M. Chowdhury, Md Rakib Hasan, M. Chowdhury, Saad Mohammad Bhuiya, Md. Saniat Rahman Zishan
Nowadays Air Conditioner (AC) has become a more important appliance in our life. Gas leakage, blockage in the evaporator and compressor coil, pipelines as well as dust in the air filters, are the major reasons behind AC explosion. Many people have been injured over the years due to AC blasts. In this paper a system is developed that uses sensor technology and smart devices to reduce AC blast. As a result, pipeline leaks or blockage fault detection system is planned and constructed using MQ-02, TTC 103, optical dust sensors for gas detection, temperature detection and for detecting dust density respectively. Also bacteria can be detected through MQ-3 gas sensor as it combines with AC refrigerant and produces ethanol. This system is also digitally connected to smart devices (cellphones) and a control device (RM MINI 3) so that user can receive a detection notification at any time and operate AC from any location. By implementing these sensors, the initial target was achieved. The work is low cost and environment friendly. Index Terms— Explosions, blockage, leakage, RM MINI 3, cellphone, refrigeration cycle, sensor, safety
如今，空调(AC)已成为我们生活中越来越重要的电器。气体泄漏，蒸发器和压缩机盘管堵塞，管道堵塞以及空气过滤器中的灰尘是交流爆炸的主要原因。多年来，由于交流电爆炸，许多人受伤。本文开发了一种利用传感器技术和智能设备来降低交流爆炸的系统。为此，规划构建了管道泄漏或堵塞故障检测系统，采用MQ-02、TTC 103、光学粉尘传感器分别进行气体检测、温度检测和粉尘密度检测。另外，通过MQ-3型气体传感器可以检测到细菌，因为它与交流制冷剂结合产生乙醇。该系统还与智能设备(手机)和控制设备(RM MINI 3)进行数字连接，以便用户可以随时收到检测通知，并从任何位置操作AC。通过实施这些传感器，实现了最初的目标。这项工作成本低，对环境友好。索引术语-爆炸，堵塞，泄漏，RM MINI 3，手机，制冷循环，传感器，安全
{"title":"Design And Development Of Air Conditioner (AC) Monitoring And Management System","authors":"M. Chowdhury, Md Rakib Hasan, M. Chowdhury, Saad Mohammad Bhuiya, Md. Saniat Rahman Zishan","doi":"10.53799/ajse.v21i3.260","DOIUrl":"https://doi.org/10.53799/ajse.v21i3.260","url":null,"abstract":"Nowadays Air Conditioner (AC) has become a more important appliance in our life. Gas leakage, blockage in the evaporator and compressor coil, pipelines as well as dust in the air filters, are the major reasons behind AC explosion. Many people have been injured over the years due to AC blasts. In this paper a system is developed that uses sensor technology and smart devices to reduce AC blast. As a result, pipeline leaks or blockage fault detection system is planned and constructed using MQ-02, TTC 103, optical dust sensors for gas detection, temperature detection and for detecting dust density respectively. Also bacteria can be detected through MQ-3 gas sensor as it combines with AC refrigerant and produces ethanol. This system is also digitally connected to smart devices (cellphones) and a control device (RM MINI 3) so that user can receive a detection notification at any time and operate AC from any location. By implementing these sensors, the initial target was achieved. The work is low cost and environment friendly. \u0000 \u0000Index Terms— Explosions, blockage, leakage, RM MINI 3, cellphone, refrigeration cycle, sensor, safety \u0000 ","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128733867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md. Redowan Mahmud Arnob, Sabiqun Nahar, Mohammad Nasir Uddin
