Network security becomes indispensable to our daily interactions and networks. As attackers continue to develop new types of attacks and the size of networks continues to grow, the need for an effective intrusion detection system has become critical. Numerous studies implemented machine learning algorithms to develop an effective IDS; however, with the advent of deep learning algorithms and artificial neural networks that can generate features automatically without human intervention, researchers began to rely on deep learning. In our research, we took advantage of the Convolutional Neural Network’s ability to extract spatial features and the Long Short-Term Memory Network’s ability to extract temporal features to create a hybrid intrusion detection system model. We added batch normalization and dropout layers to the model to increase its performance. Based on the binary and multiclass classification, the model was trained using three datasets: CIC-IDS 2017, UNSW-NB15, and WSN-DS. The confusion matrix determines the system’s effectiveness, which includes evaluation criteria such as accuracy, precision, detection rate, F1-score, and false alarm rate (FAR). The effectiveness of the proposed model was demonstrated by experimental results showing a high detection rate, high accuracy, and a relatively low FAR.

The rapid evolution and growth of the internet through the last decades led to more concern about cyber-attacks that are continuously increasing and changing. As a result, an effective intrusion detection system was required to protect data, and the discovery of artificial intelligence’s sub-fields, machine learning, and deep learning, was one of the most successful ways to address this problem. This paper reviewed intrusion detection systems and discussed what types of learning algorithms machine learning and deep learning are using to protect data from malicious behavior. It discusses recent machine learning and deep learning work with various network implementations, applications, algorithms, learning approaches, and datasets to develop an operational intrusion detection system.

Healthcare monitoring systems in hospitals and other health facilities have grown significantly, and portable healthcare monitoring systems using emerging technologies such as Internet of Things (IoT) technologies have aided the advancement of healthcare monitoring systems. Many studies have focused on intelligent healthcare systems in an IoT context to improve components, including wearable sensors and hardware devices, intelligent data collecting and processing, and network connections. Even while these applications are necessary and helpful for enhancing wireless healthcare settings related to monitoring, detection, and diagnostics, it might be challenging to fully understand how IoT characteristics are currently intertwined with its architecture. Accordingly, this work adds to the academic literature by thoroughly reviewing all significant areas of wireless healthcare monitoring system advancements. This research also examines a state-of-the-art healthcare monitoring system component under IoT. One hundred and ninety-four related articles were collected and filtered based on the system components defined. This study includes a thorough review and a list of genuine concerns with novel critical solutions. The study can facilitate academics and practitioners by giving them direction and vital information for future research.

This paper aims to investigate the impact of adopting lean manufacturing principles on operational efficiency by eliminating seven major lean wastes (or Muda) in a Malaysian stationery manufacturer. Much of the research on lean considers its application to larger organisations with stable demand patterns. This research examines a small- and medium-sized enterprise (SME) with a volatile demand pattern. A process activity mapping (PAM) methodology was utilized to identify the potential for waste elimination. PAM is a visual tool that considers every step in a production process. Value-added and non-value-added activities are therefore examined to understand hidden wastes and their sources. The results revealed that the adopted lean principles significantly reduce the waiting times. This time reduction resulted in savings (reduction of cycle time) and to a certain extent, can be a crucial driver in continuous improvement sustainability in the production process. The study focuses on a single case study and provides a springboard for further research. Future studies examining the results across a broader sample of organisations would develop the findings further. The extant literature cites mixed success for lean implementation programmes. The results demonstrate that lean is still recognised as a powerful approach to improving operations in SMEs. This paper reflects on the application of lean in a real case study showing the impact of lean on operational performance of an SME.

Firefly algorithm is among the nature-inspired optimization algorithms. The standard firefly algorithm has been successfully applied to many engineering problems. However, this algorithm might be stuck in stagnation (the solutions do not enhance anymore) or possibly fall in premature convergence (fall into the local optimum) in searching space. It seems that both issues could be connected to exploitation and exploration. Excessive exploitation leads to premature convergence, while excessive exploration slows down the convergence. In this study, the classical firefly algorithm is modified such that make a balance between exploitation and exploration. The purposed modified algorithm ranks and sorts the initial solutions. Next, the operators named insertion, swap and reversion are utilized to search the neighbourhood of solutions in the second group, in which all these operators are chosen randomly. After that, the acquired solutions combined with the first group and the firefly algorithm finds the new potential solutions. A multi-echelon supply chain network problem is chosen to investigate the decisions associated with the distribution of multiple products that are delivered through multiple distribution centres and retailers and demonstrate the efficiency of the proposed algorithm.

Advanced technology in agriculture has enabled the manipulation of the artificial light spectrum in plant development such as improving yield and plant growth. Light manipulation using light-emitting diodes or LEDs can inhibit, delay, or even promote flowering. Some studies have shown that far-red (FR) light can stop flowering, but studies have not fully explored the best method involving intensity and duration to induce plant growth. This paper presents results on LED light manipulation techniques, particularly FR light, on plant flowering control and plant elongation. The light manipulation technique on the combination of colors, photoperiods, and intensities proved that it can stop flowering, and stimulate and control the growth of plants during cultivation. The system was monitored using an Internet-of-Things (IoT) remote monitoring system, and it performed data mining. The results showed that plants that were grown under artificial sunlight (T5) and normal light (T1) treatments were superior compared to others. The FR light delayed flowering until 50 days of planting and accelerated the plant growth and increased the fresh weight by 126%. The experiment showed that a high variable intensity at 300 µmol m⁻¹s⁻¹ showed a great performance and produced the largest leaf area of 1517.0 cm² and the highest fresh weight of 492.92 g. This study provides new insights to the researchers and the farming community on artificial light systems in improving plant factory production efficiency and in determining the best plant cultivation approach to create a stronger indoor farming management plant.