TNI Journal of Engineering and Technology

A Study of Silk Yarn Dyeing with Natural Dye from Annatto Tree Seeds

2020-12-25T10:22:59+07:00

The purposes of this study were to investigate chemical properties, colour properties, colour fastness to washing and light as well as the comparing silk yarn dyeing from annatto seed extract with laboratory process. The research process included chemical measurement, wavelength measurement of the extract, silk yarn dyeing in the laboratory, color shades measurement with CIELAB, the test of color fastness to washing and light, and the color comparing between dyeing in the model and in the laboratory. Findings indicate that annatto seed extract was acid as its average pH 4.37 and composed of tannin, a phenolic compound, structured as disubstituted hydroxy aromatic (o – para hydroxyl aromatic) and anthraquinone, as a flavonoid compound. The color of the silk yarn after dyeing with annatto seed extract was orange – yellow with brightness (L*) was between 73.01 and 73.53 as the result of dyeing with Ca 4%, Alum 0.01% and the annatto seed extract. The red – green (a*) was between 31.80 and 32.17 and most of which was red as the result of dyeing with Ca1%, Alum 0.05% and the annatto seed extract. The yellow- blue (b*) was between 63.92 and 64.64 and most of which was yellow as the result of dyeing with Ca 1%, Alum 0.025%, and annatto seed extract. The colour fastness to washing of the dyed silk yarn was good meanwhile the colour fastness to light was between fair and good. The colour properties of dyeing in the model was not different from one in the laboratory.

Detection of COVID-19 using Deep Learning with CT Scan Images

2020-12-25T10:23:00+07:00

The demand of testing the potential infected patient of “new corona virus” or COVID-19 has been enormously increased as the virus is still continuously and immensely spread in many countries. The popular method of testing is to analyze the genetic material of the virus with reverse transcription - polymerase chain reaction (RT-PCR). Recently, the chest x-rays have been introduced to diagnose the infection as it is considered to be easier and crucial method in this circumstance, especially when combine with a deep learning that can recognize and detect the abnormality of lung parenchyma, in which considered to be the signature of COVID-19 effectively. The purpose of this article is to adapt the mask region-based convolutional neural networks (Mask RCNN) to segment the regions that had been affected by the virus by using computed tomography (CT) scan on the chest. The prediction of the tissues regions that have been damaged will help the medical team to classify if the patients are in ‘mild’ or ‘danger’ situation easier. From the model test result processed on google cloud platform, this model F1 scores equivalent to 89% and has the average of speed inference at 9.71 second.

Dimensional Blurring of Large Face Image Based on Structural Similarity

2020-12-25T10:23:01+07:00

Face masking is widely used in print media, digital media and various online images for privacy and security protection. This research proposes an innovative face-blurring method focusing on large face blurring in large image size which usually requires a high degree of blur level to anonymize face. This great blur causes the face to be flat or very smooth and lack of visual dimension. Therefore, this research exploits the local structural similarity between large blurred and original images with Gaussian filter and contrast adjustment to adaptively create an opacity map for smoothly and appropriately blurring of face components. The details of main components are then very blurry and difficult to recognize personal identity while other parts of the face are less blurred. This adaptively face smoothing can improve a sense of dimensional perception and help to visually anonymize the portrait more natural resulting in the higher average value of structural similarity to the original image. The proposed method can be further applied to an aesthetically image censoring.

