Search

Lots of women all over the globe are affected by thinning hair, and the number of females suffering from the disease is growing per year. Another important component in the development of thinning hair is genetics. One of the most important goals is to make a clinical condition. For example, in the area of medicine, categorization is critical since one of the primary goals of the doctor is to determine whether or not a patient suffers from an illness. Alopecia areata is a kind of chronic illness that causes baldness in the affected region. AA may cause baldness for a variety of causes thus, testing may be essential to confirm if it is the source of the loss of hair. Machine learning approaches have shown promise in a variety of fields, including dermatology, and may be useful in identifying alopecia areata for better prediction and diagnosis. Proper detection of an illness is also influenced by the fluctuating character of illness signs. Deep learning algorithms for identifying hair loss levels in males using facial pictures in this research. In this situation, a special training database, including face photos with varying degrees of baldness, has been generated. Furthermore, despite the limited accessibility of hairs in such images, a matching approach for mechanically categorizing face images to design categorization tables of male baldness from the medical field is provided. The outcomes of the experiments demonstrate the potential and efficiency for medical, security, and business apps. Related work in machine learning for hair illness categorization has also been addressed. The main objective of this study to analyze several machine learning and deep learning strategies for the identification of alopecia as well as in humans, as well as to determine the accuracy of extracting features methodologies.

Biomedical document feature extraction and ranking play an essential role in the real-time document key phrase extraction and ranking. International classification of disease (ICD-10) is a list of medical related terms such as disease symptoms, abnormal discovery and disease signs. In most of the conventional methods, finding, extraction and ranking of biomedical disease patterns with the gene terms help to rank the phrase or document. However, the contextual disease patterns of these methods areindependent of gene entities, disease entities and drug discovery codes for document ranking and summarization.Conventional word embedding models such as gain ratio, entropy,Glove, chi-square and probabilistic measures are used to find the essential key terms and its relationships using static gene disease databases.The main objective of the proposed work is to optimize the word embedding model along with the key-phrase ranking and classification. Most of the biomedical applications use pre-trained gene-disease database with limited number of gene names for keyphrase ranking and classification process. In this work, an integrated gene-disease database and ICD drug database codes are used to train the model using the optimized SVM classification model and Bayesian estimation model.

In underwater acoustic sensor networks (UASNs), the reliable transfer of data from the source nodes located underwater to the destination nodes at the surface through the network of intermediate nodes is a significant challenge due to various unique characteristics of UASN such as continuous mobility of sensor nodes, increased propagation delay, restriction in energy, and heightened interference. Recently, the location-based opportunistic routing protocols seem to show potential by providing commendable quality of service (QoS) in the underwater environment. This study initially reviews all the latest location-based opportunistic routing protocols proposed for UASNs and discusses its possible limitations and challenges. Most of the existing works focus either on improving the QoS or on energy efficiency, and the few hybrid protocols that focus on both parameters are too complex with increased overhead and lack techniques to overcome communication voids. Further, this study proposes and discusses an easy-to-implement energy-efficient location-based opportunistic routing protocol (EELORP) that can work efficiently for various applications of UASN-assisted Internet of Underwater Things (IoUTs) platforms with reduced delay. We simulate the protocol in Aqua-Sim, and the results obtained show better performance than existing protocols in terms of QoS and energy efficiency.

In this paper, the proposed algorithm to detect the bias from the datasets and to mitigate the bias in the datasets was observed. The consequences of this work shows that not only bias in a model can be decreased without forfeiting model performance rate, but improving the performance. Class imbalance, KL divergence, sample disparity and Kolmogorov-Smirnov (KS) are the pre-training metrics used in the work. Each metric is given weightage and the features are detected based on the maximum weightage. The model is trained to learn the unbiased data and shows the significant improvement in the performance of the system. ROC curve, False Positive Rate and False Negative Rate is used for bias trade-off. The comparison between FPR and FNR before mitigating bias and after mitigating bias is performed and its results are significantly improved.

