作者：
R. Krishna NayakG. Srinivasa RaoResearch Scholar
Department of Computer Science and Engineering GITAM (Deemed to be University) GITAM School of Technology Visakhapatnam Andhra Pradesh 530045 India Associate Professor
Department of Computer Science and Engineering GITAM (Deemed to be University) GITAM School of Technology Visakhapatnam Andhra Pradesh 530045 India
Cloud computing platform enables online services for data sharing, storage, and resource utilization to the cloud users. However, the major problem that occurs during cloud access is the server gets underloaded or ove...
详细信息
Cloud computing platform enables online services for data sharing, storage, and resource utilization to the cloud users. However, the major problem that occurs during cloud access is the server gets underloaded or overloaded affecting the processing time and resulting in the reduced quality of service (QoS). Specifically, the user tasks are allocated among the Virtual Machines (VMs) with diverse lengths, starting times, and processing times. Hence, load balancing is essential for ensuring that all the VMs are utilized appropriately. Consequently, this research proposes multi-objective optimization for load balancing while considering the network parameters such as makespan reduction, balanced CPU utilization, energy consumption minimization and throughput maximization. Specifically, the proposed MO-survivors’ optimization algorithm exploits the multi-objective fitness function considering the QoS constraints for selecting the VMs based on the capacity for achieving the parallel load execution. Further, the proposed algorithm effectively handles the network traffic, offers proper utilization of resources, manages the load capacity, and reduces the overprovision of infrastructure. The experimental outcomes reveals that the proposed MO-survivors’ optimization for load balancing exhibited better performance with 30 VMs attaining an improvement of 1.77 % over TSMGWO in terms of throughput, and attaining the makespan reduction of 223.03 s with TSMGWO. Further, the proposed approach revealed a reduced degree imbalance of 0.012 over TSMGWO and improved the resource utilization by 5.36 % compared to TSMGWO. Moreover, the results reveal the outstanding performance of the proposed MO-survivors optimization over the other existing algorithms used in the analysis.
This paper presents the summary of the Sclera Segmentation and Joint Recognition Benchmarking Competition (SSRBC 2023) held in conjunction with IEEE International Joint Conference on Biometrics (IJCB 2023). Different ...
This paper presents the summary of the Sclera Segmentation and Joint Recognition Benchmarking Competition (SSRBC 2023) held in conjunction with IEEE International Joint Conference on Biometrics (IJCB 2023). Different from the previous editions of the competition, SSRBC 2023 not only explored the performance of the latest and most advanced sclera segmentation models, but also studied the impact of segmentation quality on recognition performance. Five groups took part in SSRBC 2023 and submitted a total of six segmentation models and one recognition technique for scoring. The submitted solutions included a wide variety of conceptually diverse deep-learning models and were rigorously tested on three publicly available datasets, i.e., MASD, SBVPI and MOBIUS. Most of the segmentation models achieved encouraging segmentation and recognition performance. Most importantly, we observed that better segmentation results always translate into better verification performance.
The many real-world applications of machine learning-based approaches over the past several decades have shown the potential of data-driven methodology in a variety of computing fields. Higher education computer curri...
详细信息
ISBN:
(数字)9798331541583
ISBN:
(纸本)9798331541590
The many real-world applications of machine learning-based approaches over the past several decades have shown the potential of data-driven methodology in a variety of computing fields. Higher education computer curricula are beginning to include machine learning, and more and more institutions are incorporating it into K–12 computer instruction. Given the growing prevalence of computational learning in K–12 computer teaching, it is imperative to investigate how agency and intuition develop in these kinds of settings. However, considering the challenges educators and schools already have in integrating conventional learning, understanding the challenges connected with teaching algorithms for learning across grades K–12 provides an even more challenging barrier for computer education research. the curriculum's incorporation of artificial intelligence and *** article outlines the potential for data mining education in grades K–12. These advancements include modifications to technology, philosophy, and practice. The study puts the present findings in the larger framework of computing education and discusses some differences that K–12 computer educators should keep in mind while tackling this issue. The study focuses on key components of the fundamental shift that is required in order to successfully integrate machine learning into more thorough K–12 computing curricula. A critical first step is to abandon the notion that next-generation computational thinking requires rule-based, "traditional" programming.
