Software defect prediction is a critical task in software engineering, enabling organizations to proactively identify and address potential issues in software systems, thereby improving quality and reducing costs. In this study, we evaluated and compared various machine learning models, including logistic regression (LR), random forest (RF), support vector machines (SVMs), convolutional neural networks (CNNs), and eXtreme Gradient Boosting (XGBoost), for software defect prediction using a combination of diverse datasets. The models were trained and tested on preprocessed and feature‐selected data, followed by optimization through hyperparameter tuning. Performance evaluation metrics were employed to analyze the results comprehensively, including classification reports, confusion matrices, receiver operating characteristic–area under the curve (ROC‐AUC) curves, precision–recall curves, and cumulative gain charts. The results revealed that XGBoost consistently outperformed other models, achieving the highest accuracy, precision, recall, and AUC scores across all metrics. This indicates its robustness and suitability for predicting software defects in real‐world applications.

Abstract The research addresses energy consumption, latency, and network reliability challenges in wireless sensor network communication, especially in military security applications. A multi-agent context-aware model employing the belief-desire-intention (BDI) reasoning mechanism is proposed. This model utilizes a semantic knowledge-based intelligent reasoning network to monitor suspicious activities within a prohibited zone, generating alerts. Additionally, a BDI intelligent multi-level data transmission routing algorithm is proposed to optimize energy consumption constraints and enhance energy-awareness among nodes. The energy optimization analysis involves the Energy Percent Dataset, showcasing the efficiency of four wireless sensor network techniques (E-FEERP, GTEB, HHO-UCRA, EEIMWSN) in maintaining high energy levels. E-FEERP consistently exhibits superior energy efficiency (93 to 98%), emphasizing its effectiveness. The Energy Consumption Dataset provides insights into the joule measurements of energy consumption for each technique, highlighting their diverse energy efficiency characteristics. Latency measurements are presented for four techniques within a fixed transmission range of 5000 m. E-FEERP demonstrates latency ranging from 3.0 to 4.0 s, while multi-hop latency values range from 2.7 to 2.9 s. These values provide valuable insights into the performance characteristics of each technique under specified conditions. The Packet Delivery Ratio (PDR) dataset reveals the consistent performance of the techniques in maintaining successful packet delivery within the specified transmission range. E-FEERP achieves PDR values between 89.5 and 92.3%, demonstrating its reliability. The Packet Received Data further illustrates the efficiency of each technique in receiving transmitted packets. Moreover the network lifetime results show E-FEERP consistently improving from 2550 s to round 925. GTEB and HHO-UCRA exhibit fluctuations around 3100 and 3600 s, indicating variable performance. In contrast, EEIMWSN consistently improves from round 1250 to 4500 s.

Peer-to-peer (P2P) energy trading built on a smart information system in networked microgrids (MGs) is an emerging economic approach to facilitate energy sharing among networked MGs to achieve mutual cost-effective operation and improve the reliability and stability of energy supply service. Such a distributed market urges the need for an efficient energy trading strategy that incentivizes self-interested MGs to participate in energy trading. In this paper, we propose a distributed real-time P2P energy trading strategy that integrates energy trading into energy management and enables MGs with renewable energy sources (RESs) and energy storage systems (ESSs) to manage their storage scheduling, energy supply and energy trading in a dynamic manner. Jointly considering the randomness of renewable energy generation, the time-dependent load demand, the operational constraints of ESSs and the distance-dependent energy transmission losses associated with energy exchange, the proposed energy control and trading mechanism minimizes the time average operational costs of individual MGs while reducing energy transmission losses within the system.

Compared to well-established underwater acoustic communication techniques, underwater wireless optical communication (UWOC) offers significantly more transmission bandwidth and can be used in multiple short-range marine applications. Color-shift keying (CSK) is a modulation techniques advocated for deploying high data rate transmission in red, green and blue (RGB) based laser technology. It utilizes light sources that produce Lambertian light patterns. Consequently, the broadcast message arrives at the receiver via line-of-sight (LoS) pathways, with the Rician distribution being used to model the appropriate channel. This paper analyzes UWOC visible light communication (VLC) links using light emitting diodes (LDs) as transmitter with small angular divergence. The channel direct current (DC) gains is considered in the analysis to show the channel gain, signal-to-noise ratio (SNR), channel capacitance, and outage probability. This study also looks at the outage probability or the locally observed SNR of the CSK link below the threshold set for a particular quality of services. The results are depicted for a random white light in an UWOC system clean ocean. They shows that the SNR of the RGB Based Laser UWOC is proportional to $P_{t}/N_{0}$. The results also shows that the channel capacity increases with $P_{t}/N_{0}$ depending on the attenuation intensity $\beta$. Finally, as the data rate increases with a fixed $P_{t}/N_{0}$, the outage probability increases. The data rate increases with $P_{t}/N_{0}$ and the transmission power with a fixed value outage probability.

