Sriwijaya University

Feature selection (FS) is one of the important tasks of data preprocessing in data analytics. The data with a large number of features will affect the computational complexity, increase a huge amount of resource usage and time consumption for data analytics. The objective of this study is to analyze relevant and significant features of huge network traffic to be used to improve the accuracy of traffic anomaly detection and to decrease its execution time. Information Gain is the most feature selection technique used in Intrusion Detection System (IDS) research. This study uses Information Gain, ranking and grouping the features according to the minimum weight values to select relevant and significant features, and then implements Random Forest (RF), Bayes Net (BN), Random Tree (RT), Naive Bayes (NB) and J48 classifier algorithms in experiments on CICIDS-2017 dataset. The experiment results show that the number of relevant and significant features yielded by Information Gain affects significantly the improvement of detection accuracy and execution time. Specifically, the Random Forest algorithm has the highest accuracy of 99.86% using the relevant selected features of 22, whereas the J48 classifier algorithm provides an accuracy of 99.87% using 52 relevant selected features with longer execution time.

Particle Swarm Optimization (PSO) is a biologically inspired computational search and optimization method developed in 1995 by Eberhart and Kennedy based on the social behaviors of birds flocking or fish schooling. A number of basic variations have been developed due to improve speed of convergence and quality of solution found by the PSO. On the other hand, basic PSO is more appropriate to process static, simple optimization problem. Modification PSO is developed for solving the basic PSO problem. The observation and review 46 related studies in the period between 2002 and 2010 focusing on function of PSO, advantages and disadvantages of PSO, the basic variant of PSO, Modification of PSO and applications that have implemented using PSO. The application can show which one the modified or variant PSO that haven't been made and which one the modified or variant PSO that will be developed.

BACKGROUND: Information technology has shifted paper-based documentation in the health care sector into a digital form, in which patient information is transferred electronically from one place to another. However, there remain challenges and issues to resolve in this domain owing to the lack of proper standards, the growth of new technologies (mobile devices, tablets, ubiquitous computing), and health care providers who are reluctant to share patient information. Therefore, a solid systematic literature review was performed to understand the use of this new technology in the health care sector. To the best of our knowledge, there is a lack of comprehensive systematic literature reviews that focus on Fast Health Interoperability Resources (FHIR)-based electronic health records (EHRs). In addition, FHIR is the latest standard, which is in an infancy stage of development. Therefore, this is a hot research topic with great potential for further research in this domain. OBJECTIVE: The main aim of this study was to explore and perform a systematic review of the literature related to FHIR, including the challenges, implementation, opportunities, and future FHIR applications. METHODS: In January 2020, we searched articles published from January 2012 to December 2019 via all major digital databases in the field of computer science and health care, including ACM, IEEE Explorer, Springer, Google Scholar, PubMed, and ScienceDirect. We identified 8181 scientific articles published in this field, 80 of which met our inclusion criteria for further consideration. RESULTS: The selected 80 scientific articles were reviewed systematically, and we identified open questions, challenges, implementation models, used resources, beneficiary applications, data migration approaches, and goals of FHIR. CONCLUSIONS: The literature analysis performed in this systematic review highlights the important role of FHIR in the health care domain in the near future.

Pada masa pandemi Covid-19 pendidikan dilakukan secara daring atau online dari rumah masing-masing untuk mencegah dan menghindari penyebaran virus Covid-19. Oleh karena itu artikel ini bertujuan menjelaskan perkembangan pendidikan Indonesia di masa pandemi Covid-19 dan memberikan solusi yang tepat untuk pembelajaran daring. Metode penelitian yang digunakan adalah studi kepustakaan yang diperoleh dari dokumen, artikel, maupun berita yang berkaitan dengan pembelajaran daring selama Covid-19. Data yang telah terkumpul dianalisis dengan menggunakan metode deskriptif yaitu metode penelitian yang berusaha mengungkap fakta kejadian yang ditulis dalam pernyataan-pernyataan yang berasal dari sumber data yang diteliti. Hasil penelitian ini adalah menjelaskan bagaimana proses dan permasalahan yang ada selama pembelajaran daring. Selain itu memberikan beberapa masukan yang dapat dilakukan untuk menyelesaikan permasalahan yang ada di pembelajaran daring selama pandemi Covid-19. Pembelajaran yang dilakukan secara daring menjadi salah satu solusi dalam menjalankan pendidikan Indonesia dimasa pandemi Covid-19 ini sehingga pembelajaran dapat berjalan dengan baik untuk mencapai tujuan pembelajaran sebenarnya.

