Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Not a member yet
424 research outputs found
Sort by
Document Preprocessing with TF-IDF to Improve the Polarity Classification Performance of Unstructured Sentiment Analysis
Get PDFSentiment analysis in terms of polarity classification is very important in everyday life, with the existence of polarity, many people can find out whether the respected document has positive or negative sentiment so that it can help in choosing and making decisions. Sentiment analysis usually done manually. Therefore, an automatic sentiment analysis classification process is needed. However, it is rare to find studies that discuss extraction features and which learning models are suitable for unstructured sentiment analysis types with the Amazon food review case. This research explores some extraction features such as Word Bags, TF-IDF, Word2Vector, as well as a combination of TF-IDF and Word2Vector with several machine learning models such as Random Forest, SVM, KNN and Naïve Bayes to find out a combination of feature extraction and learning models that can help add variety to the analysis of polarity sentiments. By assisting with document preparation such as html tags and punctuation and special characters, using snowball stemming, TF-IDF results obtained with SVM are suitable for obtaining a polarity classification in unstructured sentiment analysis for the case of Amazon food review with a performance result of 87,3 percent
Leave Management Information System using InsideDPS Software for the Efficiency of Human Resources Management
Get PDFThe purpose of this research is to study the management information system and the benefits of InsideDPS software. The study was designed with an embeded mixed method, namely quantitative-qualitative-quantitative. The questionnaire as a quantitative tool was built based on previous research (MSQ), distributed to 250 employees and 198 sets of analyzed multiple linear regression. The questionnaire was distributed 2 times, before and after qualitative research. Interviews, observation and document collection were held with informants for HR managers, IT managers, and selected employees. This study found evidence that MIS InsideDPS software can support HRD performance improvement which is also supported by increased employee satisfaction. The technical implication of the findings of this study is the need for a wider web-based MIS application in the compan
Attention-based CNN-BiLSTM for Dialect Identification on Javanese Text
Get PDFThis study proposes a hybrid deep learning models called attention-based CNN-BiLSTM (ACBiL) for dialect identification on Javanese text. Our ACBiL model comprises of input layer, convolution layer, max pooling layer, batch normalization layer, bidirectional LSTM layer, attention layer, fully connected layer and softmax layer. In the attention layer, we applied a hierarchical attention networks using word and sentence level attention to observe the level of importance from the content. As comparison, we also experimented with other several classical machine learning and deep learning approaches. Among the classical machine learning, the Linear Regression with unigram achieved the best performance with average accuracy of 0.9647. In addition, our observation with the deep learning models outperformed the traditional machine learning models significantly. Our experiments showed that the ACBiL architecture achieved the best performance among the other deep learning methods with the accuracy of 0.9944
Live Forensics Method for Acquisition on the Solid State Drive (SSD) NVMe TRIM Function
Get PDFSSD currently has a new storage media technology namely Solid State Drive Non-volatile Memory Express (SSD NVMe). In addition, SSD has a feature called TRIM. The TRIM feature allows the operating system to tell SSDs which blocks are not used. TRIM removes blocks that have been marked for removal by the operating system. However, the TRIM function has a negative effect for the digital forensics specifically related to data recovery. This study aimed to compare the TRIM disable and enable functions to determine the ability of forensics tools and recovery tools to restore digital evidence on the NVMe SSD TRIM function. The operating system used in this study was Windows 10 professional with NTFS file system. Typically, acquisition is conducted by using traditional or static techniques. Therefore, there was a need of a technique to acquire SSD by using the live forensics method without shutting down the running operating system. The live forensics method was applied to acquire SSD NVMe directly to the TRIM disable and enable functions. The tools used for live acquisition and recovery were FTK Imager Portable. The inspection and analysis phases used Sleutkit Autopsy and Belkasoft Evidence Center. This research found that in the recovery process of TRIM disabled and enabled, TRIM disabled could find evidence while maintaining the integrity of evidence. It was indicated by the same hash value of the original file and the recovery file. Conversely, when TRIM is enabled, the files were damaged and could not be recovered. The files were also not identical to the original so the integrity of evidence was not guaranteed
Time Optimization for Radius Updates in Zone Dynamics of Zone Routing Protocol
Get PDFVehicular ad hoc networks are wireless network technologies that can be used to communicate without the need for fixed infrastructure. The use of zone routing protocol which is a hybrid routing protocol in a vehicular ad hoc network environment can reduce delay, packet flooding, and excess bandwidth usage on the network. However, traditional zone routing protocol is only configured for one fixed radius value, which makes it not adapt to existing network conditions. Zone dynamics with adaptive radius values in zone routing protocol are used so that zones formed by nodes are more optimal. In adapting the radius value to make the zone dynamics necessary, the optimal configuration of the radius update time is required. Simulations and tests that have been carried out with NS-2 show that the proper update time can improve zone routing protocol performance with a low end-to-end delay and routing overhead value, but has a high packet delivery ratio
Context-Aware Smart Door Lock with Activity Recognition Using Hierarchical Hidden Markov Model
