AN INTEGRATED APPROACH BASED ON ARTIFICIAL INTELLIGENCE USING ANFIS AND ANN FOR MULTIPLE CRITERIA REAL ESTATE PRICE PREDICTION

A relatively high level of precision is required in real estate valuation for investment purposes. Such estimates of value which is carried out by real estate professionals are relied upon by the end-users of such financial information having paid a certain fee for consultation hence leaving little room for errors. However, valuation reports are often criticised for their inability to be replicated by two or more valuers. Hence, stirring to a keen interest within the academic cycle leading to the need for exploring avenues to improve the price prediction ability of the professional valuer. This study, therefore, focuses on overcoming these challenges by introducing an integrated approach that combines ANFIS with ANN termed ANFIS-AN, thereby having a reiteration in terms of ANN application to fortify price predictability. Using 255 property data alongside 12 variables, the ANFIS-AN model was adopted and its outcome was compared with that of ANN. Finally, the results were subjected to 3 different error testing models using the same training and learning benchmarks. The proposed model’s RMSE gave 1.413169, while that of ANN showed 9.942206. Similarly, using MAPE, ANN recorded 0.256438 while ANFIS-AN had 0.208324. Hence, ANFIS-AN’s performance is laudable, thus a better tool over ANN.

Rancang Bangun Pembuat Layout PCB Otomatis Berbasis Android

ABSTRACT The purpose of this research is to produce an Android-based automatic PCB layout path maker tool. This tool can automatically create a PCB layout path without etching the PCB so that it can provide efficiency in making the PCB layout path. The research method used in this study used an experimental method with a quantitative approach. This research was conducted at the Jakarta State University Jakarta mechanical workshop laboratory in January 2020, testing carried out namely manual and automatic testing, manual testing including the making of lines and flat shapes using paper media and PCB boards, automatic testing includes making pcb lines automatically using media PCB board. The conclusion of this research is that the PCB Layout path making tool can automatically work as planned. The tool can make the PCB Layout path according to the design that is sent via Bluetooth communication serial. Automatic PCB layout maker tool has an average error percentage of under 5%. Testing is done in 2 ways, namely manual and automatic testing, in manual testing the average error is 0.297% and the automatic error testing is 0.136%. ABSTRAK Tujuan penelitian ini adalah menghasilkan alat pembuat jalur layout PCB otomatis berbasis android. Alat ini dapat membuat jalur layout PCB secara otomatis tanpa harus meng-etching PCB sehingga dapat memberikan efisiensi pada pembuatan jalur layout PCB. Metode penelitian yang digunakan dalam penelitian ini menggunakan metode eksperimen dengan pendekatan kuantitatif. Penelitian ini dilakukan di laboratorium bengkel mekanik Universitas Negeri Jakarta pada bulan Januari 2020, pengujian yang dilakukan yaitu pengujian secara manual dan otomatis, pengujian manual meliputi pembuatan garis dan bangun datar menggunakan media kertas dan papan PCB, pengujian otomatis meliputi pembuatan jalur pcb secara otomatis menggunakan media papan PCB. Kesimpulan dari penelitian ini adalah alat pembuat jalur Layout PCB secara otomatis dapat bekerja sesuai dengan yang di rencanakan. Alat dapat membuat jalur Layout PCB sesuai dengan desain yang dikirimkan melalui serial komunikasi Bluetooth. Alat pembuat layout PCB otomatis memiliki persentase error rata-rata di bawah 5%. Pengujian dilakukan dengan 2 cara yaitu pengujian manual dan otomatis, pada pengujian manual rata-rata error didapatkan sebesar 0,297% dan pengujian otomatis rata-rata error didapatkan sebesar 0.136%.

Experimental Demonstration of the Lower Leg Trajectory Error Framework Using Physiological Data as Inputs

While many studies have attempted to characterize the mechanical behavior of passive prosthetic feet to understand their influence on amputee gait, the relationship between mechanical design and biomechanical performance has not yet been fully articulated from a fundamental physics perspective. A novel framework, called lower leg trajectory error (LLTE) framework, presents a means of quantitatively optimizing the constitutive model of prosthetic feet to match a reference kinematic and kinetic dataset. This framework can be used to predict the required stiffness and geometry of a prosthesis to yield a desired biomechanical response. A passive prototype foot with adjustable ankle stiffness was tested by a unilateral transtibial amputee to evaluate this framework. The foot condition with LLTE-optimal ankle stiffness enabled the user to replicate the physiological target dataset within 16% root-mean-square (RMS) error. Specifically, the measured kinematic variables matched the target kinematics within 4% RMS error. Testing a range of ankle stiffness conditions from 1.5 to 24.4 N·m/deg with the same user indicated that conditions with lower LLTE values deviated the least from the target kinematic data. Across all conditions, the framework predicted the horizontal/vertical position, and angular orientation of the lower leg during midstance within 1.0 cm, 0.3 cm, and 1.5 deg, respectively. This initial testing suggests that prosthetic feet designed with low LLTE values could offer benefits to users. The LLTE framework is agnostic to specific foot designs and kinematic/kinetic user targets, and could be used to design and customize prosthetic feet.