Our lifestyles are increasingly incorporating the Internet of Things. Every year, a growing number of gadgets gain connectivity and communication capabilities via the Internet. There are currently more than 400 million IoT devices in use worldwide, and by 2025, that number is anticipated to reach 1.5 billion. Keeping track of all IoT devices and figuring out which one to connect to in order to make service requests is getting more and more challenging. The device could also end up malfunctioning or performing poorly. We must determine the most effective method of data storage in order to provide the groundwork for how to build trust amongst devices.

Colon cancer is thought about as the third most regularly identified cancer after Brest and lung cancer. Most colon cancers are adenocarcinomas developing from adenomatous polyps, grow on the intima of the colon. The standard procedure for polyp detection is colonoscopy, where the success of the standard colonoscopy depends on the colonoscopist experience and other environmental factors. Nonetheless, throughout colonoscopy procedures, a considerable number (8-37%) of polyps are missed due to human mistakes, and these missed polyps are the prospective reason for colorectal cancer cells. In the last few years, many research groups developed deep learning-based computer-aided (CAD) systems that recommended many techniques for automated polyp detection, localization, and segmentation. Still, accurate polyp detection, segmentation is required to minimize polyp miss out rates. This paper suggested a Super-Resolution Generative Adversarial Network (SRGAN) assisted Encoder-Decoder network for fully automated colon polyp segmentation from colonoscopic images. The proposed deep learning model incorporates the SRGAN in the up-sampling process to achieve more accurate polyp segmentation. We examined our model on the publicly available benchmark datasets CVC-ColonDB and Warwick- QU. The model accomplished a dice score of 0.948 on the CVC-ColonDB dataset, surpassed the recently advanced state-of-the-art (SOTA) techniques. When it is evaluated on the Warwick-QU dataset, it attains a Dice Score of 0.936 on part A and 0.895 on Part B. Our model showed more accurate results for sessile and smaller-sized polyps.

The utilization of energy in blockchain division is high as resource allocation models are using this technology and the rundown of resource utilization cases is continually developing. The communicated and permanent nature of blockchain innovation might be utilized to quicken the progressing change to increasingly decentralized and digitalized vitality frameworks and to address a portion of the difficulties the business is confronting in providing security in identification of authorized users and resource allocation transactions among the authorized users. The allocated resources to the users need to be recorded, otherwise the attackers may use them for malicious operations. In any case, blockchain is a developing innovation and it is viewed as a basic vulnerability by numerous users as the difficulties and chances of execution are still to a great extent. There is in this way an absence of information and shortage of dynamic gadgets for getting why, when and how the innovation can include significant worth. The proposed Resource Allocation for Authorized Users using Time specific Blockchain Methodology (RAAUTBM) performs resource allocation to authorized users to avoid malicious actions among blockchain-based use cases and increase practical information about how blockchain could be actualized. The RAAUTBM model verifies all the users for allotting access to the system. The proposed model allots the resources only to the authorized users and to identify the malicious users and remove them from the framework. The resources once allotted to a user remains for a time interval and then the resource is re-allotted to other authorized users for avoiding delay. Resource exchanges in this segment are known to be dull and wasteful, to a limited extent because of the absence of promoted straightforwardness. This research work centers around the advancement of a blockchain application that can improve the resource exchange procedure among authorized users. The proposed model is compared with the traditional methods and the results demonstrate that the proposed model is effective in allocating resources only to the authorized users.

The use of advanced technologies has increased drastically to maintain any sensitive records related to education, health, or finance. It helps to protect the data from unauthorized access by attackers. However, all the existing advanced technologies face some issues because of their uncertainties. These technologies have some lapses to provide privacy, attack-free, transparency, reliability, and flexibility. These characteristics are essential while managing any sensitive data like educational certificates or medical certificates. Hence, we designed an Industry 5.0 based blockchain application to manage medical certificates using Remix Ethereum blockchain in this paper. This application also employs a distributed application (DApp) that uses a test RPC-based Ethereum blockchain and user expert system as a knowledge agent. The main strength of this work is the maintenance of existing certificates over a blockchain with the creation of new certificates that use logistic Map encryption cipher on existing medical certificates while uploading into the blockchain. This application helps to quickly analyze the birth, death, and sick rate as per certain features like location and year.

