- Home
- A-Z Publications
- Recent Patents on Engineering
- Previous Issues
- Volume 18, Issue 9, 2024
Recent Patents on Engineering - Volume 18, Issue 9, 2024
Volume 18, Issue 9, 2024
-
-
Medical Image Classification Using DL-based Feature Extraction in IoMT
More LessAim: Recent advances in Artificial Intelligence (AI) and the addition of Deep Learning (DL) have made it possible to analyse both real-time and historical data from the Internet of Things (IoT). Recently, IoT technology has been implemented in healthcare schemes as IoMT to aid in medical diagnoses. Medical image classification is useful for predicting and identifying serious diseases at an early stage, which is crucial in the diagnostic process. Background: When it comes to managing, treating, and preventing illness, medical photographs are an essential element of a patient’s health record. However, it is a difficult issue in computer-based diagnostics to classify images using efficient characteristics. Objective: The patent study aimed to develop a deep learning-based classification model for feature extraction. Methods: Levy flight optimization is employed to pick the weight for the classification model optimally. At the end of the day, the optimal weight led to a better classification result and a higher degree of precision when analyzing medical photos for disease. Results: We tested the proposed results in MATLAB and compared them with conventional methods of classification. The suggested model’s best results include 97.71% accuracy on a brain dataset and 97.2% accuracy on an Alzheimer’s disease dataset. Conclusion: The proposed algorithm’s high rate of convergence proves that it can successfully balance the exploration and exploitation phases by avoiding capturing in local optimization and classifying thresholds rapidly. In light of the need for improved accuracy, precision, and computational speed in clinical picture classification, a novel approach based on soft sets has been presented.
-
-
-
A Secure Network with Minimization of Energy for E-healthcare Application in IoMT
Authors: Rajanikanth Aluvalu, Uma Maheswari V., Mohan A. and Yadaiah BalagoniAims: Protect patient healthcare records. Background: The adaptability of the digital healthcare system is a major factor in its recent rise in popularity. Utilizing the digital healthcare system has resulted in an ever-increasing number of healthcare apps. The Internet of Medical Things (IoMT) is a newly emerging digital healthcare system using various biomedical sensors and the cutting-edge capabilities of wireless systems and cloud computing. Since IoMT can exchange data between various connecting nodes thanks to the combination of other technologies, security and energy consumption provide the greatest challenge to the IoMT infrastructure. Objective: Reduce the cost of communication in order to strengthen defenses against unauthorized access and increase energy efficiency. Method: This patent study provides a protocol for protecting patients; medical records called the request-type-based energy-aware framework (Re-EAF) based on patent. The primary goal is to reduce the cost of communication in order to strengthen defences against unauthorized access and increase energy efficiency. An identifying unit called a request-type energy aware framework has been proposed. The proposed method avoids treating all requests the same by instead characterizing them based on the identified criteria and characteristics. Using Constrained Application Protocol (CoAP), remote patient monitoring can increase the safety of gathered data. Results: Using Constrained Application Protocol (CoAP), remote patient monitoring can increase the safety of gathered data. Using a software-defined networking (SDN) framework, our research ensures that data and requests are sent and received as effectively and efficiently as possible while conserving energy. Conclusion: In this research, the transmitted healthcare data is encrypted via cipher Block-chaining. The experimental study demonstrates that the suggested Re-EAF consumes less energy while producing a higher throughput than conventional methods.
-
-
-
Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep Learning Algorithm
Background: The majority of wearable technology that is present in various patents for Internet of Medical Things (IoMT) health monitoring systems is introduced to recognize various bodily indicators. The enumerated patents indicate that monitored values are sent to a central server, where they are all treated by experts at the appropriate moment. Therefore, a new patent technique by expanding the use of wireless devices, has been discovered that such communication technologies can recognize specific depression traits and mood swings. Objectives: The major objective of the proposed method is to analyze the disputes that arise in the characteristics of an individual by observing the leveling periods that are identified from the processed image. In addition, the rate of data transfer in case of any dispute is maximized therefore recognition problem is solved at a minimized distance. Further, the steady state probability values are achieved at low delay thus minimizing the dropout packets in the monitored system using IoMT and LSTM. Methods: A balanced record with four distinct parameters—such as livelihood, self-reliance, correlation, and precision—is employed with the projected model on IoMT for depression identification. As a result, high data transfer rates and low distance separation are used to process the identification framework. Additionally, by combining an original matrix representation with the input feature set using LSTM, a novel framework with great efficiency is created. Results: In order to assess the results of IoMT using LSTM, four situations are split apart and their probability ratios are calculated. The results of each situation are then contrasted with the current methodology, and it is found that when there is a low dropout ratio, depression in a person is quickly diagnosed. Conclusion: The comparison analysis demonstrates that the proposed method, when compared to the current method, offers the best-compromised outcomes at roughly 64%.
