Generation Of Intelligent Systems Research Articles

The current status of the development of photomemoryristors in the field of neuromorphic vision

As a new type of device, photoelectric memristors have the potential to mimic the human visual system. Researchers have been able to realize image enhancement, noise reduction, recognition and classification functions through optoelectronic modulation, which has a wide range of applications in the fields of neuromorphic computing and image processing. This paper discusses and analyzes the overview of amnesia, the research progress of photoelectric amnesia, as well as the application and prospect of photoelectric amnesia in artificial vision systems. Through the discussion, this paper concludes that photoelectric memristors have important application potentials in visual perception and recognition, intelligent surveillance systems, and medical image analysis. Photoelectric memristors can simulate part of the functions of the human visual system, provide more efficient and accurate image processing solutions, and are expected to bring technological breakthroughs in a number of application areas. By improving the accuracy and efficiency of image recognition and categorization, it can promote the development of intelligent systems. This is not only an important impetus for basic scientific research, but also has a profound impact on practical applications and industrial development. The prospect of wide application of photoelectric memristor means that it has the potential to become a core component of the next generation of intelligent systems, which will drive the progress and change of the whole field of science and technology.

AIS-NIDS: An intelligent and self-sustaining network intrusion detection system

The ever-evolving landscape of network security is continually molded by the dynamic evolution of attack vectors and the relentless emergence of new, highly sophisticated attacks. Attackers consistently employ increasingly advanced techniques, rendering their actions elusive and formidable. In response to this ever-growing threat, the demand for intelligent and autonomous security systems has reached paramount importance. In this paper, we introduce AIS-NIDS (An Intelligent and Self-Sustaining Network Intrusion Detection System), an innovative network intrusion detection system (NIDS) that delves into the realm of packet-level analysis. By doing so, AIS-NIDS is capable of identifying threats with intricate payload-level details, a level of granularity that traditional NIDS relying solely on flow-level data may overlook. The defining feature of AIS-NIDS is its dual functionality, driven by autonomous and intelligent learning. It not only autonomously distinguishes between benign and unknown attacks using machine learning models but also conducts incremental learning, adapting to new attack classes. In essence, AIS-NIDS bridges the gap between traditional NIDS and the next generation of intelligent systems, endowing the system with the capacity for independent decision-making and real-time adaptability in the face of evolving threats. Our extensive experiments stand as a testament to AIS-NIDS’ ability to efficiently manage and identify new attack classes, thus establishing it as a valuable asset in the reinforcement of network infrastructures. Through our experimentation, we have demonstrated the practical efficacy of the proposed approach by simulating a real-world scenario in which certain attack classes are unknown. AIS-NIDS not only effectively identified these unknown threats but also autonomously learned to recognize them as it encountered them, enhancing the system’s capabilities for future encounters with these threats.

A Modeling and Verification Method of Cyber-Physical Systems Based on AADL and Process Algebra

Cyber-Physical Systems (CPS) are the next generation of intelligent systems that integrate information control devices with physical resources. With increasingly close connections between CPS components and frequent interactions, potential defects grow exponentially, rendering the operating environment of CPS unreliable. Therefore, research on methods and theories to ensure the correctness, safety and reliability of CPS is not only an important research topic but also an inevitable challenge. In this paper, we propose a CPS modeling and verification method based on Architecture Analysis & Design Language (AADL) and process algebra to address this challenge. Due to the continuous, time-constrained, stochastic, uncertain and concurrent characteristics of CPS, this paper considers both flexibility and rigor in the modeling process. We first extend the ability of AADL to describe the multiple characteristics of CPS and propose Hybrid Probability-AADL (HP-AADL). Second, this paper introduces conditional execution, conditional interruption and probability operators into Temporal Calculus of Communication Systems (TCCS) and designs a new formal modeling language Hybrid Probability-Temporal Calculus of Communication Systems (HP-TCCS). However, HP-AADL is a semi-formal modeling language that cannot be directly used for formal verification, it cannot strictly guarantee the quality of the established CPS models, including its functional correctness and safety. Therefore, this paper proposes transformation rules from HP-AADL to HP-TCCS, which enables model checking of CPS models described in HP-AADL within HP-TCCS. Additionally, this paper designs a new formal specification language HPAT-Spatial Temporal Logic (HPAT-STL) based on Probabilistic Computation Tree Logic (PCTL) and Spatial Logic, which characterizes the temporal, probabilistic and spatial properties of CPS model. To achieve formal verification of HP-TCCS model and HPAT-STL formulas, this paper proposes a model checking algorithm HPAT-Model Checking Algorithm (HPAT-MCA). Finally, we discuss a typical CPS example to demonstrate the effectiveness of our proposed method in ensuring correct, safe and reliable CPS.

