Design of Centralized Intelligent Expert System and Contamination Detection of Tissue Cultured Sugarcane Crop

This paper presents the design a cloud based IoT enabled smart agriculture application for Hi-Tech tissue cultured sugarcane crop entitled “Design of Centralized Intelligent Expert System and Contamination Detection of Tissue Cultured Sugarcane Crop”. This expert system comprises of Raspberry Pi-4 (RPi), Arduino-Mega, GSM-Modem (Sim900) and sensor-modules for monitoring and control of essential parameters of laboratory for monitoring the physical parameters. The parameters monitored are temperature, humidity and light intensity of the tissue culture growth rooms with artificial day light timing and control, however, AI-based health prediction suggests the image processing for detection of culture contamination of sugarcane crop inside the growth-room. In addition, fire-smoke sensor and methane gas sensor are incorporated for fire protection and to avoid any disastrous situation. Three numbers of webcams are attached to the RPi for monitoring growth and health of explants. An AI-Model / weight was developed for detection of contamination that predicts the for health of Tissue Cultured Sugarcane Crop. Moreover, image enhancement was covered applying Generative Adversarial Networks (GAN)”. In this system, the RPi reads sensor's data through Arduino and convert it to data-frame with timestamp and geo-tag. The data along with the captured images are sent to a centralize cloud application for applying data mining and Artificial Intelligence; however, the model of contamination detection has been applied at edge device. This is to get meaningful insights of data for future decision making in maximizing crop yield and quality. Due to the great need of sugarcane crop in Pakistan, the Plant Tissue Culture (PTC) technology has been incorporated with Artificial Intelligence, the proposed system is aimed to be installed at established PTC-growth-rooms for sugarcane crop so the experts of field can be connected to the cloud application for its monitoring, control and data analytics. In addition, the use of telepresence through cloud application will enable PTC-experts to provide assistance to the remote user and resolve their issues timely, thus extending PTC technology all over the country which will eventually lead to increased crop yield with quality products in affordable price.

Analysis of Efficient FPGA Based Pid Controller For Dc-Dc Buck Boost Converter Using Hardware Co-Simulation Setup

Converters are widely used in smart grid applications where multilevel dc voltage source are required in a system. There are few critical challenges in existing converters such as low efficiency, slow response time, large circuit size due to more number of switches subsequently poor quality of PWM signal. Moreover, a separate converter is required for each source used in the circuit. In this work, we proposed and analyse an efficient FPGA based PID controller using Hardware Co-simulation for DC-DC Buck Boost Converter. We have successfully integrated two different sources of energy which are being fed to the power stage. The control of this converter topology is implemented by using FPGA kits Virtex5 and Virtex7. Furthermore, efficiency of both kits is compared and analysed. The proposed converter has high efficiency, fast response time and compact size due to least number of switches as compared to conventional topology of such converters.

Energy Efficient Crypto Suit for Secure Underwater Sensor Communication using Genetic Algorithm

With the advancement in technology, there has been a keen interest of researchers and industrial institution in the use of Underwater Sensors Networks (UWSN). This study is devoted to the secure communication between the underwater sensors networks which is now a day’s most widely used for oceanographic abnormalities, and to track submarines that perform the surveillance and navigation. But UWSNs has its limitations such as multipath, propagation delay, low bandwidth, and limited battery as compared to traditional WSNs that causes a low life in comparison with WSNs. Secure communication in UWSNs is more difficult due to the above-mentioned limitations which need ultralightweight components. There are many miscellaneous attacks due to which sensors can be able to lose both data availability and integrity that is why this study is basically to design an efficient algorithm that possesses less computation and use less space for secure communication. The proposed algorithm will initially establish the first half of the key through a genetic algorithm and then will develop the remaining part. After that encryption algorithm is proposed for the secure communication between UWSNs and its performance will be evaluated based on throughput, running time, space usage, and avalanche effect.

Analysis of Harmonic Distortion Reduction through Modular Multi-Level Inverter using Nearest Level Modulation (NLM) Control Strategy

The research paper presents the control strategy to reduce THD (Total Harmonic Distortions) losses by the implementation of the Nearest Level Modulation control technique in a Modular Multilevel Converter. Modular Multilevel Converter is found one of the leading technologies in Power Electronics & Control, its applications are very common in HVDC systems, FACTS (Flexible Alternating-current Transmission system), Variable frequency drives and Electric vehicles as well. The power quality of MMC is better and has lesser THD in comparison to conventional converters like 2-level converters with carrier-based modulation techniques. The MMC has been designed with high scalability and has high voltage and power capacity. Sub-module is an integral part of MMC which is built up as an identical and controllable part of it. This converter is also called a controllable voltage source (VSC). Researchers aim to come up with a detailed review of control methods and necessary operations applied to MMC-based systems for HVDC, particularly focusing to control the total harmonic distortions. Power converters use many modulation techniques, but the existing techniques contribute to a great part in switching losses. MMC up to 49 levels, by implementing the Nearest Level Modulation (NLM) technique, is robust and has less complexity for the systems like MMC-HVDC, and the levels control the total harmonic distortions. In this research paper, the reduction of THD by increasing the voltage levels in MMC is comprehensively evaluated. The simulation results in MATLAB/Simulink are used to examine and confirm the proposed control strategy for stable operation of MMC for HVDC application.