Support Vector Machines (SVM) is one of machine learning methods that can be used to perform classification task. Many researchers using SVM library to accelerate their research development. Using such a library will save their time and avoid to write codes from scratch. LibSVM is one of SVM library that has been widely used by researchers to solve their problems. The library also integrated to WEKA, one of popular Data Mining tools. This article contain results of our work related to complexity analysis of Support Vector Machines. Our work has focus on SVM algorithm and its implementation in LibSVM. We also using two popular programming languages i.e C++ and Java with three different dataset to test our analysis and experiment. The results of our research has proved that the complexity of SVM (LibSVM) is O(n3) and the time complexity shown that C++ faster than Java, both in training and testing, beside that the data growth will be affect and increase the time of computation.

BACKGROUND: As Indonesia moves to provide health coverage for all citizens, understanding patterns of morbidity and mortality is important to allocate resources and address inequality. The Global Burden of Disease 2016 study (GBD 2016) estimates sources of early death and disability, which can inform policies to improve health care. METHODS: We used GBD 2016 results for cause-specific deaths, years of life lost, years lived with disability, disability-adjusted life-years (DALYs), life expectancy at birth, healthy life expectancy, and risk factors for 333 causes in Indonesia and in seven comparator countries. Estimates were produced by location, year, age, and sex using methods outlined in GBD 2016. Using the Socio-demographic Index, we generated expected values for each metric and compared these against observed results. FINDINGS: In Indonesia between 1990 and 2016, life expectancy increased by 8·0 years (95% uncertainty interval [UI] 7·3-8·8) to 71·7 years (71·0-72·3): the increase was 7·4 years (6·4-8·6) for males and 8·7 years (7·8-9·5) for females. Total DALYs due to communicable, maternal, neonatal, and nutritional causes decreased by 58·6% (95% UI 55·6-61·6), from 43·8 million (95% UI 41·4-46·5) to 18·1 million (16·8-19·6), whereas total DALYs from non-communicable diseases rose. DALYs due to injuries decreased, both in crude rates and in age-standardised rates. The three leading causes of DALYs in 2016 were ischaemic heart disease, cerebrovascular disease, and diabetes. Dietary risks were a leading contributor to the DALY burden, accounting for 13·6% (11·8-15·4) of DALYs in 2016. INTERPRETATION: Over the past 27 years, health across many indicators has improved in Indonesia. Improvements are partly offset by rising deaths and a growing burden of non-communicable diseases. To maintain and increase health gains, further work is needed to identify successful interventions and improve health equity. FUNDING: The Bill & Melinda Gates Foundation.

Particle Swarm Optimization (PSO) is a biologically inspired computational search and optimization method developed in 1995 by Eberhart and Kennedy based on the social behaviors of birds flocking or fish schooling.A number of basic variations have been developed due to improve speed of convergence and quality of solution found by the PSO.On the other hand, basic PSO is more appropriate to process static, simple optimization problem.Modification PSO is developed for solving the basic PSO problem.The observation and review 46 related studies in the period between 2002 and 2010 focusing on function of PSO, advantages and disadvantages of PSO, the basic variant of PSO, Modification of PSO and applications that have implemented using PSO.The application can show which one the modified or variant PSO that haven't been made and which one the modified or variant PSO that will be developed.