Smart homes are an integral component in developing smart cities. This paper studies the problem of real-time energy management of controllable loads for Internet of Things (IoT) connected homes with renewable energy generators and energy storage devices. By exploiting the delay tolerance of elastic loads, we develop a joint real-time energy storage control and load management system, aiming to minimize the long term time-averaged energy consumption cost without reducing energy consumption. This residential energy management problem is formulated as a constrained stochastic programming problem. A Lyapunov-based control algorithm is designed to decompose the long-term optimization problem into per-slot sub-problems and provide an asymptotically online optimal solution that is able to quickly adapt to the system dynamics without requiring any statistics of time-varying load demand and stochastic renewable generation. The proposed online control algorithm jointly optimizes energy consumption, load scheduling, and energy charging/discharging actions while satisfying the time-varying energy consumption preference of the user in each time slot. It is demonstrated through numerical simulations that the low-complexity online control algorithm ensures the load demand of the user served with a lower delay at a relatively low cost.

The normal and stable operation of the modern power systems rely on accurate situational awareness and visibility as recent researches and experiences have shown that the cyber-physical infrastructures are highly vulnerable to cyberattacks and intrusions. Attackers can design various intrusive injections to disrupt the operation thereby triggering failures, loss of synchronism, economic losses and sometimes injuries to employees. Hence, there have continuously been crucial need for timely, accurate identification and detection of these intrusions. Several traditional intrusion detection systems proposed in the literature have proven inefficient as they are computationally incompetent for the complex nature of the modern power systems. An alternative has been identified in form of machine learning techniques. This paper presents an empirical comparison of five prominent machine learning algorithms: K-nearest neighbors, Decision Tree, Naive Bayes, Random Forest and AdaBoost for predicting intrusion attacks into power systems network. The idea is to present the best possible classifier for the analyzed test systems and also to show that each of the developed algorithms can perform exceptionally well within some context. The developed algorithms were evaluated using a simulated voltage dataset generated from a load flow analysis of a 24-bus power systems case study. Experimental analysis and results obtained showed the feasibility of applying machine learning techniques in successfully predicting and detecting intrusions into power systems network.

Machine-to-machine (M2M) visible light communication (VLC) is a communication architecture that makes it possible for heterogeneous devices to interact without human intervention using visible light modulated at certain frequency to enable communication. M2M VLC based is one of the feasible applications of internet of things (IoTs). This paper proposed a machine type communication (MTC) for M2M VLC based with an incorporation of energy harvesting system using a power transfer unit (PTU) with a centralized VLC access point (AP) with a probabilistic model, where an investigation is performed to show the signal to noise ratio (SNR) distribution with a semi angle at half power of a chosen link. This is done by varying some parameters.This model considers the channel analysis and light emitting diodes (LEDs) are place at the ceiling showing how bit rate can be effected for VLC AP with equal separation for a mobile devices or users. Such network aims at interconnecting billions of devices while investing the throughput performance of the M2M VLC based where a cluster of energy harvesting devices communicating with a VLC AP. This paper aims at proposing a design at the physical layer using various modulation schemes, demodulation, synchronization, error correction and so forth to ensure optimal communication can be made to the internet. Both LEDs-based analog transceiver devices and photo-detectors are exploited. The method is implemented in simulation and considering the performance and flexibility of the system.

This paper describes a low-cost sensor using a microcontroller dsPIC30F6014A. A simple method to measure the specific heat capacity of liquids using transient technique. A sensor has been designed to measure time and temperature accurately which in turn lead to the measurement of the specific heat capacity of liquids. To test the proposed solution in the present work, different liquids have been used include organic compounds, inorganic compounds and polymers. The results obtained using our sensor have been validated using data available in the literature.

Visible light communications (VLC) technology has gained more interest recently. It is mostly investigated for indoor applications because of the dual use of light emitting diodes (LEDs) and its cost-effectiveness. However, few outdoor VLC applications are identified. VLC is, for example, proposed as a solution to link buildings situated at a reasonable distance in environments such as headquarters and school campuses. It is also proposed as a solution for the access network. These outdoor VLC applications are enabled by the utilization, in VLC, of light amplification by stimulated emission of radiation (LASER) diodes (LDs). One of the reasons for this is their lighting range which is higher than that of LEDs, usually used in VLC. The use of LASER beams in outdoor VLC technology over a medium distance requires the knowledge of both the channel response and the environment. In this paper, we analyze the outdoor VLC link that uses LDs as transmitting antennas with a small angle divergence. Few link evaluation metrics including the signal-to-noise ratio (SNR), the channel capacity and the outage probability are presented based on the channel direct current (DC) gain proposed in the literature. Results show that the SNR of such systems is proportional to Pt/N0, they also show that the channel capacity increases with Pt/N0 depending on the haze and fog attenuation factor, ß. Finally, the outage probability increases towards 10° as the data rate increases for a fixed Pt/N0, and for a fixed value of the outage probability, the data rate increases with Pt/No.

