Jurnal Infotel (Sekolah Tinggi Teknologi Telematika Telkom Purwokerto)
Not a member yet
392 research outputs found
Sort by
Increased Accuracy Of Sequence To Sequence Models With The CNN Algorithm For Multi Response Ranking On Travel Service Conversations Based On Chat History
Get PDFBuilding a chatbot cannot be separated from the knowledge base. The knowledge base can be obtained from data that has been labeled by the developer, documents that have been converted into pre-processing data, or information taken from social media. In this case, the data used as knowledge is chat history. In the chat history there are certainly many variations of answers and allowing a question to give rise to many answers. To overcome these multi responses, response was made. The existence of ranking, of course the response desired by the user will be more appropriate. Challenge in ranking is how to get the essence a question and find pairs questions and answers from the data. This can be solved by a sequence to sequence model. However, the problem that will arise is the consistency of the answers. The existence of a lot of chat history certainly raises many explanations, even though the question's essence is the same. For this reason the CNN algorithm as a solution to the problem. This research uses convolutional sequence to sequence which will be applied for ranking responses. We compare the efficiency of this model. By making comparisons, this model shows an accuracy of 86.7%Building a chatbot cannot be separated from the knowledge base. The knowledge base can be obtained from data that has been labeled by the developer, documents that have been converted into pre-processing data, or information taken from social media. In this case, the data used as knowledge is chat history. In the chat history there are certainly many variations of answers and allowing a question to give rise to many answers. To overcome these multi responses, response was made. The existence of ranking, of course the response desired by the user will be more appropriate. Challenge in ranking is how to get the essence a question and find pairs questions and answers from the data. This can be solved by a sequence to sequence model. However, the problem that will arise is the consistency of the answers. The existence of a lot of chat history certainly raises many explanations, even though the question's essence is the same. For this reason the CNN algorithm as a solution to the problem. This research uses convolutional sequence to sequence which will be applied for ranking responses. We compare the efficiency of this model. By making comparisons, this model shows an accuracy of 86.7
The Newton’s Polynomials Interpolation Based-Error Correction Method for Low-Cost Dive Altitude Sensor in Remotely Operated Underwater Vehicle (ROV)
Get PDFIndonesia is the one of the countries with the largest of sea area. However, the water surveillance categorized as minimum. The human resource and the low level of infrastructure are the causal of the minimum level of water surveillance. The human involvement of water surveillance has many weaknesses, such as weak against the change of the nature condition, limitation in reaching location, weak against water turbidity levels and water pollution. The utilization of ROV (Remotely Operated Underwater Vehicle) could be a solution in water surveillance problem. The development of ROV still not significant in Indonesia. The development costs are also a problem in development of ROV. Many researcher using USBL (Ultra Short Base Line) sensor to sense the depth of the ROV. However, the cost of this sensor is relatively expensive. The usage of low-cost pressure sensor could be a solution to replace the USBL sensor. The low-cost pressure sensor has a significant deviation. The implementation of Newton’s polynomials interpolation algorithm has been used to decrease the deviation level of the sensors. The result shows the algorithm has succeeded to decrease the deviation level of the pressure sensor significantly. The MSE value of default sensor was 42956.2, which is significantly worst. The Newton interpolation algorithm has been succeeded to reducing the MSE value to 17.82. The result of this research was expected to reduce the cost of the ROVs development especially for sensors cost.Indonesia is the one of the countries with the largest of sea area. However, the water surveillance categorized as minimum. The human resource and the low level of infrastructure are the causal of the minimum level of water surveillance. The human involvement of water surveillance has many weaknesses, such as weak against the change of the nature condition, limitation in reaching location, weak against water turbidity levels and water pollution. The utilization of ROV (Remotely Operated Underwater Vehicle) could be a solution in water surveillance problem. The development of ROV still not significant in Indonesia. The development costs are also a problem in development of ROV. Many researcher using USBL (Ultra Short Base Line) sensor to sense the depth of the ROV. However, the cost of this sensor is relatively expensive. The usage of low-cost pressure sensor could be a solution to replace the USBL sensor. The low-cost pressure sensor has a significant deviation. The implementation of Newton’s polynomials interpolation algorithm has been used to decrease the deviation level of the sensors. The result shows the algorithm has succeeded to decrease the deviation level of the pressure sensor significantly. The MSE value of default sensor was 42956.2, which is significantly worst. The Newton interpolation algorithm has been succeeded to reducing the MSE value to 17.82. The result of this research was expected to reduce the cost of the ROVs development especially for sensors cost
