China
Africa
Explore chapters and articles related to this topic
Mutation schemes of the hybrid clonal selection algorithm for the reconstruction of gene regulatory networks
Published in Waldemar Wójcik, Sergii Pavlov, Maksat Kalimoldayev, Information Technology in Medical Diagnostics II, 2019
A.O. Fefelov, V.I. Lytvynenko, I.A. Lurie, V.V. Osypenko, I.M. Melnychuk, W. Wójcik, S. Kalimoldayeva
The proposed hybrid algorithm is based on one of the varieties of artificial immune systems – the algorithm of clonal selection (De Castro & Von Zuben 2002). Information in work (Fefelov, Lytvynenko et al. 2017) shows the effect of the addition of a mutation operator to the clonal selection from the algorithm of differential evolution (DE mutations). Here the authors compare the results of the application of various schemes of DE mutation. A step-by-step description of the hybrid algorithm is presented below.
Combined models of artificial immune systems
Published in Waldemar Wójcik, Andrzej Smolarz, Information Technology in Medical Diagnostics, 2017
V.I. Lytvynenko, W. Wójcik, A. Smolarz, B. Suleimenov, M. Junisbekov
Artificial Immune Systems (AIS), as defined by de Castro and Timmis (de Castro 2002) are: “Adaptive systems inspired by theoretical immunology and observed immune functions, principles and models, which are applied to problem solving”. However, AIS are one of many types of algorithms inspired by biological systems, such as neural networks, evolutionary algorithms and swarm intelligence. There are many different types of algorithms within AIS and research to date has focused primarily on the theories of immune networks, clonal selection and negative selection. These theories have been abstracted into various algorithms and applied to a wide variety of application areas such as anomaly detection, pattern recognition, learning and robotics.
Artificial intelligence and immunotherapy
Published in Expert Review of Clinical Immunology, 2019
Since the first introduction of Artificial Intelligence (AI) in 1956, its aim was to tackle problems with human intelligence, but with greater speed and accuracy. AI has been inspired a lot by natural swarm intelligences, such as those observed in groupings of animals and insects. Swarm intelligences not only are observed in our surroundings, but also exist within the human body. For instance, vertebrae immune system can be considered as a swarm intelligence in that it consists of independent, self-organized agents that interact with one another to form a higher intelligence [1]. AI has profited from immune system and artificial immune system has been of use in overcoming challenges such as intrusion detection, self-healing of robots, optimization and anomaly detection. As much as immunology has served the AI, recently AI is being used in many immunological fields. Beside remarkable analytic abilities, antigen and phenotype detection, predicting prognosis and treatment outcomes, etc., are examples where AI is serving the immunologists in the field.
Attack detection and mitigation scheme through novel authentication model enabled optimized neural network in smart healthcare
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2023
The security requirements of IoT health care systems comprise of three phases of operations, such as key generation, authentication of each component of the health care unit. The assurance of privacy cannot be used again with the reasons, such as limited memory, communication bandwidth, and processing power of IoT health care systems, and the possibility to get lost and seized due to the small size of medical sensor nodes (Sahoo et al. 2021). Various problems in the technical side are needed to be resolved in the applications of medical care systems based on IoT. The capacity of data storage and transmission can be reduced by using the compression algorithms. The increased cost of the sensor nodes makes the conventional data compression strategies in applicable in most cases. The method used for compression must be selected with care in such a way that it does not affect the original data. If the original data get affected, it may lead to misdiagnosis and sometimes the confidential heal related data of the patients may be affected. With the limited power of sensor nodes in computation, the conventional encryption and security strategies are found inefficient. Thus, it is necessary for the IoT system to develop an enhanced method for the sensor nodes and the fusion of physiological signals (Azimi et al. 2021). The attack detection through machine learning is developed by several researchers such as artificial immune system (Zaminkar and Fotohi 2020) and Graph Convolutional Network (Behzad et al. 2018), light weight (Kore and Patil 2020), Artificial Neural Network, Decision Tree, Random Forest, and k-Nearest Neighbour (Alrashdi et al. 2019) for secure transmission with more accurate detection.