Under an internet of thing (IoT)-based framework, a power grid monitoring system can collect real-time transmission line data, which can then be used to predict the cascading failure risks within the grid. This study proposed a two-stage cascade failure prediction (CFP) model that integrated deep learning techniques with supervised classification algorithms to identify transmission lines susceptible to cascading failures, thereby preventing large-scale power system collapses. In the first-stage, the CFP model utilizes historical transmission line data to predict lines at risk in the next time step. In the second-stage, it assesses whether the predicted at-risk lines could trigger system instability or power outages. Three deep learning-based algorithms were employed in the first-stage, whereas three binary classification algorithms were utilized in the second-stage. The proposed CFP model was evaluated using an IEEE 39-bus system, where 2,000 cascading failure events were simulated through a real-time digital simulator (RTDS). Experimental results demonstrate that the two-stage CFP model, particularly when combining a deep neural network with a binary classifier, can accurately identify potential risk lines in the test grid with an accuracy ranging from 97.5% to 98.3%. Moreover, the CFP model exhibits strong robustness against noisy and erroneous data. These predictive results provide valuable insights for power companies in formulating preventive safety strategies against cascading failures.

In this study, a self-adaptive pulse discharge (SAPD) approach is developed and utilized to drain leftover energy from waste lead–acid batteries before entering the recycling process. This SAPD method was applied to find the optimal pulse frequency and duty cycle values for determining the discharge current from the batteries. Experiments were conducted using two parallel-connected Yuasa 12-V/6-Ah batteries. The energy recovered from the batteries was 54.7 kJ, and the corresponding recovery efficiency was 78.7%. The energy recovery efficiency could be improved to 80.9% by including three 15-min relaxation periods when the terminal voltage of the batteries reached the cutoff voltage of 10.5 V during discharge. The findings of this study could pave the way to a more sustainable future, even though major improvements in the recycling process are still required.

The issue of air pollution in urban areas is gaining attention due to the rise of environmental and health concerns, especially for the particulate matter 2.5 (PM textsubscript 2.5), which poses the greatest health risk to humans. Accurate air quality prediction data allows government officials and the public to take preventive measures in advance. Recently, many air quality prediction studies have used machine learning techniques to identify patterns and rules in air quality data. However, these studies generally adopted under-represented background levels, and the prediction intervals were often in hours, which may not be suitable for residents who needed accurate air quality forecasts. Therefore, this study proposes a deep-learning-based multi-timestamp multi-location PM2.5 prediction system built on two acrlong RNN models: 1) long short-term memory (LSTM) and 2) gated recurrent unit (GRU). Airbox data for the Taipei metropolitan area serves as the main source of training data to develop a forecasting model that can predict changes of PM2.5 levels within the next 6–30 min in different locations. The prediction results are verified by comparing them with the PM2.5 measuring results from an Internet of Things (IoT)-based acrlong OVMS, which enables real-time data sensing and collection, and wireless transmission. The error and accuracy are$0.922 \mu \text{g}$/m 3 and 100% for the LSTM-based prediction model, and$0.940 \mu \text{g}$/m 3 and 95.7% for the GRU-based prediction model, respectively. These results can be sent out as warning messages to elderly and asthmatic patients, or serve as important information for route recommendations and policy formulation.

Bad road quality brings many problems, such as putting drivers and passengers in danger and causing vehicle suspension system wear. Maintaining high-quality roads relies on regular inspections and repairs, but this is a time-consuming and labor-intensive task. To improve road quality and increase the efficiency of road repairs, an Internet of Things based anomaly detection system (ADS) is proposed to monitor road surfaces. A machine-learning method, support vector machine (SVM), is utilized to identify and classify different types of road surface anomalies. Other five classifiers are also examined using the same testing data. The high classification accuracies obtained from the proposed SVM model can be incorporated with a Google Map, so the road surface information can be easily browsed. With the proposed ADS system, it requires manpower and time that can be greatly reduced for examining surface conditions of roads and significantly improve the efficiency of road maintenance.

For overhead power grids, unexpected serious line sagging of extra-high voltage transmission lines would easily lead to major blackouts. Different direct and indirect sag measuring methods have been proposed, but they all have their own limitations. In this study, an Internet of Things (IoT)-based sag-monitoring system is proposed, which is able to perform real-time detection of line sags. The whole system has been deployed on two 161-kV lines for long-term field testing. The effectiveness of the proposed sag-monitoring system is verified through both theoretical calculation and field measurements. In this sag-monitoring system, a sag-sensing module is equipped with an embedded triaxial accelerometer to detect line sags at different spans of a single circuit. A catenary equation that takes temperature dependency into consideration is derived, so the measured accelerometer parameters can be converted to accurate line sag values. The long-term testing results show that the proposed sag-monitoring system yields an average error of 2.09%. The average differences between the sag values coming from the proposed system and a commercial sag measuring device are relatively small (between 0.57% and 4.14%), which proves that the sag values provided by the proposed system are reliable and accurate in the long-term testing. In addition, compared to the other existing sag measuring methods, the advantages of employing the proposed system are high measurement accuracy, and enabling wide field implementation, online monitoring, long-term field operation, and real-time transmission.

