Abstract: In one respect, there is provided a system for classifying malware. The system may include a data processor and a memory. The memory may include program code that provides operations when executed by the processor. The operations may include: providing, to a display, contextual information associated with a file to at least enable a classification of the file, when a malware classifier is unable to classify the file; receiving, in response to the providing of the contextual information, the classification of the file; and updating, based at least on the received classification of the file, the malware classifier to enable the malware classifier to classify the file. Methods and articles of manufacture, including computer program products, are also provided.

Abstract: A toilet is disclosed which, in general, includes a toilet bowl and a housing. The toilet bowl includes multiple apertures and a blower, wherein the blower is fluidly connected to one or more of the apertures. The housing is fluidly connected to the blower. The housing includes a gas permeable substrate and a gas chemical sensor. The gas permeable substrate comprises a first side, a second side, intercalated sorbent media, and a rapid desorption heater.

Abstract: Using a recurrent neural network (RNN) that has been trained to a satisfactory level of performance, highly discriminative features can be extracted by running a sample through the RNN, and then extracting a final hidden state hh where i is the number of instructions of the sample. This resulting feature vector may then be concatenated with the other hand-engineered features, and a larger classifier may then be trained on hand-engineered as well as automatically determined features. Related apparatus, systems, techniques and articles are also described.

Abstract: A synthetic aperture photoplethysmography (PPG) sensor is disclosed. A group or matrix of contiguous PPG sensors located on a toilet seat are conditionally combined based on sensor measurements. Conditional combinations may be based on timing data and signal-to-noise ratio data of each of the PPG measurements. Measurements associated with the conditional combinations are then used to determine a cardiac function of a toilet user.

Abstract: A toilet seat with handles is disclosed. The handles include light transmitters and light receivers. The light transmitters and receivers may be used to determine blood oxygen saturation levels and heart rate of a toilet seat user. Ultrasonic transmitters and receivers in the toilet seat handle are also disclosed for determining bone density of a toilet seat user. The handles may be retractable and may include UV sanitation.

Abstract: In one respect, there is provided a system for classifying an instruction sequence with a machine learning model. The system may include at least one processor and at least one memory. The memory may include program code that provides operations when executed by the at least one processor. The operations may include: processing an instruction sequence with a trained machine learning model configured to detect one or more interdependencies amongst a plurality of tokens in the instruction sequence and determine a classification for the instruction sequence based on the one or more interdependencies amongst the plurality of tokens; and providing, as an output, the classification of the instruction sequence. Related methods and articles of manufacture, including computer program products, are also provided.

Abstract: In one respect, there is provided a system for training a neural network adapted for classifying one or more instruction sequences. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: training, based at least on training data, a machine learning model to detect one or more predetermined interdependencies amongst a plurality of tokens in the training data; and providing the trained machine learning model to enable classification of one or more instruction sequences. Related methods and articles of manufacture, including computer program products, are also provided.

Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The at least one memory may include program code that provides operations when executed by the at least one processor. The operations may include: training, based on a training data, a machine learning model to enable the machine learning model to determine whether at least one container file includes at least one file rendering the at least one container file malicious; and providing the trained machine learning model to enable the determination of whether the at least one container file includes at least one file rendering the at least one container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.

Abstract: In one respect, there is provided a system for training a machine learning model to detect malicious container files. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one processor provides operations including: processing a container file with a trained machine learning model, wherein the trained machine learning is trained to determine a classification for the container file indicative of whether the container file includes at least one file rendering the container file malicious; and providing, as an output by the trained machine learning model, an indication of whether the container file includes the at least one file rendering the container file malicious. Related methods and articles of manufacture, including computer program products, are also disclosed.

Abstract: A medical toilet with fingerprint reading handles is disclosed. The handles extend from a side surface of a seat on the medical toilet allowing a toilet seat user to use the fingerprint reader while sitting on the medical toilet. The handles enable authentication of a user and loading of specific medical toilet functionality associated with the authenticated user. The fingerprint readers are also used to determine cardiac functions of the user in addition to authentication of the user. The handles may be retractable and may include UV sanitation.

Abstract: A power supply circuitry compatible with both source type dimmer controls and sink type dimmer controls is provided. The power supply circuitry includes an internal voltage source, a dimmer control type detection circuit, and a configuration circuit. The dimmer control type detection circuit detects a type of a dimmer control that is electrically coupled to the power supply circuitry. The configuration circuit can turn off the internal voltage source upon determining the dimmer control is of the sink type and turn on the internal voltage source upon determining the dimmer control is of the source type. Thus, the internal voltage source may generate a voltage as the dimming control signal. The dimming control signal is fed to a microcontroller that may, for example, generate a series of pulse signals that is provided to a power converter of a load (e.g., light-emitting diode luminaries) based on the dimming control signal.