Stateless Authentication with JSON Web Tokens using RSA-512 Algorithm
Get PDFToday's technology needs are getting higher, one of the technologies that continues to grow now is Web Service (WS). WS can increase service flexibility on a system. However, security at WS is one of the things that needs attention. One effort to overcome this problem is JWT (JSON Web Token). JWT is one of the authentication mechanisms in WS, with a standard signature algorithm, HMAC SHA256, RSA-256 or ECDSA. In this research we will discuss the performance of JWT RSA-512 which is implemented on SOAP and RESTful. Because based on previous research the speed performance of the 512-bit algorithm is better, but it is not yet known if applied to JWT. The test results show that the speed of the JWT RSA-512 token on the RESTful process is superior to 24.69% compared to SOAP. Then the speed of the authentication of JWT RSA-512 tokens, RESTful is superior to 11.64% compared to SOAP. Whereas in testing the size of JWT RSA-512 generated tokens, RESTful is only 1.25% superior to SOAP.Today's technology needs are getting higher, one of the technologies that continues to grow now is Web Service (WS). WS can increase service flexibility on a system. However, security at WS is one of the things that needs attention. One effort to overcome this problem is JWT (JSON Web Token). JWT is one of the authentication mechanisms in WS, with a standard signature algorithm, HMAC SHA256, RSA-256 or ECDSA. In this research we will discuss the performance of JWT RSA-512 which is implemented on SOAP and RESTful. Because based on previous research the speed performance of the 512-bit algorithm is better, but it is not yet known if applied to JWT. The test results show that the speed of the JWT RSA-512 token on the RESTful process is superior to 24.69% compared to SOAP. Then the speed of the authentication of JWT RSA-512 tokens, RESTful is superior to 11.64% compared to SOAP. Whereas in testing the size of JWT RSA-512 generated tokens, RESTful is only 1.25% superior to SOAP
Effort Estimation For Software Development On Mobile Application Of 'Tangkap Reptil'
Get PDFAn essential aspect of planning and management of software design projects is to estimate work time, costs, and human resources. The calculation solution made in this study aims to assist in calculating the estimated time of developing a reptile capture application using the Use Case Point (UCP) method. The UCP method is a software effort estimation method that shows better performance compared to other methods. The result of this research is the risk of software development on the mobile application of 'Tangkap Reptil' has a small chance, can be done in a relatively short time, and does not require a lot of resources.An essential aspect of planning and management of software design projects is to estimate work time, costs, and human resources. The calculation solution made in this study aims to assist in calculating the estimated time of developing a reptile capture application using the Use Case Point (UCP) method. The UCP method is a software effort estimation method that shows better performance compared to other methods. The result of this research is the risk of software development on the mobile application of 'Tangkap Reptil' has a small chance, can be done in a relatively short time, and does not require a lot of resources
Performance Analysis Of Firewall As Virtualized Network Function On VMware ESXi Hypervisor
Get PDFVirtualization technology is slowly being used to build network infrastructure called Network Function Virtualization (NFV). It takes network functions such as firewall, load balancer, IPS out of its hardware then uses its software to be run on high specification server. It helps to reduce vendor lock-in and creates a multiplatform network function environment for telecommunication or Internet Service Provider (ISP) company. It has a lot of benefits compared to a traditional network. One of them is reducing the number of hardware that is used in the telecom industry. This technology runs on the hypervisor that is used for the hardware management. One of the important components from NFV is Virtualized Network Function (VNF). In NFV, network devices are run on a server so that a firewall is needed. If an attack occurs on the network, it will interfere the existing network components. This paper focuses on analyzing the performance of two firewall systems: pfSense, and FortiGate. Both firewalls run on the VMware ESXi hypervisor. It compares the