Jurnal Infotel (Sekolah Tinggi Teknologi Telematika Telkom Purwokerto)
Not a member yet
392 research outputs found
Sort by
Breast Cancer Detection using Residual Convolutional Neural Network and Weighted Loss
Get PDFThis research presents a breast cancer detection system using deep learning method. Breast cancer detection in a large slide of biopsy image is a hard task because it needs manual observation by a pathologist to find the malignant region. The deep learning model used in this research is made up of multiple layers of the residual convolutional neural network, and instead of using another type of classifier, a multilayer neural network was used as the classifier and stacked together and trained using end-to-end training approach. The system is trained using invasive ductal carcinoma dataset from the Hospital of the University of Pennsylvania and The Cancer Institute of New Jersey. From this dataset, 80% and 20% were randomly sampled and used as training and testing data respectively. Training a neural network on an imbalanced dataset is quite challenging. Weighted loss function was used as the objective function to tackle this problem. We achieve 78.26% and 78.03% for Recall and F1-Score metrics, respectively which are an improvement compared to the previous approach.This research presents a breast cancer detection system using deep learning method. Breast cancer detection in a large slide of biopsy image is a hard task because it needs manual observation by a pathologist to find the malignant region. The deep learning model used in this research is made up of multiple layers of the residual convolutional neural network, and instead of using another type of classifier, a multilayer neural network was used as the classifier and stacked together and trained using end-to-end training approach. The system is trained using invasive ductal carcinoma dataset from the Hospital of the University of Pennsylvania and The Cancer Institute of New Jersey. From this dataset, 80% and 20% were randomly sampled and used as training and testing data respectively. Training a neural network on an imbalanced dataset is quite challenging. Weighted loss function was used as the objective function to tackle this problem. We achieve 78.26% and 78.03% for Recall and F1-Score metrics, respectively which are an improvement compared to the previous approach
Trajectory Tracking Control System Design For Autonomous Two-Wheeled Robot
Get PDFA trajectory tracking control system design of an autonomous two-wheeled robot (TWR) is presented. A TWR has two movements: translation (moving forward/backward) and rotation (turning to the right/left) which are commonly represented by a non-linear kinematic equations. The objective of the trajectory tracking control system is to steer the TWR move on a desired trajectory in planar space. In order to simplify the trajectory tracking control system design, the non-linear kinematic equations were approximated by linear kinematic equations through a linearization. Linear quadratics regulator (LQR) method was applied to design the control system. Computer simulations were done to evaluation performance of the designed control system. The simulation results show that the designed control system was able to make the TWR track a desired trajectory that located 1.4 meter away from the TWR initial position within 3 seconds.A trajectory tracking control system design of an autonomous two-wheeled robot (TWR) is presented. A TWR has two movements: translation (moving forward/backward) and rotation (turning to the right/left) which are commonly represented by a non-linear kinematic equations. The objective of the trajectory tracking control system is to steer the TWR move on a desired trajectory in planar space. In order to simplify the trajectory tracking control system design, the non-linear kinematic equations were approximated by linear kinematic equations through a linearization. Linear quadratics regulator (LQR) method was applied to design the control system. Computer simulations were done to evaluation performance of the designed control system. The simulation results show that the designed control system was able to make the TWR track a desired trajectory that located 1.4 meter away from the TWR initial position within 3 seconds
Energy Consumption Analysis of DBR and VBF Protocols in Underwater Sensor Networks Using Aqua-Sim at Network Simulator 2