Architecture neural network deep optimizing based on self organizing feature map algorithm

Forward neural network (FNN) execution relying on the algorithm of training and architecture selection. Different parameters using for nip out the architecture of FNN such as the connections number among strata, neurons hidden number in each strata hidden and hidden strata number. Feature architectural combinations exponential could be uncontrollable manually so specific architecture can be design automatically by using special algorithm which build system with ability generalization better. Determination of architecture FNN can be done by using the algorithm of optimization numerous. In this paper methodology new proposes achievement where FNN neurons respective with hidden layers estimation work where in this work collect algorithm training self organizing feature map (SOFM) with advantages to explain how the best architectural selected automatically by SOFM from criteria error testing based on architecture populated. Different size of dataset benchmark of 4 classifications tested for approach proposed.

Implementasi Fuzzy Tsukamoto dan IoT Pada Sistem Pendukung Keputusan Tingkat Kepadatan Lahan Parkir

Parking lots are a common thing in everyday life. The problem of parking lot's density can be a problem for managers of a place. So to overcome the problem that can occur, this study aims to design a decision support system (DSS) to determine the density of parking lots by applying the concept of IoT and Tsukamoto's fuzzy method. IoT is used to automate data retrieval to create fuzzy rule patterns. In the Tsukamoto method, each rule is represented by IF-THEN. The method for system design in this study includes the design of hardware and software. In this design, data retrieval uses an ultrasonic sensor HC-SR04 and is processed with the IoT concept using Arduino UNO and ESP8266 microcontrollers. The sensor is placed on the exit and entry path of the vehicle on the parking lot to detect vehicles entering and exiting. The parking lot used in this study is miniature. Vehicle data is processed using Tsukamoto's fuzzy logic to determine parking density decisions. Data variables used are time, duration, and density of parking lots. DSS is designed using the Laravel framework. Based on the test results, it is known that IoT devices can perform their functions properly. DSS that is made in the form of a website can also function well. The results are based on error testing, obtained error for determining the parking density level is 7,68%.

Analisis Perbandingan Metode Triple Exponential Smoothing dan Metode Winter Untuk Peramalan Tingkat Hunian Hotel Aston Denpasar

Aston Denpasar Hotel is one of the five-star hotels in Bali currently requires forecasting analysis because it has constraints in determining the number of occupancy rates in the next period. The choice of method in forecasting time series largely determines the results of forecasting, so this research is conducted to find the best method of the method to be used. The method used is Triple Exponential Smoothing one parameter from brown and Winter Multiplicative and Additive methods. Based on the analysis of the best method is the Triple Exponential Smoothing one parameter method of brown with the lowest error testing with MAPE that is equal to 23.35%. While the winter multiplicative method was 28.53% and the winter additive method was 27.38%

Clinical Changes in Cervical Neuromuscular Control Following Subconcussive Impacts

Context: Increased injury rates following concussive injury have been attributed to decreased neuromuscular coordination frequently documented following a concussion. However, altered integration between the vestibular system and oculomotor pathways following impacts at subconcussive thresholds implicate all sports-related impacts not just those at a concussive threshold in future musculoskeletal injury. While, several studies have explored the utility of vestibular and oculomotor clinical testing to detect altered neuromuscular control and then correlated those alterations to future injury risk, no research has explored the use of cervical clinical tests in the same capacity. Outcome Measures: Cervical joint position error test, Neck Disability Index and head acceleration. Interventions: Soccer headers, fatigue protocol, soccer headers + fatigue. Objective: To explore the clinical utility of a novel clinical approach to measuring changes in cervical neuromuscular control following subconcussive impacts in a controlled lab environment. Participants: 40 current female colligate club soccer athletes were recruited. Inclusion criteria included between the age of 18 and 25 and a minimum of 4-year soccer heading experience. Setting: Laboratory. Design: A repeated-measures design with 4 groups was utilized to test the hypothesis. Results: A 65%, 54%, and 49% increased error was observed following the soccer heading, fatigue only, and soccer heading + fatigue interventions, respectively. Meanwhile, the controls saw a 6% decrease in neck position error. Concussion: While, cervical joint position error testing was sensitive to decreased neuromuscular coordination following soccer heading, it was not specific enough to rule out an exercise effect in the absence of subconcussive impacts. Further research is warranted to explore the clinical utility and specificity of cervical joint position error testing to measured alterations in supraspinal processing following subconcussive impacts, and how these alterations may lead to decreased coordination and movement of the body during sports-related task.