Hygrothermic Wood Actuated Robotic Hand.

Stimulus-responsive actuators play a vital role in the new generation of intelligent systems. However, poor mechanical performance, complicated fabrication processes, and the inability to complex deformation limit their practical applications. Herein, these challenges are overcome via designing a strong hygrothermic wood actuator with asymmetric water affinity. The actuator is readily constructed by sandwiching polypyrrole-coated wood with a Ni complex hygroscopic gel top layer for moisture absorption and a polyimide bottom layer as the water barrier. The resulting hygrothermic wood spontaneously stretches and bends itself in response to moisture and thermal/light stimulation. A robotic hand and a series of grippers made of hygrothermic wood demonstrate dexterous object-hand interactions during grasping and holding, while the reversible hygrothermic property allows the actuator to be potentially applied in fire rescue scenarios to rescue trapped objects. A combination of good mechanical properties, multi-stimulus-response, complex deformation, wide working temperature range, low manufacturing cost, and biocompatibility are simultaneously realized by one device. It is thus believed that such a strong wood actuator will open up a new avenue for building intelligent robotic hand systems.

Robustness Assessment of Cyber–Physical System with Different Interdependent Mechanisms

Cyber–physical systems (CPSs) are a new generation of intelligent system that integrate communication, control and computation functions and are widely used in traditional infrastructure networks, such as power network, transportation network and others. In order to ensure the stable operation and improve the robustness of CPSs, the studies of robustness assessment have attracted much attention from academia. However, previous models assume that the failure propagation conforms to a strongly interdependent relationship, and only consider the interaction between nodes, while ignoring the interaction between nodes and links. In this paper, we develop a novel simulation model with the consideration of both the coupling modes and the failure propagation objects. Based on the simulation model, we study how the interdependent mechanisms, failure propagation probability and protection strategies affect the robustness of CPSs. The simulations of our proposed model are demonstrated in a test CPS formed by coupling two classical complex networks. Compared with previous models, our proposed model shows different performances and comprehensively characterizes the interdependent relationship of CPSs. In detail, disassortative coupling shows the worst performance and the CPS becomes more sensitive to failure propagation when Node–Link is selected as the failure propagation object. In addition, compared to the communication network, the power network is more sensitive to failure propagation. Protecting electrical nodes is a more effective way to strengthen the robustness of CPSs when conservation resources are limited. Our work provides useful advice to operators on how to effectively design and protect a CPS.

Recurrent Neural Networks with Continuous Learning in Problems of News Streams Multifunctional Processing

The main task of using neural networks is the prompt and accurate solution of various creative tasks, including the analysis and synthesis of news flows, while maintaining the continuity of learning. The result of such processing can be digests, filtered news streams, as well as event forecasts that allow for proactivity in management decisions. Known methods of news processing by neural networks and technical solutions that implement them do not fully provide a solution to the problems that arise in this area. It is necessary to expand their functionality, and improve the space-time signal binding in recurrent neural networks. When processing news flows, simultaneously with continuous training of recurrent neural networks, selection, recognition, restoration, prediction and synthesis of news should be carried out. To reduce the severity of the problem, a promising method of multifunctional processing of news flows is proposed using recurrent neural networks with a logical organization of layers and continuous learning. The method is based on the development of associative processing of textual information in streaming recurrent neural networks with controlled elements. The key features of this method are the multifunctional processing of information flows with changing laws of news appearance. The method provides for operational selection, recognition, restoration, forecasting and synthesis of news based on deep associative continuous processing of links between text elements. The neural network system that implements the proposed method differs from the known solutions by new elements, connections between them, as well as by the functions performed. The results of the experiments confirmed the extended functionality of the method. New features of processing news texts by streaming RNNs are revealed. The proposed solutions can be used to create a new generation of intelligent systems not only for word processing, but also for other types of information.

Методы и средства параллельной обработки событий для построения систем мониторинга безопасности нового поколения

Parallel event processing methods and tools needed for creating new generation systems of security monitoring are analyzed. Possibilities of data processing for intrusion detection based on functional approach are considered. Based on the results of the analysis, the specifi cation of the main stages of the parallel event processing and the scheme of their implementation as part of new generation intelligent systems of security monitoring are presented.