Abstract: The guitar pick holder is configured for use with a stringed musical instrument. The guitar pick holder handle holds and controls one or more plectrum. The guitar pick holder allows the one or more plectrum to be used simultaneously. The guitar pick holder: 1) enables the simultaneous plucking of two or more strings selected from the plurality of strings by a plurality of plectrum; 2) enables the simultaneous plucking of a single string selected from the plurality of strings by a plurality of plectrum; and 3) enables the simultaneous plucking of two or more strings by a plurality of coins. The guitar pick holder comprises a hand grip, one or more plectrum slots, and one or more reverb slots. The one or more plectrum slots and the one or more reverb slots are formed within the hand grip.

Abstract: A method and testing apparatus determine receding contact angles of liquids on surfaces by depositing a liquid in a manner whereby the volume of the drop is increased through stepwise addition of smaller drops. Each increment of volume growth causes the perimeter of the drop to advance across the surface. The incremental volume elements impart sufficient energy to the growing drop such that the drop perimeter expands beyond its equilibrium diameter for that volume. The drop perimeter tends to contract between volume additions as the excess energy is dissipated. The method and testing apparatus determine the receding contact angle between the incremental volume additions.

Abstract: A power supply for a smooth power output level transitioning includes an energy storage circuit for temporarily storing electric energy for driving a load, a semiconductor switch for pulse-width modulation (PWM) switching, and a digital PWM controller. The digital PWM controller generates a driving waveform to regulate on and off status of the semiconductor switch. The driving waveform toggles between PWM periods of a first type and PWM periods of a second type, and gradually adjusts a ratio of numbers of the PWM periods of the two types over time. The toggling driving waveform achieves one or more intermediate finer power output level that cannot be realized by a single type of PWM period with an intermediate duty cycle, due to the minimum item unit of the driving waveform limited by a clock rate of the digital PWM controller.

Abstract: A power supply circuitry compatible with both source type dimmer controls and sink type dimmer controls is provided. The power supply circuitry includes an internal voltage source, a dimmer control type detection circuit, and a configuration circuit. The dimmer control type detection circuit detects a type of a dimmer control that is electrically coupled to the power supply circuitry. The configuration circuit can turn off the internal voltage source upon determining the dimmer control is of the sink type and turn on the internal voltage source upon determining the dimmer control is of the source type. Thus, the internal voltage source may generate a voltage as the dimming control signal. The dimming control signal is fed to a microcontroller that may, for example, generate a series of pulse signals that is provided to a power converter of a load (e.g., light-emitting diode luminaries) based on the dimming control signal.

Abstract: Dynamic location tracking may be performed by a mobile app executing on a mobile computing device. A first geo-fence of a predefined size is set on a mobile operating system of a mobile computing device to notify a mobile app when the first geo-fence is crossed by the mobile computing device. The notification occurs even when the mobile app is suspended or not running. Notification is received from the mobile operating system that the mobile computing device has crossed the first geo-fence. A location of the mobile computing device is received. A second geo-fence is set on a mobile operating system of the mobile computing device based on the location of the mobile computing device.

Abstract: As part of an analysis of the likelihood that a given input (e.g. a file, etc.) includes malicious code, a convolutional neural network can be used to review a sequence of chunks into which an input is divided to assess how best to navigate through the input and to classify parts of the input in a most optimal manner. At least some of the sequence of chunks can be further examined using a recurrent neural network in series with the convolutional neural network to determine how to progress through the sequence of chunks. A state of the at least some of the chunks examined using the recurrent neural network summarized to form an output indicative of the likelihood that the input includes malicious code. Methods, systems, and articles of manufacture are also described.

Abstract: As part of an analysis of the likelihood that a given input (e.g. a file, etc.) includes malicious code, a convolutional neural network can be used to review a sequence of chunks into which an input is divided to assess how best to navigate through the input and to classify parts of the input in a most optimal manner. At least some of the sequence of chunks can be further examined using a recurrent neural network in series with the convolutional neural network to determine how to progress through the sequence of chunks. A state of the at least some of the chunks examined using the recurrent neural network summarized to form an output indicative of the likelihood that the input includes malicious code. Methods, systems, and articles of manufacture are also described.

Abstract: A complementary converter is a switch mode converter circuit that uses one pulse-width modulation (PWM) controller and one power MOSFET to run a two-stage power-factor-corrected (PFC) power supply. The two-stage power-factor-corrected power supply can include a power-factor-corrected boost converter, and a DC-to-DC converter (either step-up or step-down). The DC-to-DC converter can be, e.g., a Flyback, Forward, Cuk, or Buck Converter. The complementary converter circuit includes a voltage input section that takes a universal VAC input and rectifies the input. Then the PFC boost converter boosts the rectified half-cycle DC to a DC line at a higher voltage. The complementary converter circuit further includes an integrated circuit with the power-factor-correction and PWM switching capabilities to control the converters. The DC-to-DC converter brings the voltage down to an appropriate level for the final load (e.g., LEDs).

Abstract: A wireless access point (10) connected to a fixed telecommunications network (12) broadcasts codes relating to one or more network identities (100, 101) identifying availability of wireless connection to the access point, If connection to the telecommunications network (12) is lost, it suspends one of the identity codes (100) and replaces it with a special identity code for a network identity (102) configured to co-operate with a mobile terminal (53) equipped to recognise the special identity code and transmit a message over another communications link (6, 49) to alert a service centre (7) to the fault (13).