Latar Belakang: Kesehatan mental merupakan sektor penting dalam mewujudkan kesehatan secaramenyeluruh. Terdapat sekitar 450 juta orang menderita gangguan mental dan perilaku di seluruh dunia,terbanyak di India (4,5%). Satu dari empat orang menderita satu atau lebih gangguan mental selama masahidup mereka. Gangguan mental jika tidak ditangani dengan tepat, akan bertambah parah, dan akhirnya dapatmembebani keluarga, masyarakat, serta pemerintah. Studi ini bertujuan mengetahui situasi kesehatan mentalpada masyarakat Indonesia dan strategi penanggulangannya.Metode: Tulisan ini menggunakan analisis deskriptif eksploratif, melalui tinjauan literatur dan kajian datasekunder. Unit analisis yaitu situasi kesehatan mental di Indonesia.Hasil Penelitian: Berdasarkan kajian data Riskesdas 2013 diketahui prevalensi gangguan mental berat padapenduduk Indonesia 1,7%, terbanyak di Yogyakarta, Aceh, Sulawesi Selatan. Adapun gangguan mentalemosional dengan gejala-gejala depresi dan kecemasan sekitar 6%. Hingga saat ini, masih terdapat stigmadan diskriminasi terhadap orang dengan gangguan mental di Indonesia, sehingga mengalami penangananserta perlakuan salah seperti pemasungan. Oleh karena itu strategi yang optimal perlu dilakukan bagi setiapindividu, keluarga dan masyarakat dengan pendekatan promotif, preventif, kuratif, dan rehabilitatif secaramenyeluruh, terpadu dan berkesinambungan. Kesehatan mental dapat ditingkatkan dengan intervensikesehatan masyarakat yang efektif. Paradigma dalam gerakan kesehatan mental yang lebih mengedepankanpada aspek pencegahan serta peran komunitas untuk membantu optimalisasi fungsi mental individu.Kesimpulan: Masih banyaknya kasus gangguan kesehatan mental pada masyarakat, dan penanganannyayang salah di Indonesia. Pemerintah perlu melakukan upaya penanggulangan yang menyeluruh, dimulaiadanya peraturan kebijakan yang menjadi dasar dukungan pendanaan dan akses ke pelayanan kesehatanmental serta didukung pendekatan berbasis komunitas.Kata kunci: adanya peraturan kebijakan yang menjadi dasar dukungan pendanaan dan akses ke pelayanan kesehatanmental serta didukung pendekatan berbasis komunitas.Kata kunci: Depresi, gangguan mental, psikososial, psikososial, skizofrenia., gangguan mental, psikososial, pemasungan, skizofrenia.

Intruders have become more and more sophisticated thus a deterrence mechanism such as an intrusion detection systems (IDS) is pivotal in information security management. An IDS aims at capturing and repealing any malignant activities in the network before they can cause harmful destruction. An IDS relies on a well-trained classification model so the model is able to identify the presence of attacks effectively. This paper compares the performance of IDS by exerting random forest classifier with respect to two performance measures, i.e. accuracy and false alarm rate. Three public intrusion data sets, i.e NSL-KDD, UNSW-NB15, and GPRS are employed in the experiment. Furthermore, different tree-size ensembles are considered whilst other best learning parameters are obtained using a grid search. Our experimental results prove the superiority of random forest model for IDS as it significantly outperforms the similar ensemble, i.e. ensemble of random tree + naive bayes tree and other single classifier, i.e. naive bayes and neural network in terms of k-cross validation method.

The purpose of this study is to illuminate the motivation of the students at English Department of Sriwijaya Polytechnics toward their online learning during the Covid-19 pandemic era. Due to sudden transformation from traditional face-to-face learning approach to remotely digital learning, some present studies revealed that students’ motivation in online learning was affected both intrinsically and extrinsically. Using snowball sampling, there were eight students participated in individual interviews and fourteen students in focus group interviews. The gained data from both interviews were analysed using thematic analysis. It was revealed that the students’ motivation toward their online learning was intrinsically affected more by their ambition to learn new knowledge and enjoyment in experiencing new learning method. It was also influenced extrinsically by external regulation and environmental condition. However, amotivation or the state of lack motivation also happened due to poor external supporting facilities.

The selection of biomaterials for bearing in total hip arthroplasty is very important to avoid various risks of primary postoperative failure for patients. The current investigation attempts to analyze the Tresca stress of metal-on-metal bearings with three different materials, namely, cobalt chromium molybdenum (CoCrMo), stainless steel 316L (SS 316L), and titanium alloy (Ti6Al4V). We used computational simulations using a 2D axisymmetric finite element model to predict Tresca stresses under physiological conditions of the human hip joint during normal walking. The simulation results show that Ti6Al4V-on-Ti6Al4V has the best performance to reduce Tresca stress by 45.76% and 39.15%, respectively, compared to CoCrMo-on-CoCrMo and SS 316L-on-SS 316L.