Abstract 1925: DrugCell: A visible neural network to guide personalized medicine

Abstract Many potential cancer therapies fail during clinical trials, in part due to difficulty in predicting how different cancers will respond to a given drug. Here we develop DrugCell, a “visible” neural network (VNN) that predicts anti-cancer drug responses by modeling the hierarchical organization of a human cancer cell. Using 509,294 examples of different cancer cell drug treatments, we trained a novel branched neural network (NN). The first branch is a VNN which represents the human cancer cell by structurally mirroring the hierarchical organization of cellular subsystems with collections of neurons representing protein complexes, signaling pathways, and cellular functions. During training, this VNN learns which cellular subsystems contribute to therapeutic responses based on the mutational profile of the genome. The second NN is fully connected and models the chemical structure of each drug. These two NNs connect to a series of fully connected layers that simulate a cellular drug treatment. DrugCell outperformed ElasticNet as well as a matched structure random model. Analysis of the top layer of the VNN showed that DrugCell learned cancer cell states that explain well described chemogenetic relationships and in some cases learned tissue types from the underlying mutational profiles. When running simulations with DrugCell, genotypes and chemical structures induce differential patterns of subsystem activity, allowing for in silico investigations into the molecular mechanisms underlying cancer drug responses. For example, we found that the pathways mediating sensitivity to etoposide included MAPK signaling, PI3K/AKT signaling and regulation of histone deacetylation. Consistent with these inferences, combinations of etoposide with an AKT, MEK or HDAC inhibitor were highly synergistic across multiple cell lines. Similar results were observed upon CRISPR/Cas9-mediated knockdown of key genes in these pathways. We also tested the generalizability of DrugCell to more patient-relevant contexts by evaluating its ability to predict effective mono- and combination therapies. For example, DrugCell was able to accurately predict monotherapy response in leukemia patient samples across a panel of drugs. DrugCell suggested combinations of sorafenib and DNA damaging agents or tandutinib and PI3K/MTOR inhibitors to be effective combination therapies in this leukemia cohort. Subsequent validation showed that these combinations were highly synergistic across multiple leukemia cell lines. Lastly, DrugCell was able to accurately suggest effective and ineffective drug combinations in a pan-cancer PDX tumor cohort and significantly improve progression-free survival compared to monotherapy. DrugCell serves as an important step towards next generation intelligent systems in drug discovery and personalized medicine. Citation Format: Brent M. Kuenzi, Jisoo Park, Samson Fong, Kyle Sanchez, Jason Kreisberg, Jianzhu Ma, Trey Ideker. DrugCell: A visible neural network to guide personalized medicine [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 1925.

Bayesian Network Based C2P Risk Assessment for Cyber-Physical Systems

Cyber-Physical Systems (CPS) refer to a new generation of intelligent systems with integrated computational performance and physical capabilities. However, with the expansion of system complexity and the enhancement of system openness, most CPS become not only safety-critical but also security-critical since they involv physical objects, computer networks and communications. In the past decade, it is no longer rare to see safety incidents and security attacks happening in industries. Identifying risks in CPS is critical to ensure the normal operation of these systems. The Cyber-to-Physical (C2P) risk is defined as the impact of cyber threats on physical process safety. In this paper, a C2P risk assessment model based on hierarchical Bayesian Network (BN) is proposed, and the feasibility of this model is verified by constructing two undesired event scenarios on a typical CPS. The quantitative risk values are explained and compared through qualitative risk analysis and assessment.