Evaluation of Oil-Based Power Generation of Pakistan. SWOT-Delphi Approach

Pakistan is heavily dependent on imported fuel for power generation. Depending on imported fuel has not only increased GHG emissions, but it has also put a burden on the national exchequer and raised apprehensions on energy security. This paper thus investigates the consequences of oil-based power generation on the economy, environment, and energy security of Pakistan. SWOT-Delphi approach has been adopted. The study discovered that the use of imported oil for power generation is detrimental to the economy, environment, and energy security of Pakistan. It further suggests that Pakistan should immediately abandon oil-based power generation and explore green energy alternatives for its sustainable economic growth. This study uses a hybrid model that combines strength, weakness, opportunity, and threat (SWOT) analysis with the Delphi method.

Research on various PV arrays manufacturing data for power comparison and optimization through extremum seeking technique

The increasing environmental repercussions and depletion of nonrenewable energy resources have cautioned and enabled researchers to incorporate renewable energy systems. Amongst the renewable energy resources, the solar energy system has been utilized in most parts of the world due to cheaper, reliable, robust and sustainable energy resource than other resources. The Maximum Power Point Tracking (MPPT) techniques are used for increasing the power output of PV array. The Perturb and Observe (P&O) technique is widely used MPPT technique due to higher efficiency and ease in implementation. The proposed “Perturb and Observe (P&O)” MPPT technique is incorporated through Matlab Simulation software on PV arrays of various companies. The results are then compared through comparative analysis and optimum results are recommended for the manufacturing companies.

Design and Development of Sindhi Text Based CAPTCHAs for Regional Websites

Bots are created to use the resources maliciously on World Wide Web. The misuse of the resources could be prevented by employing CAPTCHAs. Several types of CAPTCHAs are being used against the bots (robot) attacks but text-based CAPTCHA type is the most popular being very secured and easy to use. Latin language based text CAPTCHAs can be found ubiquitously on Internet but English text based CAPTCHAs are already decoded by many researchers. Thus, a novel Sindhi language based text CAPTCHA was proposed for regional websites where Arabic style script was utilized. This scheme offered two fold benefits: first, the proposed scheme could easily be understood by averagely literate person; second, this scheme paved a way for Arabic style OCR developers to understand Sindhi language specific features and facilitate Sindhi text recognition in future. A survey was also conducted to analyze the usability and strength of proposed CAPTCHA.

Urban Road Traffic Sign Detection & Recognition with Time Space Relationship Model

Detection and recognition of urban road traffic signs is an important part of the Modern Intelligent Transportation System (ITS). It is a driver support function which can be used to notify and warn the driver for any possible incidence on the current stretch of road. This paper presents a robust and novel Time Space Relationship Model for high positive urban road traffic sign detection and recognition for a running vehicle. There are three main contributions of the proposed framework. Firstly, it applies fast color-segment algorithm based on color information to extract candidate areas of traffic signs and reduce the computation load. Secondly, it verifies the traffic sign candidate areas to decrease false positives and raise the accuracy by analysing the variation in preceding video-images sequence while implementing the proposed Time Space Relationship Model. Lastly, the classification is done with Support Vector Machine with dataset from real-time detection of TSRM. Experimental results indicate that the accuracy, efficiency, and the robustness of the framework are satisfied on urban road and detect road traffic sign in real time.

Sequential Modeling for the Recognition of Activities in Logistics

Activity recognition is an important task in cyber physical system research and has been the focus of researchers worldwide. This paper presents a method for activity recognition in logistic operations using data from accelerometer and gyroscope sensors. A Long Short Term Memory (LSTM) recurrent neural network, bidirectional LSTM and a Convolutional LSTM (ConvLSTM) are used to classify between six activities being performed in the logistics operations being carried out. Comparing the performance of the LSTMs to the Conv-LSTM network, the designed Bi-LSTM RNN outperforms the other networks considered

A Deep Learninag based Non-invasive and Real-Time Fault Detection System for 3-Phase Induction Motors

Induction motor plays a major role in industry. Despite of its strong structure, induction motors are often prone to faults. There are different types of faults that occurs in the induction motor such as bearing faults, winding faults, etc. Thus motors in major applications require continuous and effective monitoring. In this paper, a stand-alone and non-invasive condition monitoring system that can monitor the condition of 3-phase induction motor using motor current signatures with aid of deep learning (DL) approaches. The proposed system extracts the features using non-invasive current sensors it further samples the features using an analog to digital converter (ADC) and organizes the data acquired from ADC using Raspberry-pi microcomputer. The current data acquired from induction motor is used to train and test the DL models including Multilayer Perceptron (MLP), Long Short-term Memory (LSTM), and One-Dimensional Convolutional Neural Networks (1DCNN). The comparative analysis is demonstrated and the LSTM model as best fault classifier among all with accuracy up to 100%. Finally, the real-time testing of the device showed that the developed system can effectively monitor the conditions of motor using non-invasive current sensors.