Ti-6Al-4V is classified among the most commonly used Ti-alloys and is extensively used in aerospace and medical industries where low-density, high strength and outstanding corrosion resistance are required. This material cannot be processed by conventional machining methods because of its high strength. Abrasive Waterjet Machining, abbreviated as AWJM, is an unconventional machining process suitable for machining Ti-6Al-4V as it generates less heat affected zone. The quality of AWJM is governed by process parameters, the selection of these parameters is critical in this technology to achieve the desirable output measures. This paper provides an experimental investigation for the performance analysis of process parameters on machining Ti-6Al-4V using abrasive waterjet technology. In order to select appropriate parameters, a mathematical equations were developed using Regression Investigation Method (RIM) Artificial Neural Network (ANN) procedures. Based on the input and output data collected from the experiments, modelling is done and tested for the different set of data to ensure the accuracy. These mathematical models can be used to identify the static and dynamic behavior of the process. These models will further help in simulating the process, expanding the design facilities and studying the physical and chemical variation in the process. Models provide understanding the operations, control methods and the possible optimization. The developed models also help in documenting the performance of the existing system.

The Internet of Underwater Things (IoUT) is the connection of underwater objects/sensor nodes to gather the information about various attributes. The collection of data is performed by the sensing nodes while they are deployed in underwater scenario and the sensed data is sent to the sink node having acoustic and radio modems through the acoustic channel. The data forwarding in the underwater scenarios follow a particular routing mechanism to address the concern of limited energy of sensor nodes. In this paper, we address the application, challenges and also the brief review of various routing algorithms proposed for Underwater Wireless Sensor Network (UWSN). This study will not only cover the state-of-the-art proposed routing techniques for UWSN but also the fundamental concepts of UWSN. It is discerned from the proposed study that there is a need to develop energy efficient data routing techniques for UWSNs to increase the lifespan of underwater sensor nodes.

Abrasive waterjet machining (AWJM) is one of the unconventional machining practices and is used widely in industries. The key output performance measures in this technique are depth of cut and surface roughness. This paper presents the experimental investigation on machining conditions of abrasive waterjet process in machining mild steel. Taguchi’s method of design of experiments was used to select input process parameters by varying water pressure, traverse speed, abrasive mass flow rate and standoff distance. The depth of cut and surface roughness were measured using Sigma Scope 500 profile projector and surface roughness tester respectively. After getting the required data from the experimental setup the same data is fed to the artificial neural networks and back propagation algorithm procedure is used to train the data using MATLAB programming package. It is observed that the artificial neural network (ANN) model was able to foresee the new set of data. This mathematical modelling tool can be used to predict dynamic varying different types of input to identify the stability of the system.

Post Quantum Cryptography (sometimes referred to as a quantum-proof, quantum-safe or quantum-resistant) refers to cryptographic algorithms (usually public-key algorithms) that are thought to be secure against an attack by a quantum computer. PQC is all about preparing for the era of quantum computing by updating existing mathematical-based algorithms and standards. The cryptographic community is working on post-quantum cryptography in order to provide alternatives using hard mathematical problems that cannot be broken by quantum computers. A hybrid scheme is recommended to ease the transition into the post-quantum era. A hybrid scheme is a combination of a traditional and a post-quantum scheme. The resulting scheme is at least as secure as one of the schemes used. In hybrid key establishment, two independent key exchanges are performed one with a traditional scheme like ECDHE and one with a post-quantum scheme like NewHope [1]. In this paper, we propose possible best-fit hybrid digital signatures.