Get PDFContext-Aware Security demands a security system such as a Smart Door Lock to be flexible in determining security levels. The context can be in various forms; a person’s activity in the house is one of them and is proposed in this research. Several learning methods, such as Naïve Bayes, have been used previously to provide context-aware security systems, using related attributes. However conventional learning methods cannot be implemented directly to a Context-Aware system if the attribute of the learning process is low level. In the proposed system, attributes are in forms of movement data obtained from a PIR Sensor Network. Movement data is considered low level because it is not related directly to the desired context, which is activity. To solve the problem, the research proposes a hierarchical learning method, namely Hierarchical Hidden Markov Model (HHMM). HHMM will first transform the movement data into activity data through the first hierarchy, hence obtaining high level attributes through Activity Recognition. The second hierarchy will determine the security level through the activity pattern. To prove the success rate of the proposed method a comparison is made between HHMM, Naïve Bayes, and HMM. Through experiments created in a limited area with real sensed activity, the results show that HHMM provides a higher F1-Measure than Naïve Bayes and HMM in determining the desired context in the proposed system. Besides that, the accuracies obtained respectively are 88% compared to 75% and 82%
Development and Optimization of NoSQL Database in Food Insecurity Early Warning System Based on Local Community Participation
Get PDFAs a part of the food insecurity early warning system based on local participation, a robust and scalable database service is required. This necessity caused by the large area of services which include 34 provinces, 416 districts, 7,215 sub-districts and 80,534 villages in Indonesia. The abundant number of the expected daily transaction might not be handled properly using the traditional model. In this research, we design, implement, and optimize the NoSQL database to create scalable, dynamic, and flexible database service for the early warning system. The cohesion of the model is then measured, resulting in 5 entities with high cohesion, 16 with moderate cohesion, and 3 with low cohesion. After refactoring, we reduced the number of the low-cohesion entity into one and increased the average cohesion from 0.62 to 0.67. An empirical experiment was conducted to compare the response time before and after the refactoring. As the results, the average response time is decreased from 11.0 ms to 7.99 ms or equal to 1.38 in speedup. The experiment results suggest there is an impact of the logical data model improvement, by increasing their cohesion, to the performance of the NoSQL database
A Performance Analysis of General Packet Radio Service (GPRS) and Narrowband Internet of Things (NB-IoT) in Indonesia
Get PDFInternet of Things (IoT) refers to a concept connecting any devices onto the internet. The IoT devices cannot only use a service or server to be controlled at a distance but also to do computation. IoT has been applied in many fields, such as smart cities, industries, and logistics. The sending of IoT data can use the existing GSM networks such as GPRS. However, GPRS is not dedicated particularly to the transmission of IoT data in consideration of its weaknesses in terms of coverage and power efficiency. To increase the performance of the transmission of IoT data, Narrowband-IoT (NB-IoT), one alternative to replace GPRS, is offered for its excellence in coverage and power. This paper aims to compare the GPRS and NB-IoT technology for the transmission of IoT data, specifically in Bandung region, Indonesia. The results obtained showed that the packet loss from clients for the GPRS network was at 68%, while the one for NB-IoT was at 44%. Moreover, NB-IoT technology was found excellent in terms of battery saving compared to GPRS for the transmission of IoT data. This result showed that NB-IoT was found more suitable for transmitting the IoT data compared to GPRS
Visualization of Granblue Fantasy Game Traffic Pattern Using Deep Packet Inspection Method
Get PDFGranblue Fantasy is one of Role Playing Games (RPG). It’s a video role-playing game developed by Cygames. This research to observes the Granblue Fantasy Game. The purpose is to analyze the traffic data of the Granblue Fantasy to find the pattern using Deep Packet Inspection (DPI), Capturing the Data Traffic, Feature Extraction Process and Visualize the Pattern. The Pattern are Gacha, Solo Raid, Casino and Multiraid. This research demonstrate that Multiraid battle has more data than other pattern with TTL 237
Hopscotch Game to Support Stimulus in Children’s Gross Motor Skill using IoT
Get PDFEvery movement that has connection to stability and coordination between each body part were accounted as the gross motor skill system. If gross motor skill development were interrupted especially for 3-5 years old, their activities would be negatively affected. Foot-based games such as jumping and stepping can be used to train a child's motor balance. One example of a famous traditional game is hopscotch. Hopscotch is a game that demand high flexibility of foot movement a coordination skills thus proved scientifically can train children gross motor skill system. Various types of hopscotch games have the potential to improve children's dynamic balance. But in traditional hopscotch games it is difficult to see how the mechanism of improving children's dynamic balance is established. The development of a child's dynamic balance cannot be constantly tracked by teachers or parents. Therefore, we design and create hopscotch with an automated system that can overcome these limitations with digital records, data stored safely, system requirements easily duplicated, and more accurate. In the Hopscotch game, there are features, namely levels 1–3, and memory test, where the memory test serves to train children's memory. The hopscotch game using Footstep based capacitive sensor and LED feedback, the improved gameplay used for training and measuring child’s gross motor skill system by their time completion and true/false footstep ratio. As the result the IoT based Hopscotch game with randomized lane are successfully mimic hopscotch gameplay with its added gameplay feature, the player subject performance has increased adaptability performance through each level the capacitive sensor-based footprint system has shown 100% accuracy, the system fully response to the footstep with average 456 milliseconds reading time per step, the system interface can fully control the gameplay level and can show players performance