firewall performance in normal conditions without attacks and under SYN DoS attacks. Besides, firewall failover capabilities are evaluated. Based on the overall testing results, FortiGate has better performance than pfSense. It has better ability in handling DoS SYN attack because of lower throughput performance degradation and better FTP performance. It is concluded that FortiGate has best performance if it is compared to pfSense.Virtualization technology is slowly being used to build network infrastructure called Network Function Virtualization (NFV). It takes network functions such as firewall, load balancer, IPS out of its hardware then uses its software to be run on high specification server. It helps to reduce vendor lock-in and creates a multiplatform network function environment for telecommunication or Internet Service Provider (ISP) company. It has a lot of benefits compared to a traditional network. One of them is reducing the number of hardware that is used in the telecom industry. This technology runs on the hypervisor that is used for the hardware management. One of the important components from NFV is Virtualized Network Function (VNF). In NFV, network devices are run on a server so that a firewall is needed. If an attack occurs on the network, it will interfere the existing network components. This paper focuses on analyzing the performance of two firewall systems: pfSense, and FortiGate. Both firewalls run on the VMware ESXi hypervisor. It compares the firewall performance in normal conditions without attacks and under SYN DoS attacks. Besides, firewall failover capabilities are evaluated. Based on the overall testing results, FortiGate has better performance than pfSense. It has better ability in handling DoS SYN attack because of lower throughput performance degradation and better FTP performance. It is concluded that FortiGate has best performance if it is compared to pfSense
Modeling and Simulation of Dual-band Yagi Antennas for Voice Communication on Microsatellite
Get PDFThe design of the dual-band Yagi antenna was developed to support voice communication through voice repeaters on microsatellites in the UHF-VHV frequency from ground stations. The Yagi antenna is a type of half lambda dipole antenna that makes it easy to obtain direction and increase gain. The antenna is designed using the method of moment through a simulation with the CST microwave studio software application. The design used as an antenna element material is a type of copper pipe cylinder. The results of the Yagi antenna design in the VHF frequency consist of one driven element, one reflector element, and three director elements, while the UHF frequency consists of one reflector element and seven directors. The results of simulation parameters are obtained, such as Bandwidth of return loss below 10 dB is 4.3 MHz(VHF), and 44 MHz (UHF), VSWR (2:1) is 1.24 (VHF) and 1.36 (UHF), Gain is 9.19 dBi (VHF) and 10.5 dBi (UHF) and Beam Width is 64 degree (VHF) and 58 degree (UHF). The suitability of the antenna design target is dual-band, and Gain value in UHF is higher than VHF.The design of the dual-band Yagi antenna was developed to support voice communication through voice repeaters on microsatellites in the UHF-VHV frequency from ground stations. The Yagi antenna is a type of half lambda dipole antenna that makes it easy to obtain direction and increase gain. The antenna is designed using the method of moment through a simulation with the CST microwave studio software application. The design used as an antenna element material is a type of copper pipe cylinder. The results of the Yagi antenna design in the VHF frequency consist of one driven element, one reflector element, and three director elements, while the UHF frequency consists of one reflector element and seven directors. The results of simulation parameters are obtained, such as Bandwidth of return loss below 10 dB is 4.3 MHz(VHF), and 44 MHz (UHF), VSWR (2:1) is 1.24 (VHF) and 1.36 (UHF), Gain is 9.19 dBi (VHF) and 10.5 dBi (UHF) and Beam Width is 64 degree (VHF) and 58 degree (UHF). The suitability of the antenna design target is dual-band, and Gain value in UHF is higher than VHF
The Implementation of Top-Down Approach Method on Redesign of LAN Harvani Hotel Palembang
Get PDFIn this research, the object was taken from one of the hotels in Palembang, namely Harvani Hotel Palembang. This hotel is one of the hotels in South Sumatra Province, where this hotel has 4 floors. Harvani Hotel Palembang has a Local Area Network (LAN) which consists of several computers. LAN is very important to be applied to Harvani Hotel Palembang in order to support administrative work processes (management of hotel data, employee data, guest data to financial data) and guest needs (internet usage in every room of the Hotel which is one of the services provided by Harvani Hotel Palembang). However, the LAN owned by the Harvani Hotel Palembang still has disadvantages, such as LAN still cannot reach every hotel room on the 2nd floor. In addition, the administration side also faces obstacles because each floor of the Harvani Hotel Palembang has its own administrative section and then