Colorectal cancer (CRC) is a sort of cancer that begins in the rectum or large intestine, generally showing more impact on adults. It generally starts as tiny, non-cancerous (benign) lumps of cells called polyps that form on the colon's inward lining. Detection of colorectal cancers in early stages can reduce the risk of mortality rate. Detection of polyps through screening tests may fail because of the length of the rectum and the tiny size of the polyps. Computer-based biomedical imagining might help the radiologists sift through the information and analyse clinical pathology images better. The majority of research focuses on gland segmentation using CNN architectures, but accuracy is still challenging. In this work, encoder-decoder-based deep learning model was proposed for morphological colon gland segmentation. This research of enhanced SegNet architecture improved the system’s overall performance and, when tested on the standard benchmark Warwick-QU dataset for colonoscopy images. We trained the system by the training dataset consisting of 7225 images, and evaluation of the model is done using a test dataset divided into two parts: A (60 images), B (20 images). The results show that the proposed model is comparable to all the existing models regarding the same dataset and attain segmentation accuracy of 0.924 on Part A, 0.861 on Part B. The shape similarity of 83.145 on Part A, 88.642 on Part B, is considered adequate compared with the existing methods.

The ability of wireless sensor network (WSN) can be observed in different fields like patient wearable monitoring, health applications, intruder detection, combat monitoring and battlefield surveillance in the last few years. In such applications, WSN contains a wide range of sensor nodes, which will monitor continuously, and passes the data to end-user through base station (BS) or sink node (SN). In such applications where users are unattended to replace the sensor node frequently, that indicates users can expect long-lasting of WSN. So in this paper, we concentrated on long-lasting of WSN, by minimizing the energy utilization of sensor node in WSN. So we are applying the clustering technique. So, clustering will minimize the energy usage of the sensor node, such that it will improve the lifetime of WSN. In this, we introduced our proposed protocol “Low Energy Utilization with Dynamic Cluster Head (LEU-DCH)” which reduces the energy consumption of sensor nodes. Besides, we also have shown the best way of selecting how many clusters we need.

In future studies like IoT, Wireless Sensor Networks (WSN) plays a important role, such that it will connect millions of devices to exchange the sensed data from one place to another place. So, WSN comprises countless minimal effort wireless sensor nodes. Based on the application, we can deploy the sensor nodes into the environment, these nodes will sense the data and perform computations, and it sends back to the user through the base station (BS). Here, the constraint is that the sensor node will run on a battery, where life is very less. So, the challenging task is how to improve the life span of the sensor node. If the sensor node involves in unnecessary communication, utilization of the battery was also increasing, then the lifespan of the sensor node will decrease, and finally, it leads to death. So, the life of the entire WSN depends on the lifetime of sensor nodes. Today, we have so much researches on how to improve life span of sensor node. In this research work, we are addressing a clear comparison of clustering and without clustering. And also, in some papers for clustering, they prefer a static cluster head (CH). So, we are Analyzing and given a comparison of the static cluster head with our proposed Dynamic Cluster head.

The death of cells occurs when the blood flow is reduced among the brain resulting in a weak condition causing a medical emergency usually defined as a stroke. Stroke is the major common condition which is nowadays resulting in the maximum number of deaths among the world in the present-day situations. Stroke is involved with various uncertain constituents also these are identified by examination of pretentious specific people. In analyzing and dividing the type of infections caused by these strokes, there have been various testings done to reduce the risk factors. Depending on these predictions, understanding the symptoms causing the stroke can be implemented by four machine learning algorithms by considering the person's physical and analysis of the medicals. Of all the strokes, ischemic stroke was the deadliest which is causing major damage to adults worldwide. The major part lies in separate projections in identifying the treatment decisions that are to be followed during the acute phase of the stroke. In identifying the treatment methodologies, there is definite model algorithm for cerebral ischemia after subarachnoid hemorrhage (SAH) which is predicted earlier. In such scenerio this is improvised by developing a temporal unsupervised feature engineering approach. From this we can conclude the improved precision over standard features with 80% trained data, and 20% testing data.

The government utilizes the development of ICT in providing public facilities through a financial information system. Therefore, all public services become integrated, thus generating profits such as cost and time efficiency. This research focuses on the uneven application of financial information systems (FIS) in various regions and identifies factors that support such services’ optimization. This research explains the model of financial information systems adoption by expanding the technology acceptance model with self-efficacy and system quality. If people perceive that financial information systems are accessible and believe that they can operate the system, they will use it properly. Besides, the quality of the FIS is also the determinant of smart-government implementation. The more quality of the system provided, the more the number of people who use the system.