To dispatch the goal about walking towards the 4th Industrial Revolution, one of the main key materials that require alterations and enhancements is data communication and transmission. To keep up with the augmented rise in demand for data, fiber-optics communication and networks commence a significant role in the transfer of data at high speeds. This article exemplifies the expediency analysis of 5.76 Tbits/s SDM-PDM-Nyquist superchannel WDM hybrid multiplexing technique over a multimodal transmission link up to 10 km using C-band carrier frequencies. This system is designed to carry 48 channels of data that can be produced using 8 C-band carrier frequencies, 2 polarization states, and 3 LP modes through 3.1% Germania doped over pure silica step-index multimode fiber. The system exhibits a satisfactory performance (log BER -9.35, faithful Q-factor 6.09, extinction ratios 7.78, minimum OSNR 46.5 dB) up to a distance of 10 km. Each channel receives a satisfactory amount of power after the dual-stage amplification process in the transmission medium with an ultra-high spectral efficiency of 137% and a high bandwidth-distance product of 385 MHz.km
{"title":"Design of high capacity 5.76 Tbits/s SDM-PDM-Nyquist superchannel WDM hybrid multiplexing in 3.1% Germania doped MMF","authors":"Md. Redowan Mahmud Arnob, Sabiqun Nahar, Mohammad Nasir Uddin","doi":"10.53799/ajse.v21i3.373","DOIUrl":"https://doi.org/10.53799/ajse.v21i3.373","url":null,"abstract":"To dispatch the goal about walking towards the 4th Industrial Revolution, one of the main key materials that require alterations and enhancements is data communication and transmission. To keep up with the augmented rise in demand for data, fiber-optics communication and networks commence a significant role in the transfer of data at high speeds. This article exemplifies the expediency analysis of 5.76 Tbits/s SDM-PDM-Nyquist superchannel WDM hybrid multiplexing technique over a multimodal transmission link up to 10 km using C-band carrier frequencies. This system is designed to carry 48 channels of data that can be produced using 8 C-band carrier frequencies, 2 polarization states, and 3 LP modes through 3.1% Germania doped over pure silica step-index multimode fiber. The system exhibits a satisfactory performance (log BER -9.35, faithful Q-factor 6.09, extinction ratios 7.78, minimum OSNR 46.5 dB) up to a distance of 10 km. Each channel receives a satisfactory amount of power after the dual-stage amplification process in the transmission medium with an ultra-high spectral efficiency of 137% and a high bandwidth-distance product of 385 MHz.km","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117076500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Harvesting energy from ocean wave is a promising renewable energy source due to its high efficiency, carbon-free, it is not affected by depletion of fossil fuels, and it is replenished constantly. The existing generators used in wave energy harvesting such as linear generator and slider crank mechanism have some limitations, which include lower efficiency and technologically challenging. Thus, in this work, wave energy harvesting technique using rotational generator based on scotch yoke mechanism is proposed. A typical slider crank to convert linear motion into rotational motion is replaced by scotch yoke mechanism to yield higher efficiency. A comparison of the performance of wave energy system between employing slider crank and scotch yoke is made to evaluate the superiority of the proposed mechanism. From the results obtained in this work, it is found that the output voltage of rotational generator employing scotch yoke mechanism is higher compared to that of rotational generator employing slider crank for the same input power. Thus, rotational generator by employing scotch yoke mechanism can be one of the alternative methods for ocean wave energy harvesting.
