Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, we propose a Generative Adversarial Network-based model which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing considered tasks despite the limitation in the number of expert demonstrations, which clearly indicate the potential of our model.
Technique was used to retail for analyzing atom beryllium ion cathode of an atom lithium to six pairs of functions wave which two ?????? and the rest of the casing moderation and to analyze atom lithium ion Mob atom beryllium to three pairs of functions wave pair of casing and the rest of the casing moderation using function wave Hartree Fock and each casing email wascalculate expected values ??....
The present work focuses on the experimental implementation of one of the fiber optical sensors, the optical glass fiber built on surface Plasmon resonance. A type of optical glass fiber was used in this work, single-mode no-core fiber with pre-tapering diameter: (125.1 μm) and (125.3 μm), respectively. The taper method can be tested by measuring the output power of the optical fiber before and after chemical etching to show the difference in cladding diameter due to the effect of hydrofluoric acid with increasing time for the taper process. The optical glass fiber sensor can be fabricated using the taper method to reduce the cladding diameter of the fibers to (83.12 µm, 64.37 µm, and 52.45 µm) for single-mode fibers using Hydrofluoric
... Show MoreParticulate matter (PM) emitted from diesel engine exhaust have been measured in terms of mass, using
99.98 % pure ethanol blended directly, without additives, with conventional diesel fuel (gas – oil),to
get 10 % , 15 %, 20 % ethanol emulsions . The resulting PM collected has been compared with those
from straight diesel. The engine used is a stationary single cylinder, variable compression ratio Ricardo
E6/US. This engine is fully instrumented and could run as a compression or spark ignition.
Observations showed that particulate matter (PM) emissions decrease with increasing oxygenate
content in the fuel, with some increase of fuel consumption, which is due to the lower heating value of
ethanol. The reduction in
The present work reports the performance of three types of polyethersulfone (PES) membrane in the removal of highly polluting and toxic lead Pb2+ and cadmium Cd2+ ions from a single salt. This study investigated the effect of operating variables, including pH, types of PES membrane, and feed concentration, on the separation process. The transport parameters and mass transfer coefficient (k) of the membranes were estimated using the combined film theory-solution-diffusion (CFSD), combined film theory-Spiegler-Kedem (CFSK), and combined film theory-finely-porous (CFFP) membrane transport models. Various parameters were used to estimate the enrichment factors, concentration polarization modulus, and Péclet number. The pH values signif
... Show MoreWireless Body Area Sensor Networks (WBASNs) have garnered significant attention due to the implementation of self-automaton and modern technologies. Within the healthcare WBASN, certain sensed data hold greater significance than others in light of their critical aspect. Such vital data must be given within a specified time frame. Data loss and delay could not be tolerated in such types of systems. Intelligent algorithms are distinguished by their superior ability to interact with various data systems. Machine learning methods can analyze the gathered data and uncover previously unknown patterns and information. These approaches can also diagnose and notify critical conditions in patients under monitoring. This study implements two s
... Show MoreThe software-defined network (SDN) is a new technology that separates the control plane from data plane for the network devices. One of the most significant issues in the video surveillance system is the link failure. When the path failure occurs, the monitoring center cannot receive the video from the cameras. In this paper, two methods are proposed to solve this problem. The first method uses the Dijkstra algorithm to re-find the path at the source node switch. The second method uses the Dijkstra algorithm to re-find the path at the ingress node switch (or failed link).
... Show MoreThe aim of this research is to show the importance of the effective use
of the internet in academic libraries; to improve the services and to increase
the competence of librarians.
The research has given some recommendations to improve the quality
of services and the need for cooperative network among academic libraries.
A novel method for Network Intrusion Detection System (NIDS) has been proposed, based on the concept of how DNA sequence detects disease as both domains have similar conceptual method of detection. Three important steps have been proposed to apply DNA sequence for NIDS: convert the network traffic data into a form of DNA sequence using Cryptography encoding method; discover patterns of Short Tandem Repeats (STR) sequence for each network traffic attack using Teiresias algorithm; and conduct classification process depends upon STR sequence based on Horspool algorithm. 10% KDD Cup 1999 data set is used for training phase. Correct KDD Cup 1999 data set is used for testing phase to evaluate the proposed method. The current experiment results sh
... Show MoreEarly detection of brain tumors is critical for enhancing treatment options and extending patient survival. Magnetic resonance imaging (MRI) scanning gives more detailed information, such as greater contrast and clarity than any other scanning method. Manually dividing brain tumors from many MRI images collected in clinical practice for cancer diagnosis is a tough and time-consuming task. Tumors and MRI scans of the brain can be discovered using algorithms and machine learning technologies, making the process easier for doctors because MRI images can appear healthy when the person may have a tumor or be malignant. Recently, deep learning techniques based on deep convolutional neural networks have been used to analyze med
... Show More