Spectral shaping codes are digital codes especially designed in such a manner that their alphabets give rise to predetermined frequency spectrum envelopes. This implies that the signal energy of these alphabets will be concentrated into a predetermined range of a given frequency spectrum. The design of digital codes in the above mentioned fashion is done in order to match specific channel constraints in the design of transmission, multiplexing or storage systems. In certain applications it is desirable that spectral shaping codes provide some error correction capability or that they possess an increased robustness to errors. These errors may be introduced during transmission, processing or storage of digital information. In this paper, an interleaving method is introduced to increase the robustness of DC free codes toward burst errors whilst maintaining the spectral shaping property of DC free codes. Interleaving when applied to a coded communication system results in a reduction in the mean bit error rate (BER) of coded bit streams.

With the widespread of light emitting diodes (LEDs) as a primary source of illumination, visible light communication (VLC) offers a lot of potentials by providing both resources and energy saving advantages. This paper presents a practical implementation of an integration of Power Line Communication (PLC) and VLC. The system uses spread frequency shift keying (S-FSK) and on-off keying (OOK) in the PLC and VLC channel respectively. The system is of low complexity, low cost and dedicated to enhance low data rate application of PLC technology. The practical design is compatible with the European Committee for Electrotechnical Standardization (CENELEC) band A and the test are done on a Chinese home environment where the Electric Power Research Institute (EPRI) specifies a 3 kHz to 500 kHz band. Results illustrating the effect of sunlight on this system are presented.

A new technique of designing spectral null codes with permutation sequences is presented. These new codes have nulls at sub-multiples of the frequency of the transmitted symbols and are also DC-free codes. The choice of the corresponding channel levels given to each transmitted symbols has guaranteed the elimination of the DC component at the lower frequencies and gave an advantage on the binary spectral null codes by being DC-free codes.

The generalized moment balancing templates for spectral null codes are investigated in this paper. A new approach based on the insertion of a determined number of vectors at determinate indices of a spectral null code word, is found to balance the moment of the code word. Moment balanced code words preserve the spectral null properties and can guarantee the correction of one insertion or one deletion error. As compared to the universal template for an uncoded sequence, the redundancy is determined by the structure of the original spectral null code, however, it can be kept small. The new approach involves the applications of the optimized moment balancing template and nonbinary enumeration of the balancing moment values.

A new graph theoretic construction mapping binary sequences to permutation sequences is presented. The k-cube graph construction has reached the upper bound on the sum of the distances for certain values of the length of the permutation sequence. This contributed in a better way to understand the distance-reducing mapping, which was not investigated before.

Templates are constructed to extend arbitrary additive error correcting or constrained codes, i.e., additional redundant bits are added in selected positions to balance the moment of the codeword. The original codes may have error correcting capabilities or constrained output symbols as predetermined by the usual communication system considerations, which are retained after extending the code. Using some number theoretic constructions in the literature, insertion/deletion correction can then be achieved. If the template is carefully designed, the number of additional redundant bits for the insertion/deletion correction can be kept small-in some cases of the same order as the number of parity bits in a Hamming code of comparable length.

We investigate moment balancing templates for spectral shaping codes, e.g., dc-free codes, high-order spectral-null codes and spectral nulls code. A new approach by addingkgrouped bits at determinate indices of the code word is found to balance the moment of the code word. Moment balanced code words preserve the spectral-null properties and can guarantee to correct one insertion or deletion error. The redundancy, which is a constant factor greater than that of the universal template for uncoded sequence, can be kept small. The new approach also involves the application of the optimized moment balancing template and the non-binary enumeration of balancing moment values.

A new way of looking at permutation distance-preserving mappings (DPMs) is presented by making use of a graph representation. The properties necessary to make such a graph distance-preserving, are also investigated. Further, this new knowledge is used to analyze previous constructions, as well as to construct a new general mapping algorithm for a previous multilevel construction.

The Viterbi decoding algorithm provides maximum likelihood decoding and has found widespread application since its introduction in 1967. It is currently the most widely used technique for the decoding of codes having a state system description, including the class of linear error correcting convolutional codes. Contrary to this, it is still common practice to use combinational logic decoders for ternary line codes. These are non-linear codes frequently used in metallic cable systems due to advantages such as efficient utilization of bandwidth, and a DC free power spectral density function. We investigate in this paper the behaviour of Viterbi decoding for the most important ternary line codes, and the coding gain that can be obtained by applying soft-decision decoding. The simplification of the Viterbi decoding implementation and the reduction in latency by shortening its survivor path length, have also been investigated.