Abstract: Systems and methods for the creation of human-readable cyber incident reports from cyber incident logs, in which the cyber incident reports may link cyber incidents recorded in a cyber incident log to the existing knowledge sources. To do so, the systems and methods overcome the technical problems of conventional systems as well as the technical problems inherent in adapting artificial intelligence solutions to the creation of cyber incident reports.

Abstract: A gas turbine power generation plant (100; 200; 300; 400; 500; 600) comprising: a gasifier (102) for producing a fuel gas stream (104); a treatment arrangement (110) for treating the fuel gas of the fuel gas stream (104); a combustor (114) for receiving the treated fuel gas stream (116) and for producing a flue gas stream (118); a gas expander unit (120) for receiving the flue gas stream (118), the gas expander unit (120) being configured to be coupled to an electric generator (122); a compressor unit (126a, 126b) for supplying air to one or more of the combustor (114), solid fuel gasifier (102) and gas expander unit (120), one or more of the combustor (114), solid fuel gasifier (102) and gas expander unit (120) being configured to receive an air stream (130) from the compressor unit (126a, 126b); a sensor (134a, 134b, 134c, 134d, 134e, 134f, 134g, 134h, 134i, 134j, 134k) for determining a value of a varying physical quantity; a water fluid injector unit (136a, 136b) for injecting water fluid into one or more

Abstract: Current OT security solutions mostly provide defensive security involving monitoring and network segmentation. However, offensive security, proven effective in IT systems, is not easily applicable to OT systems due to its sensitive nature and high availability requirements. To conduct offensive security measures in OT networks, the concept of Digital Twins emerges as a viable solution but with limited progress in developing virtual replicas that accurately simulate real environments. Further, the process of creating such replicas is inherently complex and time-consuming, often involving extensive manual work. The present invention discloses an environment named as “Battle Twin,” a specialized playground designed for breach and attack simulations specifically designed for OT networks. Battle Twin focuses on mimicking the security posture of the underlying network rather than replicating its production or behavioral aspects.

Abstract: A method and related system for training a machine learning model using a federated learning structure by selectively sharing condensed data between devices includes operations to obtain datasets from client devices comprising a first client device and a second client device and updating a datasets subset to comprise a first dataset. The method further includes updating the datasets subset to comprise a second dataset based on a result indicating that a feature space distance between the first dataset and the second dataset satisfies a set of criteria and sending, to a third client device, the datasets subset comprising the first dataset and the second dataset. The method further includes obtaining, from the third client device, a set of model parameters that is derived from training based on the datasets subset and updating a server version of a machine learning model based on the set of model parameters.

Abstract: Systems and methods are described herein for novel uses and/or improvements to artificial intelligence applications. As one example, systems and methods are described for the use of an artificial intelligence-based solution in identifying fraudulent documents and/or other content. In particular, the systems and methods adapt the artificial intelligence-based solution to overcome the technical problem of insufficient training data and/or solutions that are commensurate with the time frame and resources available.

Abstract: A computer-implemented method for recordation of interaction data is disclosed. The method may include causing, via a remote device, a first electronic application operating on a user device to: monitor activity of a second electronic application operating on the user device; detect, based on the monitoring, an interaction between a user of the user device and an entity via the second electronic application; extract interaction data associated with the detected interaction from the second electronic application; and transmit the extracted interaction data to the remote device.

Abstract: System and method of generating an executable action item in response to natural language dialogue are disclosed herein. A computing system receives a dialogue message from a remote client device of a customer associated with an organization, the dialogue message comprising an utterance indicative of an implied goal. A natural language processor of the computing system parses the dialogue message to identify one or more components contained in the utterance. The planning module of the computing system identifies the implied goal. The computing system generates a plan within a defined solution space. The computing system generates a verification message to the user to confirm the plan. The computing system transmits the verification message to the remote client device of the customer. The computing system updates an event queue with instructions to execute the action item according to the generated plan upon receiving a confirmation message from the remote client device.

Abstract: Apparatuses, methods, and systems for detecting the presence of a beacon are disclosed. An embodiment includes a vehicle that includes a load arm configured to receive a bin, a first detector configured to receive a first wireless signal when the load arm is in a first position, and receive a second wireless signal when the load arm is in a second position, a second detector configured to receive a third wireless signal when the load arm is in the first position, and receive a fourth wireless signal when the load arm is in the second position, and a controller configured to detect presence of the beacon attached to an object within the bin based on the received signal strengths of the first wireless signal, the second wireless signal, the third wireless signal and the fourth wireless signal.

Abstract: The disclosure relates generally to methods and systems for predicting water quality of a river having a varying river ecosystem. Due to multiple and diverse factors, understanding and estimating the water quality of the river stream (river itself) is extremely and technically challenging. The present disclosure discloses a development of a river digital twin model utilizing a multi-modeling approach to comprehensively model the river and its varying ecosystems. The agents encompass entities that directly or indirectly introduce effluents or withdraw water from the river. Agents and their interactions are defined using a combination of behavior rules, correlations, and physics principles, creating the digital twin model that closely mimics the real river system. Physics-based equations are also employed in the present disclosure to capture the dynamics of the river, while relationships between different agents are established.