-
-
-
IoT-based Ubiquitous Healthcare System with Intelligent Approach to an Epidemic
Background: The recent pandemic has shown its different shades across various solicitations, especially in the healthcare sector. It has a great impact on transforming the traditional healthcare architecture, which is based on the physical approaching model, into the modern or remote healthcare system. The remote healthcare approach is quite achievable now by utilizing multiple modern technological paradigms like AI, Cloud Computing, Feature Learning, the Internet of Things, etc. Accordingly, the pharmaceutical section is the most fascinating province to be inspected by medical experts in restoring the evolutionary healthcare approaches. COVID-19 has created chaos in the society for which many unexpected deaths occur due to delays in medication and the improper prognosis at an irreverent plan. As medical management applications have become ubiquitous in nature and technology-oriented, patient monitoring systems are getting more popular among medical actors. Method: The Internet of Things (IoT) has achieved the solution criteria for providing such a huge service across the globe at any time and in any place. A quite feasible and approachable framework has evolved through this work regarding hardware development and predictive patent analysis. The desired model illustrates various approaches to the development of a wearable sensor medium that will be directly attached to the body of the patients. These sensor mediums are mostly accountable for observing body parameters like blood pressure, heart rate, temperature, etc., and transmit these data to the cloud storage via various intermediate steps. The storage medium in the cloud will be storing the sensor-acquired data in a time-to-time manner for a detailed analysis. Further, the stored data will be normalized and processed across various predictive models. Results and Conclusion: The model with the best accuracy will be treated as the resultant model among the numerous predictive models deployed in the cloud. During the hardware development process, several hardware modules are discussed. After receiving sensor-acquired data, it will be processed by the cloud's multiple machine-learning models. Finally, thorough analytics will be developed based on a meticulous examination of the patients' cardinal, essential, and fundamental data and communicated to the appropriate physicians for action. This model will then be used for the data dissemination procedure, in which an alarm message will be issued to the appropriate authorities.
-
-
-
Gene Variant Analysis for the Detection of Hemophilia: A Literature Review
Authors: N. Sumathi and K. Anitha KumariBackground: Proteins act as clotting factors to stop bleeding at the lesion site. This implies that people with hemophilia tend to bleed longer after an injury and are more prone to internal bleeding. Depending on the type of hemophilia, individuals with hemophilia will have lesser amounts of factor VIII or factor IX than people without it. Objective: By analyzing the gene variant of hemophilia affected patient we can predict the severity of disease at earlier stage which helps to avoid further complications. Methods: Predicting hemophilia can be achieved through potential technologies like machine learning. Using these technologies, one can detect and predict the severity of hemophilia, such as mild, moderate, or severe. Results: By comparing the methods used in protein structure analysis, the advantages and limitations of methods used in protein structure analysis are discussed. Conclusion: The best practices in predicting hemophilia are highlighted in this patent study and particularly aim at the basic understanding of applying the potential technologies in the prediction of hemophilia and its severity. This study represents recent research on hemophilia and the use of different machine learning techniques (MLT) in this area.
-
-
-
Network Anomaly Detection using Autoencoder on Various Datasets: A Comprehensive Review
Authors: Richa Singh, Nidhi Srivastava and Ashwani KumarThe scientific community is currently very concerned about information and communication technology security because any assault or network anomaly can have a remarkable collision on a number of areas, including national security, the storage of private data, social welfare, economic concerns, and more. As a result, many strategies and approaches for this goal have been developed over time, making the anomaly detection domain a large research subject. The primary concern of this patent study is to review the most crucial elements relating to anomaly detection, including an overview of background analysis and a core study on the most important approaches, procedures, and systems in the field. To make the structure of this survey easier to understand, the domain of anomaly detection was examined along with five dimensions: Detection methods in network traffic, objectives of the patent paper, various datasets used, accuracy, and open issues/gaps. The gap which has been identified after the survey can be extended as a future scope might be helpful for the researcher.