Additionally to the extensive use in clinical medicine, biological age (BA) in legal medicine is used to assess unknown chronological age (CA) in applications where identification documents are not available. Automati...
详细信息
The paper describes an innovative technique of monitoring updates on the health of people with dementia by integrating smart sensing technologies with a cloud-based platform. Because dementia is a degenerative neurops...
The paper describes an innovative technique of monitoring updates on the health of people with dementia by integrating smart sensing technologies with a cloud-based platform. Because dementia is a degenerative neuropsychiatric disease that develops with time, constant patient monitoring is essential for ensuring the health and safety of those living with the condition. The proposed system uses smart sensing devices, including wearable and ambient sensors, to monitor dementia patients' health in real-time. Data like heart rates, movements used, and ambient conditions are collected and sent to a server in the cloud for analysis. The camera can monitor and analyze visual data, capture crucial information, and help evaluate the patient's well-being. Multiple patients can be monitored effectively in real time because of the cloud-based system's scalability, accessibility, and storage capacities. For healthcare providers to recognize irregular movements, identify possible risks to health, and implement preventative measures, doctors utilize the moment data analytics devices to gather valuable insights from the acquired data. In addition, the cloud-based solution improves collaborative care and enhances patient support by allowing for continuous communication and information sent among caregivers, doctors, nurses, and family members. Predefined thresholds or anomalous occurrences may trigger alerts and messages, allowing for quick action in reaction to emergencies. Modern technology and data analytics increase the health and happiness of people with dementia.
Context: Agriculture stands as a pivotal driver of economic progress within a nation, yet the realm of technical advancements within this sector remains distressingly neglected by a multitude of governments. While far...
Context: Agriculture stands as a pivotal driver of economic progress within a nation, yet the realm of technical advancements within this sector remains distressingly neglected by a multitude of governments. While farmers contribute untiring efforts to tend to their fields, substantial time is squandered on tasks like irrigation and safeguarding crops from birds and animal threats [1, 2]. This unwavering dedication often exacts a toll on farmers’ health, leading to ailments and respiratory issues stemming from exposure to noxious gases emitted by certain crops. Extensive research endeavours [3-9] have been undertaken to alleviate the burdens faced by farmers. These efforts, however, frequently culminate in singular applications such as automated irrigation systems or electric perimeters for crop protection. A subset of researchers has also delved into probing the prevalence of harmful gases across agricultural fields. This paper proposes an innovative approach to address these challenges through the utilization of Internet of Things (IoT) technology. Objective: The proposed solution canters on a NodeMCU powered intelligent crop field Monitoring-Protection-Alert (MPA) system, which serves as a technical path to revolutionize farming practices. The core objective underpinning the proposed system is the acquisition of real-time insights emanating from the crop field. This critical initiative empowers farmers with timely and accurate data, enabling them to make informed and precise decisions pertaining to their agricultural domain. Methods: By seamlessly integrating various sensors, the system detects the presence of birds, animals, and noxious gases in real-time. Furthermore, it enhances crop productivity by continuously monitoring soil parameters, including temperature and moisture levels, thereby optimizing irrigation processes. For seamless communication, the system is fortified with a GSM module that promptly alerts farmers about potential threats to their crops.
作者：
Nishath AnsariAmjan ShaikPatluri HarikaBoga VarasreeK. PurnachandSaikumar TaraAssistant Professor
Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Professor
Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Assistant Professor
Department of Computer Science and Engineering Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Assistant Professor
Department of Information Technology Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Associate Professor
Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Associate Professor
Department of Electronics and Communication Engineering CMR Technical campus Hyderabad Telangana India
Reinforcement learning has been giving new strategies to ad-lib in the fields of medication and the drug industry. It is probably the best strategy among all the AI strategies. Reinforcement learning has been compelli...