The electrocardiogram (ECG) is a widely used, noninvasive test for analyzing arrhythmia. However, the ECG signal is prone to contamination by different kinds of noise. Such noise may cause deformation on the ECG heartbeat waveform, leading to cardiologists’ mislabeling or misinterpreting heartbeats due to varying types of artifacts and interference. To address this problem, some previous studies propose a computerized technique based on machine learning (ML) to distinguish between normal and abnormal heartbeats. Unfortunately, ML works on a handcrafted, feature-based approach and lacks feature representation. To overcome such drawbacks, deep learning (DL) is proposed in the pre-training and fine-tuning phases to produce an automated feature representation for multi-class classification of arrhythmia conditions. In the pre-training phase, stacked denoising autoencoders (DAEs) and autoencoders (AEs) are used for feature learning; in the fine-tuning phase, deep neural networks (DNNs) are implemented as a classifier. To the best of our knowledge, this research is the first to implement stacked autoencoders by using DAEs and AEs for feature learning in DL. Physionet’s well-known MIT-BIH Arrhythmia Database, as well as the MIT-BIH Noise Stress Test Database (NSTDB). Only four records are used from the NSTDB dataset: 118 24 dB, 118 −6 dB, 119 24 dB, and 119 −6 dB, with two levels of signal-to-noise ratio (SNRs) at 24 dB and −6 dB. In the validation process, six models are compared to select the best DL model. For all fine-tuned hyperparameters, the best model of ECG heartbeat classification achieves an accuracy, sensitivity, specificity, precision, and F1-score of 99.34%, 93.83%, 99.57%, 89.81%, and 91.44%, respectively. As the results demonstrate, the proposed DL model can extract high-level features not only from the training data but also from unseen data. Such a model has good application prospects in clinical practice.

The green concrete capable for sustainable development is characterized by application of industrial wastes to reduce pollution of the environment. Fly ash processed with nanotechnology developed by Indonesia Center for Ceramics using Polishing Liquid Milling Technology. Nanomaterial concrete is new generation concrete formed of materials of the grain size of nanoscale. The materials used in this research were cement type I, nanosilica 10 - 150 nm, quartz powder in 0.3 - 25.0 μm, fine sand (quartz of sand) size of 50 - 650 μm, coarse aggregate in 5 - 10 mm, and superplasticizer. In this paper, mechanisms are discussed by which the incorporation of nanomaterials in concrete enhances durability to sulfate attack. Application of nanotechnology is an effective way to reduce environment pollution and improve durability of concrete. For countries like Indonesia, this technology can play an important role in meeting the huge demand for infrastructure in a sustainable manner.

Clustering is one of the main task in datamining. It is useful to group and cluster the data. There are a few ways to cluster the data such as partitional-based, hierarchical-based and density based. Partitional-based clustering is a way to cluster data with non-overlapping subsets. One of the most popular partitional-based clustering algorithm is K-means. K-means is an algorithm to cluster data in to K cluster and based their distance to its centroid. Due to the pational, a few factors that must be determined before using K-means is the value of K. Determining the value of K is a big problem because there is no universal way to find the value of K. Two popular ways to determine the value of K is using elbow and silhouette method. This method is graph based. But before using this method another factor is important to determine and that is the metrics distance that will be used. This paper will show the effect of three distance metric Manhattan, Euclidian and Minkowski in finding the value of K using elbow and silhouette method. Based on this study the choice of distance matrix used has little impact in determining the value of K in K-means using elbow and silhouette. Manhattan distance has the most variant in the elbow and silhouette graph. Elbow method is difficult to use and sometimes it is unable to define the value of K in K-means based on its graph.

Wear and wear-induced debris is a significant factor in causing failure in implants. Reducing contact pressure by using a textured surface between the femoral head and acetabular cup is crucial to improving the implant's life. This study presented the effect of surface texturing as dimples on the wear evolution of total hip arthroplasty. It was implemented by developing finite element analysis from the prediction model without dimples and with bottom profile dimples of flat, drill, and ball types. Simulations were carried out by performing 3D physiological loading of the hip joint under normal walking conditions. A geometry update was initiated based on the patient's daily routine activities. Our results showed that the addition of dimples reduced contact pressure and wear. The bottom profile dimples of the ball type had the best ability to reduce wear relative to the other types, reducing cumulative linear wear by 24.3% and cumulative volumetric wear by 31% compared to no dimples. The findings demonstrated that surface texturing with appropriate dimple bottom geometry on a bearing surface is able to extend the lifetime of hip implants.

Abstract Mitochondria are morphologically dynamic organelles constantly undergoing processes of fission and fusion that maintain integrity and bioenergetics of the organelle: these processes are vital for cell survival. Disruption in the balance of mitochondrial fusion and fission is thought to play a role in several pathological conditions including ischemic heart disease. Proteins involved in regulating the processes of mitochondrial fusion and fission are therefore potential targets for pharmacological therapies. Mdivi‐1 is a small molecule inhibitor of the mitochondrial fission protein Drp1. Inhibiting mitochondrial fission with Mdivi‐1 has proven cytoprotective benefits in several cell types involved in a wide array of cardiovascular injury models. On the other hand, Mdivi‐1 can also exert antiproliferative and cytotoxic effects, particularly in hyperproliferative cells. In this review, we discuss these divergent effects of Mdivi‐1 on cell survival, as well as the potential and limitations of Mdivi‐1 as a therapeutic agent.

