Generative Adversarial Network for Imitation Learning from Single Demonstration

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.

IoT System on Dynamic Fish Feeder Based on Fish Existence for Agriculture Aquaponic Breeders

Maintaining and breeding fish in a pond are a crucial task for a large fish breeder. The main issues for fish breeders are pond management such as the production of food for fishes and to maintain the pond water quality. The dynamic or technological system for breeders has been invented and becomes important to get maximum profit return for aquaponic breeders in maintaining fishes. This research presents a developed prototype of a dynamic fish feeder based on fish existence. The dynamic fish feeder is programmed to feed where sensors detected the fish's existence. A microcontroller board NodeMCU ESP8266 is programmed for the developed hardware. The controller controls the feeding and feedback mechanism based on attached sensors. An ultrasonic sensor is programmed with the controller to detect the level of food and waterproof ultrasonic to detect existing fish. The humidity sensor was used to measure the humidity in the food container to control the food freshness. Two servo motors were used to move the waterproof sensor to attract the fish and to dispense the food to the fish when existed. The result presents four measured levels that are the temperature of the food container, the quality of food based on humidity measured, fish detection counter and level of fish food in the container. Data analytics on all the measured levels was presented on the ThingSpeak platform by using Blynk to get data collections from all sensors. This research is significant for fish breeders that support IR4.0 system connected online and mobile apps which also contribute to today’s agriculture.

Impact of Denial-of-Service Attack on Directional Compact Geographic Forwarding Routing Protocol in Wireless Sensor Networks

Directional Compact Geographic Forwarding (DCGF) routing protocol promises a minimal overhead generation by utilizing a smart antenna and Quality of Service (QoS) aware aggregation. However, DCGF was tested only in the attack-free scenario without involving the security elements. Therefore, an investigation was conducted to examine the routing protocol algorithm whether it is secure against attack-based networks in the presence of Denial-of-Service (DoS) attack. This analysis on DoS attack was carried out using a single optimal attacker, A1, to investigate the impact of DoS attack on DCGF in a communication link. The study showed that DCGF does not perform efficiently in terms of packet delivery ratio and energy consumption even on a single attacker.

Design of L-Band Multiwavelength Laser for TDM/WDM PON Application

This paper presents on the design of L-Band Multiwavelength laser for Hybrid Time Division Multiplexing/ Wavelength Division Multiplexing (TDM/WDM) Passive Optical Network (PON) application. In this design, an L-band Mulltiwavelength Laser is designed as the downstream signals for TDM/WDM PON. The downstream signals ranging from 1569.865 nm to 1581.973 nm with 100GHz spacing. The multiwavelength laser is designed using OptiSystem software and it is integrated into a TDM/WDM PON that is also designed using OptiSystem simulation software. By adapting multiwavelength fiber laser into a TDM/WDM network, a simple and low-cost downstream signal is proposed. From the simulation design, it is found that the proposed design is suitable to be used in TDM/WDM PON for up to 64 Optical Network Units (ONUs).

Performance Analysis on Multiple Device Connections of Small Office Home Office Network

Malaysia has been supported by one of the high-speed fiber internet connections called TM UniFi. TM UniFi is very familiar to be used as a medium to apply Small Office Home Office (SOHO) concept due to the COVID-19 pandemic. Most of the communication vendors offer varieties of network services to fulfill customers' needs and satisfaction during the pandemic. Quality of Services is queried by most users by the fact of increased on users from time to time. Therefore, it is crucial to know the network performance contrary to the number of devices connected to the TM UniFi network. The main objective of this research is to analyze TM UniFi performance with the impact of multiple device connections or users' services. The study was conducted to analyze the QoS on its traffic, packets transfer, RTT, latency, and throughput. Wireshark simulation program has been used as a network traffic capture where PCAP files have been analyzed by using PCAP Analyzer for Splunk. Traffic filtering has been enabled to capture selected traffic to measure network performance. The result shows that better network performance can be achieved if a smaller number of devices are connected at the same time. The percentage of packet loss, RTT, latency is increased when more users connected at the same time. The throughput also shows a decrease for multi-device connections. Based on the analysis it can be concluded that TM UniFi still can provide good network services for the SOHO network environment and sufficient bandwidth despite the rapid user growth in Malaysia.

Synthesizing, Structuring, and Characterizing Bioactivities of .Cr(III), La(III), and Ce(III) .Complexes with Nitrogen, Oxygen .and Sulpher donor bidentate Schiff base ligands

Two Schiff bases, namely, 3-(benzylidene amino) -2-thioxo-6-methyl 2,5-dihydropyrimidine-4(3H)-one (LS])and 3-(benzylidene amino)-6-methyl pyrimidine 4(3H, 5H)-dione(LA)as chelating ligands), were used to prepare some complexes of Cr(III), La(III), and Ce(III)] ions. Standard physico-chemical procedures including metal analysis M%, element microanalysis (C.H.N.S) , magnetic susceptibility, conductometric measurements, FT-IR and UV-visible Spectra were used to identify Metal (III) complexes and Schiff bases (LS) and (LA). According to findings, a [Cr(III) complex] showed six coordinated octahedral geometry, while [La(III), and Ce(III) complexes]were structured with coordination number seven. Schiff's bases and mineral complexes were examined in vitro to investigate potential inhibition against Gram-positive bacteria such as Pseudonomous aerugionosa and Gram-negative bacteria such as Staphylococcus aureus. The low concentration for inhibition has been also determined by studying the minimal inhibitory concentrations MIC .Antibiotics (Ampicillin, Amoxicillin) have been chosen to contrast their activity. Furthermore, Anti-fungal activity against two types of fungi ʺAspergillus flavusʺ and ʺPenicillum Spp.ʺ was studied for these compounds. The results of the antibacterial activity were better compared to the standard drugs.