Abstract C006: DrugCell: A visible neural network to guide precision medicine

Abstract Many potential cancer therapies fail during clinical trials, in part due to difficulty in predicting how a particular population of cancer cells will respond to a given drug. Here we develop DrugCell, a “visible” neural network that predicts anti-cancer drug responses by modeling the hierarchical organization of a human cancer cell. We devised a branched visible neural network combining two heterogeneous neural networks. The structure of the first neural network mirrors the hierarchical organization of cellular subsystems (e.g., complexes, pathways and organelles). During training, this neural network learns which cellular subsystems contribute to therapeutic responses based on the mutational profile of the genome. The second neural network is fully connected and models the chemical structure of each drug. These two neural networks connect to a series of small, fully connected layers that simulate a cellular drug treatment conditioned on a genetic mutation landscape. By this design, DrugCell can be used to predict how any cancer cell would respond to any small molecule inhibitor. DrugCell outperformed Elastic Net (rho = 0.80 versus 0.74) while maintaining performance similar to that of a fully connected (black box) neural network (rho = 0.82). When making predictions using DrugCell, genotypes and chemical compound structures induce differential patterns of subsystem activity, enabling in silico investigations of the molecular mechanisms underlying cancer drug response. We therefore applied DrugCell to highlight pathways mediating sensitivity to multiple FDA-approved therapies. Top pathways regulating paclitaxel sensitivity included G2 DNA damage checkpoint, consistent with previous studies showing BRCA1 mediates G2/M arrest in response to paclitaxel, and regulation of TOR signaling, which has previously been described to mediate paclitaxel resistance in multiple cancers. Accordingly, combination of paclitaxel with the mTOR inhibitor, MK8669, was highly synergistic across multiple cell lines. Similarly, pathways mediating sensitivity to topoisomerase II inhibitors included cholinergic receptor signaling and regulation of histone deacetylation. In support of these mechanisms, combination of etoposide, a topoisomerase II inhibitor, with AKT or MEK inhibitors (downstream of the cholinergic receptor) or the HDAC inhibitor vorinostat were highly synergistic across multiple cell lines. Similar results were observed upon CRISPR/Cas9 mediated knockdown of key genes in these pathways. Finally, we used DrugCell to predict effective therapeutic combinations for acute myeloid leukemia patients, leading to identification of drug combinations currently in clinical trials including lenalidomide + DNMT inhibitors and tandutinib + PI3K/MTOR inhibitors. Armed with interpretability and generalizability, DrugCell serves as an important step towards a next generation of intelligent systems in drug discovery and precision medicine. Citation Format: Brent M Kuenzi, Jisoo Park, Samson Fong, Jason Kreisberg, Trey Ideker. DrugCell: A visible neural network to guide precision medicine [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference on Molecular Targets and Cancer Therapeutics; 2019 Oct 26-30; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2019;18(12 Suppl):Abstract nr C006. doi:10.1158/1535-7163.TARG-19-C006

Advances and Emerging Challenges in Cognitive Internet-of-Things

The evolution of Internet of Things (IoT) devices and their adoption in new generation intelligent systems has generated a huge demand for wireless bandwidth. This bandwidth problem is further exacerbated by another characteristics of IoT applications, i.e., IoT devices are usually deployed in massive number, thus leading to an awkward scenario that many bandwidth-hungry devices are chasing after the very limited wireless bandwidth within a small geographic area. As such, cognitive radio has received much attention of the research community as an important means for addressing the bandwidth needs of IoT applications. When enabling IoT devices with cognitive functionalities including spectrum sensing, dynamic spectrum accessing, circumstantial perceiving, and self-learning, one will also need to fully study other critical issues such as standardization, privacy protection, and heterogeneous coexistence. In this article, we investigate the structural frameworks and potential applications of cognitive IoT. We further discuss the spectrum-based functionalities and heterogeneity for cognitive IoT. Security and privacy issues involved in cognitive IoT are also investigated. Finally, we present the key challenges and future direction of research on cognitive-radio-based IoT networks.

IIOT-Based Intelligent Control and Management System for Motorcycle Endurance Test

The Industrial Internet of Things (IIOT) is a new generation intelligent system based on the real-time network and embedded system. It combines the global Internet with the new capabilities of direct control of the physical world to promote the rapid development of manufacturing industry and other industries. In this paper, a four-layer IIOT architecture, that is perception executive layer (data acquisition), cognitive layer (business logic, identification, classification), network layer (communication layer), and control layer (external participation), is proposed aiming to the design goal to realize the intelligent management and remote control of motorcycle ’s endurance test. This architecture has a good guiding role for the design and development of IIOT and service-oriented architecture. On this basis, the paper builds the new Internet of Thing test platform management system with the ability of digital intelligent control, intelligent perception and remote intensive management. The system includes a management platform and five sub-system: front-end data acquisition system, control feedback and processing system, data transmission system, database management system, and cloud management system. By improving the interface capability of external (detection) parameters and establishing protocol relationships, the system become an open system with easy management, upgrading, extension, and compatibility. Thus realized the remote monitoring and control management on the endurance test process, improved the ability of cloud services through the cloud monitoring and management platform, and achieved the test control and management systematic, modular, digital, and intelligent.

