectric memories have been increasingly popular with the discovery of ferroelectricity in hafnium oxide at a shallow thickness and compatibility with complementary metal-oxide-semiconductor-compatible processes. The single transistor-based ferroelectric cell makes them ideal for non-volatile embedded memory solutions, bridging the gap between on-chip SRAM and external data storage (e.g. Flash). This paper begins with discovering ferroelectricity in Rochelle salt and discusses the neoteric progress up to successful integration with 3D memory.

Background: Triage of patients with skin diseases often includes an initial assessment by a nurse or general practitioner, followed by a dermatologist. Artificial intelligence (AI) systems have been reported to improve clinician ability to diagnose and triage skin conditions. Previous studies have also shown that diagnosis in patients with skin of color can be more challenging. Purpose: This study seeks to determine the performance of AI in the screening and triage of benign-neoplastic, malignant-neoplastic, and non-neoplastic skin conditions for Fitzpatrick IV-VI skin types. Methods: A set of 163 non-standardized clinical photographs of skin disease manifestations from patients with Fitzpatrick IV-VI skin types were obtained through a publicly available dataset (Scale AI and MIT Research Lab, “Fitzpatrick 17 Dataset”). All photos were diagnosed by a specialist and categorized into three disease classes: benign-neoplastic, malignant-neoplastic, or non-neoplastic. There were 23, 14, and 122 cases of each disease class, respectively. Results: Overall, the AI was able to classify the disease classes with a high degree of accuracy for the Top 1 diagnosis (86.50%). Based on its first prediction, the AI demonstrated the greatest accuracy when classifying non-neoplastic conditions (90.98%), high accuracy of detecting malignant-neoplastic conditions (77.78%), and moderate accuracy of classifying benign-neoplastic conditions (69.57%). Conclusion: The AI had an overall accuracy of 86.50% in diagnosing skin disease in Fitzpatrick IV-VI skin types. This is an improvement over reported clinician diagnostic accuracy of 44.3% in darker skin types. Incorporating AI into front-line screening of skin conditions could thereby assist in patient triage and shorten the time to accurate diagnosis.

Solar forecast error can be represented in electric utility production cost modeling to assess impacts of uncertainty in different scenarios. We use reforecasts (a.k.a., historical forecasts, hindcasts) that were developed to be concurrent with synthetic solar generation profiles (matching each hour in the same year), along with asynchronous forecasts (i.e., with errors remapped from different hours and/or years), to explore impacts on model results. We demonstrate that production cost increases non-linearly with forecast error, and that our method for remapping asynchronous forecast errors to a solar generation profile produces results that are similar to the concurrent forecasts, but with about 20\% lower cost impacts due to forecast error.

Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the “utility” of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vsUncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, namely CT scans of head and neck and prostate MRs. Uncertainty heatmaps (i.e. predictive entropy) are evaluated using ROC and Precision-Recall curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available on https://github.com/prerakmody/ bayesuncertainty-error-correspondence.

Glaucoma, an abnormality in the eye condition that, if not treated within safe time limit, can result in visual loss. Glaucoma diagnosis requires professionals to identify minor structural changes in the structure of the optic disc and optic cup from retinal fundus images in a short period of time. Deep learning algorithms have been employed effectively in the segmentation of biomedical images and the identification of disease. To accomplish good generalization, model training requires comprehensive annotations, which is a difficult task. The intended objective of the present study is to come up with and train an distinctive multi-task deep learning model for automated fundus image segmentation and classification. The multitask model learns for segmentation task of Optic Disc (OD) and Optic Cup (OC) and classification task for accurate glaucoma detection using both structural and image based features. The multi-task model proposed a modified U-net architecture in which Mobile-Netv2 is used in the encoder part, Graph Convolution Network (GCN) is used in the decoder part, and an attention module (AM) is used to locate the region of interest (ROI) for better feature extraction. The implementation of this model is done using three fundus image datasets such as ORIGA, REFUGE, and DRISTI-GS. The performance of the proposed multi-task model is compared with some existing methods and shows maximum accuracy of 97.43% and AUROC of 0.985 for glaucoma detection task and high quality OD and OC segmented images with dice coefficient of 97.95% and 96.11% respectively for segmentation task.