{"title":"Ocean Wave Energy Harvesting via Scotch Yoke-based Rotational Generation","authors":"Md. Zahir Hossain, H. Illias","doi":"10.53799/ajse.v21i3.503","DOIUrl":"https://doi.org/10.53799/ajse.v21i3.503","url":null,"abstract":"Harvesting energy from ocean wave is a promising renewable energy source due to its high efficiency, carbon-free, it is not affected by depletion of fossil fuels, and it is replenished constantly. The existing generators used in wave energy harvesting such as linear generator and slider crank mechanism have some limitations, which include lower efficiency and technologically challenging. Thus, in this work, wave energy harvesting technique using rotational generator based on scotch yoke mechanism is proposed. A typical slider crank to convert linear motion into rotational motion is replaced by scotch yoke mechanism to yield higher efficiency. A comparison of the performance of wave energy system between employing slider crank and scotch yoke is made to evaluate the superiority of the proposed mechanism. From the results obtained in this work, it is found that the output voltage of rotational generator employing scotch yoke mechanism is higher compared to that of rotational generator employing slider crank for the same input power. Thus, rotational generator by employing scotch yoke mechanism can be one of the alternative methods for ocean wave energy harvesting.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125127307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md. Tanvir Mahtab, A. G. M. Zaman, Montasir Rahman Mahin, Mohammad Nazim Mia, Md. Tanjirul Islam
The endeavour of predicting stock prices using different mathematical and technological methods and tools is not new. But the recent advancements and curiosity regarding big data and machine learning have added a new dimension to it. In this research study, we investigated the feasibility and performance of the multiple regression method in the prediction of stock prices. Here, multiple regression was used on the basis of the incremental machine learning setting. The study conducted an experiment to predict the closing price of stocks of six different organizations enlisted in the Dhaka Stock Exchange (DSE). Three years of historical stock market data (2017-2019) of these organizations have been used. Here, the Multiple Regression, Squared Loss Function, and Stochastic Gradient Descent (SGD) algorithms are used as a predictor, loss function, and optimizer respectively. The model incrementally learned from the data of several stock-related attributes and predicted the closing price of the next day. The performance of prediction was then analysed and assessed on the basis of the rolling Mean Absolute Error (MAE) metric. The rolling MAE scores found in the experiment are quite promising.
{"title":"Stock Price Prediction: An Incremental Learning Approach Model of Multiple Regression","authors":"Md. Tanvir Mahtab, A. G. M. Zaman, Montasir Rahman Mahin, Mohammad Nazim Mia, Md. Tanjirul Islam","doi":"10.53799/ajse.v21i3.490","DOIUrl":"https://doi.org/10.53799/ajse.v21i3.490","url":null,"abstract":"The endeavour of predicting stock prices using different mathematical and technological methods and tools is not new. But the recent advancements and curiosity regarding big data and machine learning have added a new dimension to it. In this research study, we investigated the feasibility and performance of the multiple regression method in the prediction of stock prices. Here, multiple regression was used on the basis of the incremental machine learning setting. The study conducted an experiment to predict the closing price of stocks of six different organizations enlisted in the Dhaka Stock Exchange (DSE). Three years of historical stock market data (2017-2019) of these organizations have been used. Here, the Multiple Regression, Squared Loss Function, and Stochastic Gradient Descent (SGD) algorithms are used as a predictor, loss function, and optimizer respectively. The model incrementally learned from the data of several stock-related attributes and predicted the closing price of the next day. The performance of prediction was then analysed and assessed on the basis of the rolling Mean Absolute Error (MAE) metric. The rolling MAE scores found in the experiment are quite promising.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122770321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we discussed a new Sumudu transform iterative method and successfully applied on linear and nonlinear fractional integro-differential equations. The obtained results are compatible with those that have been obtained by other methods. The fractional derivative here is described in the Caputo sense. The proposed method is found to be powerful and efficient.
{"title":"Adaptation of Sumudu Transform Iterative Method for Solving Fractional Integro-Differential Equations","authors":"Eman Abuteen","doi":"10.53799/ajse.v21i3.435","DOIUrl":"https://doi.org/10.53799/ajse.v21i3.435","url":null,"abstract":"In this paper, we discussed a new Sumudu transform iterative method and successfully applied on linear and nonlinear fractional integro-differential equations. The obtained results are compatible with those that have been obtained by other methods. The fractional derivative here is described in the Caputo sense. The proposed method is found to be powerful and efficient.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127222447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract— Concentrating solar energy system is a potential solar thermal technology, wherein parabolic trough concentrators (PTC) are becoming growingly popular. In this research, both analytical and experiment analyses have been done. The experiment has compared with analytical results. to examine the effect of different operating parameters. Water and water-carbon nanotube (w-CNT) are used to explore the performance of PTC system. Optimum receiver diameter is found 51.80 mm for the maximum efficiency of the collector. During optimization, mass flow rate and concentration ratio are found to be influencing on the thermal efficiency and heat removal factor. Investigations show improvement in heat transfer for added nanoparticles. Heat transfer rate is better in laminar flow than in turbulent flow. After analytical analyses, an experiment has been done using water and carbon nanotube and compared with analytical results. Results show that for every 1oC increase in outlet temperature heat gain and thermal efficiency with water increase at the rate of 0.02 kJ/s and 1.6% respectively. On the other hand, for w-CNT as HTF, for every 100 W/m2 increase in irradiance, heat gain augments at a rate of 0.23 kJ/s and thermal efficiency upsurges by around 7%. Flow rate of working fluids and solar irradiance are found to have respective negative and positive impact on thermal efficiency of the parabolic trough collector.