Modelo test-bed de simulación y evaluación de criptografía de curva elíptica en redes IPv6 de próxima generación

En la actualidad, las redes móviles e inalámbri­cas de nueva generación, tales como las redes de área personal IPv6 de baja potencia (6LoWPAN), redes de sensores inalámbricos sobre IPv6 y re­des móviles IPv6 jerárquicas se encuentran bajo rigurosa investigación y desarrollo, pues repre­sentan el paso por seguir en la evolución de las redes Machine-to-Machine (M2M), al tiempo que apoyan el acceso de banda ancha de la próxima generación de tecnologías y sistemas inteligentes sobre Internet futuro.Estas redes de nueva generación imponen res­tricciones en cuanto al poder de procesamiento, ancho de banda y recursos de energía, lo que re­presenta una gran limitante en la implementación de mecanismos de seguridad. En este sentido, en lo últimos años han surgido diversas propuestas para la administración de claves, procedimien­tos de firma digital y cifrado de datos basados en curvas elípticas e híper-elípticas, que logran ni­veles de seguridad equivalentes a los algoritmos convencionales basados en algoritmos Diffie-Hellman y Rivest-Shamir-Adleman (RSA), pero que reducen la longitud de clave y, por ende, los recursos computacionales y de red asociados.Este artículo examina los algoritmos basados en criptografía de curvas elípticas (ECC) y su apli­cación a redes móviles e inalámbricas de nueva generación habilitadas para IPv6. Así mismo, describe un modelo de simulación para la eva­luación de ECC, donde se comparan los recursos computacionales necesarios y las limitaciones en mecanismos ligeros de seguridad.

Unraveling the Relationship between Grapes and Health1–4

As described in this Supplement and elsewhere, consumption of grapes or grape products has been associated with various health benefits. Resveratrol is a unique component of grapes. Following our report on potential cancer chemopreventive activity, thousands of studies have been performed to characterize the mode of action of this substance. Nonetheless, scores of additional chemicals are known to be constituents of grapes, several of which are capable of mediating biological responses. Accordingly, when considering grapes and health, a holistic view appears to be more meaningful, taking into account all chemical components, metabolism, biological potential, biodistribution, absorption, processing, etc. To fathom such a massive amount of information, we propose the creation of focused ontologies. Grapes seem reasonable as a test bed for exploring this approach, especially because a fair amount of results are available with whole-grape powder. In essence, by utilizing a next generation intelligent system, attempts can be made to leverage the existing complexity. This approach involves bringing together all available information, together with expert judgment, and processing this information through a computational “engine” or engines to provide suggested solutions (or implicit functional relationships). Accomplishment of this task, employing grapes as a prototype, could lead to broader application by incorporating the myriad of features associated with other fruits and vegetables. The ability to correlate heretofore-uncharacterized “signatures” with biologic outcome could fundamentally transform copious amounts of disparate information into a coherent explanation of human disease prevention.

SensEdu - an Internet course for teaching sensorics

Conventional teaching of sensors, based on lectures, static written materials, laboratories, etc., has become rather difficult recently, at all levels of education. The main objective of the described project is the development of a multimedia supported education material that teaches the application of microelectronics and packaging technologies in designing smart sensor devices for the next generation intelligent systems. The new approach of teaching sensorics tries to exploit all advantages of multimedia computer aided teaching not only for keeping the competitiveness but also in order to overcome the specific difficulties of the particular area. The course material will be available for the technical community, for other university professors for teaching, and also will continuously be developed on the Internet and on CDs. The paper will highlight the structure of the course material and demonstrate the animated sensor examples.

Basic Science in Medical Reasoning: An Artificial Intelligence Approach.

A new generation of intelligent systems is growing up in the community of Artificial Intelligence in Medicine. The main goal of these systems is the representation and use of real theory of diseases, as they are represented in medical textbooks or in scientific articles, rather than the heuristic shortcuts of human experts. In this paper, we will argue that the difficulties in the integration of basic science and clinical knowledge in intelligent systems arise from ontological differences between these kinds of knowledge and that the solution can be found in their dynamic integration during the reasoning process. In order to illustrate this point, we will first describe an epistemological analysis of the interplay between basic science knowledge and clinical knowledge, and then we will provide the example of a computational architecture implementing this view.

Book review: Essentials of Fuzzy Modeling and Control by Ronald R. Yager and Dimitar P. Filev (John Wiley, 1994)

Essentials of Fuzzy Modeling and Control, on its back cover, presents itself as the only comprehensive guide in the field: it "gives you all the concepts, tools, and techniques for fuzzy control and modeling in one volume. The book follows a logical, pedagogically consistent format designed to fully acquaint readers with the entire range of fuzzy concepts, tools, and modeling techniques. While it is an excellent general introduction for students, the authors' ultimate goal is to give researchers an opportunity to acquire everything they need to build the kinds of fuzzy rule-based models used in the development of the controllers now being used for the next generation of intelligent systems."