-
-
-
Performance Analysis of Semi-refined Digital Forearm Modeling and Simplified Forearm Model in Electromagnetic Simulation
Authors: Jiangming Kuang, Yuping Qin and Shuang ZhangObjective: The objective of this patent study is to analyze the performance difference between simplified and digital models based on medical images. Methods: According to the characteristics of human anatomy, the finite element simulation software COMSOL Multiphysics 5.5 was employed to construct a simplified arm model using cylinders and a digital arm model based on Chinese digital human regarding electroacupuncture therapy as an example. A comparative analysis was then performed considering three aspects: mesh number, potential distribution, and resource consumption. Results: Through analysis, the digital arm model based on Chinese digital human requires significantly more mesh cells than the simplified arm model in mesh generation. Meanwhile, because the digital arm model based on the Chinese digital human fully expresses the nonuniformity of the tissue distribution in a real human body, its signal distribution in its interior is also relatively scattered, and the coupling potential slightly differs at the electrode vertex with the smallest change. In addition, the digital arm model has much higher resource consumption and computer hardware resource requirements compared with the simplified arm model. Conclusion: As a result, the digital model based on the Chinese digital human can more fully express the tissue distribution and electrical signal characteristics of a real human body. However, due to its high computational requirements, appropriate simplification can be selected to improve the computational efficiency of the model in practical applications.
-
-
-
Geometric Feature of DNA Sequences
By Hongjie XuBackground: The primary goal of molecular phylogenetics is to characterize the similarity/ dissimilarity of DNA sequences. Existing sequence comparison methods with some patented are mostly alignment-based and remain computationally arduous. Objective: In this patent study, we propose a novel alignment-free approach based on a previous DNA curve representation without degeneracy. Method: The method combines two important geometric elements that describe the global and local features of the curve, respectively. It allows us to use a 24-dimensional vector called a characterization vector to numerically characterize a DNA sequence. We then measure the dissimilarity/ similarity of various DNA sequences by the Euclidean distances between their characterization vectors. Results: We compare our approach with other existing algorithms on 4 data sets including COVID-19, and find that our apporach can produce consistent results and is faster than the alignment-based methods. Conclusion: The method stated in this study, can assist in analyzing biological molecular sequences efficiently and will be helpful to molecular biologists.
-
-
-
An IoT-based Intelligent Irrigation and Weather Forecasting System
Authors: Sirivella S. Srikar and Pachipala YellammaIntroduction: The most crucial ingredient in agriculture is water. The amount of water that plants require must be provided to them. However, growers alternate between giving their plants more water than they truly need and giving them less and partly because they become overwatered due to meteorological circumstances like unexpected rainfall. Methods: We employ an IoT-based intelligent irrigation system to get around this problem. It includes a centrifugal pump, a motor driver board, and a soil moisture sensor with YL69 probes. When the soil moisture level drops, the pump automatically delivers water to the plants with minimal human involvement. The electrical conductivity theory is how the sensor for soil moisture functions. A DHT11 sensor and a barometer, which provide information on the local temperature, humidity, and atmospheric pressure, are both parts of the weather monitoring system with the help of this, farmers can forecast the local weather and plan their irrigation accordingly. Results: In this patent study, the thing speak API enables us to continually monitor information from a computer or mobile device, and the ESP8266 module links the complete system to the internet. Through this approach, water waste is reduced, and irrigation efficiency is increased while crop health and quality are preserved. Conclusion: Overall, this research demonstrated how the Internet of Things-based intelligent irrigation systems may enhance agricultural water management. By combining soil moisture monitoring, weather monitoring, and autonomous management, we may develop irrigation techniques that are more precise, effective and patent leading to higher crop yields and sustainable agricultural practices.
-
-
-
Two-Dimensional MXene-Based Functional Composites for Photocatalysts: Current Status and Perspectives
Authors: Yingchun Chen, Mengjie Liang and Chi ZhangMXenes, as novel two-dimensional (2D) transition metal carbides, nitrides or carbonitrides, have excellent metal conductivity, high carrier mobility, and surface-terminated groups regulated band structure. It can be thus used as a cocatalyst in photocatalytic systems to improve the photocatalytic properties. This patent review represented recent research progress on the controllable construction of MXene-based functional composites with zero-dimensional (0D), onedimensional (1D), 2D, and three-dimensional (3D) semiconductor photocatalysts and their applications for photocatalysts. Extensive information related to 2D MXene-Based composites for photocatalysts and their associated patents were collected. The construction methods and photocatalytic enhancement mechanisms of 2D MXene-based composite photocatalysts were given. Due to their excellent physical and chemical properties, 2D MXene composites have been widely used in pollutant removal, hydrogen production, CO2 reduction, and nitrogen fixation. Through the construction of 2D MXene-based functional composite photocatalysts with novel structures and excellent performance, it provides a new perspective for the design and construction of high-efficiency photocatalysts. The future research directions of MXene-based composite photocatalysts was proposed.