Abstract: Methods and systems are described herein for minimizing development time in artificial intelligence models by automating model selection based on dataset fittings of time-series data prior to hyperparameter optimization. For example, the system may apply a profiling model using a time-series embedding of the dataset combined with the aggregate statistical profile. In either case, the profiling model may be trained on the scoring policy and/or a time-series embedding of the dataset combined with the aggregate statistical profile to determine a likelihood of the effectiveness of a given model on the given dataset and/or likely hyperparameters for the given model.

Abstract: Methods and systems are described herein for minimizing development time in artificial intelligence models by automating model selection based on dataset fittings of time-series data prior to hyperparameter optimization. The systems and methods described herein aim to reduce the redundancies and improve the efficiencies of model selection, model training, and/or hyperparameter selection. The systems and methods achieve this by using information about the attributes of the time-series dataset that may be used to determine a model that may be most effective at fitting a given dataset. If a model is selected prior to hyperparameter optimization, the time and resources spent training, fitting, and/or tuning models that are not selected can be avoided.

Abstract: Disclosed is a compound of formula (I), in which R1, R2, R3, R4, R5, X1, X2, X3, X4, and X5 are described herein. The small molecule compounds of formula (I) activate the functional activity of relaxin family peptide receptor 2 (RXFP2), thereby providing therapeutic treatments for a variety of disorders, such as a bone disorder, hypogonadism, cryptorchidism, polycystic ovary syndrome, cancer, infertility, or an ocular wound.

Abstract: The present invention relates to an heparanase-binding and heparanase-neutralizing monoclonal antibody (IgG-1 mAb A54), including its epitope (HBD-II) and mode of interaction with heparanase, pharmaceutical composition comprising same, and uses thereof e.g. for inhibiting or treating a disease or disorder associated with heparanase activity, including but not limited to cancer, inflammation, viral infection, diabetes and related complications. The present invention further provides combinatorial cancer therapies, comprising the heparanase-neutralizing mAb and an additional anti-cancer treatment such as chemotherapy or radiation.

Abstract: Systems and methods generate requests for encrypted (e.g., secured) credentials and data using one of a plurality of API plugins that are selected based on an access protocol for a network partition at which requested data is determined to be stored. Through the use of the dynamically-selected API plugins, the systems and methods may provide the aforementioned functions while being compatible with the different access protocols that may be encountered when providing centralized management across a diverse spectrum of user accounts, networks, and/or cloud platforms.

Abstract: A well system and a related method are discussed. The well system, in one aspect, includes a wellbore extending through a subterranean hydrocarbon producing zone, as well as production tubing located in the wellbore, the production tubing including a first inflow control valve configured to regulate a first inflow of hydrocarbons from the subterranean hydrocarbon producing zone into the production tubing. The well system, in accordance with this aspect, further includes a flange coupled to the production tubing and having a fitting positioned proximate a downhole end thereof, and a fiber optic cable installed within the wellbore, an end connector of the fiber optic cable coupled end to end with the fitting of the flange to fix the fiber optic cable relative to the first inflow control valve.

Abstract: In some implementations, a device may utilize a machine learning model to determine a set of candidate manufacturing entities associated with an exchange of an item. The device may cause a first automated action to be performed. The first automated action may include providing information identifying the set of candidate manufacturing entities to a device of a user that is associated with the exchange. The device may receive a response indicating the manufacturing entity associated with item. The device may identify a block in a blockchain associated with the manufacturing entity. The device may map the exchange information to the block to enable the item information associated with the item to be associated with the exchange.

Abstract: Image analysis is a vital field since images can provide contextual, environmental, and emotional factors. Conventional methods are facing challenges in analyzing an image accurately when the image is having lesser data or if the image is having less resolution. Conventional machine learning architectures are computationally intensive when run on high power computing devices for training and inference. The present disclosure provides a robust deep learning model to inference in any given environmental condition. Initially, image data is generated using a pre-trained Generative Adversarial Network (GAN). The GAN receives a plurality of images of varying domain and generates image data. The image data is annotated and segmented to obtain a contextual label map. The contextual label map is given as input to a pre-trained transfer learning model to obtain a plurality of image attributes including number of objects and activity performed by each object.

Abstract: Various well-perforating systems and methods are disclosed incorporating a self-shunting detonator. The detonator may include an electrically-conductive detonator body. A resistor initiator inside the detonator body includes first and second leads. A grounding element inside the detonator body couples the detonator body to the first lead. An electrically-conductive clip coupled to the second lead includes an arm biased to electrical contact with an external surface of the detonator body to shunt the detonator. The arm is moveable away from the detonator body to un-shunt the detonator, such as automatically in response to insertion into a detonator housing.

Abstract: The invention provides stable coronavirus spike proteins. Immunogenic compositions comprising same and the methods of using these immunogenic compositions are also provided.

Abstract: A method for singulating, orientating and distributing tie plates along a section of a track of a railroad is disclosed using a vehicle adapted to travel on rails including a tie plate singulating assembly, a tie plate flipping assembly, a tie plate quarter turn assembly, and a distribution assembly. The tie plate flipping assembly flips shoulder-side down tie plates into a shoulder-side up orientation while maintaining shoulder-side up tie plates in the shoulder-side up orientation. A diverter of the tie plate quarter turn assembly advances tie plates into a rotation inducing abutment resulting in the tie plates turning toward a desired orientation. The distribution assembly distributes tie plates to accumulation slides, controlling distribution with a dealer assembly and orienting discharge assembly to distribute the tie plates in a desired spacing and orientation along the track of a railroad.