at the end of each work shift, reports from each administrative section are submitted to the administrative department on the 1st floor using external storage media. Therefore, it is necessary to redesign the Harvani Hotel Palembang LAN by applying the Top-Down Approach Method. The results of LAN redesign in this research will be displayed using Cisco Packet Tracer simulator software, where from the simulation results it can be seen that the new design of the Harvani LAN Hotel Palembang has connected the entire computer of each room and every floor of the Hotel. Therefore, if the results of this simulation are applied to Harvani Hotel Palembang, then the administrative work process can be managed directly because all data has been stored on the database server. In addition, this new LAN design has also reached all guest rooms of Harvani Hotel Palembang, so guests can access the internet in their respective rooms more comfortable.In this research, the object was taken from one of the hotels in Palembang, namely Harvani Hotel Palembang. This hotel is one of the hotels in South Sumatra Province, where this hotel has 4 floors. Harvani Hotel Palembang has a Local Area Network (LAN) which consists of several computers. LAN is very important to be applied to Harvani Hotel Palembang in order to support administrative work processes (management of hotel data, employee data, guest data to financial data) and guest needs (internet usage in every room of the Hotel which is one of the services provided by Harvani Hotel Palembang). However, the LAN owned by the Harvani Hotel Palembang still has disadvantages, such as LAN still cannot reach every hotel room on the 2nd floor. In addition, the administration side also faces obstacles because each floor of the Harvani Hotel Palembang has its own administrative section and then at the end of each work shift, reports from each administrative section are submitted to the administrative department on the 1st floor using external storage media. Therefore, it is necessary to redesign the Harvani Hotel Palembang LAN by applying the Top-Down Approach Method. The results of LAN redesign in this research will be displayed using Cisco Packet Tracer simulator software, where from the simulation results it can be seen that the new design of the Harvani LAN Hotel Palembang has connected the entire computer of each room and every floor of the Hotel. Therefore, if the results of this simulation are applied to Harvani Hotel Palembang, then the administrative work process can be managed directly because all data has been stored on the database server. In addition, this new LAN design has also reached all guest rooms of Harvani Hotel Palembang, so guests can access the internet in their respective rooms more comfortable
Investigation of Human Emotion Pattern Based on EEG Signal Using Wavelet Families and Correlation Feature Selection
Get PDFEmotions is one of the advantages given by God to human beings compared to other living creatures. Emotions have an important role in human life. Many studies have been conducted to recognize human emotions using physiological measurements, one of which is Electroencephalograph (EEG). However, the previous researches have not discussed the types of wavelet families that have the best performance and canals that are optimal in the introduction of human emotions. In this paper, the power features of several types of wavelet families, namely Daubechies, symlets, and coiflets with the Correlation Feature Selection (CFS) method to select the best features of alpha, beta, gamma and theta frequencies. According to the results, coiflet is a method of the wavelet family that has the best accuracy value in emotional recognition. The use of the CFS feature selection can improve the accuracy of the results from 81% to 93%, and the five most dominant channels in the power features of alpha and gamma band on T8, T7, C5, CP5, and TP7. Hence, it can be concluded that the temporal of the left brain is more dominant in recognition of human emotions.Emotions is one of the advantages given by God to human beings compared to other living creatures. Emotions have an important role in human life. Many studies have been conducted to recognize human emotions using physiological measurements, one of which is Electroencephalograph (EEG). However, the previous researches have not discussed the types of wavelet families that have the best performance and canals that are optimal in the introduction of human emotions. In this paper, the power features of several types of wavelet families, namely Daubechies, symlets, and coiflets with the Correlation Feature Selection (CFS) method to select the best features of alpha, beta, gamma and theta frequencies. According to the results, coiflet is a method of the wavelet family that has the best accuracy value in emotional recognition. The use of the CFS feature selection can improve the accuracy of the results from 81% to 93%, and the five most dominant channels in the power features of alpha and gamma band on T8, T7, C5, CP5, and TP7. Hence, it can be concluded that the temporal of the left brain is more dominant in recognition of human emotions