-
-
-
Evolution of Nuvoton Microcontroller-based Education Board
Authors: Hudaverdi E. Elp and Remzi InanBackground: The novel coronavirus pandemic has not only affected people's health. The pandemic has also affected their social life and work. For all the reasons mentioned, international trade has suffered and is still in the process of recovery. Objective: Especially in the semiconductor industry, many manufacturers postponed their deliveries to future periods and this triggered the chip crisis. Many hightech industries, including the automotive industry, were deeply affected by the consequences of the crisis, with factories halting or slowing down production. Despite the shortage of chip stocks, Nuvoton has a large amount of Microcontroller Units (MCUs), but due to the shortage of resources, education and libraries, software developers have not been able to integrate their products in a limited time. Methods: In this paper, the Nuvoton Education Board has presented 20 common examples for embedded software developers and beginners. Results: The PCB is designed considering all modules connected to separate General Purpose Input Output (GPIO) pins to make multiple module examples without changing the peripherals and pin configuration of the MCU. Clock configuration has been simplified and unnecessary details have been meticulously removed to make the examples easily understandable. Nuvoton NuMaker M263KI V1.3 was added on the designed PCB. Conclusion: The PCB contains almost all the necessary electronics to learn embedded software and use Nuvoton MCUs in industrial projects. The board is supported with user interfaces and printed documentation. The codes are explained with command lines to teach users even small details. A patent application has been filed for the proposed education board.
-
-
-
Study on Influencing Factors of Liquid Carbon Dioxide Blasting in Rock Cutting
Authors: Jianwei Li, Guiwen Zhang, Huadong Liu, Shanglong Zhang and Xuansheng ChengBackground: At present, although some scholars have studied liquid carbon dioxide blasting, there are still some problems to be solved, such as the influencing factors of the liquid carbon dioxide blasting effect. Based on the project of Jiu’e railway, this paper studies the influencing factors of liquid carbon dioxide blasting in rock cutting. Objective: The patent study aims to show the influence of different blasting hole depths and jet directions on the effect of liquid carbon dioxide blasting and fracture development. Methods: Considering the influence of jet direction and different blasting hole depth on liquid carbon dioxide blasting in rock cutting, the fracture development law at different blasting hole depths is analyzed, the stress characteristics of jet direction and non-jet direction are discussed, and fracture development process is analyzed in detail from the viewpoint of energy. Moreover, related patents on liquid carbon dioxide blasting devices are also reviewed. The research on law of fracture development and optimal blasting hole depth is the highlight of this paper. Results: The influence of different blasting hole depths, jet directions on effect of liquid carbon dioxide blasting and fracture development is analyzed, When the depth of blasting hole is 2.5 m, the fractures can extend to bench surface but cannot extend to the bottom of the excavation surface. When the hole depth is 5.0 m, the fractures cannot extend to the bench surface. The fractures can be extended to the bottom of the excavation face and the bench surface when the blasting hole depth is 4.0. Moreover, the liquid carbon dioxide blasting can effectively blast the rock cutting, and the optimal blasting hole depth is 4 m. Conclusion: Through the analysis results, considering the influencing factors of fracture number, fracture length and consumption of blasting energy, a blasting hole depth of 4 m is considered the best option.
-
-
-
Bi-directional Projection Framework for Fast Single Image Super Resolution
Authors: Ying Zhou, Zhichao Zheng and Quansen SunBackground: Collaborative Representation (CR) has been widely used in Single Image Super Resolution (SISR) with the assumption that Low-resolution (LR) and high-resolution (HR) features can be linearly represented by neighborhoods and share consistent CR coefficients. Numerous patents and journal papers have been published. However, this CR consistency does not hold in the reconstruction phase, which leads to degraded performance. Methods: To fulfill this gap, we propose a novel bi-directional projection model (BDPM) to establish a bi-directional mapping between LR and HR features without any consistency constraint. The multiple projection matrices are offline computed to reduce reconstruction time greatly. We further develop several strategies to extract features and group neighborhoods such that local structures can be preserved better. Results: Compared to the learning-based methods, BDPM is about 2 to 10 times faster and compared to the reconstruction-based methods, it is about 500 to 2,000 times faster. Conclusion: The empirical studies verify the effectiveness of BDPM and extensive experimental results demonstrate that BDPM achieves better SISR performance than many state-of-the-arts.
-