To quickly isolate suspected cases to control the epidemics, this study proposes a body temperature monitoring system with a thermography based on the Internet of Things (IoT) architecture. The collected data are transmitted to a back-end platform via wireless communication. Using the analyzed data, the platform provides services, such as instant alerts for any anomalies, infectious disease outbreak prediction, and risk level assessment for a given area, and it will be a great help to epidemic prevention. The mean absolute percentage error and root mean square error of the proposed monitoring system under an extensive series of experiments are 0.04% and 0.0204°C, respectively. It shows that the body temperature measured by the thermal imaging sensor in the system can accurately represent the actual body temperature after specific calibrations that take the environmental temperature into account. It can also be expanded to a decision supporting system to help schools or government agencies to make proper decisions to stop the spread of infectious diseases.

Dynamic thermal rating (DTR) is a technique that can effectively reduce the complexity of the decision-making processes for a smart grid. Internet-of-Things-based DTR monitoring systems can be used to achieve reliable and low-cost remote monitoring of power grids, but this method is heavily reliant on collecting accurate real-time meteorological data by sensors deployed on the power lines. However, deploying sensors on each span of the line may not be feasible due to the high cost of such sensors. Thus, this article proposes a modified binary particle swarm optimization (MBPSO) strategy to solve multiobjective combinational decision problems. The proposed method is able to determine the minimum number of sensors required to achieve nearly ideal performance. A 161-kV line located between Xizhi and Minquan, part of the Taiwan Power Company transmission system, was selected as the experimental target. The MBPSO algorithm was solved based upon hourly meteorological data provided by Taiwan's Central Weather Bureau. The results obtained with the proposed method show that only one sensor needs to be deployed on the third span of the line to effectively monitor more than 89.6% of high conductor temperature events, and the root mean square error on the reconstructed conductor temperature distribution is less than 0.8 °C.

One of the critical concerns in wireless sensor networks (WSNs) is the continuous maintenance of sensing coverage. Many particular applications, such as battlefield intrusion detection and object tracking, require a full-coverage at any time, which is typically resolved by adding redundant sensor nodes. With abundant energy, previous studies suggested that the network lifetime can be maximized while maintaining full coverage through organizing sensor nodes into a maximum number of disjoint sets and alternately turning them on. Since the power of sensor nodes is unevenly consumed over time, and early failure of sensor nodes leads to coverage loss, WSNs require dynamic coverage maintenance. Thus, the task of permanently sustaining full coverage is particularly formulated as a hybrid of disjoint set covers and dynamic-coverage-maintenance problems, and both have been proven to be nondeterministic polynomial-complete. In this paper, a hybrid memetic framework for coverage optimization (Hy-MFCO) is presented to cope with the hybrid problem using two major components: 1) a memetic algorithm (MA)-based scheduling strategy and 2) a heuristic recursive algorithm (HRA). First, the MA-based scheduling strategy adopts a dynamic chromosome structure to create disjoint sets, and then the HRA is utilized to compensate the loss of coverage by awaking some of the hibernated nodes in local regions when a disjoint set fails to maintain full coverage. The results obtained from real-world experiments using a WSN test-bed and computer simulations indicate that the proposed Hy-MFCO is able to maximize sensing coverage while achieving energy efficiency at the same time. Moreover, the results also show that the Hy-MFCO significantly outperforms the existing methods with respect to coverage preservation and energy efficiency.

Wireless real-time surveillance systems are very valuable for monitoring ecology of wildlife, since the in-situ situation could be grasped immediately. Power source is usually constrained in the wild areas. Thus, in this paper, we developed a low power-consumption image transmission system (called energy-efficient visual eyes system) by integrating a MSP430 micro controller, FPGA circuit, a solar powered battery, a digital camera, and a GPRS (General Packet Radio Service) modem. In order to make a monitoring system suitable for circumstances of wild islands, the proposed system is designed with a packet transmitting strategy capable of enhancing pixel validity while effectively decreasing power consumption. Practically, the proposed system is deployed on a wild island in Taiwan near East China Sea, where is a habitat for migrant seabirds. The experimental results show that the system design is feasible to ecological monitoring and able to effectively maintain the completeness of images with energy efficiency.

A fuzzy logic approach, called FuzzyTRN, to infer transcriptional regulatory networks (TRN) inSaccharomycescerevisiaeis proposed. FuzzyTRN predicts potential regulators and their target genes using sequences analysis on transcription factor binding sites (TFBS) of transcriptional factors (TF) and promoter region of target genes. Those potential regulators and target genes are used to form vertices in the TRN. Furthermore, multiple sets of microarray gene expression data (MGED) are used by FuzzyTRN to predict links in the TRN. FuzzyTRN predicts transcriptional interactions by recognizing expression patterns of genes. In this study, a number of confirmed genetic interactions are utilized to train FuzzyTRN. 112 indirect genetic interactions that were confirmed by quantitative real-time polymerase chain reaction (qRT-PCR) experiments, and 259 and 86 direct genetic interactions that were collected by TRANSFAC database and literature surveying, were used as training set in this work. A simulation that encompasses 170 TFs and 40 target genes has been conducted and checked against YEASTRACT database to evaluate the performance of the proposed algorithm.