Reinforcement learning has been giving new strategies to ad-lib in the fields of medication and the drug industry. It is probably the best strategy among all the AI strategies. Reinforcement learning has been compelling to discover strategies that could treat the immense number of deadly infections. In this paper, a detailed new methodology about what Reinforcement Leaning and what is drug revelation and what are various techniques utilized in Reinforcement learning, how Reinforcement learning could be utilized in different utilization of medication plan such as target identification, hit discovery, hit to lead, lead optimization. The consequence of the paper illustrates the summarized data of different approaches for the development and discovery of drugs. A clear illustration of various work done in the field of drug discovery, discuss different pros and cons of Reinforcement learning as well emphasize primary challenges need to handle and how to defeat them in the future.
In this fast-pacing world one of the substantial problems faced is the drastic increase in waste generation and ensuring efficient and rational management of waste. Recycling tasks reduce waste production, mitigate th...
In this fast-pacing world one of the substantial problems faced is the drastic increase in waste generation and ensuring efficient and rational management of waste. Recycling tasks reduce waste production, mitigate the environment and improve the whole nation’s prosperity in the future. Inappropriate handling and discarding of useless materials have led to the contamination of groundwater and defiled the land resources. Therefore, it is vital that the methods and processes involved in waste collection and segregation is examined as the present-day disposal system is inefficient, time consuming, cumbersome and not completely viable due to their large amount. The proposed model provides a way of solving the above stated problems by detecting, identifying and segregating the waste materials. The proposed system is an automated waste classifier which uses a deep learning-based object detection model to classify objects into different categories. Using YOLOv5, an object detection algorithm the waste can be identified successfully from the image taken with the help of a camera and classify them into categories. This result is then sent to a segregation unit which categorizes the waste into the designated bin by rotating the conveyor belt using a motor. The proposed model operated at a Mean Average Precision(mAP) of 0.726 and an F1-Score of 0.83. This method of segregation of waste will enable faster ways to recycle the waste and save time and resources.
Diabetes Mellitus (DM) is a metabolic disorder characterized by aberrant insulin secretion and function, resulting in elevated blood glucose levels and chronic damage to organs. Diabetic Foot Ulcers (DFU) are a signif...
Diabetes Mellitus (DM) is a metabolic disorder characterized by aberrant insulin secretion and function, resulting in elevated blood glucose levels and chronic damage to organs. Diabetic Foot Ulcers (DFU) are a significant complication of DM, frequently leading to lower limb amputation if not effectively managed. DFU imposes a substantial burden on patients, families, and healthcare systems, particularly in developing nations where treatment expenses can be overwhelming. Leveraging machine learning and deep learning techniques allows for accurate identification of foot ulcers in diabetic individuals, facilitating early detection and prompt treatment, consequently mitigating the risk of complications and improving the overall quality of life for DM patients. The study focuses on utilizing deep learning and machine learning models to classify diabetic foot ulcers. The results reveal that the RESNET18 model outperforms the SVM models, achieving an accuracy of 97.9%. The study suggests that deep learning models, notably the RESNET18, are more suitable for identifying diabetic foot ulcers.
This article considers the task of determining the priority of factors influencing the selection of information technology for distance education. Since this process is one of those ones that are difficult to describe...
详细信息
ISBN:
(纸本)9798350334326
This article considers the task of determining the priority of factors influencing the selection of information technology for distance education. Since this process is one of those ones that are difficult to describe in the form of mathematical formulas, it is suggested to use the graph method and the method of analysis of hierarchies for calculations. These methods have shown themselves to be good in solving this kind of *** the course of the conducted survey among the participants of the educational process, eight factors are singled out, which, according to the correspondents, have a certain weight when selecting the information technology for distance education. Thus, such factors are singled out: communication tools; educational facilities; user data management; usability; adaptation; technical aspects; administration; course management. As the conducted studies show, the factor of usability acquires the highest priority level. The factor of course management, which is on the fourth step of the hierarchy, is at a lower level in terms of importance. According to calculations, the factors of the first hierarchy level turn out to be the least important: communication tools; educational facilities. These research findings are important for those educational institutions that are at a crossroads in their choice and they will help to decide on such information technologies.
暂无评论