This study explores the use of Bayesian penalized regression models in analyzing high-dimensional Raman spectroscopy data for disease detection, showcasing superior accuracy compared to traditional machine learning methods. The findings introduce a groundbreaking approach that revolutionizes disease diagnosis by leveraging Bayesian analysis and shrinkage priors, enabling more precise and effective identification of infections in saliva or blood serum samples.

This paper presents the simulated study of 72Ah battery bank, where the possibile causes of faults are analyzed  due to varying temp. conditions from 22º Celsius to 59º Celsius (71.6º F to 138.2º F), charging conditions, which can lead to short-circuit, potentially causing electrical shock, fire hazard, personal injury,property damage etc. Each cell is 3.7 V, 6.66 Wh,1800 mA.The system comprises of 400 cells in 40 parallel arrays with 10 cells in each array and four battery management system (BMS) designs were used in the simualtion. The short-circuit study has been divided into two fault categories. First one due to faults inside the design of battery management system (BMS) alone in which nine faults are studied where the simulation was run for 20 hours (72000 seconds) of simulation time for each of the nine fauts, that is 180 hrs or 648000 seconds of simulation time. The second fault cause is attributed due to mixed faults which comprises faults due to batteries in battery bank and due to faulty BMS which resulted in improper charging of the cells. Eleven faults are found in the second case, where again, the simulation was run for 20 hours (72000 seconds) of simulation time for each of the eleven fauts, that is 220 hrs or 792000 seconds. In total, the simulation study is of 1440 000 seconds or 400 hrs or 16.666 days. The data leading to this study and conclusions has also been uploaded.

Vehicular Ad Hoc Networks (VANETs), have developed as a means of facilitating communication between vehicles and the infrastructure around them. A basis for numerous applications aiming at enhancing traffic management, infotainment services, and road safety is provided by VANETs, which use wireless communication technologies to permit the transmission of information between vehicles. A dynamic and self-organizing network can be created by vehicles having onboard communication tools like sensors, GPS receivers, and wireless transceivers. Vehicle-to- Vehicle (V2V) or Vehicle-to-Infrastructure (V2I) communication is made possible by this network, which also enables vehicle-to-infrastructure communication. The foundation of VANETs is the integration of V2V and V2I communication, which enables effective data distribution and collaborative decision-making among infrastructure and vehicles. The primary motivation behind VANETs is to enhance road safety. VANETs can greatly minimise the danger of collisions and increase traffic efficiency by letting vehicles to communicate real-time information about traffic conditions, road hazards, and potential accidents. Additionally, VANETs provide potential for cutting-edge driver assistance technologies like intersection management and collision avoidance, which improve the security and dependability of the transportation system. To ensure the effectiveness and dependability of VANETs, a number of issues related to their deployment must be resolved. The main problems with VANETs are highlighted in this paper along with the solutions developed by researchers and industry professionals.

Quality management is of utmost importance in the healthcare industry as it directly impacts service efficiency and patient outcomes. In recent years, machine learning has emerged as a game-changing innovation in this field. This paper aims to delve into the various applications of machine learning in healthcare, including predictive analytics, clinical decision-making, patient monitoring, and healthcare quality assessment. While machine learning offers numerous advantages, its implementation poses certain challenges, such as concerns regarding data privacy, security, validation, and result interpretation. To address these challenges and explore the effectiveness of machine learning in healthcare management, this study focuses on two hypotheses. Hypothesis 1 investigates the influence of technical components on individuals visiting hospitals for health checkups. The results indicate that, despite the relatively low frequency of health checkups, respondents hold a positive perception of the investigative diagnosis process. This suggests the successful implementation of technical management components in healthcare settings. Moving on to Hypothesis 2, this hypothesis examines the relationship between the availability of medical advice by phone and patient satisfaction with their doctor's treatment. The findings indicate that the availability of telephonic medical advice does not significantly influence patient satisfaction. This highlights the need to explore additional factors that contribute to patient happiness beyond telephonic medical advice alone. The t-test results also support this conclusion, further emphasizing that telephonic medical advice is not a major determinant of patient happiness. Consequently, further research is necessary to identify the key factors that significantly impact patient satisfaction within healthcare settings. In summary, this paper sheds light on the significance of quality management in healthcare, the transformative potential of machine learning, and its applications in various areas of healthcare. The study's findings contribute to a better understanding of the impact of technical components on health checkups and the relationship between telephonic medical advice and patient satisfaction. Further research in this field will help identify and address the critical factors that shape patient satisfaction in healthcare environments. Please note that the above summary is a condensed version of the original text.