{"title":"Experimental Performance Investigation of a Nanofluid Based Parabolic Trough Concentrator in Malaysia","authors":"A. Nahar, M.K. Islam,, Md. Hasanuzzaman","doi":"10.53799/ajse.v21i3.437","DOIUrl":"https://doi.org/10.53799/ajse.v21i3.437","url":null,"abstract":"Abstract— Concentrating solar energy system is a potential solar thermal technology, wherein parabolic trough concentrators (PTC) are becoming growingly popular. In this research, both analytical and experiment analyses have been done. The experiment has compared with analytical results. to examine the effect of different operating parameters. Water and water-carbon nanotube (w-CNT) are used to explore the performance of PTC system. Optimum receiver diameter is found 51.80 mm for the maximum efficiency of the collector. During optimization, mass flow rate and concentration ratio are found to be influencing on the thermal efficiency and heat removal factor. Investigations show improvement in heat transfer for added nanoparticles. Heat transfer rate is better in laminar flow than in turbulent flow. After analytical analyses, an experiment has been done using water and carbon nanotube and compared with analytical results. Results show that for every 1oC increase in outlet temperature heat gain and thermal efficiency with water increase at the rate of 0.02 kJ/s and 1.6% respectively. On the other hand, for w-CNT as HTF, for every 100 W/m2 increase in irradiance, heat gain augments at a rate of 0.23 kJ/s and thermal efficiency upsurges by around 7%. Flow rate of working fluids and solar irradiance are found to have respective negative and positive impact on thermal efficiency of the parabolic trough collector.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129263927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The main focus of this paper is to minimize the response induced from seismic excitation using Tuned Liquid Damper (TLD) modified with rubber mesh. An over-head water tank was used as passive damper. A prototype structure with 20 inch by 20 inch steel plate slab and 6 ft height was constructed as a two storied prototype structural model to perform shake table experiment. Time history of El-Centro earthquake was applied as input ground motion using shake table. Different cases of rubber mesh with different water height were studied. From the uncontrolled and controlled data, it was found that in almost every case displacement decreases. Optimal water depth of rubber mesh was suggested on which displacement decreases most. From the results, it was concluded that the TLD modified with rubber mesh is very effective and efficient way to reduce structural vibration.
{"title":"Shake Table Testing of Tuned Liquid Damper Modified with Rubber Mesh to Control Seismic Vibration of Structure","authors":"M. S. Rahman, A. Hasnat, S. Yashin, H. Ahmed","doi":"10.53799/ajse.v21i2.390","DOIUrl":"https://doi.org/10.53799/ajse.v21i2.390","url":null,"abstract":"The main focus of this paper is to minimize the response induced from seismic excitation using Tuned Liquid Damper (TLD) modified with rubber mesh. An over-head water tank was used as passive damper. A prototype structure with 20 inch by 20 inch steel plate slab and 6 ft height was constructed as a two storied prototype structural model to perform shake table experiment. Time history of El-Centro earthquake was applied as input ground motion using shake table. Different cases of rubber mesh with different water height were studied. From the uncontrolled and controlled data, it was found that in almost every case displacement decreases. Optimal water depth of rubber mesh was suggested on which displacement decreases most. From the results, it was concluded that the TLD modified with rubber mesh is very effective and efficient way to reduce structural vibration.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122063331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the field of biomedical, HIFU is a non-invasive therapeutic method that employs non-ionizing acoustic waves to increase the temperature. According to its high efficiency and cheap cost, it has been the main focus of this research. The key stages of this tumor ablation include mechanical and thermal effects. Simulations on tissue ablation with HIFU were implemented in this research to investigate how multiple tissue ablation works and how to enhance tumor ablation while avoiding injury to surrounding healthy tissue by altering the optimal intensity, power, focal length and lens radius of curvature. In order to find the optimal features of the proposed model, this analysis employs clinical applications. Numerous soft and hard tissues from the human body were chosen for this analysis. At a specified acoustic power and exposure period, each tissues optimal frequency (1.6 MHz to 3.5 MHz) and power (120 W to 140 W) were obtained for effective tissue ablation. This research performed all computations by changing the focal length from 55 mm to 65 mm. The outcomes of this therapy might require several weeks to comfortably remove tumor. This optimum result indicates that HIFU tumor ablation procedure has a high probability of success.