Unifying The Evaluation Criteria Of Many Objectives Optimization Using Fuzzy Delphi Method

Many objective optimizations (MaOO) algorithms that intends to solve problems with many objectives (MaOP) (i.e., the problem with more than three objectives) are widely used in various areas such as industrial manufacturing, transportation, sustainability, and even in the medical sector. Various approaches of MaOO algorithms are available and employed to handle different MaOP cases. In contrast, the performance of the MaOO algorithms assesses based on the balance between the convergence and diversity of the non-dominated solutions measured using different evaluation criteria of the quality performance indicators. Although many evaluation criteria are available, yet most of the evaluation and benchmarking of the MaOO with state-of-art algorithms perform using one or two performance indicators without clear evidence or justification of the efficiency of these indicators over others. Thus, unify a set of most suitable evaluation criteria of the MaOO is needed. This study proposed a distinct unifying model for the MaOO evaluation criteria using the fuzzy Delphi method. The study followed a systematic procedure to analyze 49 evaluation criteria, sub-criteria, and its performance indicators, a penal of 23 domain experts, participated in this study. Lastly, the most suitable criteria outcomes are formulated in the unifying model and evaluate by experts to verify the appropriateness and suitability of the model in assessing the MaOO algorithms fairly and effectively.

Temperature Stress on Physiological and Morphological Traits in Rhizophora apiculata

Global warming has had considerable effects on vital ecosystems, which has also been caused by increased temperatures and CO2 that follow changes in different abiotic factors, which poses threats to mangrove forests environment. This research was conducted to examine the physiological and morphological characteristics of the Rhizophora apiculata mangrove regarding higher air temperature for the variety of tree species that respond to climate change. Seedlings were cultivated for three months in regulated growth chambers with three varying temperatures of 38°C, 21°C under CO2 at 450 ppm, and ambient CO2 concentration i.e., 450 ± 20 ppm under average temperature at 28°C as the control condition. The plants were treated every 48 hours with 3 L of saline water of 28 ppt. After two weeks at high temperature, the mangrove showed positive results for all parameters. The temperature variations resulted in major variations, such as negative for increased temperature resulting in extreme damage to many samples while positive for decreased temperature resulting in slow development. The physiological results show decreased photosynthesis rates compared to controlled samples. These findings indicate that low photosynthetic capability levels could have occurred due to reduced CO2 fixative reaction mechanism, photosynthetic pigment material, and the discrepancy between respiratory and photosynthesis rate.

Serum prolactin, Preptin, CCL 18 and genetic polymorphisms in Iraqi women with polycystic ovary syndrome.

The polycystic ovary syndrome is an endocrine condition. One of the leading causes of female infertility and the most common disorder among women. The work was being carried out on 100 Iraqi women (50 cases confirmed with PCOS and 50 controls). Between October 2019 and March 2020, blood samples were collected from the Advanced Institute of Infertility Diagnosis and Assisted Reproductive Technology at AL-Nahrain University and a private laboratory. ELISA was used to evaluate the biochemical parameters of preptin, FSH, insulin, LH, and CCL 18 in serum samples from the AFIAS-6 (AFIAS Automated Immunoassay System). The findings of the analysis indicate that, as opposed to the control group, values of prolactin (ng/ml), LH (mIU/ml), Preptin (pg/ml) and CCL 18 (ng/ml) Quite higher in PCOS sickness (p < 0.001) Compared with the patient group, the values of testosterone (ng/ml) and FSH (mIU/ml) was noticeably higher (p <0.05), and PRLR gene expression levels in PCOS patients were significantly increased by 3.6 times. I n summary, the levels of Preptin and CCL18 can be regarded as PCOS markers.

Numerical Analysis of Least-Squares Group Finite Element Method for Coupled Burgers' Problem

In this paper, a least squares group finite element method for solving coupled Burgers' problem in 2-D is presented. A fully discrete formulation of least squares finite element method is analyzed, the backward-Euler scheme for the time variable is considered, the discretization with respect to space variable is applied as biquadratic quadrangular elements with nine nodes for each element. The continuity, ellipticity, stability condition and error estimate of least squares group finite element method are proved. The theoretical results show that the error estimate of this method is . The numerical results are compared with the exact solution and other available literature when the convection-dominated case to illustrate the efficiency of the proposed method that are solved through implementation in MATLAB R2018a.