Get PDFFor decades, there have been significant interests in monitoring the aquatic environment for scientific exploration, commercial exploitation, coastline protection, and even disasters prevention and mitigation such as tsunami warnings. Highly precise, real-time, and temporal-spatial continuous aquatic environment monitoring system is extremely important for underwater life. To support and simulate such monitoring system, underwater sensor networks (UWSN) have emerged as a very powerful technique for many applications on underwater environment, including monitoring, measurement, surveillance, and control by using Aqua-Sim. Aqua-Sim is a simulator for UWSN developed on Network Simulator 2 platform which effectively simulates the attenuation of underwater acoustic channels and the collision behaviors in long delay acoustic networks. Currently, there are several routing protocols for UWSN which are implemented in Aqua-Sim. On this research, we did a simulation on Aqua-Sim by performing Vector-based Forwarding (VBF) protocol and Depth-based Routing (DBR) protocol performance analysis based on energy consumption parameter. Based on the result, it can be concluded that the VBF routing protocol requires more energy consumption than the DBR routing protocol.For decades, there have been significant interests in monitoring the aquatic environment for scientific exploration, commercial exploitation, coastline protection, and even disasters prevention and mitigation such as tsunami warnings. Highly precise, real-time, and temporal-spatial continuous aquatic environment monitoring system is extremely important for underwater life. To support and simulate such monitoring system, underwater sensor networks (UWSN) have emerged as a very powerful technique for many applications on underwater environment, including monitoring, measurement, surveillance, and control by using Aqua-Sim. Aqua-Sim is a simulator for UWSN developed on Network Simulator 2 platform which effectively simulates the attenuation of underwater acoustic channels and the collision behaviors in long delay acoustic networks. Currently, there are several routing protocols for UWSN which are implemented in Aqua-Sim. On this research, we did a simulation on Aqua-Sim by performing Vector-based Forwarding (VBF) protocol and Depth-based Routing (DBR) protocol performance analysis based on energy consumption parameter. Based on the result, it can be concluded that the VBF routing protocol requires more energy consumption than the DBR routing protocol
Open Loop and Closed Loop Power Control Analysis on LTE
Get PDFLTE downlink is using Orthogonal Frequency Division Multiple Access (OFDMA) multiple access system which have high invulnerability from multipath problem. One of the weakness of OFDM system is the high level from Peak to Average Power Ratio (PAPR) that requires higher level transmit power for maintaining the Bit Error Rate (BER) requirement. Using uplink scheme with Single Carrier FDMA (SC-FDMA) which is OFDMA modification, will be offered better level of PAPR than its conventional OFDM. The main problem of using OFDMA is the high level of PAPR, while using SC-FDMA the problem is intra-cell interference. Intra-cell or inter-cell interference is the common problem that can reduce the LTE performance. Minimizing received power for each users (UE) which is still at acceptable tolerance parameter, can be used for reducing the interference problem to another UE. Power control is the appropriate solution for minimizing the interference level. In this paper will be analyzed the power control using open loop and closed loop scheme at LTE network. The simulation result shows that without power control schemes, the transmit power of UE was 23 dBm. While, after applying power control scheme, the transmit power was 18.8 dBm at α=0.4 of open loop condition and 9.05 dBm at closed loop condition. Using this transmit power value as the UE power can improve the SINR performance. The SINR average value without power control scheme was only 20.38 dB which is lower than using open loop scheme was achieved 22.44 dB, and 24.02 dB at closed loop scheme.LTE downlink is using Orthogonal Frequency Division Multiple Access (OFDMA) multiple access system which have high invulnerability from multipath problem. One of the weakness of OFDM system is the high level from Peak to Average Power Ratio (PAPR) that requires higher level transmit power for maintaining the Bit Error Rate (BER) requirement. Using uplink scheme with Single Carrier FDMA (SC-FDMA) which is OFDMA modification, will be offered better level of PAPR than its conventional OFDM. The main problem of using OFDMA is the high level of PAPR, while using SC-FDMA the problem is intra-cell interference. Intra-cell or inter-cell interference is the common problem that can reduce the LTE performance. Minimizing received power for each users (UE) which is still at acceptable tolerance parameter, can be used for reducing the interference problem to another UE. Power control is the appropriate solution for minimizing the interference level. In this paper will be analyzed the power control using open loop and closed loop scheme at LTE network. The simulation result shows that without power control schemes, the transmit power of UE was 23 dBm. While, after applying power control scheme, the transmit power was 18.8 dBm at α=0.4 of open loop condition and 9.05 dBm at closed loop condition. Using this transmit power value as the UE power can improve the SINR performance. The SINR average value without power control scheme was only 20.38 dB which is lower than using open loop scheme was achieved 22.44 dB, and 24.02 dB at closed loop scheme