This work presents the analysis of short-circuit at solar power plant along with calculations,in three part series. The solar power plant is privately owned with rated capacity of 415 kW capable to produce minimum of 880 kWh , providing electricity to six consumers hospital, market/business center, industrial facility, two sectors comprising 400 households and to the Govt. owned 1 MVA, 11kV/400V, Dyn11 distribution transformer. In this study, twelve faults at certain conditions which bypass protectionary switch gear and trigger short circuit in the plant, as per electrical NEC standards is modeled with practical real-world operating conditions, has been analyzed. The failure of protectionary circuit from faults resulting in complete destruction of the solar plant but the successful protection of the DISCOM substation has been analyzed and presented with parameters. In this study, all the faults excluding the faults due to faulty battery management has been collectively presented which trigger uncontrolled short-circuit. The faults have been deliberately induced in the normal operating conditions and twelve such faults at consumer and grid site have been analyzed.

Microservice architecture is considered a dominant architectural style in current software systems. It views a software system as a collection of small and independent services called microservices. In the highly dynamic enterprise domain, new features have to be introduced regularly and the microservice architectural style achieves quick time-to-market. However, software engineers (e.g., developers or architects) often face the challenge of not having a holistic software architectural view of the system they are working with. This is specifically emphasized in the nature of the microservice architecture, as microservices are small, distributed and the dependencies and interactions between them are high. In our previous work, we demonstrated the requirements for building a Model Driven Architecture (MDA) approach called Microservice Architecture Recovery (MiSAR). This paper starts by reporting on an empirical study conducted on nine microservice systems with the aim of defining the MDA artefacts to semi-automatically recover architectural models of microservice systems. The study resulted in defining a set of: 1) requirements to be present in a metamodel for recovering microservice architecture, which we have implemented incrementally to obtain a MiSAR metamodel and 2) mapping rules to transform the Platform Specific Model to a Platform Independent one. Then, the Model-Driven artefacts (metamodels and transformations) are implemented to support the semi-automatic recovery of microservice architecture. Finally, we evaluated MiSAR in 3 case studies by semi-automatically recovering the architectural models of 3 systems and compared the recovered architectural models with their actual implemented architectures and with their documented ones. We demonstrate that MiSAR artefacts can produce effective and expressive architectural models of implemented microservice systems.

The lock-in amplifier is a commonly used technique for the processing of noisy signals with a known periodicity that involves multiplying the signal with one or more reference signals of the same periodicity and low-pass filtering the results. This enables the recovery of the amplitude and phase of the signal being measured. Another well studied technique to reduce the noise of periodic signals is the coherent averaging method, where the samples of a noisy signal with a known periodicity are averaged coherently. In this paper, a novel system combining both algorithms is proposed. In this approach, the signal is first averaged coherently for a number of cycles (Nca) and then passed through a conventional lock-in with a moving average filter of a whole number of periods of the signal (Nma) as a lowpass filter. In this scenario, the question of how to distribute the incoming samples between the coherent average and the conventional lock-in scheme arises. The mathematical aspects of this issue were evaluated, leading to the conclusion that the calculation results remain identical as long as the product NcaNma remains constant. However, it was observed that the number of operations required for each algorithm varies. By maximizing the number of samples used for the coherent average, the number of multiplications involved can be drastically reduced from NcaNmaM to just M, where M represents the number of samples in a single period of the signal. The drawbacks are the need for space to store the averaged signal, a slower convergence to the result, and an extra cycle in the calculations. Any lockin system with moving average filter can take advantage of these results. Particularly in this study, they are employed to nearly double the achievable clock frequency of a lock-in system implemented on a Cyclone V FPGA, taking it from 119.39 MHz to 216.54 MHz without the use of hardware embedded multipliers.

In this paper, the comparsion between pulse width modulation(PWM), Direct Memory Access(DMA), power supply and current consumption by peripherals and core in five processors viz., SAMD21G18A, TMS570LS0432, AM3352BZCED60, AM1808EZCE and XCZU3EG-1SBVA484E is studied from designing point of view in applications where power generation, power consumption and autonomy is critical. The contrast has been drawn from datasheets, reference manual and minor calculations and is basically a synopsis.