A neuro-fuzzy inference system that recognizes the expression patterns of genes in microarray gene expression (MGE) data, called GeneCFE-ANFIS, is proposed to infer gene interactions. In this study, three primary features are utilized to extract genes' expression patterns and used as inputs to neuro-fuzzy inference system. The proposed algorithm learns expression patterns from the known genetic interactions, such as the interactions confirmed by qRT-PCR experiments or collected through text-mining technique by surveying previously published literatures, and then predicts other gene interactions according to the learned patterns. The proposed neuro-fuzzy inference system was applied to a public yeast MGE data set. Two simulations were conducted and checked against 112 pairs of qRT-PCR confirmed gene interactions and 77 TFs pairs collected from literature respectively to evaluate the performance of the proposed algorithm.

A novel method for evolutionary optimization, called integrated radiation optimization (IRO), is proposed for solving nonlinear multidimensional optimization problems. Many modern optimization techniques explore the search space by sharing information they have found. In this study, the con cept of gravitational radiation in Einstein’s theory of general relativity is utilized as a fundamental theory for searching optimal solution in the search space. The idea of developing the algorithm and its detailed procedures are introduced. This work applied the proposed IRO to find the minimum value of a static polynomial function, and some applications that are known to be difficult. The preliminary experimental results show that the performance of the proposed IRO is promising, and IRO shows great performance in solving other NP-hard search and optimization problems.

To assist in the inspection of sleep-related diagnosis and research, an adaptive method for processing long-term polysomnography (PSG) is proposed in this paper. The extracted features of segmented PSG based on wavelet analysis can be used for clustering the segments with similar pattern into a group. The adaptive fuzzy clustering was used to estimate the clusters within the PSG recordings, the optimal number of clusters and the optimal features of an individual subject. The novel method with the adaptive-to-subject concept exhibits four advantages in comparison with other approaches: 1) full automated, 2) adaptive to the diversity of physiological signals among subjects, 3) less sensitive to noise and artifacts, and 4) effective visualization of analysis results for clinicians. The simulation results show the superiority of the proposed method in long-term PSG analysis

In this paper, an optimum approach to design PID controllers has been proposed. PID control schema based on classical control theory has been widely used in industrial control processes. Since most of the control systems have nonlinear properties, it is difficult to determine optimal parameters for a given PID controllers. This study utilizes the particle swarm optimization algorithm as solution method to search for PID parameters that capable of minimizing the integral absolute control error. At the same time, the transient response is guaranteed by minimizing the maximum overshoot, settling time, rising time of step response. Moreover, we also utilize ε-constraint method to improve the performance of the controllers. Finally, experimental results demonstrate that better control performance and robustness can be achieved in comparison with known methods.

In this paper, a novel robust unsupervised video object tracking algorithm is proposed. The proposed algorithm combines several techniques: mathematical morphology, region growing, region merging, and trajectory estimation, for tracking several predetermined video objects, simultaneously. A modified mathematical morphological edge detector was employed to sketch the contour of the video frame; and an edge-based object segmentation algorithm was applied to the contour for partitioning the predetermined objects; moreover, according to the motion of the objects, the proposed algorithm can estimate and partition the objects in following video frames, automatically. The proposed algorithm is also robustness against mobile cameras. The experimental results show that the proposed algorithm can precisely partition and track multiple video objects

A new concept for the optimization of nonlinear functions is proposed. For most of the proposed evolutionary optimization algorithms, such as particle swarm optimization and ant colony optimization, they search the solution space by sharing known knowledge. The proposed algorithm is based on the Einstein's general theory of relativity, which we utilize the concept of gravitational field to search for the global optimal solution for a given problem. In this paper, detail procedure of the proposed algorithm is introduced. The proposed algorithm has been tested on an application that is known difficult with promising and exciting results.

In this paper, a novel approach for edge-based image segmentation is proposed. Image segmentation and object extraction play an important role in supporting content-based image coding, indexing, and retrieval. However, it's always a tough task to partition an object in a graph-based image. We proposed an image segmentation algorithm by integrating mathematical morphological edge detector with region growing technique. The images are first enhanced by morphological closing operations, and then detect the edge of the image by morphological dilation residue edge detector. Moreover, we deploy growing seeds into the edge image that obtained by the edge detection procedure. By cross comparing the growing result and the detected edges, the partition lines of the image are generated. In this paper, we presented the theoretical backgrounds and procedure illustrations of the proposed algorithm. Furthermore, the proposed algorithm is implemented in C++ language and evaluate on several images with promising results.