{"title":"Non-Invasive Heat-Induced Numerous Tissue Ablation Simulation in a Medical Environment Using Different Focal Length High Intensity Focused Ultrasound Apparatus","authors":"Anika Tun Naziba, Mohammad Nasir Uddin","doi":"10.53799/ajse.v21i2.378","DOIUrl":"https://doi.org/10.53799/ajse.v21i2.378","url":null,"abstract":"In the field of biomedical, HIFU is a non-invasive therapeutic method that employs non-ionizing acoustic waves to increase the temperature. According to its high efficiency and cheap cost, it has been the main focus of this research. The key stages of this tumor ablation include mechanical and thermal effects. Simulations on tissue ablation with HIFU were implemented in this research to investigate how multiple tissue ablation works and how to enhance tumor ablation while avoiding injury to surrounding healthy tissue by altering the optimal intensity, power, focal length and lens radius of curvature. In order to find the optimal features of the proposed model, this analysis employs clinical applications. Numerous soft and hard tissues from the human body were chosen for this analysis. At a specified acoustic power and exposure period, each tissues optimal frequency (1.6 MHz to 3.5 MHz) and power (120 W to 140 W) were obtained for effective tissue ablation. This research performed all computations by changing the focal length from 55 mm to 65 mm. The outcomes of this therapy might require several weeks to comfortably remove tumor. This optimum result indicates that HIFU tumor ablation procedure has a high probability of success.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114398123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Meta-heuristic and Heuristic algorithms that have been introduced for deep neural network optimization is in this paper. Artificial Intelligence, and also the most used Deep Learning methods are all growing in popularity these days, thus we need faster optimization strategies for finding the results of future activities. Neural Network Optimization with Particle Swarm Optimization, Backpropagation (BP), Resilient Propagation (Rprop), and Genetic Algorithm (GA) is used for numerical analysis of different datasets and comparing each other to find out which algorithms work better for finding optimal solutions by reducing training loss. Genetic algorithm and also bio-inspired Particle Swarm Optimization is introduced in this paper. Besides, Resilient Propagation and Conventional Backpropagation algorithms which are application-specific algorithms have also been introduced. Meta-heuristic algorithms GA and PSO are a higher-level formula and problem-independent technique that may be used to a diverse number of challenges. The characteristic of Heuristic algorithms has extremely specific features that vary depending on the problem. The conventional Backpropagation (BP) based optimization, the Particle Swarm Optimization methodology, and Resilient Propagation (Rprop) are all fully presented, and how to apply these procedures in Artificial Deep Neural networks Optimization is also thoroughly described. Applied numerical simulation over several datasets proves that the Meta-heuristic algorithm Particle Swarm Optimization and also Genetic Algorithm performs better than the conventional heuristic algorithm like Backpropagation and Resilient Propagation.