Investigation of E-Health Acceptance Factor
Get PDFThe E-Health is used to support information technology to maximize the tasks and medical services in the hospital. However, the hospital’s management still have some issues due to E-Health implementation, particularly in the interaction with the system. This study identifies significant factors affecting the implementation of E-Health. Testing a model has been done, to identify factors affecting E-Health acceptance. Quantitative Research methods has been done is implemented in this research, by conducting a survey of 150 respondents on health practitioners in the District Hospital of Gunung Mas Province of Central Kalimantan. Random Sampling Method has been done is performed by doctors, nurses, medical record officers, and midwives. Meanwhile, model testing has been done with Structural Equation Model (SEM) analysis technique. The results of this study show that computer self-efficacy factor is the most powerful factor influencing user's opinion about perceived ease of use and perceived the usefulness of E-Health (significant p <0.05), followed by compatibility, top management support, information quality, system quality, facilitating condition, service quality, complexity, and adaptability. Hospital management needs to work together as a team effort to medical practitioners to apply E-Health in hospitals. Supports and awareness from various parties, such as government, IT support, and resources are expected to help implement E-Health in rural areas. The result of this study could be a decision in taking steps to implement E-Health in the future, in order to improve services of people in rural areas.The E-Health is used to support information technology to maximize the tasks and medical services in the hospital. However, the hospital’s management still have some issues due to E-Health implementation, particularly in the interaction with the system. This study identifies significant factors affecting the implementation of E-Health. Testing a model has been done, to identify factors affecting E-Health acceptance. Quantitative Research methods has been done is implemented in this research, by conducting a survey of 150 respondents on health practitioners in the District Hospital of Gunung Mas Province of Central Kalimantan. Random Sampling Method has been done is performed by doctors, nurses, medical record officers, and midwives. Meanwhile, model testing has been done with Structural Equation Model (SEM) analysis technique. The results of this study show that computer self-efficacy factor is the most powerful factor influencing user's opinion about perceived ease of use and perceived the usefulness of E-Health (significant p <0.05), followed by compatibility, top management support, information quality, system quality, facilitating condition, service quality, complexity, and adaptability. Hospital management needs to work together as a team effort to medical practitioners to apply E-Health in hospitals. Supports and awareness from various parties, such as government, IT support, and resources are expected to help implement E-Health in rural areas. The result of this study could be a decision in taking steps to implement E-Health in the future, in order to improve services of people in rural areas
Design of AXI4-Stream based Modulator IP Core for Visible Light Communication System-on-Chip
Get PDFIn this paper, the design of AXI4-Stream based modulator IP core for Visible Light Communication is reported. The modulator IP core conforms to the AXI4-Stream protocol standard, which is widely used in System-on-Chip (SoC) design. There are three modulation types in this IP core namely, Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), and Quadrature Amplitude Modulation-16 (QAM-16). These modulation types are commonly used in the DCO-OFDM system. The modulation types can be selected programmatically from software that runs in the main processor by accessing the control register. The output of the modulator is designed for DCO-OFDM modulation using 64-point IFFT. According to the simulation results, this modulator IP core can achieve a throughput of 95.36 Mb/s, 184.77 Mb/s, and 347.81 Mb/s for BPSK, QPSK, and QAM-16, respectively. This modulator IP core is reusable in the DCO-OFDM system, so it increases productivity in DCO-OFDM system design.In this paper, the design of AXI4-Stream based modulator IP core for Visible Light Communication is reported. The modulator IP core conforms to the AXI4-Stream protocol standard, which is widely used in System-on-Chip (SoC) design. There are three modulation types in this IP core namely, Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), and Quadrature Amplitude Modulation-16 (QAM-16). These modulation types are commonly used in the DCO-OFDM system. The modulation types can be selected programmatically from software that runs in the main processor by accessing the control register. The output of the modulator is designed for DCO-OFDM modulation using 64-point IFFT. According to the simulation results, this modulator IP core can achieve a throughput of 95.36 Mb/s, 184.77 Mb/s, and 347.81 Mb/s for BPSK, QPSK, and QAM-16, respectively. This modulator IP core is reusable in the DCO-OFDM system, so it increases productivity in DCO-OFDM system design