Optimation Free Space Optic (FSO) Design with Kim Model Using Space Diversity
Get PDFThe development of communication services in remote rural areas is difficult to use cable-based systems such as Digital Subscriber Line (DSL) and FTTx. One solution to solve this problem is to use a wireless system such as radio communication. Free Space Optic (FSO) communication system is a better choice compared to radio communication because of the flexibility of frequency usage. One of the problems of the FSO communication system is the range not too far. The range of the FSO can be increased by using the space diversity method. This study compared FSO systems that not use space diversity and FSO systems that use space diversity in three weather conditions, namely clear, haze, and fog. In taking data results using Kim model propagation with variations in the range between 100 – 2000 meters. The modulation used in this study is external modulation. The result of the analysis of FSO performance after adding space diversity, the range of FSO increases as far as 1200 meters when the condition is clear. During the haze condition, the FSO range increase as far as 800 meters. During the fog condition, the FSO range has increased as far as 300 meters. By adding space diversity, the Q-factor value has increased, and BER (Bit Error Rate) has decreased.The development of communication services in remote rural areas is difficult to use cable-based systems such as Digital Subscriber Line (DSL) and FTTx. One solution to solve this problem is to use a wireless system such as radio communication. Free Space Optic (FSO) communication system is a better choice compared to radio communication because of the flexibility of frequency usage. One of the problems of the FSO communication system is the range not too far. The range of the FSO can be increased by using the space diversity method. This study compared FSO systems that not use space diversity and FSO systems that use space diversity in three weather conditions, namely clear, haze, and fog. In taking data results using Kim model propagation with variations in the range between 100 – 2000 meters. The modulation used in this study is external modulation. The result of the analysis of FSO performance after adding space diversity, the range of FSO increases as far as 1200 meters when the condition is clear. During the haze condition, the FSO range increase as far as 800 meters. During the fog condition, the FSO range has increased as far as 300 meters. By adding space diversity, the Q-factor value has increased, and BER (Bit Error Rate) has decreased
Performance Analysis of Fetal-Phonocardiogram Signal Denoising Using The Discrete Wavelet Transform
Get PDFThe obligation for comprehensive fetal heart rate investigation had driven to improve the passive and non-invasive diagnostic instruments despite the USG or CTG method. Fetal phonocardiography (f-PCG) utilizing the auscultation method met the above criteria, but its interpretation frequently disturbed by the presence of noise. For instance, maternal heart and body organ sounds, fetal movements noise, and ambient noise from the environment where it is recording are the noise that corrupted the f-PCG signal. In this work, the use of discrete wavelet transforms (DWT) to eliminate noise in the f-PCG signal with SNR as the performance parameters observed. It was observing the effect of changes in wavelet type and threshold type on the SNR value. The test was carried out on f-PCG data taken from physio.net. Initial SNR values ranged from -26.7 dB to -4.4 dB; after application of DWT procedure to f-PCG, SNR increased significantly. Based on the test results obtained, wavelet type coif1 with the soft threshold gave the best result with 11.69 dB in SNR value. The coif1 had a superior result than other mother wavelets that use in this work, so the fPCG signal analysis for fetal heart rate investigation suggested to use it.The obligation for comprehensive fetal heart rate investigation had driven to improve the passive and non-invasive diagnostic instruments despite the USG or CTG method. Fetal phonocardiography (f-PCG) utilizing the auscultation method met the above criteria, but its interpretation frequently disturbed by the presence of noise. For instance, maternal heart and body organ sounds, fetal movements noise, and ambient noise from the environment where it is recording are the noise that corrupted the f-PCG signal. In this work, the use of discrete wavelet transforms (DWT) to eliminate noise in the f-PCG signal with SNR as the performance parameters observed. It was observing the effect of changes in wavelet type and threshold type on the SNR value. The test was carried out on f-PCG data taken from physio.net. Initial SNR values ranged from -26.7 dB to -4.4 dB; after application of DWT procedure to f-PCG, SNR increased significantly. Based on the test results obtained, wavelet type coif1 with the soft threshold gave the best result with 11.69 dB in SNR value. The coif1 had a superior result than other mother wavelets that use in this work, so the fPCG signal analysis for fetal heart rate investigation suggested to use it