{"title":"In-Depth Case Study on Artificial Neural Network Weights Optimization Using Meta-Heuristic and Heuristic Algorithmic Approach","authors":"Victor Stany Rozario, P. Sutradhar","doi":"10.53799/ajse.v21i2.379","DOIUrl":"https://doi.org/10.53799/ajse.v21i2.379","url":null,"abstract":"The Meta-heuristic and Heuristic algorithms that have been introduced for deep neural network optimization is in this paper. Artificial Intelligence, and also the most used Deep Learning methods are all growing in popularity these days, thus we need faster optimization strategies for finding the results of future activities. Neural Network Optimization with Particle Swarm Optimization, Backpropagation (BP), Resilient Propagation (Rprop), and Genetic Algorithm (GA) is used for numerical analysis of different datasets and comparing each other to find out which algorithms work better for finding optimal solutions by reducing training loss. Genetic algorithm and also bio-inspired Particle Swarm Optimization is introduced in this paper. Besides, Resilient Propagation and Conventional Backpropagation algorithms which are application-specific algorithms have also been introduced. Meta-heuristic algorithms GA and PSO are a higher-level formula and problem-independent technique that may be used to a diverse number of challenges. The characteristic of Heuristic algorithms has extremely specific features that vary depending on the problem. The conventional Backpropagation (BP) based optimization, the Particle Swarm Optimization methodology, and Resilient Propagation (Rprop) are all fully presented, and how to apply these procedures in Artificial Deep Neural networks Optimization is also thoroughly described. Applied numerical simulation over several datasets proves that the Meta-heuristic algorithm Particle Swarm Optimization and also Genetic Algorithm performs better than the conventional heuristic algorithm like Backpropagation and Resilient Propagation.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116622678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Signal design is an important component for good performance of radar systems. Here, the problem of determining a good radar signal with the objective of minimizing autocorrelation sidelobes is addressed. Linear Frequency Modulated signal (LFM) is frequently used pulse compression waveform. But using LFM makes it necessary to use weighting techniques in order to reduce the side lobes which considerably decrease the SNR. At the radar receiver, the LFM signal results in first side lobe of -13dB corresponding to the main lobe. This may reduce the resultant SNR usually by 1 or 2dB. In this paper, an attempt is done to design a radar signal to attain low autocorrelation Peak Side Lobe Ratio (PSLR) which exhibits high SNR and high range resolution. In order to maintain high SNR and to get suppressed side lobes of the signal, one can use Non-Linear Frequency Modulation (NLFM). A NLFM signal is designed for different time sweeps called as Improved NLFM. In Improved NLFM the total time sweep and bandwidth are divided into Two Stage and Tri-Stage sweeps NLFM. The quality of the overall best radar signal is assessed through the parameter PSLR for different values of BT. From this analysis, it is found that the tri stage NLFM gives the low PSLR up to -17.62dB. Simulation results shows the reduction in the sidelobe level from LFM to NLFM and in Improved two and Tri-Stage NLFM.
{"title":"Peak Side Lobe Reduction analysis of NLFM and Improved NLFM Radar signal","authors":"Anoosha Chukka, B. T. Krishna","doi":"10.53799/ajse.v21i2.440","DOIUrl":"https://doi.org/10.53799/ajse.v21i2.440","url":null,"abstract":"Signal design is an important component for good performance of radar systems. Here, the problem of determining a good radar signal with the objective of minimizing autocorrelation sidelobes is addressed. Linear Frequency Modulated signal (LFM) is frequently used pulse compression waveform. But using LFM makes it necessary to use weighting techniques in order to reduce the side lobes which considerably decrease the SNR. At the radar receiver, the LFM signal results in first side lobe of -13dB corresponding to the main lobe. This may reduce the resultant SNR usually by 1 or 2dB. In this paper, an attempt is done to design a radar signal to attain low autocorrelation Peak Side Lobe Ratio (PSLR) which exhibits high SNR and high range resolution. In order to maintain high SNR and to get suppressed side lobes of the signal, one can use Non-Linear Frequency Modulation (NLFM). A NLFM signal is designed for different time sweeps called as Improved NLFM. In Improved NLFM the total time sweep and bandwidth are divided into Two Stage and Tri-Stage sweeps NLFM. The quality of the overall best radar signal is assessed through the parameter PSLR for different values of BT. From this analysis, it is found that the tri stage NLFM gives the low PSLR up to -17.62dB. Simulation results shows the reduction in the sidelobe level from LFM to NLFM and in Improved two and Tri-Stage NLFM. \u0000 ","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117272254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：