Risk Factor Assessment of Software Usability Using Fuzzy-Analytic Hierarchy Process Method
Get PDFSoftware adds significant value to a wide range of products and services. Thus, in the process of software development, maintaining the quality of the software is an important aspect that the developer must do. In several software quality models, usability is stated as one of significant factor that gives impact to software performance. The existence of problems in usability will lead to less useful of the software. This research was conducted to assess software usability risk factors which derived from the attributes and sub-attributes of usability, that affecting the quality of the software negatively. The importance of risk factors assessed by using fuzzy-AHP that was used to identify the dominant factor that become the source of risk. The risk assessment on software usability with fuzzy methodology made it possible to process the evaluation of the respondents defined by linguistic format, in which information can be processed from the data were insufficient. This fuzzy methodology allowed to process the data that were subjective, inaccurate or vague.Software adds significant value to a wide range of products and services. Thus, in the process of software development, maintaining the quality of the software is an important aspect that the developer must do. In several software quality models, usability is stated as one of significant factor that gives impact to software performance. The existence of problems in usability will lead to less useful of the software. This research was conducted to assess software usability risk factors which derived from the attributes and sub-attributes of usability, that affecting the quality of the software negatively. The importance of risk factors assessed by using fuzzy-AHP that was used to identify the dominant factor that become the source of risk. The risk assessment on software usability with fuzzy methodology made it possible to process the evaluation of the respondents defined by linguistic format, in which information can be processed from the data were insufficient. This fuzzy methodology allowed to process the data that were subjective, inaccurate or vague
Prototype of Long-Range Radio Communication for e-Nelayan Devices using LoRaWAN
Get PDFIn this paper, development progress of a long-range radio communication-based fishing assistant system called e-Nelayan is reported. The purpose of the system is to increase the productivity, safety, and welfare of fishermen using mobile phone and long-range radio based system that enables them to report maritime violations, access and exchange information regarding weather, fishing area, marketplace, and also communication with mainland using Android-based mobile phone within extended range. We used LoRaWAN as a base technology for long-range communication scheme. In this work, the test conducted to obtain an insight to e-Nelayan device (LoRa-based) received RSSI and its packet loss. The received data collected in a server also includes the GPS tracking data. The test results show that our system reached approximately 5 km of distance between end-node to the LoRa Gateway within urban area (LoS configuration) and about 2 km for NLOS configuration.In this paper, development progress of a long-range radio communication-based fishing assistant system called e-Nelayan is reported. The purpose of the system is to increase the productivity, safety, and welfare of fishermen using mobile phone and long-range radio based system that enables them to report maritime violations, access and exchange information regarding weather, fishing area, marketplace, and also communication with mainland using Android-based mobile phone within extended range. We used LoRaWAN as a base technology for long-range communication scheme. In this work, the test conducted to obtain an insight to e-Nelayan device (LoRa-based) received RSSI and its packet loss. The received data collected in a server also includes the GPS tracking data. The test results show that our system reached approximately 5 km of distance between end-node to the LoRa Gateway within urban area (LoS configuration) and about 2 km for NLOS configuration
