Search

Finding a brain tumor yourself by a human in this day and age by looking through a large quantity of magnetic-resonance-imaging (MRI) images is a procedure that is both exceedingly time consuming and prone to error. It may prevent the patient from receiving the appropriate medical therapy. Again, due to the large number of image datasets involved, completing this work may take a significant amount of time. Because of the striking visual similarity that exists between normal tissue and the cells that comprise brain tumors, the process of segmenting tumour regions can be a challenging endeavor. Therefore, it is absolutely necessary to have a system of automatic tumor detection that is extremely accurate. In this paper, we implement a system for automatically detecting and segmenting brain tumors in 2D MRI scans using a convolutional-neural-network (CNN), classical classifiers, and deeplearning (DL). In order to adequately train the algorithm, we have gathered a broad range of MRI pictures featuring a variety of tumour sizes, locations, forms, and image intensities. This research has been double-checked using the support-vector-machine (SVM) classifier and several different activation approaches (softmax, RMSProp, sigmoid). Since "Python" is a quick and efficient programming language, we use "TensorFlow" and "Keras" to develop our proposed solution. In the course of our work, CNN was able to achieve an accuracy of 99.83%, which is superior to the result that has been attained up until this point. Our CNNbased model will assist medical professionals in accurately detecting brain tumors in MRI scans, which will result in a significant rise in the rate at which patients are treated. [ABSTRACT FROM AUTHOR]

In healthcare, a diagnosis is reached after a thorough physical assessment and analysis of the patient's medicinal history, as well as the utilization of appropriate diagnostic tests and procedures. 1.7 million People worldwide lose their lives every year due to complications from chronic kidney disease (CKD). Despite the availability of other diagnostic approaches, this investigation relies on machine learning because of its superior accuracy. Patients with chronic kidney disease (CKD) who experience health complications like high blood pressure, anemia, mineral-bone disorder, poor nutrition, acid abnormalities, and neurologicalcomplications may benefit from timely and exact recognition of the disease's levels so that they can begin treatment with the most effective medications as soon as possible. Several works have been investigated on the early recognition of CKD utilizing machine-learning (ML) strategies. The accuracy of stage anticipations was not their primary concern. Both binary and multiclass classification methods have been used for stage anticipation in this investigation. Random-Forest (RF), Support-Vector-Machine (SVM), and Decision-Tree (DT) are the prediction models employed. Feature-selection has been carried out through scrutiny of variation and recursive feature elimination utilizing cross-validation (CV). 10-flod CV was utilized to assess the models. Experiments showed that RF utilizing recursive feature removal with CV outperformed SVM and DT. [ABSTRACT FROM AUTHOR]

The internet, like automated tools, has grown to better our daily lives. Interacting IoT products and cyber-physical systems. Generative Adversarial Network's (GANs') generator and discriminator may have different inputs, allowing feedback in supervised models. AI systems use neural networks, and adversarial networks analyse neural network feedback. Cyber-physical production systems (CPPS) herald intelligent manufacturing. CPPS may launch cross-domain attacks since the virtual and real worlds are interwoven. This project addresses enhanced Cyber-Physical System(CPS) feedback structure for Denial-of-Service (DoS) defence. Comparing sensor-controller and controller-to-actuator DoS attack channels shows a swapping system modelling solution for the CPS's complex response feedback. Because of the differential in bandwidth between the two channels and the suspects' limited energy, one person can only launch so many DoS assaults. DoS attacks are old and widespread. Create a layered switching paradigm that employs packet-based transfer techniques to prevent assaults. The discriminator's probability may be used to assess whether feedback samples came from real or fictional data. Cognitive feedback can assess GA feedback data. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are made up of low-energy tiny sensor nodes that can monitor specific environment and transfer data among themselves without the use of a physical media. With the rapid improvements in information technology in recent years, there has been a growing interest among various enterprises in using wireless sensor technologies. Sensor nodes in a WSN with limited energy detect an event, gather data, and send it to the sink node, which is the base node, for further processing and assessment. The design and placement of the sink node can affect a few aspects of WSNs, such as energy consumption and lifetime. Despite their many advantages, WSNs are regarded vulnerable and unprotected. Sinkhole, an adversary attack places serious dangers to the security of such networks within a vast class of varied security assaults that may damage the system's performance. A sinkhole attack is one of the most harmful types of intrusions because it introduces a compromised or created node into the network that tries to entice network traffic by displaying its incorrect and fraudulent routing update. It can also be utilised to send the base station (BS) bogus or fraudulent information. The paper proposes an efficient algorithm for sinkhole attack detection called M-path Sinkhole Attack Detection (MSAD), a solution to the sinkhole problem in WSN. It is suitable for devices with limited resources like sensors. For energy saving in WSNs, the proposed system applies the concept of clustering, and then the proposed simple and light algorithm for intrusion detection algorithm is applied. The proposed method is evaluated against recent algorithms C-LEACH, S-LEACH, ABC and MS-LEACH algorithms and it is found that the proposed method detects the attack with an accuracy rate of 97%, which is higher than other algorithms. [ABSTRACT FROM AUTHOR]

One of the primary challenges in Wireless Sensor Networks (WSNs) is security. This research proposes an efficient fuzzy trust evaluation of cloud collaboration outlier detection (FTCO) in WSNs to ensure security in clustered WSNs. In the beginning, an interval type-2 fuzzy logic controller is used for trusts estimation in an open wireless medium to deal with transmission uncertainty. Then, to prevent fraudulent nodes from becoming cluster heads (CHs), an outlier detection based on density approach is employed to obtain an adaptive trust threshold. Furthermore, a fuzzy-based CHs election mechanism is proposed to strike a balance among security assurance and energy conservation, with a normal sensor node with greater residual energy or lower trust in various nodes having a higher possibility of being the CH. Experimental tests show that our fuzzy-based clustering technique can highly defend the network against assaults from hostile or the compromised nodes within the network and the network lifetime is found to be 40 % higher than other systems. [ABSTRACT FROM AUTHOR]