The blockchain, with its own attributes, has got a lot of consideration toward the start of its introduction to the world and been applied in numerous fields. Simultaneously, its security issues are uncovered continually and digital attacks have caused huge troubles in it. At present, there is little concern and research in the field of system security of the blockchain. This paper presents the uses of blockchain in wireless systems which deliberately dissect the security of each layer of the blockchain and possible digital attacks, expose the difficulties brought by the blockchain to arrange oversight, and sum up exploring the progress in providing security to the ad hoc networks. The proposed model portrays the group model of blockchain administrations; their unwavering quality is affirmed based on test information. Data communication is known to be an inefficient activity as far as message multifaceted nature, and overhead is observed. When data transmission is initiated and all nodes using the same available route, congestion in the network is increased. Notwithstanding the effect on the framework execution, inefficient model may have serious impacts on results with respect to security and affability of the blockchain. In the proposed work, an efficient model is designed that can be used in ad hoc networks to reduce the overhead of the network. As the overhead or congestion in the network is more, the performance of the ad hoc system will be decreased. To avoid such circumstances and to improve the network performance, the proposed Congestion Control Reduction with Blocks Linking (CCRBL) for generating blockchain is introduced. The proposed method is compared with the traditional congestion control systems in terms of congestion levels, same route usage levels, congestion reduction levels and throughput, and the results show that the proposed method is more efficient in congestion reduction.

Mobile Ad Hoc Networks (MANETs) are infrastructure-less networks that are mainly used for establishing communication during the situation where wired network fails. Security related information collection is a fundamental part of the identification of attacks in Mobile Ad Hoc Networks (MANETs). A node should find accessible routes to remaining nodes for information assortment and gather security related information during route discovery for choosing secured routes. During data communication, malicious nodes enter the network and cause disturbances during data transmission and reduce the performance of the system. In this manuscript, a Time Interval Based Blockchain Model (TIBBM) for security related information assortment that identifies malicious nodes in the MANET is proposed. The proposed model builds the Blockchain information structure which is utilized to distinguish malicious nodes at specified time intervals. To perform a malicious node identification process, a Network Block Monitoring Node (NBMN) is selected after route selection and this node will monitor the blocks created by the nodes in the routing table. At long last, NBMN node understands the location of malicious nodes by utilizing the Blocks created. The proposed model is compared with the traditional malicious node identification model and the results show that the proposed model exhibits better performance in malicious node detection.

Advanced privacy preservation approaches are used to be protecting sensitive and important data of various application areas like Communication systems, Healthcare, Education and Financial Sector. In the Healthcare area, the important and sensitive task is a medical certificate that acts as medical evidence of a person which helps for many purposes. Deception in issuance as well as in verification of medical certificates has existed for a long time in health care centers due to lack of reliable mechanisms. In the issue of medical evidence to a person, needs to consider a method which has advanced features like transparency, immutable, reliable and decentralized properties. Hence, in this paper, blockchain technology is used to design and develop a model with advanced features for reducing forgery in medical pieces of evidence. In this approach, a regulatory body will authorize the Health care centers (Hospitals) for issuing medical certificates to the required persons in a decentralized approach. Here smart contract system helps to verify the certificate authenticity from any authorized one in the world. The main strength of the paper gives the Blockchain-based model as a solution to the issue related to proof of a certificate of medical evidence.

In recent times, malware detection mechanism systems of mobile smart devices are getting growing concentration from researchers. With the quick expansion of malwares found in mobile devices, preventing the secrecy of mobile users is incredibly imperative and necessary. Intrusion detection systems are programming devices that consequently assemble information, dissect it and recognize such occurrences. These systems advanced to intrusion aversion systems (IPS) including extra counteractive action capacities. In Intrusion detection systems, accuracy rate plays a significant role in measuring the effectiveness of an approach. One of the motivations of this study is to increase the true positive as well as reducing the false-positive rates beyond other studies.