Analisis User Throughput Based Mobility Load Balancing Menggunakan Prediksi Regresi Logaritmik Reference Signal Received Quality Di Jaringan Akses Radio Long Term Evolution
No full textThe improvement of Long Term Evolution (LTE) radio access network services is affecting the increased value of traffic load in its network, which is causing traffic unbalance between cells in LTE Radio Access Network (RAN). Users will be served with ineffective resource block allocation which will make the total of gained throughput are not optimal. A method is required to move network load from overloaded cells to underloaded cells in order to balance the resource block allocation optimally. By using NS-3.26 simulation, User Throughput Based (UTB) predictive Mobility Load Balancing (MLB) method is tested with RandomWalkMobilityModel for each user. This method produces an improvement of 2,29 % in average of total throughput of 63,33 % successful optimization.The improvement of Long Term Evolution (LTE) radio access network services is affecting the increased value of traffic load in its network, which is causing traffic unbalance between cells in LTE Radio Access Network (RAN). Users will be served with ineffective resource block allocation which will make the total of gained throughput are not optimal. A method is required to move network load from overloaded cells to underloaded cells in order to balance the resource block allocation optimally. By using NS-3.26 simulation, User Throughput Based (UTB) predictive Mobility Load Balancing (MLB) method is tested with RandomWalkMobilityModel for each user. This method produces an improvement of 2,29 % in average of total throughput of 63,33 % successful optimization
Analysis of Position Angle of Arrival in Multipath Fading Channel using Correlated Double Ring Channel Model for VANET Communications
Get PDFCorrelated Double Ring channel modeling in the mobile to mobile communication system (M2M) and vehicular based communication system was pointed out. This modeling required the transmitter and receiver were randomly moving and surrounded by scatterers in a static ring. The scatterers’ positions were placed randomly at the radius of the ring of transmitter and receiver. Received signals were measured based on complex envelope parameters. Two signals propagation scenarios were implemented, they were signals of Rayleigh and Rician distributed. In order to calculate the Rayleigh and Rician complex envelope values, there were some parameters involved which were Angle of Arrival (AoA) and velocity of transmitter and receiver that created Doppler effects. The effects of AoA parameter were investigated towards envelope complex values of Rayleigh and Rician according to predetermined various velocities and scatterers’ positions were divided into four positions criteria. The simulation result shows that for scheme 2 at velocity 40 m/s, distribution magnitude for Rayleigh is 0,1 and Rician is 0,5. It concludes that Rician distribution always outperforms Rayleigh distribution for all predetermined velocities and this scheme give the largest magnitude over all. This is because of the closest distance between scatterers of transmitter and receiver. Also, certain velocities range over all scatterers’ positions, the magnitude of Rayleigh and Rician complex envelope have similar graphic tendency.Correlated Double Ring channel modeling in the mobile to mobile communication system (M2M) and vehicular based communication system was pointed out. This modeling required the transmitter and receiver were randomly moving and surrounded by scatterers in a static ring. The scatterers’ positions were placed randomly at the radius of the ring of transmitter and receiver. Received signals were measured based on complex envelope parameters. Two signals propagation scenarios were implemented, they were signals of Rayleigh and Rician distributed. In order to calculate the Rayleigh and Rician complex envelope values, there were some parameters involved which were Angle of Arrival (AoA) and velocity of transmitter and receiver that created Doppler effects. The effects of AoA parameter were investigated towards envelope complex values of Rayleigh and Rician according to predetermined various velocities and scatterers’ positions were divided into four positions criteria. The simulation result shows that for scheme 2 at velocity 40 m/s, distribution magnitude for Rayleigh is 0,1 and Rician is 0,5. It concludes that Rician distribution always outperforms Rayleigh distribution for all predetermined velocities and this scheme give the largest magnitude over all. This is because of the closest distance between scatterers of transmitter and receiver. Also, certain velocities range over all scatterers’ positions, the magnitude of Rayleigh and Rician complex envelope have similar graphic tendency