In designing porous scaffolds, permeability is essential to consider as a function of cell migration and bone tissue regeneration. Good permeability has been achieved by mimicking the complexity of natural cancellous bone. In this study, a porous scaffold was developed according to the morphological indices of cancellous bone (porosity, specific surface area, thickness, and tortuosity). The computational fluid dynamics method analyzes the fluid flow through the scaffold. The permeability values of natural cancellous bone and three types of scaffolds (cubic, octahedron pillar, and Schoen’s gyroid) were compared. The results showed that the permeability of the Negative Schwarz Primitive (NSP) scaffold model was similar to that of natural cancellous bone, which was in the range of 2.0 × 10−11 m2 to 4.0 × 10−10 m2. In addition, it was observed that the tortuosity parameter significantly affected the scaffold’s permeability and shear stress values. The tortuosity value of the NSP scaffold was in the range of 1.5–2.8. Therefore, tortuosity can be manipulated by changing the curvature of the surface scaffold radius to obtain a superior bone tissue engineering construction supporting cell migration and tissue regeneration. This parameter should be considered when making new scaffolds, such as our NSP. Such efforts will produce a scaffold architecturally and functionally close to the natural cancellous bone, as demonstrated in this study.

As most of the pristine forests of South-east Asia have been lost, the ability of its animal species to coexist with humans becomes increasingly important. Dian's tarsier Tarsius dianae , one of the smallest primates, lives in forests of central Sulawesi, Indonesia that are experiencing a dramatic increase in degradation by humans. To evaluate the effects of anthropogenic disturbance on tarsiers we used a comprehensive approach to estimate habitat suitability for these nocturnal insecthunters. On four study plots along a gradient of human land-use we determined population densities, home range sizes, nightly path lengths and group sizes of T. dianae . In total we captured 71 individuals and radio-tracked 30 of these. In more undisturbed sites, population densities were high and travel distances small. We found the smallest home ranges in slightly disturbed forest. In a heavily disturbed plantation densities were low, and ranges and nightly path lengths were large. These results show that undisturbed and slightly degraded forests are the most suitable tarsier habitats, and that focusing on different population parameters could lead to differing conclusions about the suitability of particular habitats.

This study aims to determine the determinant of customer satisfaction and their implications for consumer loyalty. The method used in this study is a survey method. The population in this study is that consumers who have use the services of tour and travel companies in South Sumatra. This research use of purposive sampling technique. To meet the minimum requirements path analysis then taken sample of 200 respondents to the provisions of the election to travel agencies customers in South Sumatra. The results showed that there are influences between the variables of service quality, trust and corporate image on consumer satisfaction. There is influence between service quality and customer satisfaction. There is influence between trust and customer satisfaction. There are influences between service quality, trust and customer satisfaction on consumer loyalty. There is influence between service quality and customer loyalty. There is no influence between trusts on customer loyalty. There is influence between customer satisfaction and customer loyalty.

The researce objective was to the effect of different drying temperatures and times on the characteristics of fish salted Siamese gourami (Trichogaster pectoralis) using oven. This research was conducted on October until November 2012 in the Fishery Processing Technology Laboratory, Faculty of Agriculture and Bioproses Laboratory, Faculty of Engineering, Sriwijaya University of Indralaya. The research used Factorial Randomized Completely Block design with 3 difference drying temperature and 5 difference time then 2 replicated. The treatment of temperature (50oC, 60oC and 70oC) and time (0, 6, 12, 18 and 24 hours). Parameters observed were moisture content, ash content, fat content, protein content, carbohydrate content, hedonic quality test : appearance, aroma, flavor and texture. The results showed that the difference drying temperature and drying time was significant on moisture content, ash content, fat content, protein content, carbohydrate content, hedonic quality test : appearance, aroma, flavor and texture. Interaction of kinds of different drying temperatures and times had significant effect on moisture content, ash content, protein content and carbohydrate content. The best treatment was combination of T3t2 with oven temperature 70°C for 12 hours with moisture content 39.05%, ash content 6.85%, protein content 42.41 %, fat content 10.22%, carbohydrate content 1.66%, appearance 7.8, aroma 7.08, and flavor 7.08 and texture 7.82