Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

Putrada, Aji Gautama; Abdurohman, Maman; Perdana, Doan; Nuha, Hilal Hudan

doi:10.1109/access.2022.3169765

Cited by 43 publications

(17 citation statements)

References 384 publications

(278 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The test results show that SMOTE on naïve Bayes is more effective than SMOTE on KNN. According to the paper [33], naïve Bayes and KNN have very different characteristics. Naïve Bayes has a high bias and low variance model.…”

Section: B Discussionmentioning

confidence: 99%

Overcoming Data Imbalance Problems in Sexual Harassment Classification with SMOTE

Putrada

Wijaya²,

Oktaria³

2022

ijoict

Self Cite

View full text Add to dashboard Cite

Delivery of justice with the help of artificial intelligence is a current research interest. Machine learning with natural language processing (NLP) can classify the types of sexual harassment experiences into quid pro quo (QPQ) and hostile work environments (HWE). However, imbalanced data are often present in classes of sexual harassment classification on specific datasets. Data imbalance can cause a decrease in the classifier's performance because it usually tends to choose the majority class. This study proposes the implementation and performance evaluation of the synthetic minority over-sampling technique (SMOTE) to improve the QPQ and HWE harassment classifications in the sexual harassment experience dataset. The term frequency-inverse document frequency (TF-IDF) method applies document weighting in the classification process. Then, we compare naïve Bayes with K-Nearest Neighbor (KNN) in classifying sexual harassment experiences. The comparison shows that the performance of the naïve Bayes classifier is superior to the KNN classifier in classifying QPQ and HWE, with AUC values of 0.95 versus 0.92, respectively. The evaluation results show that by applying the SMOTE method to the naïve Bayes classifier, the precision of the minority class can increase from 74% to 90%.

show abstract

Section: B Discussionmentioning

confidence: 99%

Overcoming Data Imbalance Problems in Sexual Harassment Classification with SMOTE

Putrada

Wijaya²,

Oktaria³

2022

ijoict

Self Cite

View full text Add to dashboard Cite

show abstract

“…Internet of things (IoT) [6][7][8][9] can connect people with devices and can share data in real time. IoT makes it easier for humans to do various jobs.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of LoRaWAN Class A and Class C in the Measurement of Nutrient Content Systems

2023

IJIES

View full text Add to dashboard Cite

This research was evaluated the measurement of the nutrient contents of Nitrogen (N), Phosphorus (P), and Potassium (K) in the soil using Antares LR201 microcontroller board and LoRaWAN class A and class C networks with ANTARES platform as the network server. Later the data was monitored and controlled using an Android application which aims to compare the two types of networks. In this study, several tests were carried out, namely SNR, RSSI, delay, and packet loss. The test was carried out in the city of Bandung with different LoRa signal strength that could be seen on Telkom IoT web. Based on experiment, LoRaWAN class C has higher QoS performance for delay, SNR, RSSI, and packet loss than LoRaWAN class A for test location distance of 0, 1, 2, and 4 km away from BTS LoRa. According to the ITU-T G.1010 standard, the delay value produced in this experiment is in the "Very good" category, packet loss value is in the Very good "category", and the RSSI value is in the "Enough" category. And the SNR value is in the recommended category of SF10. Also, it can be concluded that the redder LoRa coverage location map reveals, the better QoS value obtained. In testing the sending and receiving of downlink data in terms of delay, according to the downlink data mechanism in class A, downlink data can be sent if the uplink data has been sent. While class C downlink data can be sent at any time.

show abstract

“…Many recent studies analyzed low energy efficiency and high user comfort within smart LED systems in different scenarios [ 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. More precisely, refs.…”

Section: Introductionmentioning

confidence: 99%

“…Complete surveys of the smart lighting systems were presented in [ 19 , 20 ]. A detailed state-of-the-art of the smart lighting systems is given in [ 19 ], mostly focusing on industrial area.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Smart Dimmable LED Lighting Systems †

Petkovic

Bajović

Vukobratović

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper proposes energy-efficient solutions for the smart light-emitting diode (LED) lighting system, which provides minimal energy consumption while simultaneously satisfying illuminance requirements of the users in a typical office space. In addition to artificial light from dimmable LED lamps, natural daylight coming from external sources, such as windows, is considered as a source of illumination in an indoor environment. In order to reduce total energy consumption, the smart LED system has the possibility to dim LED lamps, resulting in reduced LED output power. Additionally, various LED lamps’ functionality, such as semi-angle of the half illuminance and LED tilting, are introduced as an additional parameter to be optimized to achieve greater energy saving of the designed system. In order to properly exploit external lighting, the idea to reduce overall daylight intensity at a users’ location is realized by the option to dim the windows with a shading factor. Based on the users’ requirements for a minimal and desired level of illumination, the proposed optimization problems can be solved by implementing different optimization algorithms. The obtained solutions are able to give instructions to a smart LED system to manage and control system parameters (LEDs dimming levels, semi-angles of the half illuminance, orientation of LEDs, the shading factor) in order to design total illumination, which ensures minimal energy consumption and users’ satisfaction related to illuminance requirements.

show abstract

Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

Cited by 43 publications

References 384 publications

Overcoming Data Imbalance Problems in Sexual Harassment Classification with SMOTE

Overcoming Data Imbalance Problems in Sexual Harassment Classification with SMOTE

Performance Analysis of LoRaWAN Class A and Class C in the Measurement of Nutrient Content Systems

Smart Dimmable LED Lighting Systems †

Contact Info

Product

Resources

About