Hybrid Energy Harvesting System Based on Regenerative Braking System and Suspension Energy Harvesting for Middle Electric Vehicle

2020-12-25T10:23:02+07:00

This research proposed a hybrid energy harvesting system (HEHS) based on Suspension Energy Harvesting using a regenerative shock absorber (RSA) with SC/Battery hybrid energy storage system (SCB-HESS) based regenerative braking system (RBS) for the middle electric vehicle (MEV). In the regenerative braking mode, the artificial neural network (ANN)-based RBS control mechanism was utilized to optimize the switching scheme of the three-phase inverter and transferred the braking energy to be stored in the energy storage devices. Furthermore, a supercapacitor-based RSA is capable of harvesting the vehicular suspension-vibration energy and converting it into electrical energy to extend energy storage devices. The experimental total energy harvesting efficiency of the supercapacitor-based RSA ranges between 21.74% and 49.93%, with an average total efficiency of 31.93%. In addition, the research findings revealed that the proposed hybrid energy harvesting system based on SCB-HESS-based RBS with suspension energy harvesting using RSA enhanced the regeneration efficiency of 31.75% compared with SCB-HESS-based RBS MEVs.

Improving the Performance of IEEE 802.11 DCF with Constant Contention Window by Reducing the Wasted Time Slots

2020-12-25T10:23:02+07:00

In the contention resolution of the IEEE 802.11 DCF algorithm with constant contention window, there may be wasted slots at the end of the frame. This paper proposes two algorithms to improve the performance of IEEE 802.11 DCF algorithm with constant contention window by using the method of reducing the wasted slots at the end of the frame. The first algorithm is reducing wasted slots at the end of last frame (RLF) and the second algorithm is reducing wasted slots at the end of every frames (REF). Based on the results, it is found that the REF algorithm offers superior performance and the RLF algorithm performs better than the IEEE 802.11 DCF with constant contention window algorithm. We can conclude that both proposed algorithms can improve system performance, especially when there are large amounts of slots per frame. The appropriate number of slots per frame should be used in order to ensure optimal system performance.

Local Maxima Niching Genetic Algorithm Based Automated Water Quality Management System for Betta splendens

2020-12-25T10:23:03+07:00

Rearing Betta splendens is one of the most popular aquarium hobbies around the world. There are many IoT solutions done so far to monitor the water quality of the aquarium. Some machine learning and IoT based solutions are also available to do regression on the sensor data. In this paper, we propose a new framework and algorithm to predict the abnormalities in water quality which may affect the health of the fish. The algorithm proposed in this paper uses a local maxima niching genetic algorithm for optimization which effectively finds the local maxima on the new data streaming in and provides the approximate timestamp on the next possible water change or treatment to avoid the fish from getting infected. Many existing timestamp methods are seasonal but in terms of optimization in terms of unpredictable environment such as water, there needs a better technique for optimization. The qualitative and quantitative results proved that the health of fish using the proposed framework had better living conditions and avoided the attack of parasitic infections than those in existing and normal captivity methods. The accuracy of the proposed methodology increased by 5% within the variations made.

Performance Testing between ZigBee, LoRa and IEEE1888 Networks in Community Energy Management System

2020-12-25T10:23:04+07:00

The Community Energy Management System (CEMS) with IEEE1888 standard comprises buildings with metering systems and gateways (GW), which are linked to the system for efficient data management, and wireless systems installed in various places, which ZigBee is mostly used with the limitation only on short-range communication. Therefore, this paper presents the system development that extends the transmission from within ZigBee range to LoRa through aggregator (AG) and enables the transmission to be forwarded to the system with IEEE 1888 standard. The test results can be divided into 3 parts as follows: (1) Received Signal Strength Indicator (RSSI). For ZigBee, RSSI value increases from 5 to 20 meters upon an additional repeater is installed within the building. For LoRa, the maximum coverage in the test area reaches 573 meters with RSSI value equal to -95.1 dBm. (2) AG test. The result finds that in the case of data transmission is consistent with the period of 700 milliseconds and higher, the success rate is 100%. However, in the case of random transmission, the success rate is only 60%. (3) GW test, which is conducted by comparing the hop between GW and server. For the distance of 1 hop, the Round Trip Time (RTT) value does not exceed 100 milliseconds. Nevertheless, for the distance of 18 hops, the RTT value increase more than 4 times. Consequently, the tests in this research can be used as a guideline for design and development to optimize the future system extension.